Intelligent warehouse location management system

Abstract

The invention relates to the technical field of intelligent storage, and discloses an intelligent storage location management system, which comprises demand analysis and data preparation, hardware deployment and network establishment, algorithm development and optimization, system integration and test, and online operation and continuous optimization. According to the intelligent warehouse location management system, through deep demand analysis, core demands of business scenes, inventory scales, operation processes and the like of enterprises are clarified, system design and actual high matching of the enterprises are ensured, resource waste is avoided, real-time order demands are combined, AGV and robot operation paths are optimized by utilizing reinforcement learning or a genetic algorithm, the cargo handling time is shortened, and the working efficiency is improved. The energy consumption is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent warehousing, and particularly to an intelligent warehousing location management system. Background Art

[0002] Intelligent warehousing is a warehousing management system integrating advanced technologies such as information technology, Internet of Things technology, automation technology, and artificial intelligence. It realizes the automated and intelligent management of goods stored in the warehouse through highly integrated software and hardware facilities, thereby improving the efficiency and accuracy of warehousing operations. The background technology of the intelligent warehousing location management system is developed based on the upgrading requirements of the traditional warehousing management mode and the integrated application of modern information technology, Internet of Things technology, automation technology, and artificial intelligence technology. This system has characteristics such as real-time inventory management, intelligent location allocation, and visual monitoring, bringing a revolutionary change to the warehousing management of enterprises. Therefore, the present application now proposes an intelligent warehousing location management system. Summary of the Invention

[0003] (I) Technical Problems to be Solved Aiming at the deficiencies of the existing technology, the present invention provides an intelligent warehousing location management system, which has the advantages of shortening the goods handling time and reducing energy consumption, and solves the problems of low work efficiency and high use cost existing in some current warehousing systems.

[0004] (II) Technical Solutions To achieve the above object, the present invention provides the following technical solutions: An intelligent warehousing location management system includes requirements analysis and data preparation, hardware deployment and network construction, algorithm development and optimization, system integration and testing, online operation and continuous optimization. The specific steps are as follows: S1. Define the business requirements and deeply understand the operation mode, types of goods, and storage requirements of the warehouse; S2. Collect the floor plan of the warehouse, goods information, and inbound and outbound records; S3. Collect the floor plan of the warehouse, goods information, and inbound and outbound records. Use RFID readers, sensors, and cameras to read and write goods information, and then build a stable and efficient network environment through communication and data transmission between hardware devices; S4. Design a location allocation algorithm based on the actual situation and requirements of the warehouse, and optimize the performance and efficiency of the algorithm through testing and adjustment; S5. Integrate hardware devices, algorithms, databases, etc. into the system to form a complete intelligent warehousing location management system; S6. Conduct comprehensive functional testing, performance testing, and security testing on the system; S7. Deploy the system to the actual warehouse environment and start running. Continuously optimize the functions and performance of the system according to the actual operation of the system.

[0005] Preferably, the requirement analysis and data preparation include business requirement research, data collection and cleaning, and warehouse modeling. When collecting and cleaning data, historical data is imported and the attributes of goods are labeled. The warehouse modeling constructs a digital twin warehouse through laser scanning or 3D modeling tools, divides the storage location grid and numbers them.

[0006] Preferably, the hardware deployment and network construction include the installation of sensors and tags, the configuration of automation equipment, and the construction of a communication network. For the installation of sensors and tags, weight sensors and electronic tags are installed on the shelves, RFID tags are bound to the goods, and UWB positioning base stations are deployed on the ceiling to achieve centimeter-level positioning of the goods. For the configuration of automation equipment, magnetic strips or SLAM paths are deployed for AGVs, and the grasping accuracy of the robotic arm is calibrated.

[0007] Preferably, the algorithm development and optimization include the dynamic storage location allocation algorithm, the path planning algorithm, and the prediction model training. The dynamic storage location allocation algorithm is as follows: Step 1: Input parameters, including the size of the goods, the frequency of inbound and outbound, the order correlation, and the shelf life. Step 2: Optimization objectives, minimizing the picking path and maximizing the space utilization rate. Step 3: Implementation method, allocating high-frequency goods to the storage areas near the entrances and exits, and storing the associated order goods nearby. The path planning algorithm combines the real-time occupancy status of the storage locations, dynamically adjusts the paths of AGVs and pickers to avoid congestion, uses the Dijkstra algorithm to calculate the shortest path, and superimposes the obstacle avoidance logic. The prediction model training is based on LSTM to predict the inventory demand and pre-occupy the storage locations.

[0008] Preferably, the system integration and testing include software function development and system joint debugging and testing. The software function development includes a 3D visualization dashboard, a task scheduling engine, and an exception warning module, specifically as follows: 3D visualization dashboard: Integrate Unity3D and Three.js to display the real-time status of the storage locations, idle / occupied / abnormal. Task scheduling engine: Connect to the API of the AGV control platform (such as ROS) to issue inventory transfer instructions. Exception warning module: Set a rule engine to trigger warnings for storage location overload or temperature and humidity exceeding the standard. The simulation test simulates the inbound and outbound scenarios during the peak period through digital twins to verify the robustness of the algorithm. The stress test simulates concurrent tasks to improve the system response time.

[0009] Preferably, the online operation and continuous optimization include phased online operation and dynamic optimization. The phased online operation enables basic functions, including storage location allocation and path planning, and gradually opens advanced functions, including predictive replenishment and unmanned scheduling. The dynamic optimization iterates algorithms based on operation data, regularly generates reports on storage location utilization rates, and eliminates inefficient storage strategies.

[0010] Compared with the prior art, the present invention provides an intelligent storage location management system for a warehouse, which has the following beneficial effects: 1. Through in-depth requirements analysis, this intelligent storage location management system for a warehouse clarifies core requirements such as the enterprise's business scenario, inventory scale, and operation process, ensuring a high degree of match between system design and the actual situation of the enterprise, avoiding resource waste. Combining real-time order requirements, it uses reinforcement learning or genetic algorithms to optimize the operation paths of AGVs and robots, shortening the cargo handling time and reducing energy consumption.

[0011] 2. Through energy consumption monitoring and operation process optimization, this intelligent storage location management system for a warehouse reduces the long-term warehousing operation cost, while reducing carbon emissions, supporting the goal of green warehousing. Automated operation and intelligent scheduling effectively shorten the order processing time limit, enabling the enterprise to achieve a comprehensive transformation of warehousing management from the traditional mode to the intelligent and digital mode, significantly enhancing the market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of the working process of the intelligent storage location management system for a warehouse of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0014] Please refer to Figure 1 , an intelligent storage location management system for a warehouse, including requirements analysis and data preparation, hardware deployment and network construction, algorithm development and optimization, system integration and testing, online operation and continuous optimization. The specific steps are as follows: S1. Clarify the business requirements and deeply understand the operation mode, types of goods, and storage requirements of the warehouse; S2. Collect the floor plan of the warehouse, goods information, and inbound and outbound records; S3. Collect the floor plan of the warehouse, goods information, and inbound and outbound records. Use RFID readers, sensors, and cameras to read and write goods information, and then build a stable and efficient network environment through communication and data transmission between hardware devices. S4. Design a storage location allocation algorithm based on the actual situation and requirements of the warehouse, and optimize the performance and efficiency of the algorithm through testing and adjustment; S5. Integrate hardware devices, algorithms, databases, etc. into the system to form a complete intelligent warehouse storage location management system; S6. Conduct comprehensive functional testing, performance testing, and security testing on the system; S7. Deploy the system to the actual warehouse environment to start running, and continuously optimize the functions and performance of the system according to the actual operation situation of the system.

[0015] Furthermore, the requirements analysis and data preparation include business requirements research, data collection and cleaning, and warehouse modeling. When collecting and cleaning data, historical data is imported and the attributes of goods are labeled. The warehouse modeling constructs a digital twin warehouse through laser scanning or 3D modeling tools, divides the storage location grid and numbers them.

[0016] Furthermore, the hardware deployment and network construction include the installation of sensors and tags, the configuration of automation equipment, and the construction of communication networks. For the installation of sensors and tags, weight sensors and electronic tags are installed on the shelves, RFID tags are bound to goods, and UWB positioning base stations are deployed on the ceiling to achieve centimeter-level positioning of goods; for the configuration of automation equipment, AGVs are deployed with magnetic strips or SLAM paths, and the robotic arms are calibrated for grasping accuracy.

[0017] Furthermore, the algorithm development and optimization include the dynamic storage location allocation algorithm, path planning algorithm, and prediction model training. The dynamic storage location allocation algorithm is as follows: Step 1: Input parameters, including the size of goods, inbound and outbound frequency, order correlation, and shelf life; Step 2: Optimization objectives, minimizing the picking path and maximizing space utilization; Step 3: Implementation method, allocating high-frequency goods to storage locations near the entrance and exit, and storing related order goods nearby; The path planning algorithm combines the real-time occupancy status of storage locations to dynamically adjust the paths of AGVs and pickers to avoid congestion, uses the Dijkstra algorithm to calculate the shortest path, and superimposes the obstacle avoidance logic. The prediction model training is based on LSTM to predict inventory demand and pre-occupy storage locations.

[0018] Furthermore, the system integration and testing include software function development and system joint debugging and testing. The software function development includes a 3D visualization dashboard, a task scheduling engine, and an exception warning module, which are specifically as follows: 3D visualization dashboard: Integrate Unity3D and Three.js to display the real-time status of storage locations, idle / occupied / abnormal; Task scheduling engine: Interface with the API of the AGV control platform (such as ROS) to issue inventory transfer instructions; Abnormal warning module: Set up a rule engine to trigger warnings for overloaded storage locations or exceeded temperature and humidity standards; The simulation test simulates the inbound and outbound scenarios during peak periods through digital twins to verify the robustness of the algorithm. The stress test simulates concurrent tasks to improve the system response time.

[0019] Furthermore, the online operation and continuous optimization include phased online operation and dynamic optimization. The phased online operation enables basic functions, including storage location allocation and path planning, and gradually opens up advanced functions, including predictive replenishment and unmanned scheduling. The dynamic optimization iterates the algorithm based on operation data, regularly generates a storage location utilization report, and eliminates inefficient storage strategies. Example 1: An intelligent warehouse storage location management system includes requirement analysis and data preparation, hardware deployment and network construction, algorithm development and optimization, system integration and testing, online operation and continuous optimization. The specific steps are as follows: S1. Clearly define the business requirements and deeply understand the operation mode, types of goods, and storage requirements of the warehouse; S2. Collect the floor plan of the warehouse, goods information, and inbound and outbound records; S3. Collect the floor plan of the warehouse, goods information, and inbound and outbound records. Use RFID readers, sensors, and cameras to read and write goods information, and then build a stable and efficient network environment through communication and data transmission between hardware devices. S4. Design a storage location allocation algorithm based on the actual situation and requirements of the warehouse, and optimize the performance and efficiency of the algorithm through testing and adjustment; S5. Integrate hardware devices, algorithms, databases, etc. into the system to form a complete intelligent warehouse storage location management system; S6. Conduct comprehensive functional testing, performance testing, and security testing on the system; S7. Deploy the system to the actual warehouse environment to start operation, and continuously optimize the functions and performance of the system according to the actual operation situation of the system.

[0020] Example 2: An intelligent warehouse location management system proposed according to an embodiment. Requirement analysis and data preparation include business requirement research, data collection and cleaning, and warehouse modeling. When collecting and cleaning data, historical data is imported and the attributes of goods are labeled. The warehouse modeling constructs a digital twin warehouse through laser scanning or 3D modeling tools, divides the warehouse location grid and numbers it. Hardware deployment and network construction include the installation of sensors and tags, the configuration of automated equipment, and the construction of a communication network. Weight sensors and electronic tags are installed on the shelves during the installation of sensors and tags, RFID tags are bound to goods, and UWB positioning base stations are deployed on the ceiling to achieve centimeter-level positioning of goods; for the configuration of automated equipment, AGVs are deployed with magnetic strips or SLAM paths, and the robotic arm is calibrated for grasping accuracy.

[0021] Embodiment 3: An intelligent warehouse location management system proposed according to an embodiment. Algorithm development and optimization include a warehouse location dynamic allocation algorithm, a path planning algorithm, and a prediction model training. The warehouse location dynamic allocation algorithm is as follows: Step 1: Input parameters, including the size of goods, the frequency of inbound and outbound, order correlation, and shelf life; Step 2: Optimization objectives, minimizing the picking path and maximizing space utilization; Step 3: Implementation method, allocating high-frequency goods to storage locations near the entrance and exit, and storing related order goods nearby; The path planning algorithm combines the real-time occupancy status of warehouse locations, dynamically adjusts the paths of AGVs and pickers to avoid congestion, uses the Dijkstra algorithm to calculate the shortest path, and superimposes obstacle avoidance logic. The prediction model training is based on LSTM to predict inventory demand and pre-occupy warehouse locations. Through in-depth demand analysis, the core requirements such as the business scenario, inventory scale, and operation process of the enterprise are clarified to ensure that the system design highly matches the actual situation of the enterprise and avoid resource waste. Combining real-time order demands, the operation paths of AGVs and robots are optimized using reinforcement learning or genetic algorithms to shorten the goods handling time and reduce energy consumption.

[0022] Embodiment 4: An intelligent warehouse location management system proposed according to an embodiment. System integration and testing include software function development and system joint debugging and testing. The software function development includes a 3D visualization dashboard, a task scheduling engine, and an exception warning module, which are specifically as follows: 3D visualization dashboard: Integrates Unity3D and Three.js to display the real-time status of warehouse locations, idle / occupied / abnormal; Task scheduling engine: Docks with the API of the AGV control platform (such as ROS) to issue relocation instructions; Exception warning module: Sets a rule engine to trigger warnings for warehouse location overloading or temperature and humidity exceeding the standard; The simulation test simulates the inbound and outbound scenarios during peak periods through digital twins to verify the robustness of the algorithm, and the stress test simulates concurrent tasks to improve the system response time; Go-live and continuous optimization include phased go-live and dynamic optimization. The phased go-live enables basic functions, including storage location allocation and path planning, and gradually opens up advanced functions, including predicted replenishment and unmanned scheduling. The dynamic optimization iterates the algorithm based on operation data, regularly generates a storage location utilization report, and eliminates inefficient storage strategies; Through the optimization of the operation process, the warehousing operation cost can be reduced in the long term, while carbon emissions are reduced, supporting the goal of green warehousing. Automated operations and intelligent scheduling effectively shorten the order processing time, enabling the enterprise to achieve a comprehensive transformation of warehousing management from the traditional mode to an intelligent and digital one, significantly enhancing the market competitiveness.

[0023] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent warehouse location management system, characterized in that: It includes requirements analysis and data preparation, hardware deployment and network construction, algorithm development and optimization, system integration and testing, online operation and continuous optimization. The specific steps are as follows: S1. Define business requirements, and deeply understand the operation mode, types of goods, and storage requirements of the warehouse; S2. Collect the floor plan of the warehouse, goods information, and inbound and outbound records; S3. Collect the floor plan of the warehouse, goods information, and inbound and outbound records. Use RFID readers, sensors, and cameras to read and write goods information, and then build a stable and efficient network environment through communication and data transmission between hardware devices; S4. Design a storage location allocation algorithm based on the actual situation and requirements of the warehouse, and optimize the performance and efficiency of the algorithm through testing and adjustment; S5. Integrate hardware devices, algorithms, databases, etc. into the system to form a complete intelligent warehouse storage location management system; S6. Conduct comprehensive functional testing, performance testing, and security testing on the system; S7. Deploy the system to the actual warehouse environment to start running, and continuously optimize the functions and performance of the system according to the actual operation situation of the system.

2. The intelligent warehouse location management system according to claim 1, characterized in that: The requirements analysis and data preparation include business requirements research, data collection and cleaning, and warehouse modeling. When collecting and cleaning data, historical data is imported and the attributes of goods are labeled. The warehouse modeling constructs a digital twin warehouse through laser scanning or 3D modeling tools, divides the storage location grid, and numbers it.

3. An intelligent warehousing location management system according to claim 1, characterized in that: The hardware deployment and network construction include sensor and label installation, automated equipment configuration, and communication network construction. For sensor and label installation, install weight sensors and electronic tags on the shelves, bind RFID tags to goods, and deploy UWB positioning base stations on the ceiling to achieve centimeter-level positioning of goods; for automated equipment configuration, deploy magnetic strips or SLAM paths for AGVs, and calibrate the grasping accuracy of robotic arms.

4. An intelligent warehouse location management system according to claim 1, characterized in that: The algorithm development and optimization include storage location dynamic allocation algorithm, path planning algorithm, and prediction model training. The storage location dynamic allocation algorithm includes the following: Step 1: Input parameters, including goods size, inbound and outbound frequency, order correlation, and shelf life; Step 2: Optimization objectives, minimizing the picking path and maximizing space utilization; Step 3: Implementation method, allocate high-frequency goods to storage locations near the entrance and exit, and store related order goods nearby; The path planning algorithm combines the real-time storage location occupancy status, dynamically adjusts the paths of AGVs and pickers to avoid congestion, uses the Dijkstra algorithm to calculate the shortest path, and superimposes the obstacle avoidance logic. The prediction model training is based on LSTM to predict inventory requirements and pre-occupy storage locations.

5. An intelligent warehousing location management system according to claim 1, characterized in that: The system integration and testing include software function development and system joint debugging and testing. The software function development includes a 3D visualization dashboard, a task scheduling engine, and an exception warning module. Specifically as follows: 3D visualization dashboard: Integrate Unity3D and Three.js to display the real-time storage location status, idle / occupied / abnormal; Task scheduling engine: Interface with the AGV control platform (such as ROS) API to issue relocation instructions; Exception warning module: Set a rule engine to trigger warnings for storage location overload or temperature and humidity exceeding the standard; The simulation test simulates the inbound and outbound scenarios during peak periods through digital twins to verify the robustness of the algorithm, and the stress test simulates concurrent tasks to improve the system response time.

6. The intelligent warehouse location management system according to claim 1, wherein: The online operation and continuous optimization include phased online launch and dynamic optimization. The phased online launch enables basic functions, including storage location allocation and path planning, and gradually opens up advanced functions, including predicted replenishment and unmanned scheduling. The dynamic optimization iterates the algorithm based on operation data, regularly generates a storage location utilization report, and eliminates inefficient storage strategies.

Images