Efficient intelligent warehousing system and storage method

Abstract

The invention discloses an efficient intelligent warehousing system and a storage method, and relates to the technical field of warehousing management, the system comprises the following components: a virtual digital twinborn model construction module, a business scene simulation module, a potential problem prediction module and an operation process optimization module; according to the system, the virtual digital twinborn model in 1: 1 mapping with the actual storage environment is constructed, synchronous updating is carried out in combination with data collected by the sensor network in real time, the system can accurately reflect the dynamic condition of the actual storage environment, and the service scene simulation module is utilized to simulate the real storage environment. The system can simulate warehousing operation processes in different business scenes in a virtual environment, automatically adjust cargo storage positions, equipment scheduling schemes and personnel task allocation, so that the efficiency and precision of warehousing management are remarkably improved, and in addition, the operation process optimization module can predict and improve the efficiency and accuracy of warehousing management according to simulation results and potential problems. The operation process of the actual warehousing system is automatically optimized, and the overall operation efficiency is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an efficient intelligent warehouse system and storage method. Background Art

[0002] With the rapid development of e-commerce and the logistics industry, warehouse management faces unprecedented challenges. The continuous expansion of warehouse scale, the increasing variety of goods, and the increasing demand for delivery speed from customers have greatly increased the complexity and difficulty of warehouse management. In order to meet these challenges, the warehouse management system needs to have a high level of intelligence and automation, which can reflect the dynamic situation of the warehouse environment in real time and automatically optimize the warehouse operation process to improve management efficiency and accuracy.

[0003] Traditional warehouse management systems mostly use manual management and simple information technology, which has many shortcomings. First, traditional systems cannot reflect the dynamic changes of the warehouse environment in real time, such as the real-time location of goods and the operating status of equipment, making it difficult for managers to obtain accurate information in a timely manner and make scientific decisions. Secondly, traditional systems lack intelligent and automated support in cargo storage location adjustment, equipment scheduling and personnel task allocation, and rely on the experience and intuition of managers, which easily leads to inefficient management and waste of resources. In addition, traditional systems lack the ability to predict potential problems and cannot detect and deal with possible equipment failures and inventory anomalies in advance, increasing operational risks and costs.

[0004] To sum up, the traditional warehouse management system can no longer meet the needs of modern warehouse management. In order to improve the efficiency and accuracy of warehouse management and reduce operating costs and risks, it is particularly important to develop an efficient intelligent warehouse system and storage method. Summary of the Invention

[0005] The purpose of this invention is to make up for the shortcomings of the existing technology and provide an efficient intelligent warehousing system and storage method. It can accurately reflect the dynamic situation of the actual warehousing environment by constructing a virtual digital twin model that is mapped 1:1 with the actual warehousing environment and synchronously updating it in combination with the data collected in real time by the sensor network. At the same time, the system also has functions such as business scenario simulation, potential problem prediction and operation process optimization, which can significantly improve the efficiency and accuracy of warehousing management, reduce costs and improve overall operational efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an efficient intelligent warehousing system includes the following components: a virtual digital twin model construction module, a business scenario simulation module, a potential problem prediction module and an operation process optimization module;

[0007] The virtual digital twin model construction module uses 3D modeling technology to combine the actual warehouse layout, shelf structure, cargo type, and equipment parameter information to build a virtual digital twin model. This model not only includes the physical spatial structure of the warehouse, but also covers the real-time location of cargo, the operating status of equipment, and the dynamic work trajectory of personnel. It collects data from the actual warehouse environment in real time through a sensor network and synchronously updates this data to the virtual digital twin model.

[0008] The business scenario simulation module sets different business scenario simulation parameters based on the virtual digital twin model. The system simulates the operation process of warehousing operations in a virtual environment according to the set scenario parameters. During the simulation process, the model automatically adjusts the storage location of goods, the scheduling plan of equipment, and the task allocation of personnel according to preset rules and algorithms to cope with different business scenarios.

[0009] The potential problem prediction module analyzes the data generated during the simulation process and uses machine learning algorithms and data analysis models to predict potential problems. Once a potential problem is predicted, the system will promptly issue an early warning and provide corresponding solution suggestions;

[0010] The operation process optimization module automatically optimizes the operation process of the actual warehousing system based on simulation results and potential problem predictions. The system sends the optimized operation plan to the warehouse management system to guide warehouse managers to adjust cargo storage strategies, equipment scheduling plans, and personnel work arrangements. At the same time, the system will track the implementation effect of the optimization plan in real time and further adjust the optimization strategy based on actual feedback.

[0011] Furthermore, in the virtual digital twin model construction module, an improved spatial mapping algorithm is used to construct the virtual digital twin model. The algorithm formula is:

[0012]

[0013] Where M is the final constructed virtual digital twin model, n is the number of data dimensions, and w i is the weight of the i-th data dimension, P i is the actual layout data of the warehouse, S i is the shelf structure data, E i is the device parameter data, C i is the cargo type data, weight w i The determination is made through the hierarchical analysis method, inviting experts in the warehousing field to compare and score the importance of each data dimension, constructing a judgment matrix, and calculating after consistency test, the function f iCustomized according to different data types, the spatial coordinate conversion function is used to accurately convert the actual physical coordinates into the coordinates in the virtual model, ensuring that the spatial structure of the model is consistent with the actual one.

[0014] Furthermore, in the business scenario simulation module, for the adjustment of the storage location of goods in the scenario where the order volume increases significantly, an order correlation optimization algorithm is adopted, and the formula is:

[0015]

[0016] Where R is the priority of the new storage area to which the goods should be adjusted, m is the order quantity, α j is the urgency weight of the jth order, and its value is determined by the difference between the expected delivery time of the order and the current time. The smaller the difference, the greater the weight. j is the quantity of the goods included in the j-th order, d j is the historical frequency of the j-th order. The algorithm comprehensively considers the urgency of the order, the quantity of goods in the order, and the historical frequency of the order to accurately determine the area where the goods should be moved to, which is more convenient for picking. Compared with the traditional method that only considers the order quantity, it can more comprehensively optimize the storage location and improve the picking efficiency.

[0017] Furthermore, in the potential problem prediction module, for equipment failure prediction, a prediction algorithm based on the association between time series and equipment performance indicators is adopted, and the formula is:

[0018] F t =β1×x t-1 +β2×y t-1 +β3×z t-1 +∈ t

[0019] Among them F t is the probability of equipment failure at time t, x t-1 is the running speed of the device at the previous moment, y t-1 is the temperature of the device at the previous moment, z t-1 is the power of the device at the previous moment, β1, β2, β3 are the weights of the corresponding parameters, which are obtained by regression analysis of a large number of historical equipment failure data and performance index data at the corresponding moment, ∈ t This algorithm combines multiple key performance indicators of the equipment and can more accurately predict the time and type of equipment failure compared to single indicator prediction, providing early warning for equipment maintenance.

[0020] Furthermore, in the potential problem prediction module, for inventory backlog or stockout prediction, an inventory dynamic balance algorithm is used, and the formula is:

[0021] I k =γ1×sk -γ2×d k +γ3×p k

[0022] Among them I k is the inventory risk index of the kth type of goods, s k is the current inventory quantity, d k The demand for the product in the future is predicted based on historical sales data and market trends. The forecast demand is obtained by exponential smoothing combined with market research data. k is the replenishment cycle of the goods, γ1, γ2, and γ3 are weights. By analyzing the inventory data of different goods in different market environments, the particle swarm optimization algorithm is used to iteratively calculate the optimal weight combination. When I k When the set threshold is exceeded, an early warning may occur, and when I k When the price falls below the set threshold, an early warning of a possible stock-out situation will be issued, providing accurate forecasts for inventory management.

[0023] Furthermore, in the operation process optimization module, for personnel task allocation optimization, a personnel-task matching algorithm is adopted, and the formula is:

[0024] M ij =δ1×e i ×t j +δ2×s i ×d j +δ3×l ij

[0025] Among them, M ij is the matching degree between the i-th person and the j-th task, e i is the skill proficiency of the i-th person, which is obtained through personnel training records and historical work performance evaluation, t j is the difficulty coefficient of the jth task, which is determined based on factors such as the complexity of the task and the number of required steps. i is the current work saturation of the i-th person, which is obtained by counting the ratio of the expected completion time of the tasks he has undertaken to the total working time, d j is the urgency of the jth task, which is determined according to the order delivery time, etc., l ij is the distance between the i-th person's location and the j-th task execution location, calculated through the personnel positioning system and the warehouse map. δ1, δ2, and δ3 are weights. By simulating different personnel and task allocation scenarios and aiming at maximizing overall operational efficiency, the optimal weights are obtained through genetic algorithm search. This algorithm comprehensively considers personnel skills, task characteristics, work saturation, and location factors to achieve more reasonable personnel and task allocation and improve operational efficiency.

[0026] Furthermore, during the sensor network data collection process, an adaptive data collection frequency adjustment algorithm is adopted, and the formula is:

[0027] f a =f0×(1+θ1×Δx+θ2×Δy+θ3×Δz)

[0028] where f a is the adjusted sensor data acquisition frequency, f0 is the initial acquisition frequency, Δx is the rate of change of the equipment operating status, which is calculated by the difference between the current operating parameters of the equipment and the parameters at the previous moment, Δy is the rate of change of the frequency of goods entering and leaving the warehouse, which is calculated based on the change in the number of goods entering and leaving the warehouse per unit time, Δz is the complexity of the change in the personnel's movement trajectory, which is measured by the change in the personnel's movement speed and the number of changes in the movement direction, θ1, θ2, and θ3 are weights. According to the requirements of different types of sensors for data timeliness in different warehousing scenarios, the data is determined through expert experience combined with fuzzy comprehensive evaluation method. When the storage environment changes drastically, the sensor acquisition frequency is automatically increased to ensure timely acquisition of key data to update the virtual digital twin model. When the environment is stable, the acquisition frequency is reduced to save energy and data transmission bandwidth.

[0029] Furthermore, during the data interaction between the virtual digital twin model and the actual warehouse system, a data consistency verification algorithm is adopted, and the formula is:

[0030]

[0031] Where C is the data consistency index, q is the number of data check items, v k is the data value in the virtual digital twin model, r k is the corresponding data value in the actual warehousing system, λ k is the importance weight of the kth data verification item, which is determined by the hierarchical analysis method based on the degree of influence of the data on the warehousing operation decision. When C exceeds the set threshold, the system automatically starts the data tracing and repair process. By comparing the timestamps and transmission log information of the sensor collected data, the source of the data inconsistency is found and corrected, ensuring that the virtual digital twin model and the actual warehousing system always maintain data consistency, providing a reliable data foundation for subsequent simulation, prediction and optimization.

[0032] Furthermore, in the business scenario simulation module, for the simulation of sudden equipment failure scenarios, a fault propagation and impact analysis algorithm is used, and the formula is:

[0033]

[0034] Among them I l is the fault impact index of the lth affected device or operation link, u is the number of devices or operation links associated with the faulty device, μh is the weight of the degree of association between the hth associated device or operation link and the faulty device, which is determined by analyzing the physical connection relationship between the devices, the upstream and downstream relationship of the operation process, etc. h is the importance coefficient of the hth associated equipment or operation link itself, which is obtained based on its criticality in the warehousing operation and the factors affecting the overall efficiency. hl is the probability of a fault propagating from the hth associated object to the lth object. This is obtained through statistical analysis of historical cases of similar fault propagation. The algorithm can accurately simulate the propagation path of a sudden equipment failure in the warehouse system and the degree of impact on other equipment and operational links, providing a detailed basis for formulating response strategies. Compared with simple fault hypothesis simulations, it is more in line with the actual impact of faults in complex warehouse environments.

[0035] On the other hand, an efficient intelligent storage method comprises the following specific steps:

[0036] S1. Virtual digital twin model construction steps: Build a virtual digital twin model that maps 1:1 with the actual warehouse environment. Specifically, utilize a sensor network to collect real-time data on goods in and out of the warehouse, equipment operating parameters, and personnel movement paths in the actual warehouse environment. This data is then synchronously updated into the virtual digital twin model, enabling the virtual model to accurately reflect the dynamic conditions of the actual warehouse environment.

[0037] S2. Business scenario simulation setting step: Based on the constructed virtual digital twin model, simulation parameters for different business scenarios are set. By setting these parameters, the warehouse operation process is simulated in the virtual environment. The simulation process covers a series of warehouse-related activities such as cargo storage, handling, equipment scheduling, and personnel operation;

[0038] S3. Simulation Data Prediction and Analysis Step: Conduct in-depth analysis of the data generated during the simulation process, using specific algorithms and data analysis tools to uncover potential patterns in the simulation data and predict potential problems, including but not limited to equipment failures, inventory anomalies, and low operational efficiency.

[0039] S4. Operation process optimization execution steps: Based on the simulation results and the prediction of potential problems, the operation process of the actual warehousing system is automatically optimized, and the optimized operation plan is applied to the actual warehousing management. The cargo storage strategy, equipment scheduling plan and personnel work arrangement are adjusted to improve the overall operation efficiency and reliability of the warehousing system.

[0040] Compared with the existing technology, this efficient intelligent warehousing system and storage method have the following beneficial effects:

[0041] 1. The present invention constructs a virtual digital twin model that is mapped 1:1 with the actual warehousing environment, and updates it synchronously with the data collected in real time by the sensor network. The system can accurately reflect the dynamic situation of the actual warehousing environment. Using the business scenario simulation module, the system can simulate the warehousing operation process under different business scenarios in a virtual environment, automatically adjust the storage location of goods, equipment scheduling plan and personnel task allocation, thereby significantly improving the efficiency and accuracy of warehousing management. In addition, the operation process optimization module can automatically optimize the operation process of the actual warehousing system based on the simulation results and potential problem predictions, further improving the overall operational efficiency.

[0042] 2. By analyzing the data generated during the simulation process and using machine learning algorithms and data analysis models, the present invention can predict possible equipment failures and potential inventory anomalies, and promptly issue early warning information and provide corresponding solution suggestions. This not only helps managers take measures in advance to prevent problems from occurring, but also avoids decreased production efficiency and increased costs caused by problems. At the same time, the application of adaptive data acquisition frequency adjustment algorithm and data consistency verification algorithm ensures the accuracy and timeliness of system data, provides a reliable data basis for subsequent simulation, prediction and optimization, and further reduces operating costs.

[0043] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0045] Figure 1 This is an efficient intelligent warehousing system process operation diagram;

[0046] Figure 2 The flowchart of an efficient intelligent storage method is shown. DETAILED DESCRIPTION

[0047] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0048] Example 1

[0049] This example describes the explosive growth in order volume during e-commerce promotions, which places extremely high demands on the efficient operation of the warehousing system. A large e-commerce company's regional central warehouse adopted this intelligent warehousing system, effectively responding to the challenges of the promotion and achieving intelligent and efficient warehouse management.

[0050] With advanced 3D modeling technology and improved spatial mapping algorithms A virtual digital twin model is constructed by combining the actual warehouse layout, shelf structure, cargo type and equipment parameter information. The warehouse is filled with various sensors, which are like sensitive tentacles, collecting real-time cargo entry and exit records, equipment operating parameters, and personnel movement path data. For example, when goods enter and exit the warehouse, sensors installed on shelves and aisles can accurately record the type, quantity, entry and exit time and corresponding shelf position of the goods. Sensors on the equipment continuously monitor the equipment's operating speed, power, and working time parameters. Positioning devices worn by personnel can track their movement trajectories in the warehouse. These data are synchronized to the virtual digital twin model in real time through high-speed networks, ensuring that the model can accurately reflect the dynamic changes in the actual storage environment, providing a solid data foundation for subsequent simulation and optimization.

[0051] In the scenario of a significant increase in order volume, simulation parameters are set in the business scenario simulation module, and an order correlation optimization algorithm is used. Adjust the storage location of goods. Take a popular electronic product as an example. During the promotion period, this product appeared in a large number of urgent orders, and the quantity in each order was large. At the same time, its historical frequency of appearance was also high. Through algorithm calculation, the new storage area priority R value of this product is higher. Based on this, the system adjusts it to an area that is closer to the sorting area and more convenient for picking. During the adjustment process, the system automatically plans the transportation route, dispatches the transportation equipment, and quickly transfers the electronic product to the target location, greatly shortening the picking time and improving order processing efficiency.

[0052] Using the prediction algorithm based on the association between time series and equipment performance indicators (F t =β1×x t-1 +β2×y t-1 +β3×z t-1 +∈ t ) Predict equipment failure. For example, the automatic sorting equipment in the warehouse has been running stably before the big promotion, but by measuring its running speed x at the previous moment, t-1 , temperature y t-1 , power z t-1 The data is analyzed and the prediction algorithm shows that during the peak promotion period, the probability of failure of the device is F. tIf the safety threshold is exceeded, the system will issue early warning information in time and provide corresponding maintenance suggestions, such as preparing spare parts in advance and arranging technicians to be on standby. At the same time, the dynamic inventory balance algorithm (I k =γ1×s k -γ2×d k +γ3×p k ) Predict inventory backlog or out-of-stock situations. For a popular clothing item, based on the current inventory quantity s k , combining historical sales data and market trends to predict future demand k , and the replenishment period p k , calculate its inventory risk index I k , if I k If the set threshold is exceeded, the system will warn that there may be inventory backlogs. Enterprises can adjust their marketing strategies in time, such as launching promotional activities. k If the price falls below the set threshold, an early warning will be issued regarding a possible stock-out. The company can arrange for replenishment in advance to avoid customer loss due to stock-outs.

[0053] According to the simulation results and potential problem prediction, the operation process optimization module uses the personnel-task matching algorithm (M ij =δ1×e i ×t j +δ2×s i ×d j +δ3×l ij ) Optimize personnel task allocation. During the promotion period, there is an urgent order that needs to be processed. The order contains multiple goods and the task is difficult. The system assigns tasks based on the personnel's skill proficiency. i , current working saturation i and the distance l between the personnel location and the task execution location ij , combined with the urgency of the task d j and difficulty coefficient t j , calculate the matching degree M between each person and the task ij Finally, an employee with high skill proficiency, low workload and close proximity to the task execution location was assigned to handle the order, which greatly improved the efficiency and accuracy of order processing. At the same time, the system tracked the implementation effect of the optimization plan in real time and further adjusted the optimization strategy based on actual feedback to ensure that the warehousing system always maintained efficient operation during the promotion period.

[0054] Example 2

[0055] This example describes a large manufacturing company. With the rapid expansion of its business scale, the original warehouse can no longer meet the growing storage and logistics needs. To this end, the company built a new modern warehouse. The new warehouse has a more complex spatial layout, with multiple layers of shelves, various types of storage areas, and advanced automated handling equipment. Before opening the new warehouse, the company faced the challenge of how to determine the most reasonable cargo storage layout, equipment configuration, and personnel workflow to achieve efficient warehouse management, reduce operating costs, and ensure smooth production.

[0056] With the help of professional 3D modeling software, the company accurately constructs a virtual digital twin model based on the architectural drawings of the new warehouse, shelf design plans, and the size, weight, and storage characteristics of various production raw materials and finished products. Various sensors in the warehouse, such as cargo position sensors installed on shelves, operating status sensors on handling equipment, and positioning devices that record personnel movement trajectories, continuously transmit and synchronously update the real-time collected data to the virtual model, which enables the virtual model to dynamically reflect the actual situation in the warehouse and provide an accurate foundation for subsequent simulation and analysis.

[0057] Based on the virtual digital twin model, the company's warehouse management team began to set a variety of simulation parameters. For cargo storage strategies, they tried different storage layouts based on product categories, production batches, and in-and-out frequencies. In terms of equipment scheduling plans, they considered the quantity combination, driving path planning, and task allocation rules of different handling equipment (such as forklifts, automated guided vehicles (AGVs), etc.). For personnel task allocation, they simulated the division of responsibilities and workload arrangements of different positions (such as warehouse managers, forklift drivers, sorters, etc.).

[0058] Through in-depth analysis of large amounts of simulation data, the system successfully predicted a series of potential problems. In terms of storage layout, it was found that placing large but lightweight raw materials at the bottom of high-rise shelves would require frequent adjustments to the height of the handling equipment during transportation, wasting time and energy. In terms of equipment configuration, if there are too many automated guided vehicles (AGVs), congestion will frequently occur in narrow aisles, reducing overall transportation efficiency. The problem of unreasonable allocation of personnel tasks is also more prominent. For example, some warehouse managers are responsible for too large an area, resulting in excessively long inventory and search times, while staff in some areas are idle for a long time.

[0059] Based on the simulation results and predictions of potential problems, the system automatically generated an optimized work process plan. In terms of warehouse layout optimization, large and lightweight raw materials were moved to the middle position of the high-rise shelves to facilitate quick access by handling equipment. For equipment scheduling, the number of AGVs was reduced, and the driving routes were replanned, and reasonable avoidance rules were set to effectively avoid congestion. In terms of personnel task allocation, the work areas were re-divided according to the cargo storage volume and operation complexity of the warehouse area to ensure a relatively balanced workload for each staff member. At the same time, the optimized plan also includes a detailed equipment maintenance plan and personnel training arrangements to ensure its smooth implementation.

[0060] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An efficient intelligent warehousing system, characterized by: The system includes the following components: a virtual digital twin model construction module, a business scenario simulation module, a potential problem prediction module, and an operation process optimization module: The virtual digital twin model construction module uses 3D modeling technology to combine the actual warehouse layout, shelf structure, cargo type, and equipment parameter information to build a virtual digital twin model. This model not only includes the physical spatial structure of the warehouse, but also covers the real-time location of cargo, the operating status of equipment, and the dynamic work trajectory of personnel. It collects data from the actual warehouse environment in real time through a sensor network and synchronously updates this data to the virtual digital twin model. The business scenario simulation module sets different business scenario simulation parameters based on the virtual digital twin model. The system simulates the operation process of warehousing operations in a virtual environment according to the set scenario parameters. During the simulation process, the model automatically adjusts the storage location of goods, the scheduling plan of equipment, and the task allocation of personnel according to preset rules and algorithms to cope with different business scenarios. The potential problem prediction module analyzes the data generated during the simulation process and uses machine learning algorithms and data analysis models to predict potential problems. Once a potential problem is predicted, the system will promptly issue an early warning and provide corresponding solution suggestions; The operation process optimization module automatically optimizes the operation process of the actual warehousing system based on simulation results and potential problem predictions. The system sends the optimized operation plan to the warehouse management system to guide warehouse managers to adjust cargo storage strategies, equipment scheduling plans, and personnel work arrangements. At the same time, the system will track the implementation effect of the optimization plan in real time and further adjust the optimization strategy based on actual feedback.

2. An efficient intelligent warehousing system according to claim 1, characterized in that: In the virtual digital twin model construction module, an improved spatial mapping algorithm is used to construct the virtual digital twin model. The algorithm formula is: Where M is the final constructed virtual digital twin model, n is the number of data dimensions, and w i is the weight of the i-th data dimension, P i is the actual layout data of the warehouse, S i is the shelf structure data, E i is the device parameter data, C i For the cargo type data, function f i It is customized according to different data types and uses spatial coordinate conversion functions to accurately convert actual physical coordinates into coordinates in the virtual model.

3. The efficient intelligent warehousing system according to claim 1, characterized in that: In the business scenario simulation module, for the adjustment of cargo storage location in the scenario where the order volume increases significantly, an order correlation optimization algorithm is used, and the formula is: Where R is the priority of the new storage area to which the goods should be adjusted, m is the order quantity, α j is the urgency weight of the jth order, o j is the quantity of the goods included in the j-th order, d j is the historical frequency of the j-th order. The algorithm comprehensively considers the urgency of the order, the quantity of goods in the order, and the historical frequency of the order to accurately determine the area where the goods should be adjusted to be more convenient for picking.

4. The efficient intelligent warehousing system according to claim 1, characterized in that: In the potential problem prediction module, for equipment failure prediction, a prediction algorithm based on the association between time series and equipment performance indicators is adopted, and the formula is: F t =β1×x t-1 +β2×y t-1 +β3×z t-1 +∈ t Among them F t is the probability of equipment failure at time t, x t-1 is the running speed of the device at the previous moment, y t-1 is the temperature of the device at the previous moment, z t-1 is the power of the device at the previous moment, β1, β2, β3 are the weights of the corresponding parameters, ∈ t is the error term.

5. The efficient intelligent warehousing system according to claim 1, characterized in that: In the potential problem prediction module, for inventory backlog or stockout prediction, the inventory dynamic balance algorithm is adopted, and the formula is: I k =γ1×s k -γ2×d k +γ3×p k Among them I k is the inventory risk index of the kth type of goods, s k is the current inventory quantity, d k is the demand for the product in the future predicted based on historical sales data and market trends, k is the replenishment cycle of the goods, γ1, γ2, γ3 are weights, when I k When the set threshold is exceeded, an early warning may occur, and when I k When the price falls below the set threshold, an early warning is issued that a stock-out situation may occur.

6. The efficient intelligent warehousing system according to claim 1, characterized in that: In the work process optimization module, for personnel task allocation optimization, the personnel-task matching algorithm is adopted, and the formula is: M ij =δ1×e i ×t j +δ2×s i ×d j +δ3×l ij Among them, M ij is the matching degree between the i-th person and the j-th task, e i is the skill proficiency of the i-th person, t j is the difficulty coefficient of the jth task, s i is the current job saturation of the i-th person, d j is the urgency of the jth task, l ij is the distance between the location of the i-th person and the location where the j-th task is executed, and δ1, δ2, and δ3 are weights.

7. The efficient intelligent warehousing system according to claim 1, characterized in that: During the sensor network data collection process, an adaptive data collection frequency adjustment algorithm is used, and the formula is: f a =f0×(1+θ1×Δx+θ2×Δy+θ3×Δz) where f a is the adjusted sensor data collection frequency, f0 is the initial collection frequency, Δx is the rate of change of the equipment operating status, Δy is the rate of change of the frequency of goods in and out of the warehouse, which is calculated based on the change in the number of goods in and out of the warehouse per unit time, Δz is the complexity of the change in the personnel's movement trajectory, which is measured by the change in the personnel's movement speed and the number of changes in the movement direction. θ1, θ2, and θ3 are weights. When the storage environment changes drastically, the sensor collection frequency is automatically increased to ensure timely acquisition of key data to update the virtual digital twin model. When the environment is stable, the collection frequency is reduced.

8. The efficient intelligent warehousing system according to claim 1, characterized in that: During the data interaction between the virtual digital twin model and the actual warehouse system, a data consistency verification algorithm is adopted, and the formula is: Where C is the data consistency index, q is the number of data check items, v k is the data value in the virtual digital twin model, r k is the corresponding data value in the actual warehousing system, λ k is the importance weight of the kth data verification item. When C exceeds the set threshold, the system automatically starts the data tracing and repair process. By comparing the timestamps of the sensor collected data and the transmission log information, the source of the data inconsistency is found and corrected.

9. The efficient intelligent warehousing system according to claim 1, characterized in that: In the business scenario simulation module, for the simulation of sudden equipment failure scenarios, the fault propagation and impact analysis algorithm is adopted, and the formula is: Among them I l is the fault impact index of the lth affected device or operation link, u is the number of devices or operation links associated with the faulty device, μ h is the weight of the closeness of the association between the hth associated equipment or operation link and the faulty equipment, a h is the importance coefficient of the hth associated equipment or operation link itself, b hl is the probability of a fault propagating from the hth associated object to the lth object. The algorithm can accurately simulate the propagation path of a sudden equipment failure in the warehouse system and the degree of impact on other equipment and operation links, providing a detailed basis for formulating response strategies.

10. An efficient intelligent storage method, applicable to an efficient intelligent storage system according to any one of claims 1 to 9, characterized in that: The specific steps of this method are: S1. Virtual digital twin model construction steps: Build a virtual digital twin model that maps 1:1 with the actual warehouse environment. Specifically, utilize a sensor network to collect real-time data on goods in and out of the warehouse, equipment operating parameters, and personnel movement paths in the actual warehouse environment. This data is then synchronously updated into the virtual digital twin model, enabling the virtual model to accurately reflect the dynamic conditions of the actual warehouse environment. S2. Business scenario simulation setting step: Based on the constructed virtual digital twin model, simulation parameters for different business scenarios are set. By setting these parameters, the warehouse operation process is simulated in the virtual environment. The simulation process covers a series of warehouse-related activities such as cargo storage, handling, equipment scheduling, and personnel operation; S3. Simulation Data Prediction and Analysis Step: Conduct in-depth analysis of the data generated during the simulation process, using specific algorithms and data analysis tools to uncover potential patterns in the simulation data and predict potential problems, including but not limited to equipment failures, inventory anomalies, and low operational efficiency. S4. Operation process optimization execution steps: Based on the simulation results and the prediction of potential problems, the operation process of the actual warehousing system is automatically optimized, and the optimized operation plan is applied to the actual warehousing management. The cargo storage strategy, equipment scheduling plan and personnel work arrangement are adjusted to improve the overall operation efficiency and reliability of the warehousing system.

Images