A method and platform for intelligent warehouse inventory dynamic management based on digital twin technology
The intelligent warehouse inventory management method built through digital twin technology dynamically adjusts warehouse locations and replenishment strategies, solving the problem of low efficiency in traditional warehouse management and achieving efficient and low-cost warehouse operations.
Patent Information
- Application Number
- CN202611235316.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-14
- Publication Date
- 2026-11-10
AI Technical Summary
In traditional warehouse storage management, frequently picked goods are stored far from the work exit, which increases walking distance and reduces operational efficiency.
A smart warehouse inventory dynamic management method based on digital twin technology is adopted. By collecting physical warehouse data to build a digital twin model, storage location optimization analysis and replenishment forecasting are carried out to achieve dynamic adjustment and efficient management of warehouse locations.
This improved warehouse operational efficiency, reduced costs, and ensured timely and efficient fulfillment of supply demands.
Smart Images

Figure CN123070841A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of warehouse management technology, and in particular to an intelligent warehouse inventory dynamic management method and platform based on digital twin technology. Background Technology
[0002] Digital twins fully utilize data from physical models, sensors, and operational history to integrate multidisciplinary, multi-physical, multi-scale, and multi-probability simulation processes, completing mapping in virtual space to reflect the entire lifecycle of the corresponding physical equipment.
[0003] Current warehouse storage, especially large warehouse storage, has placed higher demands on management. Traditional warehouse storage management mainly relies on fixed storage location allocation, which results in high-frequency picking items being stored far from the work exit, significantly increasing walking distance and reducing operational efficiency.
[0004] Therefore, designing an intelligent warehouse inventory dynamic management method and platform based on digital twin technology, and how to achieve efficient dynamic management of warehouse storage to improve warehouse operating efficiency and reduce costs, are urgent problems to be solved. Summary of the Invention
[0005] This invention provides a method and platform for intelligent warehouse inventory dynamic management based on digital twin technology.
[0006] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a method for intelligent warehouse inventory dynamic management based on digital twin technology is provided. The method includes: collecting physical warehouse management data, constructing a digital twin model to form a real-time dynamic twin of the warehouse; performing storage location optimization analysis based on the real-time dynamic twin of the warehouse to form real-time storage location optimization data; and performing replenishment analysis based on demand forecasting based on the real-time dynamic twin of the storage location to form replenishment forecasting analysis data.
[0007] Therefore, the above method establishes a digital twin model of the warehouse based on physical warehouse management data to dynamically reflect changes in warehouse storage data. It also optimizes warehouse locations by leveraging the popularity of different stored items, effectively improving warehouse operational efficiency. Furthermore, it uses demand forecasting analysis to predict replenishment data, enabling timely and efficient replenishment. The entire warehouse management and operation, utilizing the digital twin model, achieves efficient and reliable operation, significantly improving warehouse operational efficiency and effectively ensuring that the warehouse fully meets supply demands while maintaining reasonable cost control.
[0008] Optionally, physical warehouse management data is collected to construct a digital twin model, forming a real-time dynamic twin of the warehouse, including: performing full-domain parameterization processing based on physical warehouse management data to form full-domain parameterized data; and performing real-time change analysis of storage locations for inbound and outbound events based on physical warehouse management data to form real-time dynamic management data of storage locations.
[0009] Therefore, the construction of digital twin models using physical warehouse management data is mainly aimed at creating digital twins of warehousing conditions. However, before this, it is necessary to quantify and standardize the basic parameters of the warehouse to provide a parameter foundation for the dynamic model of storage locations. It can be understood that parameterization using physical warehouse management parameters involves mapping the entire domain of data, including storage location and operating parameters, into a parameterized manner. This entire domain data is provided by equipment and facilities, including but not limited to industrial cameras, RFID, LiDAR, PLCs, and temperature / humidity / vibration sensors. After completing the entire domain parameterization, the focus is on dynamically tracking different storage locations to ensure that the established digital twin can effectively reflect the dynamic status of the storage locations in real time.
[0010] Optionally, based on the physical warehouse management data, perform full-domain parameterization processing to form full-domain parameterized data, including: determining the location coordinates of different storage locations based on the physical warehouse management data. ,in, , i represents the storage location number in the warehouse. This represents the position parameter of storage location numbered i in the first direction. This represents the position parameter of storage location numbered i in the second direction. This parameter represents the position of storage location numbered i in the third direction; based on the storage location coordinates of different storage locations... Determine the corresponding equivalent operating distance for the storage location. ,in, , This parameter indicates the location of the warehouse's entrance and exit in the first direction. This indicates the location of the warehouse's entrance and exit in the second direction. This parameter indicates the location of the warehouse's entrance / exit on a third-party upward direction. This represents the equivalence factor for vertical operations; based on physical warehouse management data, the storage capacity of different storage locations is determined. Based on physical warehouse management data, determine the inventory levels of previously stored items at different storage locations at the previous moment. And establish a time-varying matrix based on the previous inventory. Where j represents the ID of a different storage item; based on physical warehouse management data, determine the total number of outbound transactions for each storage item within the previous analysis time window. .
[0011] Therefore, this application primarily focuses on analyzing storage location changes and predicting replenishment based on digital twin data, considering management efficiency. Thus, the analysis of all parameters needs to fully cover these aspects. All parameterization includes storage location information, the equivalent single-trip operation distance for inbound and outbound operations at storage locations, capacity information for different storage locations, storage quantity information for different stored items at corresponding storage locations, and the number of outbound operations for different stored items within the analysis period. Storage location information forms the basis for subsequent operational analysis at storage locations. Regarding the equivalent single-trip operation distance, since the transportation methods in the horizontal direction differ from those in the vertical direction, there will be differences in energy consumption, etc. The vertical operational equivalence factor can quantify the operational equivalence in all three directions. The vertical operational equivalence factor can be defined based on a comparison of transportation methods. Storage location capacity is a crucial basis for determining whether a storage location can still accommodate new storage. Here, the inventory quantity of stored items is obtained from the previous moment. Real-time operations are implemented based on event-based conditions, primarily used to establish a reasonable time-varying matrix, providing a data foundation for subsequent analysis. The quantification of the total number of outbound shipments is mainly to provide a reference for subsequent storage location optimization. The quantification of storage location capacity and the inventory of stored goods needs to consider two aspects. First, the basis for both quantifications needs to be consistent, that is, to ensure that the units of the quantification parameters are the same. This avoids increased data analysis complexity or errors due to inconsistent quantification units during subsequent storage location optimization.
[0012] Optionally, based on physical warehouse management data, real-time changes in storage locations are analyzed for inbound and outbound events to generate real-time dynamic management data for storage locations. This includes: determining the real-time inbound and outbound times for different storage locations based on physical warehouse management data, and obtaining the corresponding real-time event changes for storage locations. Based on the time-varying matrix of previous inventory Determine the real-time inventory of stored items at each storage location. ,in, Based on different real-time storage inventory levels For the time-varying matrix of the previous inventory Update the data to form a real-time inventory time-varying matrix. .
[0013] Therefore, the most basic aspect of real-time dynamic management of storage locations is the dynamic tracking of the stored items in each storage location to ensure the accuracy and timeliness of inventory data. This is achieved by dynamically updating the storage quantity in real time based on inbound and outbound events, building upon the previously determined storage quantity. This ensures smooth continuation of subsequent dynamic changes, and the repeated confirmation and updating of inbound and outbound events guarantees the accuracy and timeliness of storage information. For real-time changes in storage location events, the parameter is negative for outbound events and positive for inbound events.
[0014] Optionally, storage location optimization analysis is performed based on the real-time dynamic twin of the warehouse to form real-time storage location optimization data, including: performing heat-based storage location surface analysis based on the real-time dynamic twin of the warehouse to form initial storage location surface data; and performing storage location optimization analysis based on the initial storage location surface data to form real-time storage location optimization data.
[0015] Therefore, it can be seen that for different types of stored goods, the frequency and total amount of inbound and outbound operations in the warehouse vary due to different demands. Adjusting the location of stored goods closer to the inbound and outbound entrances can improve inbound and outbound efficiency. Of course, when selecting existing storage locations for inbound and outbound operations, especially for outbound operations, if multiple storage locations exist for the same item, the location near the inbound and outbound entrance will be preferred. For a given storage location, which is the optimal solution determined in the previous analysis cycle, using a reasonable analysis cycle as a reference for storage location optimization can ensure the stability and rationality of storage location adjustments. It is understandable that different stored goods have different storage volumes, resulting in different required storage locations. Essentially, storage location optimization analysis is an optimization adjustment of the storage location surface where the stored goods are located, that is, obtaining the optimal cluster of storage locations required for that stored goods, ensuring that the supply of inbound and outbound goods can efficiently meet demand. Of course, the optimization of storage locations also needs to consider the frequency of use of different storage items. The higher the frequency, the greater the workload of the storage item. Therefore, the closer the storage item with the greater workload is to the inlet and outlet, the higher the management efficiency of the warehouse. Thus, when conducting the analysis, it is also necessary to consider the workload of different storage items. Of course, this consideration is based on the analysis period.
[0016] Optionally, based on the real-time dynamic twin of the warehouse, a heat-based analysis of the storage space area is performed to form initial storage space area data, including: the total number of outbound shipments corresponding to different stored items. Determine the corresponding storage heat value ,in, J is the maximum value of number j; based on the storage heat value The storage surface analysis is performed on different storage items in descending order of demand as follows: The total periodic demand corresponding to each storage item is obtained. ,in, , This represents the average outbound volume per unit time. Indicates the lead time for replenishment. Indicates the redundancy coefficient; the currently available storage locations are calculated based on the equivalent operating distance of the storage location. Storage is allocated to the corresponding storage items in ascending order of quantity until the total storage capacity of all allocated storage locations is not less than the total periodic demand. The collection of stored items is assigned to all storage locations to form the corresponding initial storage location surface.
[0017] Therefore, the storage space analysis based on heat (or popularity) primarily aims to provide the total outbound demand for different stored items under the premise that no replenishment is needed in the next cycle. However, considering the different outbound frequencies of various stored items, the allocation of storage space cannot be arbitrary. This is to avoid storing items with low outbound frequencies occupying a large number of spaces close to the inbound / outbound entrances, thus reducing warehouse operational efficiency. The heat value of different stored items is based on the proportion of outbound frequency to the total outbound volume, thereby determining the order of storage space allocation for different stored items. When allocating storage space for different stored items, all currently available storage spaces are used as a benchmark. The condition for successful allocation is that the total storage capacity of the allocated storage spaces is not less than the total demand estimated based on the average outbound volume per unit time. The average outbound volume per unit time can be determined based on the outbound level in the previous analysis period. The replenishment lead time is the time from when the replenishment operation is carried out to when the goods are actually put into storage. This time is calculated from the start time of the analysis period. In essence, the replenishment period is a predicted time for inbound replenishment based on the previous analysis period. The redundancy coefficient can be set as needed.
[0018] Optionally, based on the initial storage surface data, storage optimization analysis is performed to generate real-time storage optimization data, including: for different storage materials, determining the initial storage surface corresponding to the storage material to be optimized as the initial target storage surface; for the initial target storage surface, based on the equivalent operating distance of different storage locations... Storage locations are extracted in descending order of capacity. The ratio of the extracted storage locations to the total number of storage locations in the initial storage area does not exceed the optimized storage location ratio. If the ratio of the total capacity of the extracted storage locations to the total capacity of all storage locations in the initial storage area does not exceed the capacity limit ratio, the extracted storage locations are marked as storage locations to be optimized; otherwise, storage location optimization is not performed on the initial target storage area. If there are storage locations to be optimized, the storage location is determined based on the storage heat value. From highest to lowest heat value, storage objects with lower heat values that are adjacent to the initial target storage level are identified and marked as storage objects to be optimized. Within the initial storage level of these storage objects, storage objects are then processed according to their equivalent operating distance. Multiple storage locations are extracted in ascending order of capacity, ensuring that the total capacity of the extracted locations does not exceed the total capacity of all storage locations to be optimized. The extracted storage locations are then combined with the remaining storage locations in the initial target storage location surface after removing the storage locations to be optimized, forming the optimized storage location surface corresponding to the storage item in the initial target storage location surface. All storage locations to be optimized are then combined with the remaining storage locations in the initial storage location surface corresponding to the storage item to be optimized, forming the optimized storage location surface corresponding to the storage item to be optimized. After optimizing the storage locations for all storage items, the total capacity of each optimized storage location surface is verified: if the total capacity of the optimized storage location surface is less than the corresponding total demand for the period... Then, in the currently available storage locations, the equivalent working distance of the storage location will be used. Extract storage sites in ascending order of capacity to the corresponding optimized storage surfaces, ensuring that the total capacity of the optimized storage surfaces is not less than the total demand for the cycle. .
[0019] Therefore, the purpose of real-time storage location optimization is to adjust the storage locations corresponding to items with relatively low heat values, so that these locations also include good storage locations with shorter equivalent operating distances. However, this optimization must be limited to ensure its rationality. This application optimizes only the storage locations of adjacent items in terms of heat value. This avoids situations where storage locations with inherently low heat values are too close to the inlet / outlet, which would not achieve efficient utilization of storage locations. Of course, to ensure that the optimized storage locations do not significantly change in capacity and require the addition of more vacant storage locations far from the inlet / outlet, reasonable control over the number and capacity of the storage locations to be optimized is necessary. Therefore, the number of storage locations extracted for optimization cannot exceed the optimization ratio, and the capacity cannot exceed the capacity limit ratio, to avoid substantial changes to the storage locations and significantly reducing inlet / outlet efficiency. The optimization ratio and capacity limit ratio can be set according to actual conditions. Once optimizable storage locations are identified, exchanging some storage locations between two storage areas does not guarantee that the total capacity of the exchanged locations will be the same. Therefore, after the exchange, it is necessary to determine whether the total capacity of the storage areas meets the total demand for the cycle, and if not, to supplement a small number of idle storage locations. Although storage location optimization may have a certain negative impact on the operational efficiency of storage locations for high-demand items, it does create storage locations closer to the inbound and outbound entrances for various high-demand items at the overall warehouse management level, thus improving outbound efficiency at the overall level.
[0020] Optionally, based on the real-time dynamic twin of the storage location, replenishment analysis based on demand forecasting is performed to generate replenishment forecasting analysis data, including: for different optimized storage locations after verification, the equivalent operating distance of the storage location is calculated. The lowest storage location is designated as the primary picking location, and the capacity of the primary picking location is set as the primary picking capacity. The total capacity of the remaining storage locations in the optimized storage area, excluding the main picking location, is determined and marked as the total warehouse transfer capacity. Obtain the demand forecasting function Determine the predicted consumption amount ,in, , Indicates the time consumed; based on the main picking capacity. Total warehouse capacity and predicted consumption We conduct replenishment forecast analysis to generate replenishment forecast analysis data.
[0021] Therefore, digital twins establish dynamic warehouse storage location change data, which can be used to achieve reasonable and effective replenishment forecasting, thereby enabling timely replenishment preparation and improving warehouse management efficiency. Replenishment forecasting is based on demand forecasting. The demand forecasting function is a forecast curve formed by analyzing outbound change data over historical analysis periods, while replenishment forecasting considers changes in the total amount of stored goods. Therefore, forecasting analysis needs to consider the inventory situation of the entire storage area to ensure that all stored goods have a high turnover rate.
[0022] Optionally, based on the master picking capacity Total warehouse capacity and predicted consumption To conduct replenishment forecasting analysis and generate replenishment forecasting analysis data, including: setting the minimum master pick inventory level. Based on the main picking capacity Determine the total allowable consumption of the main picker. ,in, Based on the total allowable consumption of the master picker. Total warehouse capacity and predicted consumption Determine if it satisfies The minimum consumption time is set as the minimum replenishment time.
[0023] Therefore, the main picking location is the storage location for goods shipped out, while other storage locations are auxiliary storage locations used for inventory adjustments to the main picking location. When forecasting replenishment, it's necessary to consider depleting the inventory in all auxiliary storage locations until the remaining inventory at the main picking location reaches a near-stockout threshold. This threshold is measured by the minimum main picking inventory level, with the specific value set based on actual conditions. The ultimate goal of forecasting is to determine the replenishment time, thereby making adequate preparations for replenishment.
[0024] Secondly, an intelligent warehouse inventory dynamic management platform based on digital twin technology is provided. The system is configured to execute the methods described in the first aspect, including: a data acquisition unit for collecting physical warehouse management data; a model building unit for building a digital twin model based on the physical warehouse management data collected by the data acquisition unit to form a real-time dynamic warehouse twin; a storage location optimization unit for performing storage location optimization analysis based on the real-time dynamic warehouse twin formed by the model building unit to form real-time storage location optimization data; and a replenishment forecasting unit for performing replenishment analysis based on demand forecasting based on the real-time dynamic warehouse twin formed by the model building unit and the real-time storage location optimization data formed by the storage location optimization unit to form replenishment forecasting analysis data.
[0025] Therefore, this platform acquires the basic warehouse management data required for digital twin creation through the data acquisition unit. Based on this, a dynamic digital twin model is established. The storage location optimization unit and replenishment prediction unit can then use this dynamic digital twin model to make more reasonable adjustments and optimizations to storage locations and predict replenishment times, greatly improving warehouse management efficiency while ensuring the efficient and continuous operation of the warehouse. Different functional units are combined to form a tightly integrated system that enables dynamic management. Attached Figure Description
[0026] Figure 1 A schematic diagram illustrating a scenario application of the intelligent warehouse inventory dynamic management platform based on digital twin technology provided in this embodiment of the invention; Figure 2 A flowchart illustrating the intelligent warehouse inventory dynamic management method based on digital twin technology provided in this embodiment of the invention; Figure 3 A schematic diagram illustrating the model construction of the intelligent warehouse inventory dynamic management method based on digital twin technology provided in this embodiment of the invention; Figure 4 A schematic diagram of the structure of an intelligent warehouse inventory dynamic management platform based on digital twin technology provided in an embodiment of the present invention. Detailed Implementation
[0027] The technical solution of the present invention will now be described with reference to the accompanying drawings.
[0028] In the description of the embodiments of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this invention, words such as "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.
[0029] To facilitate understanding of the embodiments of the present invention, firstly, let's take... Figure 1 The present invention describes in detail the intelligent warehouse inventory dynamic management method and system based on digital twin technology, which is applicable to the embodiments of the present invention, using the example of an intelligent warehouse inventory dynamic management scenario based on digital twin technology.
[0030] refer to Figures 1-3 This intelligent warehouse inventory dynamic management method based on digital twin technology is applicable to the above-mentioned platform, and the specific process is as follows: S1: Collect physical warehouse management data, construct a digital twin model, and form a real-time dynamic twin of the warehouse.
[0031] Collect physical warehouse management data, construct a digital twin model, and form a real-time dynamic twin of the warehouse, including: performing full-domain parameterization processing based on physical warehouse management data to form full-domain parameterized data; and performing real-time change analysis of storage locations for inbound and outbound events based on physical warehouse management data to form real-time dynamic management data of storage locations.
[0032] The construction of digital twin models using physical warehouse management data primarily targets the creation of digital twins for warehousing conditions. However, prior to this, it's necessary to quantify and standardize the basic parameters of the warehouse to provide a parameter foundation for the dynamic model of storage locations. This parameterization, utilizing physical warehouse management parameters, involves mapping the entire domain of data, including storage location and operational parameters, into a parameterized manner. This comprehensive data is provided through equipment and facilities, including but not limited to industrial cameras, RFID, LiDAR, PLCs, and temperature / humidity / vibration sensors. After completing the comprehensive parameterization, the focus is on dynamically tracking different storage locations to ensure that the established digital twin can effectively reflect the dynamic status of the storage locations in real time.
[0033] Based on physical warehouse management data, perform full-domain parameterization processing to generate full-domain parameterized data, including: determining the location coordinates of different storage locations based on the physical warehouse management data. ,in, , i represents the storage location number in the warehouse. This represents the position parameter of storage location numbered i in the first direction. This represents the position parameter of storage location numbered i in the second direction. This parameter represents the position of storage location numbered i in the third direction; based on the storage location coordinates of different storage locations... Determine the corresponding equivalent operating distance for the storage location. ,in, , This parameter indicates the location of the warehouse's entrance and exit in the first direction. This indicates the location of the warehouse's entrance and exit in the second direction. This parameter indicates the location of the warehouse's entrance / exit on a third-party upward direction. This represents the equivalence factor for vertical operations; based on physical warehouse management data, the storage capacity of different storage locations is determined. Based on physical warehouse management data, determine the inventory levels of previously stored items at different storage locations at the previous moment. And establish a time-varying matrix based on the previous inventory. Where j represents the ID of a different storage item; based on physical warehouse management data, determine the total number of outbound transactions for each storage item within the previous analysis time window. .
[0034] This application primarily focuses on storage location change analysis and replenishment forecasting based on digital twin data, considering management efficiency. Therefore, the analysis of all parameters needs to fully cover this aspect. All parameterization includes storage location information, the equivalent single-trip operation distance for inbound and outbound operations at storage locations, capacity information for different storage locations, storage quantity information for different stored items at corresponding storage locations, and the number of outbound operations for different stored items within the analysis period. Storage location information forms the basis for subsequent operational analysis at storage locations. Regarding the equivalent single-trip operation distance, since the transportation methods in the horizontal direction differ from those in the vertical direction, there will be differences in energy consumption, etc. The vertical operation equivalence factor can quantify the equivalence of operations in all three directions. The vertical operation equivalence factor can be defined based on the comparison of transportation methods. Storage location capacity is an important basis for subsequently determining whether a storage location can still accommodate storage. Here, the inventory quantity of stored items is obtained from the previous moment. Real-time operations are implemented through event-based conditions, mainly used to establish a reasonable time-varying matrix, providing a data foundation for subsequent analysis. The quantification of the total number of outbound shipments is mainly to provide a reference for subsequent storage location optimization. The quantification of storage location capacity and the inventory of stored goods needs to consider two aspects. First, the basis for both quantifications needs to be consistent, that is, to ensure that the units of the quantification parameters are the same. This avoids increased data analysis complexity or errors due to inconsistent quantification units during subsequent storage location optimization.
[0035] Based on physical warehouse management data, real-time changes in storage locations are analyzed for inbound and outbound events to generate real-time dynamic management data for storage locations. This includes: determining the real-time inbound and outbound times for different storage locations based on physical warehouse management data, and obtaining the corresponding real-time event changes for each storage location. Based on the time-varying matrix of previous inventory Determine the real-time inventory of stored items at each storage location. ,in, Based on different real-time storage inventory levels For the time-varying matrix of the previous inventory Update the data to form a real-time inventory time-varying matrix. .
[0036] The most fundamental aspect of real-time dynamic management of storage locations is the dynamic tracking of the stored items in each location to ensure the accuracy and timeliness of inventory data. This is achieved by dynamically updating the storage quantity in real time based on inbound and outbound events, building upon the previously determined storage quantity. This ensures smooth continuation of subsequent dynamic changes, and the repeated confirmation and updating of inbound and outbound events guarantees the accuracy and timeliness of storage information. For real-time changes in storage location events, the parameter is negative for outbound events and positive for inbound events.
[0037] S2: Perform storage location optimization analysis based on the real-time dynamic twin of the warehouse to generate real-time storage location optimization data.
[0038] Based on the real-time dynamic twin of the warehouse, storage location optimization analysis is performed to generate real-time storage location optimization data, including: based on the real-time dynamic twin of the warehouse, heat-based storage location surface analysis is performed to generate initial storage location surface data; based on the initial storage location surface data, storage location optimization analysis is performed to generate real-time storage location optimization data.
[0039] For different types of stored goods, the frequency and total volume of inbound and outbound operations vary due to differing demands. Adjusting the location of stored goods closer to the inbound / outbound entrance can improve efficiency. Of course, when selecting existing storage locations for inbound / outbound operations, especially for outbound operations, if multiple storage locations exist for the same item, the location closest to the inbound / outbound entrance will be prioritized. For a given storage location, which represents the optimal solution determined in the previous analysis cycle, using a reasonable analysis cycle as a reference for storage location optimization ensures the stability and rationality of adjustments. It's understandable that different stored goods require different numbers of storage locations due to varying storage volumes. Essentially, storage location optimization analysis involves optimizing the storage location area where the stored goods are located, i.e., obtaining the optimal clustering of storage locations required for that specific item, ensuring that inbound / outbound supply efficiently meets demand. Of course, the optimization of storage locations also needs to consider the frequency of use of different storage items. The higher the frequency, the greater the workload of the storage item. Therefore, the closer the storage item with the greater workload is to the inlet and outlet, the higher the management efficiency of the warehouse. Thus, when conducting the analysis, it is also necessary to consider the workload of different storage items. Of course, this consideration is based on the analysis period.
[0040] Based on the real-time dynamic twin of the warehouse, heat-based storage space analysis is performed to generate initial storage space data, including: the total number of outbound transactions corresponding to different stored items. Determine the corresponding storage heat value ,in, J is the maximum value of number j; based on the storage heat value The storage surface analysis is performed on different storage items in descending order of demand as follows: The total periodic demand corresponding to each storage item is obtained. ,in, , This represents the average outbound volume per unit time. Indicates the lead time for replenishment. Indicates the redundancy coefficient; the currently available storage locations are calculated based on the equivalent operating distance of the storage location. Storage is allocated to the corresponding storage items in ascending order of quantity until the total storage capacity of all allocated storage locations is not less than the total periodic demand. The collection of stored items is assigned to all storage locations to form the corresponding initial storage location surface.
[0041] The heat-based storage space analysis primarily aims to provide the total outbound demand for different stored items under the premise that no replenishment is needed in the next cycle. Considering the varying outbound frequencies of different stored items, storage space allocation cannot be arbitrary. This avoids low-frequency outbound items occupying a large number of spaces close to the inbound / outbound entrances, thus reducing warehouse operational efficiency. The heat value of different stored items is based on the proportion of outbound frequency to total outbound volume, thereby determining the order of storage space allocation for different stored items. Storage space allocation for different stored items is based on all currently available storage spaces. The condition for successful allocation is that the total storage capacity of the allocated spaces is not less than the total demand estimated based on the average outbound volume per unit time. The average outbound volume per unit time can be determined based on the outbound levels in previous analysis cycles. The replenishment lead time is the time from the start of the replenishment operation to the actual receipt of the stored item. This time is calculated from the start time of the analysis cycle. Essentially, the replenishment cycle is a predicted inbound replenishment time based on previous analysis cycles. Redundancy coefficients can be set as needed.
[0042] Based on the initial storage level data, storage level optimization analysis is performed to generate real-time storage level optimization data. This includes: for different storage materials, determining the initial storage level corresponding to the storage material to be optimized as the initial target storage level; and for the initial target storage level, determining the storage level equivalent operating distance based on different storage levels. Storage locations are extracted in descending order of capacity. The ratio of the extracted storage locations to the total number of storage locations in the initial storage area does not exceed the optimized storage location ratio. If the ratio of the total capacity of the extracted storage locations to the total capacity of all storage locations in the initial storage area does not exceed the capacity limit ratio, the extracted storage locations are marked as storage locations to be optimized; otherwise, storage location optimization is not performed on the initial target storage area. If there are storage locations to be optimized, the storage location is determined based on the storage heat value. From highest to lowest heat value, storage objects with lower heat values that are adjacent to the initial target storage level are identified and marked as storage objects to be optimized. Within the initial storage level of these storage objects, storage objects are then processed according to their equivalent operating distance. Multiple storage locations are extracted in ascending order of capacity, ensuring that the total capacity of the extracted locations does not exceed the total capacity of all storage locations to be optimized. The extracted storage locations are then combined with the remaining storage locations in the initial target storage location surface after removing the storage locations to be optimized, forming the optimized storage location surface corresponding to the storage item in the initial target storage location surface. All storage locations to be optimized are then combined with the remaining storage locations in the initial storage location surface corresponding to the storage item to be optimized, forming the optimized storage location surface corresponding to the storage item to be optimized. After optimizing the storage locations for all storage items, the total capacity of each optimized storage location surface is verified: if the total capacity of the optimized storage location surface is less than the corresponding total demand for the period... Then, in the currently available storage locations, the equivalent working distance of the storage location will be used. Extract storage sites in ascending order of capacity to the corresponding optimized storage surfaces, ensuring that the total capacity of the optimized storage surfaces is not less than the total demand for the cycle. .
[0043] The purpose of real-time storage location optimization is to adjust the storage locations corresponding to items with relatively low heat values, ensuring that these locations also include good storage locations with shorter equivalent operating distances. However, this optimization must be limited to ensure its rationality. This application optimizes only storage locations adjacent to each other in terms of heat value. This avoids situations where storage locations with inherently low heat values are too close to the inlet / outlet, which would not achieve efficient utilization of storage locations. Of course, to ensure that the optimized storage locations do not significantly change in capacity and require the addition of more vacant storage locations far from the inlet / outlet, the number and capacity of the storage locations to be optimized need to be reasonably controlled. Therefore, the number of storage locations extracted for optimization cannot exceed the optimization ratio, and the capacity cannot exceed the capacity limit ratio, to avoid substantial changes to the storage locations and significantly reducing inlet / outlet efficiency. The optimization ratio and capacity limit ratio can be set according to actual conditions. Once optimizable storage locations are identified, exchanging some storage locations between two storage areas does not guarantee that the total capacity of the exchanged locations will be the same. Therefore, after the exchange, it is necessary to determine whether the total capacity of the storage areas meets the total demand for the cycle, and if not, to supplement a small number of idle storage locations. Although storage location optimization may have a certain negative impact on the operational efficiency of storage locations for high-demand items, it does create storage locations closer to the inbound and outbound entrances for various high-demand items at the overall warehouse management level, thus improving outbound efficiency at the overall level.
[0044] S3: Based on the real-time dynamic twin of the storage location, perform replenishment analysis based on demand forecasting to generate replenishment forecast analysis data.
[0045] Based on the real-time dynamic twin of the storage location, replenishment analysis based on demand forecasting is performed to generate replenishment forecasting analysis data, including: for different optimized storage locations after verification, the equivalent operating distance of the storage location is calculated. The lowest storage location is designated as the primary picking location, and the capacity of the primary picking location is set as the primary picking capacity. The total capacity of the remaining storage locations in the optimized storage area, excluding the main picking location, is determined and marked as the total warehouse transfer capacity. Obtain the demand forecasting function Determine the predicted consumption amount ,in, , Indicates the time consumed; based on the main picking capacity. Total warehouse capacity and predicted consumption We conduct replenishment forecast analysis to generate replenishment forecast analysis data.
[0046] Digital twins establish dynamic warehouse storage location change data, which can be used to make reasonable and effective replenishment forecasts, thereby enabling timely replenishment preparation and improving warehouse management efficiency. Replenishment forecasting is based on demand forecasting. Demand forecasting functions are prediction curves formed by analyzing outbound change data over historical analysis periods, while replenishment forecasting considers changes in the total amount of stored goods. Therefore, forecasting analysis needs to consider the inventory situation across the entire storage area to ensure high turnover of all stored goods.
[0047] Based on master picking capacity Total warehouse capacity and predicted consumption To conduct replenishment forecasting analysis and generate replenishment forecasting analysis data, including: setting the minimum master pick inventory level. Based on the main picking capacity Determine the total allowable consumption of the main picker. ,in, Based on the total allowable consumption of the master picker. Total warehouse capacity and predicted consumption Determine if it satisfies The minimum consumption time is set as the minimum replenishment time.
[0048] The main picking location is the storage location for goods shipped out. Other storage locations are auxiliary storage locations used for inventory adjustments to the main picking location. When forecasting replenishment, it's necessary to consider depleting the inventory in all auxiliary storage locations until the remaining inventory at the main picking location reaches a near-stockout threshold. This threshold is measured by the minimum main picking inventory level, with the specific value set based on actual conditions. The ultimate goal of forecasting is to determine the replenishment time, thereby making adequate preparations for replenishment.
[0049] Figure 4This is a schematic diagram of the structure of an intelligent warehouse inventory dynamic management platform based on digital twin technology provided in an embodiment of the present invention. Exemplarily, the platform includes: a data acquisition unit for acquiring physical warehouse management data; a model building unit for constructing a digital twin model based on the physical warehouse management data acquired by the data acquisition unit, forming a real-time dynamic warehouse twin; a storage location optimization unit for performing storage location optimization analysis based on the real-time dynamic warehouse twin formed by the model building unit, forming real-time storage location optimization data; and a replenishment forecasting unit for performing replenishment analysis based on demand forecasting based on the real-time dynamic warehouse twin formed by the model building unit and the real-time storage location optimization data formed by the storage location optimization unit, forming replenishment forecasting analysis data.
[0050] The platform acquires basic warehouse management data required for digital twin creation through a data acquisition unit. Based on this, a dynamic digital twin model is established. The storage location optimization unit and replenishment prediction unit can then use this dynamic digital twin model to make more reasonable adjustments and optimizations to storage locations and predict replenishment times, greatly improving warehouse management efficiency while ensuring the efficient and continuous operation of the warehouse. Different functional units work together to form a tightly integrated system that enables dynamic management.
[0051] It should be understood that the processor involved in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.
[0052] It should also be understood that the memory involved in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).
[0053] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.
[0054] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0055] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0056] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0057] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0058] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0059] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0060] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0061] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for intelligent warehouse inventory dynamic management based on digital twin technology, characterized in that, The method includes: Collect physical warehouse management data, construct a digital twin model, and form a real-time dynamic twin of the warehouse; Based on the real-time dynamic twin of the warehouse, storage location optimization analysis is performed to generate real-time storage location optimization data; Based on the real-time dynamic twin of the storage location, replenishment analysis based on demand forecasting is performed to generate replenishment forecasting analysis data.
2. The method according to claim 1, characterized in that, The process of collecting physical warehouse management data, constructing a digital twin model, and forming a real-time dynamic twin of the warehouse includes: Based on the physical warehouse management data, perform full-domain parameterization processing to form full-domain parameterized data; Based on the physical warehouse management data, real-time changes in storage locations are analyzed for inbound and outbound events to generate real-time dynamic management data for storage locations.
3. The method according to claim 2, characterized in that, The step of performing global parameterization processing based on the physical warehouse management data to form global parameterized data includes: Based on the physical warehouse management data, the coordinates of different storage locations are determined. ,in, , i represents the storage location number in the warehouse. This represents the position parameter of storage location numbered i in the first direction. This represents the position parameter of storage location numbered i in the second direction. This parameter represents the position of the storage location numbered i in the third direction. Based on the coordinates of the storage locations of different storage locations Determine the corresponding equivalent operating distance for the storage location. ,in, , This parameter indicates the location of the warehouse's entrance and exit in the first direction. This indicates the location of the warehouse's entrance and exit in the second direction. This parameter indicates the location of the warehouse's entrance / exit on a third-party upward direction. Indicates the equivalence factor for vertical operations; Based on the physical warehouse management data, the storage capacity of different storage locations is determined. ; Based on the physical warehouse management data, determine the inventory levels of previously stored items at different storage locations at the previous moment. And establish a time-varying matrix based on the previous inventory. , where j represents the number of the different storage items; Based on the physical warehouse management data, the total number of outbound shipments for different stored items within the previous analysis time window was determined. .
4. The method according to claim 3, characterized in that, The step of performing real-time storage location change analysis based on the physical warehouse management data to generate real-time dynamic storage location management data includes: Based on the physical warehouse management data, determine the real-time inbound and outbound times for different storage locations, and obtain the corresponding real-time event changes for each storage location. ; According to the aforementioned time-varying matrix of the previous inventory Determine the real-time inventory of stored items at each storage location. ,in, ; Based on different real-time storage inventory levels For the time-varying matrix in the previous inventory Update the data to form a real-time inventory time-varying matrix. .
5. The method according to claim 4, characterized in that, The step of performing storage location optimization analysis based on the real-time dynamic twin of the warehouse to generate real-time storage location optimization data includes: Based on the real-time dynamic twin of the warehouse, a heat-based analysis of the storage space is performed to form initial storage space data; Based on the initial reservoir surface data, reservoir optimization analysis is performed to generate real-time reservoir optimization data.
6. The method according to claim 5, characterized in that, The step of performing heat-based storage space analysis based on the real-time dynamic twin of the warehouse to form initial storage space data includes: Based on the total number of outbound transactions corresponding to different storage items Determine the corresponding storage heat value ,in, J is the maximum value of index j; According to the storage heat value The storage surface analysis is performed on different storage materials in descending order as follows: Obtain the total periodic demand corresponding to the storage item. ,in, , This represents the average outbound volume per unit time. Indicates the lead time for replenishment. Indicates the redundancy coefficient; The currently available storage space will be adjusted according to the equivalent working distance of the storage space. Storage is allocated to the corresponding storage items in ascending order of quantity until the total storage capacity of all allocated storage locations is not less than the total demand for the period. ; All storage locations to which the stored items are allocated form the corresponding initial storage surface.
7. The method according to claim 6, characterized in that, The step of performing reservoir optimization analysis based on the initial reservoir surface data to generate the real-time reservoir optimization data includes: For different storage items, the initial storage space corresponding to the storage item undergoing storage space optimization is determined as the initial object storage space. For the initial object storage surface, based on the equivalent operating distance of the storage location for different storage locations. Storage locations are extracted in descending order of their number, and the ratio of the extracted storage locations to the total number of storage locations in the initial storage location surface does not exceed the optimized storage location ratio. If the ratio of the total capacity of the extracted storage location to the total capacity of all storage locations in the initial storage location surface does not exceed the capacity limit ratio, then the extracted storage location will be marked as a storage location to be optimized; otherwise, the initial object storage location surface will not be optimized. If the storage location to be optimized exists, then based on the storage heat value... From high to low, the storage items with lower heat values that are adjacent to the storage items on the initial object storage surface are identified and marked as storage items to be optimized. According to the storage equivalent working distance in the initial storage surface of the storage to be optimized. Multiple storage locations are extracted in ascending order of capacity, ensuring that the total capacity of the extracted storage locations does not exceed the total capacity of all the storage locations to be optimized. The extracted storage locations are combined with the set of remaining storage locations in the initial object storage location surface after removing the storage location to be optimized, to form the optimized storage location surface corresponding to the storage item of the initial object storage location surface. The set of all remaining storage locations in the initial storage location surface corresponding to the storage object to be optimized is used to form the optimized storage location surface corresponding to the storage object to be optimized. After optimizing the storage locations of all stored items, the total capacity of each optimized storage location is verified: If the total capacity of the optimized storage surface is less than the corresponding total demand for the period Then, in the currently available storage location, the equivalent working distance of the storage location will be used. Storage locations are extracted in ascending order of capacity to the corresponding optimized storage surfaces, ensuring that the total capacity of the optimized storage surfaces is not less than the total periodic demand. .
8. The method according to claim 7, characterized in that, The step of performing replenishment analysis based on demand forecasting using the real-time dynamic twin of the storage location to generate replenishment forecast analysis data includes: For the different optimized storage sites after verification, the equivalent operating distance of the storage site is calculated. The lowest storage location is designated as the primary picking location, and the capacity of the primary picking location is set as the primary picking capacity. The total capacity of the remaining storage locations in the optimized storage area, excluding the main picking location, is determined and labeled as the total warehouse capacity. ; Obtain the demand forecasting function Determine the predicted consumption amount ,in, , Indicates the duration of time consumed; Based on the main picking capacity The total capacity of the adjusted warehouse and the predicted consumption Replenishment forecast analysis is performed to generate the replenishment forecast analysis data.
9. The method according to claim 8, characterized in that, The method based on the master picking capacity The total capacity of the adjusted warehouse and the predicted consumption The replenishment forecast analysis is performed to generate the replenishment forecast analysis data, including: Set minimum master pick inventory According to the main picking capacity Determine the total allowable consumption of the main picker. ,in, ; Based on the total allowable consumption of the master picker The total capacity of the adjusted warehouse and the predicted consumption Determine if it satisfies The minimum consumption time is set as the minimum replenishment time.
10. An intelligent warehousing and inventory dynamic management platform based on digital twin technology, characterized in that: Configured to perform the method as described in any one of claims 1-9, comprising: The data acquisition unit is used to collect physical warehouse management data; The model building unit is used to build a digital twin model based on the physical warehouse management data collected by the data acquisition unit, forming a real-time dynamic twin of the warehouse. The storage location optimization unit is used to perform storage location optimization analysis based on the real-time dynamic twin of the warehouse formed by the model construction unit, and to generate real-time storage location optimization data. The replenishment forecasting unit is used to perform replenishment analysis based on demand forecasting based on the real-time dynamic twin of the warehouse formed by the model building unit and the real-time optimization data of the storage location formed by the storage location optimization unit, and to form replenishment forecasting analysis data.
