Unmanned logistics warehouse management method and system based on real-time data

Abstract

The invention discloses an unmanned logistics warehouse management method and system based on real-time data, and relates to the technical field of logistics warehouse management, and the method comprises the steps: collecting the real-time data of the cargo inventory, the cargo location state, the equipment working state, the equipment task capability and the environment parameters in a warehouse environment in real time; obtaining cargo circulation data of cargo demand fluctuation, warehouse-in and warehouse-out records and environmental adaptability; constructing a warehouse management network model based on the data, and performing information aggregation and relation modeling on the data by taking goods, goods locations and equipment as nodes; optimizing the goods allocation according to the environmental adaptability and the environmental parameters; the inventory is dynamically adjusted according to warehouse-in and warehouse-out records and demand fluctuation; and scheduling optimization is carried out based on the equipment state. The logistics warehouse management system has the advantages that efficient utilization of inventory, goods allocation and equipment is realized through an intelligent and dynamic management mode, the problem that the goods allocation is difficult to dynamically adjust according to real-time environment change in logistics warehouse management is effectively solved, and unmanned management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics warehousing management, and in particular to an unmanned logistics warehousing management method and system based on real-time data. Background Art

[0002] With the rapid development of global e-commerce and supply chain management, logistics and warehousing management has become particularly important in modern business operations. Traditional warehouse management systems mainly rely on manual operations and static data, and perform inventory management, cargo space allocation and equipment scheduling through manual records and preset rules. In particular, they are insufficient in dynamic cargo space allocation and environmental adaptability. Existing cargo space allocation strategies usually still use preset rules and static allocation modes, and have poor adaptability to environmental conditions.

[0003] In traditional logistics and warehousing management, cargo space allocation mainly focuses on static properties such as volume and weight of goods, without fully considering real-time changes in environmental parameters (such as temperature and humidity). In such a static mode, once goods are allocated to a certain cargo space, the system generally does not re-evaluate or adjust the suitability of the cargo space unless there is human intervention. This defect is particularly obvious for some goods that are sensitive to environmental conditions (such as pharmaceuticals, food, chemicals, etc.). Traditional logistics and warehousing management makes it difficult to dynamically adjust cargo spaces according to real-time environmental changes, and often lacks refined management, resulting in the possibility that goods may be affected by improper environmental conditions, and even the risk of quality degradation or damage. Summary of the invention

[0004] In order to solve the above technical problems, an unmanned logistics warehousing management method and system based on real-time data is provided. This technical solution solves the problem raised in the above background technology that traditional logistics warehousing management is difficult to dynamically adjust cargo locations according to real-time environmental changes, and often lacks refined management, which may cause the goods to be affected by improper environmental conditions, and even lead to the risk of quality degradation or damage.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: Unmanned logistics warehousing management method based on real-time data, including: Collecting real-time storage data in the storage environment, including inventory quantity, cargo location status, equipment working status, equipment task capability and environmental parameters; Obtain the circulation data of various goods, including the volatility of demand, in-and-out records, and environmental adaptability of goods; Based on the inventory quantity, cargo location status, environmental adaptability and equipment working status, a warehouse management network model is constructed based on a graph neural network model; Use warehouse management network model to aggregate real-time data and flow data; According to the in-and-out records and demand volatility, the inventory quantity of various types of goods is dynamically adjusted through the aggregation results of the warehouse management network model; Based on the environmental adaptability of the goods and the current environmental parameters of the warehouse, the warehouse management network model is used to analyze the relationship between the goods and the environment, and the cargo position status is dynamically adjusted; Based on the working status of the equipment, the equipment status is evaluated through the aggregation results of the warehouse management network model, and the scheduling of automated equipment is dynamically adjusted in combination with the optimization algorithm, including the path planning of AGV transport vehicles, the sorting task allocation of robotic arms, and the setting of task priorities.

[0006] Preferably, the collecting of real-time storage data in the storage environment specifically includes: The inventory quantity of stored goods is collected through RFID equipment components deployed at each cargo location in the warehouse; The real-time status of goods in different cargo spaces is collected through cameras and cargo space sensors, including the three-dimensional coordinates of cargo spaces, vacancy status, occupancy status, and cargo location change information; The device working status and device task capability are obtained through the network transmission of the automated IoT devices. The device working status refers to the operating status of various automated devices in the warehouse management system at a specific time point. The device task capability refers to the ability and performance index of various automated devices in the warehouse management system to perform specific tasks. Environmental monitoring equipment and temperature and humidity sensors are used to collect real-time temperature, humidity and light parameters of each cargo location in the storage environment.

[0007] Preferably, the acquisition of the circulation data of various types of goods specifically includes: Obtain historical demand data for goods through the upstream and downstream of the supply chain, analyze the demand trends of various types of goods in different time periods, and thus obtain the volatility of demand for goods; Obtain inbound and outbound records, including the goods' inbound and outbound time, frequency, and inbound and outbound quantities of the corresponding goods; The storage environment requirements of goods are obtained through the upstream and downstream of the supply chain and the storage status of specific goods under changes in storage environment parameters are recorded, so as to obtain the environmental adaptability of the goods. The environmental adaptability of the goods is specifically to obtain the storage environment requirements of each type of goods during the production, transportation and storage process, including the optimal storage temperature, humidity range and lighting conditions.

[0008] Preferably, the building of the warehouse management network model specifically includes: Clean the collected real-time warehouse data and cargo flow data to build a standard data set, including cargo in and out records, inventory and environmental adaptability, three-dimensional coordinates of cargo locations, cargo location status and environmental parameters, equipment working status and equipment mission capabilities; Extract data features of real-time warehouse data and cargo flow data based on standard data sets, and assign feature vectors to feature data; Design a warehouse management graph construction method based on feature vectors and define graph ,in Represents a collection of nodes, including cargo nodes , cargo location node and device nodes , Represents a set of edges, including cargo-location edges , Cargo-Equipment Side and cargo space-environmental side , and build a warehouse management network model based on the graph neural network model, specifically: Each node has its own characteristics. Each node in the warehouse management network model is connected by edges. The characteristic data of each node is designed to be highly correlated with the characteristic data of its neighboring nodes. When the characteristic data of a node changes, it is determined whether the characteristic data of its neighboring nodes needs to be updated. Design a warehouse management network model based on the graph neural network model. For the feature data of each node, according to the multi-layer graph neural network layer in the warehouse management network model, the information aggregation and gradual update of the node feature data are realized through information transmission between layers, so as to manage and adjust the matching problem of goods and cargo locations, and the scheduling problem of equipment; The warehouse management graph construction method is optimized based on the genetic algorithm, and the optimal warehouse management network structure is constructed based on the graph neural network model. The warehouse management network model is trained through the standard data set to obtain the final trained warehouse management network model. Deploy the trained warehouse management network model into the warehouse management system for real-time data analysis and decision support.

[0009] Preferably, the analyzing the relationship between the cargo and the environment and dynamically adjusting the cargo position status specifically includes: Based on the information aggregation results of goods and cargo locations by the warehouse management network model, the matching degree between the environmental adaptability of goods and the environmental parameters of cargo locations is analyzed; Based on the matching degree between the environmental adaptability of the goods and the environmental parameters of the cargo space, the compatibility between the two is analyzed: ; In the formula, is the compatibility analysis function, Indicates goods , Indicates the cargo location , Indicates goods The inventory quantity, Indicates the status of the cargo space. For the environmental adaptability of the goods, is the environmental parameter of the cargo space; Based on the analysis results of the warehouse management network model, evaluate the compatibility of goods and cargo spaces; Dynamically adjust the cargo space status based on the results of the compatibility assessment; If the compatibility score between the goods and the cargo space is high, the goods are transported to the cargo space through automated equipment, and the system sets the cargo space to occupied status; If the compatibility score is low, the cargo space is marked as unavailable and the compatibility of the goods with other cargo spaces is evaluated; If there is no cargo space with a high compatibility score in the warehouse, or the quantity of goods entering the warehouse exceeds the number of cargo spaces with a high compatibility score, the environmental parameters of the free cargo space are adjusted. When the environmental parameters of the free cargo space match the goods, the goods are stored in the cargo space. Continuously monitor environmental parameters and cargo storage status, feed the latest real-time data back to the warehouse management network model through the feedback mechanism, and update the model input in real time.

[0010] Preferably, the dynamic adjustment of the inventory quantity of various types of goods specifically includes: Based on inbound and outbound records and demand volatility , obtain the inventory demand of various goods at future times: ; Where, is the time series model, Indicates the predicted The inventory quantity at the moment; Get the actual inventory quantity of each type of goods : ; In the formula, For the The inventory quantity at the moment, For the The inventory quantity at the moment, For the The quantity of inventory at the time, For the The quantity of goods shipped out at the time; Based on forecasted inventory requirements The actual inventory The differences: ; In the formula, The inventory quantity that needs to be adjusted; Will Input into the warehouse management model to change the characteristic data of the inventory quantity in the cargo node; when When , the inventory reduction operation is triggered; when When the goods are received, it is determined whether there are enough cargo spaces in the storage system to meet the environmental adaptability requirements and inventory requirements of the goods. If so, the next step is to enter the warehouse or increase the inventory. If it does not exist, then according to the environmental adaptability requirements of the goods, adjust the environmental parameters of the idle storage space equal to the inventory quantity that needs to be increased for the goods; If the number of free storage spaces and environmental parameters cannot meet the required inventory quantity of the goods, reduce the number of empty storage spaces for the goods. The quantity of inventory at the time; Continuously monitor inventory status and market demand changes, and update the input data of the warehouse management network model in real time through the feedback mechanism.

[0011] Preferably, the dynamically adjusting the scheduling of the automation equipment specifically includes: Based on the equipment working status and equipment task capabilities, the warehouse management network model is used to evaluate the operating efficiency of each automation equipment: ; In the formula, For equipment operating efficiency, The working status of the device. For equipment mission capability; Dynamically set the priority of each task based on the urgency of the goods and the order priority: ; In the formula, Indicates the priority of the task. Indicates the urgency of the task. Indicates order priority; Combined with the equipment's operating efficiency evaluation results and task priorities, the optimal path planning algorithm is used to optimize the scheduling strategy of automation equipment: ; In the formula, For equipment Scheduling strategy; The scheduling strategy is used by the automation equipment to prioritize the sorting and transportation of goods in and out of the warehouse and the transportation of goods between cargo locations according to the priority of each task.

[0012] Furthermore, an unmanned logistics warehousing management system based on real-time data is proposed, which is used to implement any of the above management methods, including: A data collection module, which is used to collect various data in the warehouse environment in real time, including the inventory quantity, storage location status, environmental parameters, and the working status and task capabilities of the automation equipment; An analysis module, wherein the analysis module is configured to construct a warehouse management network model for warehouse management, including cargo nodes, cargo location nodes, and equipment nodes, and perform information aggregation and relationship modeling to support subsequent inventory adjustment, cargo location optimization, and equipment scheduling; A control and decision module, which dynamically adjusts the inventory quantity, storage status and scheduling of automated equipment based on the output of the analysis module, and performs corresponding management and optimization operations; A real-time monitoring and feedback module, which continuously monitors the storage environment and equipment operating status, and transmits the latest real-time data and goods flow data back to the analysis module through a feedback mechanism; The user interface provides a visual operation interface for warehouse management personnel to view inventory status, cargo location distribution, equipment operation status and system adjustment suggestions in real time, and supports manual intervention and system configuration.

[0013] Preferably, the data acquisition module includes: A cargo identification subunit, which acquires and updates the inventory quantity of various types of cargo in real time through an RFID device component; A cargo location monitoring subunit, which collects information about each cargo location through cameras and sensors, monitors the status of each cargo location, and determines whether the cargo location is occupied or free; An environmental monitoring subunit, which collects storage environment parameters in real time by deploying environmental sensors to evaluate the compatibility of goods and cargo spaces; The equipment status monitoring subunit is based on the IoT device and collects the working status and task capabilities of the automation equipment in real time through network transmission, including the equipment's operating speed, task progress and fault information; A storage unit is used to store real-time data, cargo flow data, equipment operation logs and system configuration parameters.

[0014] Preferably, the control and decision module includes: An inventory management subunit, which dynamically adjusts the inventory quantity of various types of goods according to the inventory forecast results of the analysis module and implements a method for dynamic inventory adjustment; A cargo space optimization subunit, which dynamically adjusts the cargo space status based on the cargo and environment compatibility analysis result and executes a method for adjusting the cargo space status; The equipment scheduling subunit optimizes the scheduling strategy of the automation equipment and executes the equipment scheduling optimization method according to the equipment operation efficiency evaluation and task priority setting results.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The unmanned logistics warehousing management method and system based on real-time data proposed in this scheme collects data such as the inventory quantity, storage location status, environmental parameters and equipment working status of goods in the warehousing environment in real time through the data acquisition module, and integrates modeling and intelligent analysis of multiple types of data through the analysis module to achieve dynamic optimization management of inventory, storage locations and equipment. In terms of inventory management, the system predicts future inventory demand based on real-time inventory data and demand volatility, and dynamically adjusts inventory levels according to the number of storage locations and environmental parameters to avoid excess or shortage of inventory and ensure the rational use of inventory resources. In terms of storage location management, the system dynamically adjusts the storage location of goods based on the environmental adaptability of the goods and the current environmental parameters to achieve the optimal configuration of storage locations and avoid damage to goods due to environmental incompatibility. In terms of equipment scheduling, the status of automated equipment is monitored in real time, and intelligent scheduling is performed based on task priority and equipment operating efficiency to improve equipment utilization and operating efficiency, thereby achieving efficient configuration and management of warehousing resources.

[0016] The unmanned logistics warehousing management method and system based on real-time data proposed in this scheme responds to the results output by the analysis module through the control and decision-making module, and combines the real-time feedback mechanism to ensure that the system can dynamically adjust the management strategy according to the latest warehousing data and environmental changes, thereby improving the flexibility and response speed of the system. Specifically, in the inventory management process, when the system detects demand fluctuations or inventory changes, the inventory management strategy can be updated in real time to avoid resource waste or shortages caused by information lags. In the cargo space optimization process, the system automatically selects the most appropriate cargo space allocation plan and dynamically adjusts the storage environment to maintain the quality of the goods. In the equipment scheduling process, the optimal path planning and task allocation are achieved through real-time evaluation of task priorities and equipment working status, ensuring that the equipment operates in the best condition and reducing manual intervention. Through the above-mentioned intelligent data feedback and dynamic management mechanism, this scheme greatly improves the efficiency and accuracy of warehousing management, and realizes efficient, intelligent and precise unmanned logistics warehousing management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the unmanned logistics warehousing management method based on real-time data proposed by the present invention; Figure 2 A flow chart of constructing a warehouse management network model in the present invention; Figure 3 This is a flow chart of dynamically adjusting the cargo position status in the present invention; Figure 4 This is a flow chart for dynamically adjusting the inventory quantity of various types of goods in the present invention; Figure 5 It is a scheduling flow chart for dynamically adjusting the automation equipment in the present invention; Figure 6 This is a structural block diagram of the unmanned logistics warehousing management system based on real-time data proposed by the present invention; Figure 7 This is a structural block diagram of a data acquisition module in an unmanned logistics warehousing management system based on real-time data proposed by the present invention; Figure 8 This is a structural block diagram of the control and decision-making modules in the unmanned logistics warehousing management system based on real-time data proposed by the present invention. DETAILED DESCRIPTION

[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0019] Reference Figure 1 - Figure 5 As shown, the unmanned logistics warehousing management method based on real-time data includes: Collecting real-time storage data in the storage environment, including inventory quantity, cargo location status, equipment working status, equipment task capability and environmental parameters; Obtain the circulation data of various goods, including the volatility of demand, in-and-out records, and environmental adaptability of goods; Based on the inventory quantity, cargo location status, environmental adaptability and equipment working status, a warehouse management network model is constructed based on a graph neural network model; Use warehouse management network model to aggregate real-time data and flow data; According to the in-and-out records and demand volatility, the inventory quantity of various types of goods is dynamically adjusted through the aggregation results of the warehouse management network model; Based on the environmental adaptability of the goods and the current environmental parameters of the warehouse, the warehouse management network model is used to analyze the relationship between the goods and the environment, and the cargo position status is dynamically adjusted; Based on the working status of the equipment, the equipment status is evaluated through the aggregation results of the warehouse management network model, and the scheduling of automated equipment is dynamically adjusted in combination with the optimization algorithm, including the path planning of AGV transport vehicles, the sorting task allocation of robotic arms, and the setting of task priorities.

[0020] Specifically, the real-time storage data collected by this method in the storage environment include inventory quantity, storage location status, equipment working status, equipment task capability and environmental parameters. These data together constitute the system's basic understanding of the storage status. Among them, the inventory quantity reflects the current storage situation of the goods, the storage location status indicates whether each storage location is occupied and the suitability of the location, the equipment working status and task capability are used to evaluate the operating efficiency and load capacity of the automated equipment, and environmental parameters include external conditions such as temperature and humidity, which can affect the storage quality of sensitive goods. In addition, this method also obtains the circulation data of various types of goods, including demand volatility, warehouse in and out records and the environmental adaptability of goods. These data are used to reflect the circulation frequency of goods, demand change trends and their requirements for the storage environment, so that the system can dynamically adjust the storage strategy.

[0021] Furthermore, real-time storage data in the storage environment is collected, including: The inventory quantity of stored goods is collected through RFID equipment components deployed at each cargo location in the warehouse; The real-time status of goods in different cargo spaces is collected through cameras and cargo space sensors, including the three-dimensional coordinates of cargo spaces, vacancy status, occupancy status, and cargo location change information; The device working status and device task capability are obtained through the network transmission of the automated IoT devices. The device working status refers to the operating status of various automated devices in the warehouse management system at a specific time point. The device task capability refers to the ability and performance index of various automated devices in the warehouse management system to perform specific tasks. Environmental monitoring equipment and temperature and humidity sensors are used to collect real-time temperature, humidity and light parameters of each cargo location in the storage environment.

[0022] Specifically, this method will first divide the distribution of cargo locations in the warehouse into zones, and deploy the RFID equipment components, cameras and a series of sensors required for collection in different zones. For example, by deploying cameras and cargo location sensors in a certain zone, the real-time status of the goods in a certain cargo location in this zone can be collected, including the three-dimensional coordinates of the cargo location, vacant status, occupied status and cargo quantity information. The environmental parameters set for different zones are also different, so that different goods can be stored in zones that are compatible with their environmental adaptability. Automated Internet of Things devices are automated devices with networking functions, such as AGV transport vehicles and robotic arms. These automated devices can transmit data such as their own working status and task capabilities, and can also receive scheduling instructions; Furthermore, the circulation data of various types of goods are obtained, including: Obtain historical demand data for goods through the upstream and downstream of the supply chain, analyze the demand trends of various types of goods in different time periods, and thus obtain the volatility of demand for goods; Obtain inbound and outbound records, including the goods' inbound and outbound time, frequency, and inbound and outbound quantities of the corresponding goods; The storage environment requirements of goods are obtained through the upstream and downstream of the supply chain and the storage status of specific goods under changes in storage environment parameters are recorded, so as to obtain the environmental adaptability of the goods. The environmental adaptability of the goods is specifically to obtain the storage environment requirements of each type of goods during the production, transportation and storage process, including the optimal storage temperature, humidity range and lighting conditions.

[0023] Furthermore, a warehouse management network model is constructed, including: Clean the collected real-time warehouse data and cargo flow data to build a standard data set, including cargo in and out records, inventory and environmental adaptability, three-dimensional coordinates of cargo locations, cargo location status and environmental parameters, equipment working status and equipment mission capabilities; Extract data features of real-time warehouse data and cargo flow data based on standard data sets, and assign feature vectors to feature data; Design a warehouse management graph construction method based on feature vectors and define graph ,in Represents a collection of nodes, including cargo nodes , cargo location node and device nodes , Represents a set of edges, including cargo-location edges , Cargo-Equipment Side and cargo space-environmental side , and build a warehouse management network model based on the graph neural network model, specifically: Each node has its own characteristics. Each node in the warehouse management network model is connected by edges. The characteristic data of each node is designed to be highly correlated with the characteristic data of its neighboring nodes. When the characteristic data of a node changes, it is determined whether the characteristic data of its neighboring nodes needs to be updated. Design a warehouse management network model based on the graph neural network model. For the feature data of each node, according to the multi-layer graph neural network layer in the warehouse management network model, the information aggregation and gradual update of the node feature data are realized through information transmission between layers, so as to manage and adjust the matching problem of goods and cargo locations, and the scheduling problem of equipment; The warehouse management graph construction method is optimized based on the genetic algorithm, and the optimal warehouse management network structure is constructed based on the graph neural network model. The warehouse management network model is trained through the standard data set to obtain the final trained warehouse management network model. Deploy the trained warehouse management network model into the warehouse management system for real-time data analysis and decision support.

[0024] Furthermore, the relationship between the goods and the environment is analyzed, and the cargo position status is adjusted dynamically, including: Based on the information aggregation results of goods and cargo locations by the warehouse management network model, the matching degree between the environmental adaptability of goods and the environmental parameters of cargo locations is analyzed; Based on the matching degree between the environmental adaptability of the goods and the environmental parameters of the cargo space, the compatibility between the two is analyzed: ; In the formula, is the compatibility analysis function, Indicates goods , Indicates the cargo location , Indicates goods The inventory quantity, Indicates the status of the cargo space. For the environmental adaptability of the goods, is the environmental parameter of the cargo space; Based on the analysis results of the warehouse management network model, evaluate the compatibility of goods and cargo spaces; Dynamically adjust the cargo space status based on the results of the compatibility assessment; If the compatibility score between the goods and the cargo space is high, the goods are transported to the cargo space through automated equipment, and the system sets the cargo space to occupied status; If the compatibility score is low, the cargo space is marked as unavailable and the compatibility of the goods with other cargo spaces is evaluated; If there is no cargo space with a high compatibility score in the warehouse, or the quantity of goods entering the warehouse exceeds the number of cargo spaces with a high compatibility score, the environmental parameters of the free cargo space are adjusted. When the environmental parameters of the free cargo space match the goods, the goods are stored in the cargo space. Continuously monitor environmental parameters and cargo storage status, feed the latest real-time data back to the warehouse management network model through the feedback mechanism, and update the model input in real time.

[0025] Specifically, this method dynamically adjusts the storage location of the goods by analyzing the environmental adaptability of the goods and the current environmental parameters. Assuming that goods B is more sensitive to temperature and humidity, and some cargo areas in the storage environment have higher temperature and humidity fluctuations, the compatibility analysis of the environmental adaptability of goods B and the temperature and humidity parameters of the current cargo location is performed through the warehouse management network model. When the analysis result shows that goods B is incompatible with the environment of the current cargo location, the cargo location status is marked as "not suitable for storing goods B", and attempts are made to adjust the environmental parameters or move goods B to a more suitable cargo location to ensure the quality of the goods. At the same time, the changes in storage environment parameters are continuously monitored, and the allocation of cargo locations is dynamically adjusted to achieve optimization of cargo location management.

[0026] Furthermore, the inventory quantity of various goods is adjusted dynamically, including: Based on inbound and outbound records and demand volatility , obtain the inventory demand of various goods at future times: ; In the formula, is a time series model, Indicates the predicted The inventory quantity at the moment; Get the actual inventory quantity of each type of goods : ; In the formula, For the The inventory quantity at the moment, For the The inventory quantity at the moment, For the The quantity of inventory at the time, For the The quantity of goods shipped out at the time; Based on forecasted inventory requirements The actual inventory The differences: ; In the formula, The inventory quantity that needs to be adjusted; Will Input into the warehouse management model to change the characteristic data of the inventory quantity in the cargo node; when When , the inventory reduction operation is triggered; when When the goods are received, it is determined whether there are enough cargo spaces in the storage system to meet the environmental adaptability requirements and inventory requirements of the goods. If so, the next step is to enter the warehouse or increase the inventory. If it does not exist, then according to the environmental adaptability requirements of the goods, adjust the environmental parameters of the idle storage space equal to the inventory quantity that needs to be increased for the goods; If the number of free storage spaces and environmental parameters cannot meet the required inventory quantity of the goods, reduce the number of empty storage spaces for the goods. The quantity of inventory at the time; Continuously monitor inventory status and market demand changes, and update the input data of the warehouse management network model in real time through the feedback mechanism.

[0027] Specifically, this method collects data such as the inventory quantity, storage location status, equipment working status, environmental parameters, and demand volatility of goods in real time in a warehousing environment. Assuming that the demand for a certain type of good A fluctuates greatly during holidays, a comprehensive analysis is conducted on its inventory quantity and demand volatility through a warehousing management network model. Based on the analysis results, it is predicted that the demand for good A will increase significantly in the next few days. Then, it is analyzed whether there is a number of storage locations in the warehouse that is equal to the required increase in inventory quantity and compatible with the environmental parameters of good A. If so, the goods are put into storage. If not, the environmental parameters of the idle storage locations are adjusted to meet the inventory demand of good A. If the inventory demand of good A still exceeds the number of matched storage locations, the future storage quantity of the good A will be reduced.

[0028] Furthermore, the scheduling of automation equipment is dynamically adjusted, including: Based on the equipment working status and equipment task capabilities, the warehouse management network model is used to evaluate the operating efficiency of each automation equipment: ; In the formula, For equipment operating efficiency, The working status of the device. For equipment mission capability; Dynamically set the priority of each task based on the urgency of the goods and the order priority: ; In the formula, Indicates the priority of the task. Indicates the urgency of the task. Indicates order priority; Combined with the equipment's operating efficiency evaluation results and task priorities, the optimal path planning algorithm is used to optimize the scheduling strategy of automation equipment: ; In the formula, For equipment Scheduling strategy; The scheduling strategy is used by the automation equipment to prioritize the sorting and transportation of goods in and out of the warehouse and the transportation of goods between cargo locations according to the priority of each task.

[0029] Specifically, this method dynamically adjusts the scheduling strategy of automated equipment by monitoring the working status and task requirements of automated equipment in real time. It assumes that the AGV transport vehicles and robotic arms in the warehouse need to process a large number of order tasks during peak hours. The task capability and current status of each device are analyzed through the warehouse management network model. According to the evaluation results of task priority and equipment status, the path planning of the AGV is automatically optimized to ensure that the transport vehicle chooses the shortest path to improve transportation efficiency. At the same time, higher-priority sorting tasks are assigned to the robotic arms to avoid low-priority tasks from occupying resources, thereby ensuring timely processing of orders. Through this scheduling optimization, the system significantly improves the utilization rate of equipment and shortens the processing time of sorting and transportation.

[0030] Further, see Figure 6 - Figure 8 Shown An unmanned logistics warehousing management system based on real-time data is proposed to implement any of the above management methods, including: A data collection module, which is used to collect various data in the warehouse environment in real time, including the inventory quantity, storage location status, environmental parameters, and the working status and task capabilities of the automation equipment; An analysis module, wherein the analysis module is configured to construct a warehouse management network model for warehouse management, including cargo nodes, cargo location nodes, and equipment nodes, and perform information aggregation and relationship modeling to support subsequent inventory adjustment, cargo location optimization, and equipment scheduling; A control and decision module, which dynamically adjusts the inventory quantity, storage status and scheduling of automated equipment based on the output of the analysis module, and performs corresponding management and optimization operations; A real-time monitoring and feedback module, which continuously monitors the storage environment and equipment operating status, and transmits the latest real-time data and goods flow data back to the analysis module through a feedback mechanism; The user interface provides a visual operation interface for warehouse management personnel to view inventory status, cargo location distribution, equipment operation status and system adjustment suggestions in real time, and supports manual intervention and system configuration.

[0031] Furthermore, the data acquisition module includes: A cargo identification subunit, which acquires and updates the inventory quantity of various types of cargo in real time through an RFID device component; A cargo location monitoring subunit, which collects information about each cargo location through cameras and sensors, monitors the status of each cargo location, and determines whether the cargo location is occupied or free; An environmental monitoring subunit, which collects storage environment parameters in real time by deploying environmental sensors to evaluate the compatibility of goods and cargo spaces; The equipment status monitoring subunit is based on the IoT device and collects the working status and task capabilities of the automation equipment in real time through network transmission, including the equipment's operating speed, task progress and fault information; A storage unit is used to store real-time data, cargo flow data, equipment operation logs and system configuration parameters.

[0032] Furthermore, the control and decision-making module includes: An inventory management subunit, which dynamically adjusts the inventory quantity of various types of goods according to the inventory forecast results of the analysis module and implements a method for dynamic inventory adjustment; A cargo space optimization subunit, which dynamically adjusts the cargo space status based on the cargo and environment compatibility analysis result and executes a method for adjusting the cargo space status; The equipment scheduling subunit optimizes the scheduling strategy of the automation equipment and executes the equipment scheduling optimization method according to the equipment operation efficiency evaluation and task priority setting results.

[0033] In summary, the advantages of the present invention are as follows: the present invention constructs a warehouse management network model based on the graph neural network model, realizes the intelligent modeling and analysis of extremely complex relationships among multiple types of nodes (goods, cargo spaces, equipment) in the warehouse system, and has the advantages of high intelligence level, fast real-time dynamic response, high resource utilization efficiency, strong adaptability, simple and reliable operation, etc. Through the warehouse management network model, a comprehensive analysis of the storage requirements of goods and the environmental status of cargo spaces is carried out, and accurate compatibility matching between goods and cargo spaces is achieved, avoiding the problem of cargo quality degradation caused by environmental discomfort. Based on the real-time data collection and feedback mechanism, the system can timely adjust the usage status of cargo spaces according to changes in inventory status, cargo space compatibility and environmental parameters. The present invention provides an efficient, intelligent and reliable unmanned logistics warehousing management solution, which has significant technical advantages and broad application prospects, and can effectively solve the problems that traditional logistics warehousing management is difficult to dynamically adjust cargo locations according to real-time environmental changes, lacks refined management, and may cause goods to be affected by improper environmental conditions, and even have the risk of quality degradation or damage.

[0034] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An unmanned logistics warehousing management method based on real-time data, characterized in that: include: Collecting real-time storage data in the storage environment, including inventory quantity, cargo location status, equipment working status, equipment task capability and environmental parameters; Obtain the circulation data of various goods, including the volatility of demand, in-and-out records, and environmental adaptability of goods; Based on the inventory quantity, cargo location status, environmental adaptability and equipment working status, a warehouse management network model is constructed based on a graph neural network model; Use warehouse management network model to aggregate real-time data and flow data; According to the in-and-out records and demand volatility, the inventory quantity of various types of goods is dynamically adjusted through the aggregation results of the warehouse management network model; Based on the environmental adaptability of the goods and the current environmental parameters of the warehouse, the warehouse management network model is used to analyze the relationship between the goods and the environment, and the cargo position status is dynamically adjusted; Based on the working status of the equipment, the equipment status is evaluated through the aggregation results of the warehouse management network model, and the scheduling of automated equipment is dynamically adjusted in combination with the optimization algorithm, including the path planning of AGV transport vehicles, the sorting task allocation of robotic arms, and the setting of task priorities.

2. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The real-time storage data collected in the storage environment specifically includes: The inventory quantity of stored goods is collected through RFID equipment components deployed at each cargo location in the warehouse; The real-time status of goods in different cargo spaces is collected through cameras and cargo space sensors, including the three-dimensional coordinates of cargo spaces, vacancy status, occupancy status, and number of cargo spaces; The device working status and device task capability are obtained through the network transmission of the automated IoT devices. The device working status refers to the operating status of various automated devices in the warehouse management system at a specific time point. The device task capability refers to the ability and performance index of various automated devices in the warehouse management system to perform specific tasks. Environmental monitoring equipment and temperature and humidity sensors are used to collect real-time temperature, humidity and light parameters of each cargo location in the storage environment.

3. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The acquisition of the circulation data of various types of goods specifically includes: Obtain historical demand data for goods through the upstream and downstream of the supply chain, analyze the demand trends of various types of goods in different time periods, and thus obtain the volatility of demand for goods; Obtain inbound and outbound records, including the goods' inbound and outbound time, frequency, and inbound and outbound quantities of the corresponding goods; The storage environment requirements of goods are obtained through the upstream and downstream of the supply chain and the storage status of specific goods under changes in storage environment parameters are recorded, so as to obtain the environmental adaptability of the goods. The environmental adaptability of the goods is specifically to obtain the storage environment requirements of each type of goods during the production, transportation and storage process, including the optimal storage temperature, humidity range and lighting conditions.

4. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The construction of the warehouse management network model specifically includes: Clean the collected real-time warehouse data and cargo flow data to build a standard data set, including cargo in and out records, inventory and environmental adaptability, three-dimensional coordinates of cargo locations, cargo location status and environmental parameters, equipment working status and equipment mission capabilities; Extract data features of real-time warehouse data and cargo flow data based on standard data sets, and assign feature vectors to feature data; Design a warehouse management graph construction method based on feature vectors and define graph ,in Represents a collection of nodes, including cargo nodes , cargo location node and device nodes , Represents a set of edges, including cargo-location edges , Cargo-Equipment Side and cargo space-environmental side , and designed a warehouse management network model based on the graph neural network model, specifically: Each node has its own characteristics. Each node in the warehouse management network model is connected by edges. The characteristic data of each node is designed to be highly correlated with the characteristic data of its neighboring nodes. When the characteristic data of a node changes, it is determined whether the characteristic data of its neighboring nodes needs to be updated. Design a warehouse management network model based on the graph neural network model. For the feature data of each node, according to the multi-layer graph neural network layer in the warehouse management network model, the information aggregation and gradual update of the node feature data are realized through information transmission between layers, so as to manage and adjust the matching problem of goods and cargo locations, and the scheduling problem of equipment; The warehouse management graph construction method is optimized based on the genetic algorithm, and the optimal warehouse management network structure is constructed based on the graph neural network model. The warehouse management network model is trained through the standard data set to obtain the final trained warehouse management network model. Deploy the trained warehouse management network model into the warehouse management system for real-time data analysis and decision support.

5. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The analyzing the relationship between the cargo and the environment and dynamically adjusting the cargo position status specifically includes: Based on the information aggregation results of goods and cargo locations by the warehouse management network model, the matching degree between the environmental adaptability of goods and the environmental parameters of cargo locations is analyzed; Based on the matching degree between the environmental adaptability of the goods and the environmental parameters of the cargo space, the compatibility between the two is analyzed: ； In the formula, is the compatibility analysis function, Indicates goods , Indicates the cargo location , Indicates goods The inventory quantity, Indicates the status of the cargo space. For the environmental adaptability of the goods, is the environmental parameter of the cargo space; Based on the analysis results of the warehouse management network model, evaluate the compatibility of goods and cargo spaces; Dynamically adjust the cargo space status based on the results of the compatibility assessment; If the compatibility score between the goods and the cargo space is high, the goods are transported to the cargo space through automated equipment, and the system sets the cargo space to occupied status; If the compatibility score is low, the cargo space is marked as unavailable and the compatibility of the goods with other cargo spaces is evaluated; If there is no cargo space with a high compatibility score in the warehouse, or the quantity of goods entering the warehouse exceeds the number of cargo spaces with a high compatibility score, the environmental parameters of the free cargo space are adjusted. When the environmental parameters of the free cargo space match the goods, the goods are stored in the cargo space. Continuously monitor environmental parameters and cargo storage status, feed the latest real-time data back to the warehouse management network model through the feedback mechanism, and update the model input in real time.

6. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The dynamic adjustment of the inventory quantity of various goods specifically includes: Based on inbound and outbound records and demand volatility , obtain the inventory demand of various goods at future times: ； In the formula, is a time series model, Indicates the predicted The inventory quantity at the moment; Get the actual inventory quantity of each type of goods : ； In the formula, For the The inventory quantity at the moment, For the The inventory quantity at the moment, For the The quantity of inventory at the time, For the The quantity of goods shipped out at the time; Get forecasted inventory requirements Difference from actual inventory: ； In the formula, The inventory quantity that needs to be adjusted; Will Input into the warehouse management model to change the characteristic data of the inventory quantity in the cargo node; when When , the inventory reduction operation is triggered; when When the goods are received, it is determined whether there are enough cargo spaces in the storage system to meet the environmental adaptability requirements and inventory requirements of the goods. If so, the next step is to enter the warehouse or increase the inventory. If it does not exist, then according to the environmental adaptability requirements of the goods, adjust the environmental parameters of the idle storage space equal to the inventory quantity that needs to be increased for the goods; If the number of free storage spaces and environmental parameters cannot meet the required inventory quantity of the goods, reduce the number of empty storage spaces for the goods. The quantity of inventory at the time; Continuously monitor inventory status and market demand changes, and update the input data of the warehouse management network model in real time through the feedback mechanism.

7. The unmanned logistics warehousing management method based on real-time data according to claim 1 is characterized in that: The dynamically adjusting the scheduling of the automation equipment specifically includes: Based on the equipment working status and equipment task capabilities, the warehouse management network model is used to evaluate the operating efficiency of each automation equipment: ； In the formula, For equipment operating efficiency, The working status of the device. For equipment mission capability; Dynamically set the priority of each task based on the urgency of the goods and the order priority: ； In the formula, Indicates the priority of the task. Indicates the urgency of the task. Indicates order priority; Combined with the equipment's operating efficiency evaluation results and task priorities, the optimal path planning algorithm is used to optimize the scheduling strategy of automation equipment: ； In the formula, For equipment Scheduling strategy; The scheduling strategy is used by the automation equipment to prioritize the sorting and transportation of goods in and out of the warehouse and the transportation of goods between cargo locations according to the priority of each task.

8. An unmanned logistics warehouse management system based on real-time data, characterized in that: The method for implementing the unmanned logistics warehousing management method based on real-time data as claimed in any one of claims 1 to 7 comprises: A data collection module, which is used to collect various data in the warehouse environment in real time, including the inventory quantity, storage location status, environmental parameters, and the working status and task capabilities of the automation equipment; An analysis module, wherein the analysis module is configured to construct a warehouse management network model for warehouse management, including cargo nodes, cargo location nodes, and equipment nodes, and perform information aggregation and relationship modeling to support subsequent inventory adjustment, cargo location optimization, and equipment scheduling; A control and decision module, which dynamically adjusts the inventory quantity, storage status and scheduling of automated equipment based on the output of the analysis module, and performs corresponding management and optimization operations; A real-time monitoring and feedback module, which continuously monitors the storage environment and equipment operating status, and transmits the latest real-time data and goods flow data back to the analysis module through a feedback mechanism; The user interface provides a visual operation interface for warehouse management personnel to view inventory status, cargo location distribution, equipment operation status and system adjustment suggestions in real time, and supports manual intervention and system configuration.

9. The unmanned logistics warehousing management system based on real-time data according to claim 8 is characterized in that: The data acquisition module comprises: A cargo identification subunit, which acquires and updates the inventory quantity of various types of cargo in real time through an RFID device component; A cargo location monitoring subunit, which collects information about each cargo location through cameras and sensors, monitors the status of each cargo location, and determines whether the cargo location is occupied or free; An environmental monitoring subunit, which collects storage environment parameters in real time by deploying environmental sensors to evaluate the compatibility of goods and cargo spaces; The equipment status monitoring subunit is based on the IoT device and collects the working status and task capabilities of the automation equipment in real time through network transmission, including the equipment's operating speed, task progress and fault information; A storage unit is used to store real-time data, cargo flow data, equipment operation logs and system configuration parameters.

10. The unmanned logistics warehousing management system based on real-time data according to claim 8, characterized in that: The control and decision module includes: An inventory management subunit, which dynamically adjusts the inventory quantity of various types of goods according to the inventory forecast results of the analysis module and implements a method for dynamic inventory adjustment; A cargo space optimization subunit, which dynamically adjusts the cargo space status based on the cargo and environment compatibility analysis result and executes a method for adjusting the cargo space status; The equipment scheduling subunit optimizes the scheduling strategy of the automation equipment and executes the equipment scheduling optimization method according to the equipment operation efficiency evaluation and task priority setting results.

Images