Intelligent warehouse management system and method

Abstract

The invention relates to the technical field related to storage management, in particular to an intelligent warehouse management system and method, and the method comprises the steps: determining operation influence factors according to historical warehouse data, carrying out the parameter iteration optimization of a warehouse scheduling model corresponding to a warehouse operation detection index till the maximum number of iterations is reached, and determining a storage scheduling scheme list according to the material classification database, the storage layout database and the equipment scheduling database. The technical problems of low material positioning precision and insufficient inventory accuracy caused by separation of storage partition planning and an AGV carrying path and difficulty in effective consideration of the space utilization rate and the warehouse-in and warehouse-out efficiency are solved, the material storage channel, the material carrying channel and the inventory monitoring channel are integrated through the warehouse scheduling model, the matching degree of the storage planning and the AGV path is improved, and the accuracy of the storage planning and the AGV path is improved. The continuous parameter iteration enables the warehouse scheduling model to adapt to order fluctuation and equipment state change in real time, and improves the material positioning precision and inventory accuracy.

Description

Technical Field

[0001] This invention relates to the field of storage management technology, specifically to an intelligent warehouse management system and method. Background Technology

[0002] Mixed storage of multiple types of goods, high-frequency inbound and outbound operations, and cross-scenario collaborative operations have become the norm in warehouse operations. At the same time, the popularization of intelligent equipment such as AGVs, RFID, and visual recognition, as well as the maturity of technologies such as big data and reinforcement learning, have provided technical support for the transformation of warehouse management towards intelligent driving. However, warehouse scheduling relies heavily on the experience of management personnel and has poor adaptability to actual operational needs. For example, fragile items are mixed with ordinary materials, high-turnover materials are stored in remote locations, and scheduling model parameters are fixed. When AGVs run out of power or RFID reading and writing malfunctions, scheduling strategies cannot be optimized in a timely manner, which can easily lead to operational interruptions.

[0003] In summary, existing technologies suffer from several technical problems: storage partitioning planning is disconnected from AGV transport paths, making it difficult to effectively balance space utilization and inbound / outbound efficiency. Furthermore, they cannot be dynamically adjusted based on fluctuations in order volume and changes in equipment load, resulting in low material positioning accuracy and insufficient inventory accuracy. Summary of the Invention

[0004] This application provides an intelligent warehouse management system and method, aiming to solve the technical problems in the prior art, such as the disconnect between storage zoning planning and AGV handling paths, the difficulty in effectively balancing space utilization and inbound / outbound efficiency, the inability to dynamically adjust according to order volume fluctuations and equipment load changes, resulting in low material positioning accuracy and insufficient inventory accuracy.

[0005] In view of the above problems, the technical solution to achieve the present application is as follows: In a first aspect, this application provides an intelligent warehouse management system, comprising: a warehouse scheduling model establishment module, used to establish a warehouse scheduling model corresponding to warehouse operation monitoring indicators based on material storage channels, material handling channels, and inventory monitoring channels, wherein the warehouse operation monitoring indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy; an operation influencing factor determination module, used to determine operation influencing factors including material attributes, order characteristics, warehouse layout, and equipment operating status based on historical warehouse data; an iterative optimization module, used to perform parameter iterative optimization of the warehouse scheduling model based on the operation influencing factors until the maximum number of iterations is reached; and a warehouse scheduling scheme list determination module, used to determine a warehouse scheduling scheme list by referring to a material classification database, a warehouse layout database, and an equipment scheduling database using the iteratively optimized warehouse scheduling model.

[0006] Preferably, the historical warehousing data is classified according to operational efficiency, wherein the historical warehousing data includes scheduling parameter configuration, inventory fluctuation curve, order processing time, equipment failure records, and inventory error data; based on the classified historical warehousing data, the operational influencing factors corresponding to the mapping relationship are obtained by using an association rule algorithm.

[0007] Preferably, the equipment operating status includes AGV endurance, RFID reader sensitivity, e-ink screen display status, and access control permission matching degree; the warehouse scheduling model is used to integrate the collaborative operation of intelligent partitioned storage, AGV automatic handling, RFID one-key point and electronic tag precise guidance.

[0008] Preferably, a reinforcement learning mechanism is introduced, which uses the reduction of optimization error and the improvement of operational indicators as reward signals, and the increase of optimization error and equipment malfunction as penalty signals, and dynamically adjusts the weight coefficients of the material storage channel, material handling channel and inventory monitoring channel.

[0009] Preferably, the operational complexity index is assessed based on the warehouse order volume, material turnover frequency, and equipment load rate; the maximum number of iterations is dynamically configured according to the PID feedback adjustment mechanism based on the operational complexity index.

[0010] Preferably, the deviation between the actual operating efficiency and the expected efficiency corresponding to the collaborative scheduling parameters output by the warehouse scheduling model is taken as the optimization error; the optimization error is taken as the objective function for iterative optimization, and the material partition storage parameters, AGV driving path parameters, RFID inventory frequency and electronic ink screen lighting prompt logic are adjusted in each iteration.

[0011] Preferably, a multimodal sensing terminal, including an RFID reader / writer, a visual camera, an infrared access control system, and a temperature and humidity sensor, is connected to mark the storage location and real-time status of materials; based on the storage location and real-time status of materials, storage strategies, handling path schemes, and inventory monitoring schemes corresponding to the material classification database, warehouse layout database, and equipment scheduling database are matched to construct a differentiated warehousing basic framework; and a list of warehousing scheduling schemes is determined according to the differentiated warehousing basic framework.

[0012] In a second aspect, this application provides an intelligent warehouse management method, comprising: establishing a warehouse scheduling model corresponding to warehouse operation monitoring indicators based on material storage channels, material handling channels, and inventory monitoring channels, wherein the warehouse operation monitoring indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy; determining operational influencing factors including material attributes, order characteristics, warehouse layout, and equipment operating status based on historical warehouse data; iteratively optimizing the parameters of the warehouse scheduling model based on the operational influencing factors until the maximum number of iterations is reached; and determining a list of warehouse scheduling schemes by comparing the iteratively optimized warehouse scheduling model with a material classification database, a warehouse layout database, and an equipment scheduling database.

[0013] In summary, one or more technical solutions provided in this application achieve the technical effect of integrating material storage channels, material handling channels, and inventory monitoring channels through a warehouse scheduling model, thereby improving the matching degree between storage planning and AGV paths, and enabling the warehouse scheduling model to adapt to order fluctuations and equipment status changes in real time through continuous parameter iteration, thus improving the accuracy of material positioning and inventory counting. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0015] Figure 1 This application provides a structural diagram of an intelligent warehouse management system.

[0016] Figure 2 This application provides a flowchart illustrating an intelligent warehouse management method.

[0017] Figure labeling: Module 11 for establishing the warehouse scheduling model, Module 12 for determining the factors affecting operations, Module 13 for iterative optimization, and Module 14 for determining the list of warehouse scheduling schemes. Detailed Implementation

[0018] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] Example 1: The present application will be described in detail below with reference to the accompanying drawings, as follows... Figure 1 As shown, this application provides an intelligent warehouse management system, the system comprising: The warehouse scheduling model establishment module 11 is used to establish a warehouse scheduling model corresponding to warehouse operation detection indicators based on material storage channels, material handling channels, and inventory monitoring channels. The warehouse operation detection indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy. The operation influencing factor determination module 12 is used to determine the operation influencing factors, including material attributes, order characteristics, warehouse layout, and equipment operating status, based on historical warehouse data.

[0020] In one embodiment, the warehouse scheduling model building module is based on material storage channels, material handling channels, and inventory monitoring channels. By integrating these channels, it establishes a mathematical model reflecting the warehouse operation status. Warehouse operation monitoring indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy, which are used to quantify the efficiency and accuracy of warehouse operations. The operation influencing factor determination module is a component in the system used to analyze historical warehouse data. Its purpose is to identify factors that have a significant impact on warehouse operations, such as material attributes, order characteristics, warehouse layout, and equipment operating status. These factors are determined by analyzing historical warehouse data.

[0021] Optionally, the warehouse scheduling model building module integrates data from material storage channels, material handling channels, and inventory monitoring channels to construct a model that comprehensively reflects the warehouse operation status. Specifically, data from material storage channels can include information such as the storage location and density of materials; data from material handling channels can include information such as the AGV's travel path and handling task allocation; and data from inventory monitoring channels can include information such as inventory quantity and material status. By combining this data with warehouse operation monitoring indicators, the warehouse scheduling model can evaluate the efficiency and accuracy of warehouse operations in real time. Furthermore, by analyzing material positioning accuracy, it can optimize storage layout and reduce the time spent searching for materials; by analyzing space utilization, it can rationally plan storage space and improve warehouse storage capacity; by analyzing inbound and outbound efficiency, it can optimize AGV travel paths and reduce handling time; and by analyzing inventory accuracy, it can optimize the inventory process and reduce inventory errors.

[0022] The module for determining operational influencing factors identifies factors that significantly impact warehousing operations through analysis of historical warehousing data. Specifically, analysis of historical order data determines the impact of order characteristics, including order volume and frequency, on warehouse layout; analysis of equipment operating status data determines the impact of equipment malfunctions, such as insufficient AGV battery life and RFID read / write anomalies, on warehouse scheduling. These influencing factors provide crucial data support for optimizing the warehouse scheduling model. Furthermore, if historical data shows that the remote storage location of high-turnover materials leads to low inbound and outbound efficiency, then when optimizing the scheduling model, priority is given to adjusting the storage location of high-turnover materials to be closer to the inbound and outbound entrances. In this way, the warehouse scheduling model can dynamically adjust according to actual operational needs, improving the overall efficiency and accuracy of warehouse operations.

[0023] The iterative optimization module 13 is used to iteratively optimize the parameters of the warehouse scheduling model based on the operational influencing factors until the maximum number of iterations is reached; the warehouse scheduling scheme list determination module 14 is used to determine the warehouse scheduling scheme list by referring to the material classification database, warehouse layout database and equipment scheduling database with the iteratively optimized warehouse scheduling model.

[0024] In one embodiment, the iterative optimization module gradually optimizes the warehouse scheduling model by adjusting the model parameters multiple times to improve its performance and adaptability. Furthermore, each iteration fine-tunes the model parameters based on operational influencing factors until the preset maximum number of iterations is reached. The warehouse scheduling scheme determination module generates a series of feasible warehouse scheduling schemes based on the optimized warehouse scheduling model, combined with the material classification database, warehouse layout database, and equipment scheduling database. These warehouse scheduling schemes can be flexibly adjusted according to different operational scenarios and needs to meet the diverse requirements of actual operations.

[0025] Optionally, the iterative optimization module gradually adjusts the parameters of the warehouse scheduling model to better adapt to actual operational needs. Specifically, if the initial model performs poorly in terms of material positioning accuracy, the iterative optimization module will adjust the relevant parameters based on operational influencing factors, including order characteristics and equipment operating status. Each iteration calculates the deviation between the model's actual operating efficiency and expected efficiency, using this as the objective function for optimization. Through multiple iterations, the model parameters are gradually adjusted to the optimal state, thereby improving key indicators such as material positioning accuracy, space utilization, and inbound / outbound efficiency.

[0026] By utilizing an optimized warehouse scheduling model and combining it with a material classification database, a warehouse layout database, and an equipment scheduling database, specific warehouse scheduling plans are generated. Specifically, based on information from the material classification database, the most suitable storage locations are allocated to different types of materials, including fragile items and high-turnover materials; based on the warehouse layout database, the storage layout is optimized to improve space utilization; and based on the equipment scheduling database, AGV tasks are rationally arranged to avoid equipment overload or idleness. In this way, a series of precise scheduling plans are generated to meet the warehousing needs in different scenarios. Furthermore, during peak order periods, a scheduling plan is generated to prioritize the outbound shipment of high-turnover materials, ensuring maximum inbound and outbound efficiency.

[0027] Furthermore, the task influencing factor determination module 12 is used to perform the following method: The historical warehousing data is categorized according to operational efficiency. The historical warehousing data includes scheduling parameter configurations, inventory fluctuation curves, order processing times, equipment failure records, and inventory error data. Based on the categorized historical warehousing data, an association rule algorithm is used to mine the operational influencing factors corresponding to the mapping relationships.

[0028] In one embodiment, classifying historical warehousing data by operational efficiency means dividing historical data into different categories based on the actual efficiency performance of warehousing operations. Operational efficiency can be measured by various indicators, such as inbound and outbound time and inventory turnover rate. Historical warehousing data includes scheduling parameter configurations, inventory fluctuation curves, order processing time, equipment failure records, and inventory error data. These data record various information in the warehousing operation process and are an important basis for analyzing and optimizing the scheduling model. Using association rule algorithms to mine the corresponding operational influencing factors means using association rule algorithms in data mining technology to find the inherent connections and influence relationships between different factors from the classified historical data. Association rule algorithms can discover frequently occurring patterns and rules in the data, thereby determining which factors have a significant impact on warehousing operations.

[0029] Optionally, historical warehouse data can be categorized based on operational efficiency. For example, data can be divided into high-efficiency and low-efficiency operating periods. High-efficiency operating periods correspond to time periods with long order processing times and low inventory fluctuations, while low-efficiency operating periods correspond to time periods with frequent equipment failures and large inventory count errors. This categorization helps the system more accurately identify problems and optimization directions in different scenarios. Furthermore, by analyzing data from high-efficiency operating periods, it can be found that certain scheduling parameter configurations have a significant effect on improving inbound and outbound efficiency; data from low-efficiency operating periods reveals the impact of equipment failures on inventory count accuracy.

[0030] Association rule algorithms were used to mine operational influencing factors from categorized data. Specifically, analysis revealed that during high-efficiency operation periods with short order processing times, high-turnover materials were typically stored near the inbound and outbound ports, indicating that warehouse layout directly impacts inbound and outbound efficiency. Furthermore, the association rule algorithm also found that inventory accuracy was higher when there were fewer equipment failure records, demonstrating that equipment operating status is crucial for inventory efficiency. This approach accurately identified key factors such as material attributes, order characteristics, warehouse layout, and equipment operating status, using them as important bases for optimizing the scheduling model. Further, warehouse layout was adjusted based on these factors, prioritizing the storage of high-turnover materials in easily accessible locations to improve inbound and outbound efficiency. Simultaneously, optimizing equipment maintenance plans reduced equipment failures and improved inventory accuracy. Overall, this data-driven optimization method effectively improved the overall efficiency and accuracy of warehouse operations.

[0031] Furthermore, the task influencing factor determination module 12 is also used to perform the following method: The equipment operating status includes AGV endurance, RFID reader sensitivity, e-ink screen display status, and access control permission matching degree; the warehouse scheduling model is used to integrate the collaborative operation of intelligent partitioned storage, AGV automatic handling, RFID one-key point and electronic tag precise guidance.

[0032] In one embodiment, equipment operating status refers to the actual working status of various intelligent devices in the warehousing system, specifically including the endurance of AGVs (Automated Guided Vehicles), the sensitivity of RFID (Radio Frequency Identification) readers, the display status of e-ink screens, and the access control system's permission matching degree. Equipment operating status directly affects the efficiency and accuracy of warehousing operations. The warehousing scheduling model is used to integrate multiple intelligent functional modules in the warehousing system, including intelligent partitioned storage, AGV automatic handling, RFID one-key key operation, and precise electronic tag guidance. Through the collaborative work of multiple intelligent functional modules in the warehousing system, the efficiency and intelligence of warehousing operations are achieved.

[0033] Optionally, monitoring the operating status of equipment is a key aspect of ensuring efficient warehousing operations. Specifically, the endurance of AGVs directly affects the continuity of their handling tasks. If the AGV's endurance is insufficient, it may lead to interruptions in handling tasks, affecting inbound and outbound efficiency. By monitoring the AGV's battery status in real time and combining it with the warehousing scheduling model, the charging time and task allocation of AGVs can be rationally arranged to ensure that they are always in the best working state. Furthermore, when the AGV's battery level is below 20%, it is automatically guided to the charging area and tasks are reassigned to other AGVs, thereby reducing operation interruptions caused by equipment failure.

[0034] The sensitivity of RFID readers directly affects the accuracy and efficiency of inventory counting. High-sensitivity RFID readers can quickly and accurately read material information, reducing inventory errors. Warehouse scheduling models can improve inventory efficiency by optimizing RFID inventory frequency and paths. Furthermore, in high-turnover areas, the model can set a higher inventory frequency to ensure the real-time accuracy of inventory data. The display status of e-ink screens and the matching degree of access control permissions are related to the visualization and security of warehouse operations. E-ink screens can display material information and operation instructions in real time, improving the work efficiency of operators. Precise matching of access control permissions ensures that only authorized personnel can enter specific areas, ensuring warehouse security.

[0035] Preferably, intelligent partitioned storage can automatically allocate storage locations based on material attributes and turnover frequency; AGV automated handling can optimize travel routes based on storage locations and order requirements; RFID one-keyboard point-of-sale can quickly verify inventory information; and electronic tag precise guidance can guide operators to quickly find materials, realizing the collaboration of warehouse operations and significantly improving the overall efficiency of warehouse operations. Furthermore, the collaboration between intelligent partitioned storage and AGV automated handling improves inbound and outbound efficiency, and the collaboration between RFID one-keyboard point-of-sale and electronic tag precise guidance improves inventory accuracy. Overall, by integrating intelligent partitioned storage, AGV automated handling, RFID one-keyboard point-of-sale, and electronic tag precise guidance into a warehouse scheduling model for collaborative operation, the efficiency of warehouse operations is improved, and the level of intelligent warehouse management is enhanced.

[0036] Furthermore, the task influencing factor determination module 12 is also used to perform the following method: A reinforcement learning mechanism is introduced, which uses the reduction of optimization error and the improvement of operational indicators as reward signals, and the increase of optimization error and equipment malfunction as penalty signals, and dynamically adjusts the weight coefficients of the material storage channel, material handling channel and inventory monitoring channel.

[0037] In one embodiment, reinforcement learning is a machine learning method that learns optimal behavioral strategies through the interaction between an agent and its environment. Furthermore, in an intelligent warehouse management system, reinforcement learning is used to dynamically adjust the parameters of the warehouse scheduling model to optimize overall operational efficiency. The reward signal is positive feedback given to the model when the system reaches its expected goal; specifically, a positive feedback signal is issued if the optimization error decreases or operational indicators improve, prompting the model to continue adjusting parameters in the direction of optimization. The penalty signal is negative feedback given to the model when the system encounters unfavorable conditions; specifically, a negative feedback signal is issued if the optimization error increases or equipment malfunctions, prompting the model to adjust its strategy to prevent similar situations from recurring. The weight coefficients refer to the importance of material storage channels, material handling channels, and inventory monitoring channels in the warehouse scheduling model. Dynamically adjusting the weight coefficients means adjusting the priority of material storage channels, material handling channels, and inventory monitoring channels in the warehouse scheduling model based on real-time feedback to adapt to different operational scenarios.

[0038] Optionally, introducing a reinforcement learning mechanism can significantly improve the system's adaptability and optimization capabilities. By using the reduction of optimization error and the improvement of operational indicators as reward signals, the system can automatically learn and adjust parameters to achieve more efficient warehouse operations. Specifically, when the warehouse scheduling model successfully reduces the entry and exit time by optimizing the AGV's travel path, it will provide positive feedback to further strengthen this optimization strategy. This positive incentive mechanism can prompt the model to continuously optimize and improve entry and exit efficiency.

[0039] Conversely, when an increase in optimization error or abnormal equipment operation is detected, a penalty signal will be issued. Furthermore, abnormal equipment operation includes insufficient AGV battery life and RFID read / write abnormalities. If the AGV interrupts the task due to insufficient power, the system will identify this abnormality and provide negative feedback. The system will dynamically adjust the weight coefficient, reduce the priority of the AGV in the current task, and reassign the task to other equipment. At the same time, the weight of the material storage channel will be adjusted to prioritize storing high-turnover materials near the charging area, thereby reducing the risk of work interruption due to equipment failure.

[0040] Preferably, the warehouse scheduling model can adapt to various changes in warehouse operations in real time, ensuring the efficient operation of the system. Furthermore, during peak order periods, the system increases the weight of material handling channels and prioritizes optimizing AGV path planning; during equipment maintenance, the system increases the weight of inventory monitoring channels to ensure the accuracy of inventory data. Overall, this dynamic adjustment mechanism not only improves the overall efficiency of warehouse operations but also enhances the robustness and adaptability of the system, making warehouse management more intelligent and automated.

[0041] Furthermore, the task influencing factor determination module 12 is also used to perform the following method: The operational complexity index is assessed based on warehouse order volume, material turnover frequency, and equipment load rate; the maximum number of iterations is dynamically configured according to the PID feedback adjustment mechanism based on the operational complexity index.

[0042] In one embodiment, the operational complexity index is an indicator that quantitatively assesses the complexity of warehouse operations by comprehensively considering factors such as warehouse order volume, material turnover frequency, and equipment load rate. It reflects the current level of activity and task difficulty in warehouse operations. The PID (Proportional Integral Derivative, a control algorithm based on proportional, integral, and derivative) feedback adjustment mechanism is used to dynamically configure the maximum number of iterations based on the operational complexity index to ensure that the optimization process of the scheduling model can adapt to different operational scenarios.

[0043] Optionally, an operational complexity index can be calculated by comprehensively evaluating warehouse order volume, material turnover frequency, and equipment load rate. For example, an increase in order volume, a faster material turnover frequency, and an increase in equipment load rate will all lead to an increase in the operational complexity index. Based on the operational complexity index, a PID feedback adjustment mechanism is used to dynamically configure the maximum number of iterations. The PID mechanism dynamically adjusts the number of iterations by monitoring changes in operational complexity in real time to ensure that the optimization process of the scheduling model can adapt to different operational scenarios. Furthermore, when the operational complexity index is high, the maximum number of iterations is increased to more finely adjust the parameters of the scheduling model and ensure that efficient warehouse operations can still be achieved in complex environments. Conversely, when the operational complexity index is low, the system will reduce the maximum number of iterations to improve optimization efficiency and avoid unnecessary waste of computing resources.

[0044] Preferably, dynamically configuring the maximum number of iterations ensures that the scheduling model achieves the best optimization effect under different operating scenarios, significantly improving the overall efficiency and adaptability of warehouse operations. Furthermore, during peak order periods, increasing the number of iterations allows for more precise optimization of AGV travel paths and material storage locations, reducing inbound and outbound time. When operations are relatively stable, reducing the number of iterations can improve the system's response speed and ensure the efficiency of real-time scheduling.

[0045] Furthermore, the iterative optimization module 13 is also used to perform the following method: The deviation between the actual operating efficiency and the expected efficiency corresponding to the collaborative scheduling parameters output by the warehouse scheduling model is used as the optimization error; the optimization error is used as the objective function for iterative optimization, and the material partition storage parameters, AGV driving path parameters, RFID inventory frequency and electronic ink screen lighting prompt logic are adjusted in each iteration.

[0046] In one embodiment, optimization error refers to the deviation between the actual operating efficiency and the expected efficiency corresponding to the collaborative scheduling parameters output by the warehouse scheduling model. It reflects the gap between the current scheduling scheme and the ideal state and is an important indicator for measuring the performance of the scheduling model. The objective function of iterative optimization refers to the core indicator used to evaluate and guide the adjustment of model parameters during the optimization process. Specifically, optimization error is used as the objective function, and the warehouse scheduling model is gradually optimized by minimizing this error. Collaborative scheduling parameters include material partitioning storage parameters, AGV travel path parameters, RFID inventory frequency, and electronic ink screen lighting prompt logic, etc. These parameters together determine the overall scheduling strategy of the warehouse system.

[0047] Optionally, the calculation of optimization error is a key step in the iterative optimization process. Furthermore, by comparing the actual operating efficiency with the expected efficiency, the system can quantify the shortcomings of the current scheduling scheme. Specifically, if the expected inbound / outbound efficiency of the warehouse is 100 orders per hour, and the actual operating efficiency is 80 orders per hour, then the optimization error is 20 orders per hour. The optimization error reflects the gap in inbound / outbound efficiency of the current scheduling scheme. With the optimization error as the objective function, the system adjusts relevant parameters in each iteration to gradually reduce this error. Specifically, the system will adjust the material partitioning storage parameters and optimize the storage layout to bring high-turnover materials closer to the inbound / outbound entrance, thereby reducing the AGV's travel distance and time. Furthermore, by adjusting the storage parameters, the storage location of high-turnover materials is moved from areas far from the inbound / outbound entrance to areas closer to the entrance, reducing the average travel time of the AGV.

[0048] Simultaneously, the AGV's driving path parameters are adjusted to optimize its routes, avoiding congestion and inefficient travel. Furthermore, by introducing a dynamic path planning algorithm, the AGV can select the optimal path based on real-time traffic conditions, further improving inbound and outbound efficiency. Additionally, the RFID inventory frequency is adjusted according to inventory fluctuations and order demand to ensure the accuracy of inventory data. Finally, the lighting prompt logic of the e-ink screen is optimized to more accurately guide operators in material storage and retrieval. Furthermore, by optimizing the prompt logic, the time operators spend searching for materials is reduced, improving operational efficiency. Preferably, through this iterative adjustment mechanism based on optimization errors, the warehouse scheduling model is gradually optimized, achieving higher efficiency and accuracy in actual operation.

[0049] Furthermore, the warehouse scheduling scheme list determination module 14 is used to perform the following method: Connect to multimodal sensing terminals including RFID readers, vision cameras, infrared access control, and temperature and humidity sensors to mark the storage location and real-time status of materials; based on the storage location and real-time status of materials, match the storage strategies, handling path schemes, and inventory monitoring schemes corresponding to the material classification database, warehouse layout database, and equipment scheduling database to construct a differentiated warehousing basic framework; determine a list of warehousing scheduling schemes based on the differentiated warehousing basic framework.

[0050] In one embodiment, a multimodal sensing terminal refers to a device integrating multiple sensors, capable of sensing the warehousing environment and material status from different dimensions. Specifically, the multimodal sensing terminal includes an RFID reader / writer, a visual camera, an infrared access control system, and a temperature and humidity sensor. The RFID reader / writer is used to identify material tags, the visual camera is used for image recognition and monitoring, the infrared access control system is used for personnel and equipment access management, and the temperature and humidity sensor is used for environmental monitoring. Material storage location and real-time status refer to the current storage location and status information of materials obtained through the multimodal sensing terminal, such as whether the materials are in place or damaged. A differentiated warehousing infrastructure framework refers to a flexible framework built based on the classification, storage location, and real-time status of materials, combined with warehousing layout and equipment scheduling information, capable of adapting to different warehousing needs. A warehousing scheduling scheme list refers to a series of specific warehousing operation schemes generated based on the differentiated warehousing infrastructure framework, including storage strategies, handling routes, and inventory monitoring schemes.

[0051] Optionally, by deploying RFID readers, vision cameras, infrared access control systems, and temperature and humidity sensors, the storage location and status information of materials can be obtained in real time. Specifically, RFID readers can quickly identify the unique identifier of materials and determine their specific location in the warehouse; vision cameras can use image recognition technology to detect the appearance of materials and determine whether there is any damage; infrared access control systems can record the entry and exit of personnel and equipment to ensure warehouse security; and temperature and humidity sensors can monitor the warehouse environment in real time to ensure that the storage conditions of materials meet the requirements.

[0052] Based on this real-time data, we further match the material classification database, warehouse layout database, and equipment scheduling database to build a differentiated warehousing framework. Specifically, based on the information in the material classification database, we allocate the most suitable storage areas for different types of materials, including fragile items and high-value items; combined with the warehouse layout database, we optimize the storage layout and improve space utilization; and using the equipment scheduling database, we rationally arrange the handling tasks of AGVs to avoid equipment overload or idleness.

[0053] Based on a differentiated warehousing framework, a list of warehousing scheduling schemes is generated. Specifically, for high-turnover materials, a scheme is generated that prioritizes storage near the inbound and outbound ports, and the AGV transport paths are optimized to ensure rapid inbound and outbound operations. For fragile items, a scheme is generated that stores them on lower shelves to reduce the number of handling operations and mitigate the risk of damage. Ideally, personalized warehousing scheduling schemes are generated based on the characteristics and real-time status of different materials, significantly improving the efficiency and accuracy of warehousing operations. Furthermore, by optimizing storage strategies and transport paths, inbound and outbound efficiency is improved, while inventory counting accuracy is also enhanced. This differentiated and personalized scheduling scheme can effectively address complex and ever-changing warehousing needs and enhance the level of intelligence in warehousing management.

[0054] In summary, the beneficial effects of the embodiments of this application are: The application employs a warehouse scheduling model building module, which establishes a warehouse scheduling model based on material storage channels, material handling channels, and inventory monitoring channels, corresponding to warehouse operation monitoring indicators. These indicators include material positioning accuracy, space utilization, inbound / outbound efficiency, and inventory accuracy. A module for determining operational influencing factors is used to identify these factors based on historical warehouse data, including material attributes, order characteristics, warehouse layout, and equipment operating status. An iterative optimization module iteratively optimizes the warehouse scheduling model based on these operational influencing factors until the maximum number of iterations is reached. A module for determining the warehouse scheduling scheme list uses the iteratively optimized model to determine a list of warehouse scheduling schemes by comparing it with a material classification database, a warehouse layout database, and an equipment scheduling database. This application provides an intelligent warehouse management system and method. It achieves the technical effect of integrating material storage channels, material handling channels, and inventory monitoring channels through a warehouse scheduling model, improving the matching degree between storage planning and AGV paths, and enabling the warehouse scheduling model to adapt to order fluctuations and equipment status changes in real time through continuous parameter iteration, thereby improving material positioning accuracy and inventory accuracy.

[0055] Example 2, based on the same inventive concept as the intelligent warehouse management system in the foregoing examples, such as... Figure 2 As shown, this application provides an intelligent warehouse management method, the method comprising: Based on material storage channels, material handling channels, and inventory monitoring channels, a warehouse scheduling model corresponding to warehouse operation monitoring indicators is established. The warehouse operation monitoring indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy.

[0056] Based on historical warehousing data, operational influencing factors are identified, including material attributes, order characteristics, warehouse layout, and equipment operating status.

[0057] Based on the aforementioned operational influencing factors, the warehouse scheduling model is iteratively optimized with parameters until the maximum number of iterations is reached.

[0058] Using the iteratively optimized warehouse scheduling model, and comparing it with the material classification database, warehouse layout database, and equipment scheduling database, a list of warehouse scheduling schemes is determined.

[0059] Furthermore, this application provides a method for determining operational influencing factors, including material attributes, order characteristics, warehouse layout, and equipment operating status, based on historical warehousing data. The historical warehousing data is categorized according to operational efficiency. The historical warehousing data includes scheduling parameter configurations, inventory fluctuation curves, order processing times, equipment failure records, and inventory error data. Based on the categorized historical warehousing data, an association rule algorithm is used to mine the operational influencing factors corresponding to the mapping relationships.

[0060] Furthermore, the method of this application also includes: The equipment operating status includes AGV endurance, RFID reader sensitivity, e-ink screen display status, and access control permission matching degree; the warehouse scheduling model is used to integrate the collaborative operation of intelligent partitioned storage, AGV automatic handling, RFID one-key point and electronic tag precise guidance.

[0061] Furthermore, the method of this application also includes: A reinforcement learning mechanism is introduced, which uses the reduction of optimization error and the improvement of operational indicators as reward signals, and the increase of optimization error and equipment malfunction as penalty signals, and dynamically adjusts the weight coefficients of the material storage channel, material handling channel and inventory monitoring channel.

[0062] Furthermore, the method of this application also includes: The operational complexity index is assessed based on warehouse order volume, material turnover frequency, and equipment load rate; the maximum number of iterations is dynamically configured according to the PID feedback adjustment mechanism based on the operational complexity index.

[0063] Furthermore, this application provides a method for iteratively optimizing the parameters of the warehouse scheduling model until the maximum number of iterations is reached, the method further comprising: The deviation between the actual operating efficiency and the expected efficiency corresponding to the collaborative scheduling parameters output by the warehouse scheduling model is used as the optimization error; the optimization error is used as the objective function for iterative optimization, and the material partition storage parameters, AGV driving path parameters, RFID inventory frequency and electronic ink screen lighting prompt logic are adjusted in each iteration.

[0064] Furthermore, this application provides a list of warehouse scheduling schemes by comparing a material classification database, a warehouse layout database, and an equipment scheduling database. The method includes: Connect to multimodal sensing terminals including RFID readers, vision cameras, infrared access control, and temperature and humidity sensors to mark the storage location and real-time status of materials; based on the storage location and real-time status of materials, match the storage strategies, handling path schemes, and inventory monitoring schemes corresponding to the material classification database, warehouse layout database, and equipment scheduling database to construct a differentiated warehousing basic framework; determine a list of warehousing scheduling schemes based on the differentiated warehousing basic framework.

[0065] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0066] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0067] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. An intelligent warehouse management system, characterized in that, The system includes: The warehouse scheduling model establishment module is used to establish a warehouse scheduling model corresponding to warehouse operation detection indicators based on material storage channels, material handling channels, and inventory monitoring channels. The warehouse operation detection indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy. The Operation Influencing Factors Determination Module is used to determine the operational influencing factors, including material attributes, order characteristics, warehouse layout, and equipment operating status, based on historical warehousing data. The iterative optimization module is used to perform iterative optimization of the parameters of the warehouse scheduling model based on the operational influencing factors until the maximum number of iterations is reached. The warehouse scheduling scheme list determination module is used to determine the warehouse scheduling scheme list by comparing the iteratively optimized warehouse scheduling model with the material classification database, warehouse layout database, and equipment scheduling database.

2. The intelligent warehouse management system as described in claim 1, characterized in that, Based on historical warehousing data, the system identifies operational influencing factors including material attributes, order characteristics, warehouse layout, and equipment operating status. The system includes: The historical warehousing data is categorized according to operational efficiency, including scheduling parameter configurations, inventory fluctuation curves, order processing times, equipment failure records, and inventory error data. Based on the categorized historical warehouse data, the association rule algorithm is used to mine the operational influencing factors corresponding to the mapping relationships.

3. The intelligent warehouse management system as described in claim 2, characterized in that, The equipment operating status includes AGV endurance, RFID reader sensitivity, e-ink screen display status, and access control permission matching degree; The warehouse scheduling model is used to integrate the collaborative operation of intelligent partitioned storage, AGV automatic handling, RFID one-key key operation, and precise electronic tag guidance.

4. The intelligent warehouse management system as described in claim 3, characterized in that, The system also includes: Introduce a reinforcement learning mechanism, using the reduction of optimization error and the improvement of operational indicators as reward signals; Increased optimization error and abnormal equipment operation are used as penalty signals to dynamically adjust the weight coefficients of the material storage channel, material handling channel, and inventory monitoring channel.

5. The intelligent warehouse management system as described in claim 4, characterized in that, The system includes: The operational complexity index is assessed based on warehouse order volume, material turnover frequency, and equipment load rate. The maximum number of iterations is dynamically configured using the operational complexity index and a PID feedback adjustment mechanism.

6. The intelligent warehouse management system as described in claim 1, characterized in that, The system further includes iteratively optimizing the parameters of the warehouse scheduling model until the maximum number of iterations is reached, and also includes: The deviation between the actual operating efficiency and the expected efficiency corresponding to the collaborative scheduling parameters output by the warehouse scheduling model is taken as the optimization error. The objective function for iterative optimization is to optimize the error. In each iteration, the parameters of material zoning storage, AGV driving path, RFID inventory frequency, and electronic ink screen lighting prompt logic are adjusted.

7. The intelligent warehouse management system as described in claim 1, characterized in that, By comparing the material classification database, warehouse layout database, and equipment scheduling database, a list of warehouse scheduling schemes is determined. The system includes: Connect to multimodal sensing terminals including RFID readers, vision cameras, infrared access control, and temperature and humidity sensors to mark the storage location and real-time status of materials; Based on the material storage location and real-time status, the storage strategies, handling path schemes and inventory monitoring schemes corresponding to the material classification database, warehouse layout database and equipment scheduling database are matched to construct a differentiated warehousing basic framework. Based on the aforementioned differentiated warehousing infrastructure framework, a list of warehousing scheduling schemes is determined.

8. An intelligent warehouse management method, characterized in that, For implementing an intelligent warehouse management system according to any one of claims 1-7, the method comprises: Based on material storage channels, material handling channels, and inventory monitoring channels, a warehouse scheduling model corresponding to warehouse operation monitoring indicators is established. The warehouse operation monitoring indicators include material positioning accuracy, space utilization rate, inbound and outbound efficiency, and inventory accuracy. Based on historical warehousing data, identify operational influencing factors including material attributes, order characteristics, warehouse layout, and equipment operating status; Based on the aforementioned operational influencing factors, the warehouse scheduling model is iteratively optimized to obtain the maximum number of iterations. Using the iteratively optimized warehouse scheduling model, and comparing it with the material classification database, warehouse layout database, and equipment scheduling database, a list of warehouse scheduling schemes is determined.

Images