Intelligent warehouse cargo scheduling device

Abstract

The invention relates to the technical field of automatic logistics, in particular to an intelligent warehouse cargo scheduling device, which comprises a dynamic priority adjustment module, a self-adaptive classified storage module, a cargo flow optimization module, a resource allocation module, a fault analysis and maintenance module, a behavior monitoring module, an energy management module and a cost control module. According to the method, the cargo scheduling priority is optimized through a support vector machine algorithm and a decision tree method, the warehouse space utilization rate is improved by utilizing a convolutional neural network and a genetic algorithm, the cargo flow is optimized by adopting linear programming and a network flow analysis algorithm, and the cargo flow trend is estimated through an autoregressive integral moving average model and a recurrent neural network. The system utilizes a long short-term memory network to identify equipment faults and maintain, reduces the risk of accidental shutdown, improves the operation safety through a computer vision technology and a behavior identification algorithm, and utilizes an energy consumption mode analysis and cost-benefit analysis method to reduce the operation cost.

Description

Technical Field

[0001] The present invention relates to the field of automated logistics technology, and in particular to an intelligent warehousing cargo dispatching device. Background Art

[0002] The field of automated logistics technology focuses on the use of automated and intelligent systems to manage and optimize storage, retrieval and transportation processes within warehouses. By introducing automated equipment and intelligent software, automated logistics technology aims to improve the efficiency and accuracy of warehouse operations, reduce manpower requirements, and increase response speed, thereby reducing operating costs and improving service quality. The core of this technology field includes robotics, intelligent algorithms, data analysis and Internet of Things technologies to achieve automated management and intelligent decision-making in warehouse environments.

[0003] Among them, a smart warehouse cargo scheduling device is part of the automated warehouse management system, which aims to optimize the storage, retrieval and distribution process of goods. Through automated scheduling and intelligent management, it improves the efficiency and accuracy of warehouse operations, reduces cargo processing time and reduces labor costs, and achieves accurate cargo positioning, fast cargo scheduling and efficient resource allocation, thereby improving warehouse space utilization, accelerating cargo turnover and improving the overall logistics service quality.

[0004] Traditional warehouse management has shortcomings in dynamic environment adaptation, resource allocation efficiency, equipment maintenance prediction, operator safety monitoring, energy and cost management. Traditional systems rely on manual decision-making and lack real-time data analysis capabilities, resulting in slow response to cargo scheduling, insufficient utilization of storage space, uneven allocation of human and material resources, delayed equipment maintenance response, difficulty in ensuring operational safety, energy waste and poor cost control, resulting in reduced warehouse operating efficiency and increased costs, affecting the overall service quality and corporate competitiveness. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent warehouse cargo scheduling device.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: a smart warehouse cargo scheduling device includes a dynamic priority adjustment module, an adaptive classification storage module, a cargo flow optimization module, a resource allocation module, a fault analysis and maintenance module, a behavior monitoring module, an energy management module, and a cost control module;

[0007] The dynamic priority adjustment module uses a support vector machine algorithm based on cargo feature information to analyze the relationship between cargo features and warehouse operation efficiency, uses a decision tree method to logically summarize the analysis results, adjusts cargo scheduling priorities based on cargo attributes and warehouse status, and generates scheduling priority indicators;

[0008] The adaptive classification storage module uses a convolutional neural network algorithm based on the dispatch priority index to identify the type and characteristics of goods, applies a genetic algorithm to analyze the volume, weight and dispatch priority index of goods, optimizes the storage location of goods, and generates a storage optimization plan;

[0009] The cargo flow optimization module is based on the storage optimization plan, adopts a linear programming algorithm to formulate cargo storage and outbound paths, uses a network flow analysis algorithm to analyze cargo types, storage locations and destinations, optimizes the process of cargo movement within the warehouse, and generates a process optimization strategy;

[0010] The resource allocation module is based on process optimization strategy, adopts autoregressive integral moving average model, analyzes historical warehouse data, estimates the inflow and outflow trend of goods, uses recurrent neural network to analyze seasonal changes and random fluctuations in goods demand, adjusts human and warehouse resource allocation, and generates resource allocation plan;

[0011] The fault analysis and maintenance module is based on the resource allocation plan and uses a long short-term memory network to analyze the operating data of the storage equipment, including temperature, humidity, and vibration, identify the correlation and fault signs in the data, plan the maintenance and repair schedule of the equipment, reduce the risk of unexpected downtime, optimize the maintenance cycle and equipment reliability, and generate maintenance warning information;

[0012] The behavior monitoring module uses computer vision technology and behavior recognition algorithms based on maintenance warning information to identify operator behavior patterns, including handling postures and the use of safety equipment. It analyzes behavior data through anomaly detection algorithms to identify safety hazards, provide safety warnings to management, and generate safety monitoring information.

[0013] The energy management module uses energy consumption pattern analysis algorithms based on security monitoring information to analyze warehouse energy usage data and energy-saving improvement points, including power consumption, lighting and temperature control equipment, apply dynamic energy adjustment strategies, adjust energy distribution and use, and generate energy-saving adjustment strategies;

[0014] The cost control module is based on energy-saving adjustment strategies, adopts cost-benefit analysis methods and dynamic cost optimization algorithms, analyzes the cost benefits of multiple warehousing activities, including labor costs, energy costs, equipment depreciation and small and medium-sized warehouse site information, and generates cost optimization plans through detailed management and intelligent adjustment.

[0015] As a further scheme of the present invention, the scheduling priority indicators include cargo emergency response level, destination distance weight, and access frequency score; the storage optimization plan includes cargo classification labels, recommended storage areas, and cargo access path optimization plan; the process optimization strategy includes cargo handling path, cargo picking serialization plan, and cargo in and out of storage timing scheduling information; the resource allocation plan includes human resource dynamic allocation information, warehouse space utilization forecast, and automated equipment scheduling plan; the maintenance warning information includes equipment failure probability assessment, expected maintenance time point, and pre-maintenance operation plan; the safety monitoring information includes unsafe behavior detection records, potential safety risk areas, and proposals for improved safety measures; the energy-saving adjustment strategy includes energy consumption optimization area, energy-saving operation plan, and expected energy-saving effect evaluation; the cost optimization results include cost savings area analysis results, operating cost reduction strategies, and long-term cost-benefit forecast information.

[0016] As a further solution of the present invention, the dynamic priority adjustment module includes a feature weight submodule, an algorithm application submodule, and a priority calculation submodule;

[0017] The feature weight submodule uses a principal component analysis algorithm based on the cargo feature information to analyze the basic features of the cargo, including volume, weight, and access frequency, assign weights to the basic features, identify the priorities of multiple cargo features, and generate feature weight information;

[0018] The algorithm application submodule uses a support vector machine algorithm based on feature weight information to analyze the relationship between cargo features and warehouse operating efficiency, determine cargo scheduling priorities, optimize warehouse resource allocation and operating efficiency, and generate a priority association model;

[0019] The priority calculation submodule uses a decision tree algorithm based on a priority association model to analyze the priority of target goods through the weight of goods characteristics and the current state of the warehouse, improve the efficiency of goods scheduling, reduce warehouse resource consumption, and generate a scheduling priority index.

[0020] As a further solution of the present invention, the adaptive classification storage module includes an image analysis submodule, a type recognition submodule, and a position decision submodule;

[0021] The image analysis submodule uses image preprocessing technology to optimize the image quality of goods based on the scheduling priority index, applies edge detection algorithm, extracts key visual features of goods, and generates visual feature data;

[0022] The type recognition submodule uses a convolutional neural network model based on visual feature data to analyze the visual features of cargo images, including shape, color, and size, classify the cargo into multiple categories, optimize the efficiency and accuracy of cargo classification, and generate cargo classification information;

[0023] The location decision submodule is based on cargo classification information and adopts genetic algorithm to analyze the convenience and safety of cargo access through cargo key features and warehouse layout information, matches cargo storage locations, optimizes the allocation and utilization of warehouse space resources, and generates a storage optimization plan.

[0024] As a further solution of the present invention, the cargo flow optimization module includes a path planning submodule, a picking strategy submodule, and a timing management submodule;

[0025] The path planning submodule uses the Dijkstra algorithm based on the storage optimization solution to analyze the road grid and obstacles inside the warehouse, calculate the path between the cargo storage location in the warehouse and the exit, optimize the cargo transportation route, and generate the shortest path planning;

[0026] The picking strategy submodule is based on the shortest path planning and uses the queuing theory algorithm to analyze the waiting time and processing time of the goods picking process, refine the goods picking sequence and picking window, reduce the goods picking congestion, and generate a picking efficiency optimization strategy;

[0027] The timing management submodule is based on the picking efficiency optimization strategy and adopts the critical path method to perform timing management on the entire process of goods out of the warehouse, identify the key steps and time bottlenecks of the goods out of the warehouse process, optimize the operation sequence and time arrangement, reduce the goods out of the warehouse time, and generate a process optimization strategy.

[0028] As a further solution of the present invention, the resource allocation module includes a trend analysis submodule, a demand forecasting submodule, and a resource allocation submodule;

[0029] The trend analysis submodule is based on the process optimization strategy and adopts the autoregressive integral moving average model to analyze the historical warehouse data, including the inflow and outflow records of goods and seasonal demand changes, identify the flow trend of goods, and generate trend analysis information;

[0030] The demand forecasting submodule uses a long short-term memory network based on trend analysis information to analyze and forecast cargo demand, including market dynamics, changes in consumer behavior, holidays and seasonal changes, optimize warehouse resource allocation, and generate demand forecast analysis;

[0031] The resource allocation submodule uses a linear programming algorithm based on demand forecast analysis to optimize the allocation of human resources and storage space, match cargo demand with warehouse resource capacity, optimize storage and transportation costs, and generate a resource allocation plan.

[0032] As a further solution of the present invention, the fault analysis and maintenance module includes a data analysis submodule, a fault prediction submodule, and a maintenance planning submodule;

[0033] The data analysis submodule analyzes the operation data of storage equipment, including temperature, humidity, and vibration, based on the resource allocation plan, using outlier processing and data normalization, identifies equipment operation rules and abnormal traces, and generates a standardized equipment data set;

[0034] The fault prediction submodule is based on the normalized equipment data set, combined with the equipment historical operation data, and uses the long short-term memory network to analyze the relationship between multi-source data through the equipment historical operation data, identify fault signals and equipment fault points, and generate fault prediction information;

[0035] The maintenance planning submodule uses a priority queuing algorithm based on fault prediction information to analyze fault severity and urgency, develop an equipment maintenance and repair plan, including the sequence and schedule of warehouse equipment maintenance, optimize the overall maintenance process, reduce operational interruptions, and generate maintenance warning information.

[0036] As a further solution of the present invention, the behavior monitoring module includes a behavior analysis submodule, a safety assessment submodule, and a risk identification submodule;

[0037] The behavior analysis submodule uses a convolutional neural network to analyze monitoring video data based on maintenance warning information, identify operator behavior patterns, including handling postures and use of safety equipment, and generate behavior feature information;

[0038] The safety assessment submodule uses an isolation forest algorithm based on behavioral feature information to analyze the behavioral features of operators, identify behaviors that lead to safety accidents, optimize risk identification, reduce safety hazards, and generate safety risk assessment information;

[0039] The risk identification submodule uses the risk matrix assessment method based on the security risk assessment information to analyze the environment and safety specifications of warehouse operations, identify abnormal behavior levels, match preventive measures and response strategies, and generate security monitoring information.

[0040] As a further solution of the present invention, the energy management module includes a consumption analysis submodule, an energy-saving strategy submodule, and an effect evaluation submodule;

[0041] The consumption analysis submodule uses trend analysis technology based on security monitoring information to analyze warehouse energy usage data, including power consumption, lighting system usage efficiency, and energy consumption patterns of temperature control equipment, identify key factors of energy consumption, and generate energy consumption information;

[0042] The energy-saving strategy submodule uses a linear programming algorithm based on energy consumption information to identify energy-saving improvement points and formulate energy-saving measures, including adjusting the settings of lighting and temperature control systems, optimizing power usage plans, reducing energy consumption, and generating energy-saving measures plans;

[0043] The effect evaluation submodule is based on energy-saving measure planning, and through the effect evaluation model, uses energy efficiency comparison analysis to analyze the energy usage data affected by energy-saving measures, evaluate the actual effects of energy-saving measures, optimize energy-saving effects, and generate energy-saving adjustment strategies.

[0044] As a further solution of the present invention, the cost control module includes a cost analysis submodule, a saving strategy submodule, and a benefit prediction submodule;

[0045] The cost analysis submodule adopts cost-benefit analysis method based on energy-saving adjustment strategy to analyze the cost and economic benefits of various warehousing activities, identify key areas of cost optimization, including labor cost analysis, energy use evaluation and equipment depreciation calculation, and generate comprehensive cost-benefit analysis results;

[0046] The saving strategy submodule generates a saving strategy optimization plan based on the comprehensive cost-benefit analysis results, using linear programming, integer programming and random optimization techniques, through detailed management and intelligent adjustment, including optimizing human resource allocation, reducing energy consumption and extending equipment service life;

[0047] The benefit prediction submodule is based on the saving strategy optimization plan, adopts time series analysis technology, builds a prediction model, uses historical data and market dynamics, estimates the economic benefits after the strategy is implemented, and generates a cost control optimization plan.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, support vector machine algorithm and decision tree method are used to analyze the complex relationship between cargo characteristics and warehouse operation efficiency, optimize cargo scheduling priority, improve the efficiency of warehouse operation, use convolutional neural network and genetic algorithm to optimize cargo storage location, improve warehouse space utilization, linear programming and network flow analysis algorithm to optimize cargo flow, shorten cargo processing time, autoregressive integral moving average model and recurrent neural network to estimate cargo flow trend, optimize resource allocation plan, identify equipment failure and maintenance through long and short-term memory network, reduce the risk of unexpected downtime, computer vision technology and behavior recognition algorithm to improve the safety of warehouse operation, prevent the occurrence of safety accidents through real-time monitoring and analysis of operating personnel's behavior patterns, energy consumption pattern analysis and cost-benefit analysis method to ensure service quality and efficiency, optimize cost control, and reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the device of the present invention;

[0051] Figure 2 It is a schematic diagram of the device framework of the present invention;

[0052] Figure 3 It is a flow chart of the dynamic priority adjustment module of the present invention;

[0053] Figure 4 This is a flow chart of the adaptive classification storage module of the present invention;

[0054] Figure 5 It is a flow chart of the cargo flow optimization module of the present invention;

[0055] Figure 6 It is a flow chart of the resource allocation module of the present invention;

[0056] Figure 7 This is a flow chart of the fault analysis and maintenance module of the present invention;

[0057] Figure 8 Behavior monitoring module flow chart of the present invention;

[0058] Fig. 9 It is a flow chart of the energy management module of the present invention;

[0059] Fig.10 It is a flow chart of the cost control module of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0062] Embodiment 1

[0063] See also Figure 1 to Figure 2 , a smart warehouse cargo scheduling device includes a dynamic priority adjustment module, an adaptive classification storage module, a cargo flow optimization module, a resource allocation module, a fault analysis and maintenance module, a behavior monitoring module, an energy management module, and a cost control module;

[0064] The dynamic priority adjustment module uses the support vector machine algorithm based on the cargo feature information to analyze the relationship between cargo features and warehouse operation efficiency. It uses the decision tree method to logically summarize the analysis results, adjust the cargo scheduling priority according to the cargo attributes and warehouse status, and generate the scheduling priority index.

[0065] The adaptive classification storage module uses a convolutional neural network algorithm based on the dispatch priority index to identify the type and characteristics of goods, and applies a genetic algorithm to analyze the volume, weight and dispatch priority index of goods, optimize the storage location of goods, and generate a storage optimization plan;

[0066] The cargo flow optimization module is based on the storage optimization plan and adopts the linear programming algorithm to formulate cargo storage and outbound routes. It uses the network flow analysis algorithm to analyze cargo types, storage locations and destinations, optimize the process of cargo movement within the warehouse, and generate process optimization strategies.

[0067] The resource allocation module is based on process optimization strategies and adopts an autoregressive integral moving average model to analyze historical warehouse data, estimate the inflow and outflow trends of goods, and use recurrent neural networks to analyze seasonal changes and random fluctuations in cargo demand, adjust the allocation of manpower and warehouse resources, and generate a resource allocation plan;

[0068] The fault analysis and maintenance module is based on the resource allocation plan and uses a long short-term memory network to analyze the operating data of storage equipment, including temperature, humidity, and vibration, identify the correlation and fault signs in the data, plan the maintenance and repair schedule of the equipment, reduce the risk of unexpected downtime, optimize the maintenance cycle and equipment reliability, and generate maintenance warning information;

[0069] The behavior monitoring module uses computer vision technology and behavior recognition algorithms based on maintenance warning information to identify the behavior patterns of operators, including handling postures and the use of safety equipment. It analyzes behavior data through anomaly detection algorithms, identifies safety hazards, provides safety warnings to management, and generates safety monitoring information.

[0070] The energy management module uses energy consumption pattern analysis algorithms based on security monitoring information to analyze warehouse energy usage data and energy-saving improvement points, including power consumption, lighting and temperature control equipment, apply dynamic energy adjustment strategies, adjust energy distribution and use, and generate energy-saving adjustment strategies;

[0071] The cost control module is based on energy-saving adjustment strategies, and adopts cost-benefit analysis methods and dynamic cost optimization algorithms to analyze the cost benefits of multiple warehousing activities, including labor costs, energy costs, equipment depreciation, and small and medium-sized warehouse site information. Through detailed management and intelligent adjustment, it generates cost optimization plans.

[0072] Scheduling priority indicators include cargo emergency response level, destination distance weight, and access frequency score. Storage optimization plans include cargo classification labels, recommended storage areas, and cargo access path optimization plans. Process optimization strategies include cargo handling paths, cargo picking serialization plans, and cargo in and out of storage timing scheduling information. Resource allocation plans include human resource dynamic allocation information, warehouse space utilization forecasts, and automated equipment scheduling plans. Maintenance warning information includes equipment failure probability assessment, expected maintenance time points, and pre-maintenance operation plans. Safety monitoring information includes unsafe behavior detection records, potential safety risk areas, and proposals for improved safety measures. Energy-saving adjustment strategies include energy consumption optimization areas, energy-saving operation plans, and expected energy-saving effect evaluations. Cost optimization results include cost savings area analysis results, operating cost reduction strategies, and long-term cost-benefit forecast information.

[0073] In the dynamic priority adjustment module, the support vector machine algorithm is used to process cargo feature information, including volume, weight, type, etc., combined with the current operating status of the warehouse, including storage capacity and cargo flow rate. The support vector machine algorithm constructs a multi-dimensional space, where each dimension represents a cargo feature, and uses hyperplanes to classify multiple categories of cargo to optimize the decision-making process of cargo scheduling priority. The decision tree method is used to logically summarize the results of the support vector machine algorithm, and the cargo scheduling decision path is represented by a tree structure. Each node represents a decision point, including whether emergency scheduling is required and how to determine the scheduling priority. The cargo scheduling priority is dynamically adjusted according to changes in cargo attributes and warehouse status, and scheduling priority indicators are generated, including cargo emergency response level, destination distance weight, and access frequency score. The scheduling order of cargo is optimized to ensure the optimization of warehouse operation efficiency and response speed.

[0074] In the adaptive classification storage module, the convolutional neural network algorithm is used to identify the type and characteristics of goods, and the genetic algorithm is combined to optimize the storage location of goods. The convolutional neural network uses its multi-level structure to extract and classify the features of the goods image, identify the type of goods, extract the features of the goods image through the convolution layer, reduce the feature dimension through the pooling layer, and classify the goods type using the fully connected layer. The network automatically adjusts the weights through the feedforward and backpropagation algorithms to improve the accuracy of classification. The genetic algorithm is used to simulate the search process of natural selection and genetic mechanisms through the cargo volume, weight and scheduling priority indicators to capture the optimal cargo storage plan. The genetic algorithm encodes the cargo storage location plan and uses selection, crossover and mutation operations to iteratively generate a better solution, generate a storage optimization plan, improve the utilization efficiency of warehouse space, and allocate the optimal access path.

[0075] In the cargo flow optimization module, the storage and outbound paths of cargo in the warehouse are formulated and optimized through the joint action of the linear programming algorithm and the network flow analysis algorithm. The linear programming algorithm first defines the objective function and constraints of cargo storage and outbound. The objective function aims to minimize the transportation distance and time of cargo. The constraints include the feasibility of the cargo storage location and the transportation path. The optimal solution is captured through mathematical modeling of the objective function and constraints to ensure the efficiency of the cargo flow. The network flow analysis algorithm is used to analyze the relationship between cargo type, storage location and destination. The cargo flow path is optimized by constructing a network model of cargo flow. By evaluating the efficiency of various cargo flow plans, a process optimization strategy is selected to reduce transportation time and improve warehouse operation efficiency, so as to achieve efficient management of cargo movement within the warehouse, generate a process optimization strategy, improve the efficiency of cargo handling, and enhance the overall operational efficiency of the warehouse.

[0076] In the resource allocation module, the autoregressive integral moving average model and the recurrent neural network algorithm are used to estimate the inflow and outflow trends of goods and adjust resource allocation. The autoregressive integral moving average model analyzes historical warehousing data, identifies the time series characteristics of goods flow, and predicts the inflow and outflow trends of goods in the future. By analyzing the trends and seasonal factors in historical data, accurate predictions of future goods flows are provided. The recurrent neural network algorithm analyzes the seasonal changes and random fluctuations in goods demand, processes sequence data, and predicts future changes by memorizing previous information. It analyzes the long-term dependence of time series data, predicts the flow trend of goods, adjusts the allocation of manpower and warehousing resources, and generates a resource allocation plan. It generates a resource allocation plan, flexibly responds to changes in goods flow, optimizes the utilization of human resources and storage space, and improves the efficiency and flexibility of warehouse operations.

[0077] In the fault analysis and maintenance module, a long short-term memory network is used to analyze the operating data of storage equipment, including temperature, humidity, and vibration, identify signs of faults and plan maintenance schedules. Through the long short-term memory network, the long-term dependencies in the data are learned. By analyzing the equipment operation data, abnormal patterns in the data and potential failures of the equipment are identified, the possibility of equipment failure is predicted, maintenance and repairs are planned in a timely manner, the risk of unexpected downtime is reduced, the maintenance cycle is optimized and the reliability of equipment is improved. Maintenance warning information is generated to reduce the risk of unexpected downtime, optimize the maintenance cycle, improve equipment reliability, and ensure the continuity and efficiency of warehouse operations.

[0078] In the behavior monitoring module, computer vision technology and behavior recognition algorithms work together to identify the behavior patterns of operators and provide safety warnings. Computer vision technology analyzes image data in monitoring videos to identify operators' handling postures and use of safety equipment. Behavior recognition algorithms analyze image data to identify behavior patterns that pose safety risks. Anomaly detection algorithms are used to analyze behavior data to identify anomalies that deviate from normal behavior patterns, identify potential safety hazards, provide management with targeted safety warning information, generate safety monitoring information, provide management with safety warning information, improve operational safety, reduce the incidence of accidents, and ensure the safety and health of warehouse operators.

[0079] In the energy management module, the energy consumption pattern analysis algorithm is used to analyze the warehouse energy usage data, including electricity consumption, lighting and temperature control equipment usage, and apply dynamic energy adjustment strategies to optimize energy distribution and usage. By collecting and analyzing energy consumption data, inefficient areas and energy-saving improvement points in energy usage are identified, and energy usage strategies are dynamically adjusted, including adjusting the operating hours of lighting and temperature control equipment, generating energy-saving adjustment strategies, optimizing energy usage patterns, reducing energy consumption, improving energy usage efficiency, and reducing warehouse operating costs.

[0080] In the cost control module, the cost-benefit analysis method and dynamic cost optimization algorithm are used to analyze the cost-effectiveness of multiple warehousing activities and formulate cost optimization plans. By analyzing multiple cost factors such as labor costs, energy costs and equipment depreciation, potential areas for cost savings are identified. The cost-benefit analysis method is used to evaluate the economic benefits of differentiated warehousing operation plans. The dynamic cost optimization algorithm is used to simulate and optimize operation plans to capture the lowest-cost warehousing management strategy. Through detailed management and intelligent adjustment, operating costs are reduced to ensure the quality of warehousing services. Cost optimization plans are generated to reduce operating costs and improve the economic benefits of warehouse operations by identifying areas for cost savings. The long-term cost-benefit balance is emphasized to ensure the economic benefits and sustainability of warehouse operations.

[0081] See also Figure 2 and Figure 3 ,The dynamic priority adjustment module includes a feature weight submodule, an algorithm application submodule, and a priority calculation submodule;

[0082] The feature weight submodule uses the principal component analysis algorithm based on the cargo feature information to analyze the basic features of the cargo, including volume, weight, and access frequency, assign weights to the basic features, identify the priority of multiple cargo features, and generate feature weight information;

[0083] The algorithm application submodule uses the support vector machine algorithm based on feature weight information to analyze the relationship between cargo characteristics and warehouse operation efficiency, determine cargo scheduling priorities, optimize warehouse resource allocation and operation efficiency, and generate a priority association model;

[0084] The priority calculation submodule is based on the priority association model and uses the decision tree algorithm to analyze the priority of target goods through the weight of goods characteristics and the current status of the warehouse, improve the efficiency of goods scheduling, reduce warehouse resource consumption, and generate scheduling priority indicators.

[0085] In the feature weight submodule, the principal component analysis algorithm is used to process cargo feature information, including volume, weight, and access frequency. Statistical methods are used to assign weights to multiple basic features, establish the priorities of multiple cargo features, and identify key factors affecting cargo scheduling priorities. The generated feature weight information provides an accurate basis for priority calculation. Feature weight information quantifies the degree of influence of multiple features on cargo scheduling priorities, providing data support for optimizing warehouse resource allocation and operational efficiency.

[0086] In the algorithm application submodule, the support vector machine algorithm is used to perform refinement operations based on feature weight information, classify goods, analyze the relationship between goods characteristics and warehouse operation efficiency, use feature weight information to accurately determine the priority of various goods, determine the cargo scheduling priority, generate a priority association model, analyze the intrinsic relationship between goods characteristics and warehouse operation efficiency, optimize the allocation of warehouse resources, and improve operational efficiency.

[0087] In the priority calculation submodule, through the decision tree algorithm, based on the priority association model, with the cargo feature weights and the current state of the warehouse as input, the decision tree model is constructed to divide the data set layer by layer to achieve the optimal data segmentation, select the features that can best improve the warehouse operation efficiency for segmentation, build a decision tree, show the impact of various cargo features on scheduling priority, generate scheduling priority indicators, optimize cargo scheduling work, improve cargo scheduling efficiency, reduce warehouse resource consumption, and provide a powerful tool for realizing the intelligent and automated warehouse management, ensuring the optimization of the warehouse management system in terms of resource utilization and operational efficiency.

[0088] See also Figure 2 and Figure 4 ,The adaptive classification storage module includes an image analysis submodule, a type recognition submodule, and a location decision submodule;

[0089] The image analysis submodule uses image preprocessing technology to optimize the image quality of goods based on the scheduling priority index, applies edge detection algorithm, extracts key visual features of goods, and generates visual feature data;

[0090] The type recognition submodule uses a convolutional neural network model based on visual feature data to analyze the visual features of cargo images, including shape, color, and size, classify cargo into multiple categories, optimize the efficiency and accuracy of cargo classification, and generate cargo classification information;

[0091] The location decision submodule is based on cargo classification information and adopts genetic algorithm to analyze the convenience and safety of cargo access through cargo key characteristics and warehouse layout information, match cargo storage locations, optimize the allocation and utilization of warehouse space resources, and generate storage optimization solutions.

[0092] In the image analysis submodule, the quality of cargo images is optimized and key visual features are extracted through image preprocessing technology and edge detection algorithm. Image preprocessing technology, including grayscale conversion, noise removal, and contrast enhancement steps, is used to improve the analyzability of images and lay a good foundation for feature extraction. Edge detection algorithm is applied to accurately identify and extract the contour and edge visual features of cargo, generate visual feature data, optimize image quality, capture key morphological features of cargo, provide accurate input data for subsequent type recognition, and improve the accuracy and efficiency of subsequent processing.

[0093] In the type recognition submodule, the convolutional neural network model is used to classify goods based on visual feature data. The deep learning framework is used to build a convolutional neural network, and the processed visual feature data is input. The network automatically extracts deep features of the image, including shape, color, and size, through multiple layers of convolutional layers, pooling layers, and fully connected layers, and classifies the features in the output layer. The back-propagation algorithm is used to cyclically optimize the network weights to improve the accuracy of classification, generate accurate cargo classification information, improve the efficiency and accuracy of cargo classification, and provide reliable data support for warehouse management and cargo scheduling.

[0094] In the location decision submodule, the genetic algorithm is used to optimize the storage location of goods. Based on the cargo classification information and warehouse layout information, an optimization model with the convenience and safety of cargo access as the objective function is designed. The genetic algorithm searches for the optimal solution in the solution space by simulating natural selection and genetic mechanisms. Through the iterative process, the decision plan for the storage location of goods is optimized, the storage location configuration that makes the objective function reach the optimal value is matched, and the storage optimization plan is generated to improve the utilization rate of warehouse space resources, ensure the efficiency and safety of cargo access, and enhance the intelligence and automation level of warehouse management.

[0095] See also Figure 2 and Figure 5 ,The cargo flow optimization module includes the path planning submodule, the picking strategy submodule, and the timing management submodule;

[0096] The path planning submodule is based on the storage optimization solution and uses the Dijkstra algorithm to analyze the road grid and obstacles inside the warehouse, calculate the path between the cargo storage location and the exit in the warehouse, optimize the cargo transportation route, and generate the shortest path planning;

[0097] The picking strategy submodule is based on the shortest path planning and uses the queuing theory algorithm to analyze the waiting time and processing time of the goods picking process, refine the goods picking sequence and picking window, reduce the goods picking congestion, and generate the picking efficiency optimization strategy;

[0098] The timing management submodule is based on the picking efficiency optimization strategy and adopts the critical path method to perform timing management on the entire process of goods outbound, identify the key steps and time bottlenecks in the goods outbound process, optimize the operation sequence and time schedule, reduce the goods outbound time, and generate a process optimization strategy.

[0099] In the path planning submodule, the Dijkstra algorithm is used to conduct a detailed analysis of the road grid and obstacles inside the warehouse to ensure that the transportation route of goods from the storage location to the exit is the shortest. The road grid and obstacles inside the warehouse are converted into graph structure data. Each intersection and road segment becomes a node and edge in the graph. The weight of the edge represents the length of the road segment. The Dijkstra algorithm starts from the node of the cargo storage location and gradually spreads to other nodes, calculates the shortest path to multiple nodes, and captures the shortest path for cargo to leave the warehouse. The algorithm will continuously update the shortest path to multiple nodes and the predecessor node information to ensure that the final generated path is the shortest of all paths. The generated shortest path planning optimizes the cargo transportation route, reduces transportation costs and time, and provides accurate route guidance for subsequent operations.

[0100] In the picking strategy submodule, the waiting time and processing time of the goods picking process are refined through the queuing theory algorithm, the picking sequence and picking window are optimized, and the data obtained from the shortest path planning is used as input. Combined with the arrival rate and service rate of goods picking requests, a queuing system model is constructed. The queuing theory algorithm simulates differentiated picking scenarios, calculates the average waiting time and the average number of goods in the system under various conditions, adjusts the picking window and sequence, reduces the waiting time of goods in the picking process and system congestion, and improves the picking efficiency. The generated picking efficiency optimization strategy provides a specific picking operation plan for warehouse management, including the optimal picking time period and picking sequence, which effectively improves the operating efficiency of the entire warehouse.

[0101] In the timing management submodule, the critical path method is used to manage the timing of the entire process of goods outbound, optimize the operation sequence and time schedule, and based on the picking efficiency optimization strategy, the entire goods outbound process is decomposed into multiple interrelated activities and constructed into a network diagram, in which the node represents the start or end of the activity, and the edge represents the duration of the activity. The critical path method determines the shortest completion time of the entire process by identifying the critical path in the network diagram, identifies the key activities and time bottlenecks in the process, and plays a guiding role in the time management and optimization of goods outbound. By adjusting the time schedule of non-critical activities, the goods outbound time is reduced and the resource utilization rate is improved. The generated process optimization strategy file details the optimized operation sequence and time schedule, providing a scientific and reasonable time management plan for the warehouse outbound process.

[0102] See also Figure 2 and Figure 6 ,The resource allocation module includes a trend analysis submodule, a demand forecasting submodule, and a resource allocation submodule;

[0103] The trend analysis submodule is based on process optimization strategy and adopts autoregressive integral moving average model to analyze historical warehouse data, including the inflow and outflow records of goods and seasonal demand changes, identify the flow trend of goods, and generate trend analysis information;

[0104] The demand forecasting submodule uses long short-term memory networks based on trend analysis information to analyze and forecast cargo demand, including market dynamics, changes in consumer behavior, holidays and seasonal changes, optimize warehouse resource allocation, and generate demand forecast analysis;

[0105] The resource allocation submodule uses linear programming algorithms based on demand forecast analysis to optimize the allocation of human resources and storage space, match cargo demand with warehouse resource capacity, optimize storage and transportation costs, and generate a resource allocation plan.

[0106] In the trend analysis submodule, the autoregressive integrated moving average model is used to analyze historical warehouse data, including in-depth mining of the records of goods inflow and outflow and seasonal demand changes. The time series data is differentially processed, and the autoregressive and moving average parts are used to fit the stationary series to capture the trends and seasonal characteristics in the data. Through the diagnosis and model selection process, the model parameters are accurately determined to ensure the best fit, identify the long-term trends and cyclical fluctuations in the flow of goods, and the generated trend analysis information provides valuable insights for warehouse management, enabling early identification and response to fluctuations in goods demand.

[0107] In the demand forecasting submodule, long short-term memory network technology is used to refine the analysis and forecast of cargo demand based on trend analysis information, process and learn long-term dependencies in time series data, including predicting the impact of market dynamics, changes in consumer behavior, and holidays and seasonal changes on cargo demand. By inputting historical data sets, learning patterns and rules in the data, predicting future demand, and generating demand forecast analysis, it optimizes resource allocation, ensures the effective use of resources, reduces resource waste, and provides warehouse management with an accurate cargo demand forecast, thereby improving the overall operational efficiency of the warehouse.

[0108] In the resource allocation submodule, based on the results of demand forecast analysis, a linear programming algorithm is used to optimize the allocation of human resources and storage space. By defining the objective function and constraints of the resource allocation problem, the storage and transportation costs are minimized to meet the matching of cargo demand and warehouse resource capacity. The data input includes demand forecast results, warehouse capacity, human resource conditions and associated cost information. By setting the constraints of the linear programming model, including warehouse storage capacity restrictions, human resource availability restrictions and cargo processing time restrictions, the resource allocation plan that minimizes cost is captured. The generated resource allocation plan lists the allocation details of multiple resources, including the number of human resources to be allocated to each warehouse, storage space allocation and expected costs, thereby improving warehousing efficiency and optimizing warehouse operating costs.

[0109] See also Figure 2 and Figure 7 ,The fault analysis and maintenance module includes a data analysis submodule, a fault prediction submodule, and a maintenance planning submodule;

[0110] The data analysis submodule uses outlier processing and data normalization based on the resource allocation plan to analyze the operating data of storage equipment, including temperature, humidity, and vibration, identify equipment operating rules and abnormal traces, and generate a standardized equipment data set;

[0111] The fault prediction submodule is based on the normalized equipment data set, combined with the equipment historical operation data, and uses the long short-term memory network to analyze the relationship between multi-source data through the equipment historical operation data, identify fault signals and equipment fault points, and generate fault prediction information;

[0112] The maintenance planning submodule uses a priority queuing algorithm based on fault prediction information to analyze the severity and urgency of faults, formulate equipment maintenance and repair plans, including the sequence and schedule of warehouse equipment maintenance, optimize the overall maintenance process, reduce operational interruptions, and generate maintenance warning information.

[0113] In the data analysis submodule, the operation data of the storage equipment is analyzed through outlier processing and data normalization technology. Based on the operation data of the collected equipment, including temperature, humidity and vibration, the data format is time series data, recording the status of the equipment at multiple time points. The outlier processing technology is used to identify and eliminate outliers in the data to ensure the accuracy of the analysis. Through data normalization, the data is converted to a unified scale to facilitate subsequent analysis, identify the laws and abnormal traces of equipment operation, and generate a standardized equipment data set by analyzing the normal operating range and abnormal status of the equipment to show the operating status of the equipment, providing a reliable data basis for subsequent fault prediction and maintenance planning.

[0114] In the fault prediction submodule, the equipment historical operation data and the normalized equipment data set are combined, and the long short-term memory network is applied to perform fault prediction. By extracting features from the normalized equipment data set, the temperature, humidity, and vibration are converted into a format that the long short-term memory network can process. The long short-term memory network learns the long-term dependencies in the data through its unique gating mechanism, identifies potential fault signals and equipment failure points, and predicts the type and time of the fault by analyzing the relationship between the equipment's historical operation data and the current state, generating fault prediction information, identifying potential faults in advance, and implementing preventive maintenance measures to reduce equipment failure rates and improve the overall stability and efficiency of the warehousing system.

[0115] In the maintenance planning submodule, based on fault prediction information, a priority queuing algorithm is used to intelligently plan the maintenance tasks of the equipment. Based on the severity and urgency of the fault, all equipment to be maintained is prioritized to ensure that important and urgent maintenance tasks are executed first. The fault type, expected occurrence time and equipment importance factors in the fault prediction information are used as input, and the maintenance priority of each equipment is calculated through the algorithm. According to the priority information, an equipment maintenance and repair plan is formulated, including the maintenance sequence and schedule, to optimize the overall maintenance process, ensure the high reliability of key equipment, reduce the risk of operational interruptions, and improve the operational efficiency of the warehousing system. The generated maintenance warning information provides strong decision-making support for equipment managers.

[0116] See also Figure 2 and Figure 8 ,The behavior monitoring module includes a behavior analysis submodule, a safety assessment submodule, and a risk identification submodule;

[0117] The behavior analysis submodule uses a convolutional neural network to analyze monitoring video data based on maintenance warning information, identify operator behavior patterns, including handling postures and the use of safety equipment, and generate behavior feature information;

[0118] The safety assessment submodule uses the isolation forest algorithm based on behavioral feature information to analyze the behavioral features of operators, identify behaviors that lead to safety accidents, optimize risk identification, reduce safety hazards, and generate safety risk assessment information;

[0119] The risk identification submodule uses the risk matrix assessment method based on the security risk assessment information to analyze the environment and safety specifications of warehouse operations, identify the level of abnormal behavior, match preventive measures and response strategies, and generate security monitoring information.

[0120] In the behavior analysis submodule, the convolutional neural network is used to analyze the surveillance video data and identify the behavior patterns of the operators. By extracting frames from the surveillance video and taking images as input data, the convolutional neural network gradually extracts features from the image through its multi-layer structure, from simple edges and textures to complex objects and patterns, and identifies the key visual features of the operators' carrying postures and the use of safety equipment. By training the convolutional neural network model, multiple behavior patterns are identified, the behavioral characteristics of the operators are accurately analyzed, and behavioral characteristic information is generated. The accuracy and efficiency of behavior recognition are improved, providing real-time and dynamic analysis capabilities for safety monitoring. The generation of behavioral characteristic information is crucial to safety assessment and risk identification, and can identify safety hazards and improper behaviors, providing a basis for taking preventive measures.

[0121] In the safety assessment submodule, the isolation forest algorithm is used to analyze the behavioral characteristics of operators and identify behaviors that lead to safety accidents. The isolation forest algorithm is used to isolate observation points by constructing multiple isolated trees to process high-dimensional data and large-scale data sets. Abnormal points are more easily isolated due to the abnormality of their attributes. The algorithm inputs behavioral characteristic information and determines whether the behavior is abnormal by calculating the average path length of isolated sample points. It can effectively identify abnormal safety risk behaviors and generate safety risk assessment information, including the safety levels of multiple behaviors. It provides a scientific basis for formulating targeted preventive measures and improvement plans, improves the ability to prevent safety accidents, and helps to build a safer working environment.

[0122] In the risk identification submodule, the risk matrix assessment method is used, combined with the safety risk assessment information, to conduct an in-depth analysis of the warehouse operating environment and safety regulations. The risk matrix assessment method is used to classify and grade risks by assessing the possibility of incidents and the severity of the impact. The behavioral risks of operators are combined with the target conditions of the warehouse environment to identify the risk levels of various behaviors, identify high-risk, medium-risk or low-risk operating behaviors, and match corresponding preventive measures and response strategies. The generated safety monitoring information provides a multi-dimensional risk assessment result for warehouse management, guides the improvement of the working environment and the strengthening of safety education, reduces the incidence of safety accidents, strengthens the warehouse's safety management system, and ensures the safety of the operating environment and the health of operators.

[0123] See also Figure 2 and Fig. 9 ,The energy management module includes the consumption analysis submodule, the energy saving strategy submodule, and the effect evaluation submodule;

[0124] The consumption analysis submodule uses trend analysis technology based on security monitoring information to analyze warehouse energy usage data, including power consumption, lighting system efficiency, and energy consumption patterns of temperature control equipment, identify key factors of energy consumption, and generate energy consumption information;

[0125] The energy-saving strategy submodule uses a linear programming algorithm based on energy consumption information to identify energy-saving improvement points and formulate energy-saving measures, including adjusting the settings of lighting and temperature control systems, optimizing power usage plans, reducing energy consumption, and generating energy-saving measures plans;

[0126] The effect evaluation submodule is based on energy-saving measures planning. Through the effect evaluation model and energy efficiency comparative analysis, it analyzes the energy usage data affected by energy-saving measures, evaluates the actual effects of energy-saving measures, optimizes energy-saving effects, and generates energy-saving adjustment strategies.

[0127] In the consumption analysis submodule, the warehouse energy usage data is analyzed through trend analysis technology, including electricity consumption, lighting system efficiency and energy consumption patterns of temperature control equipment, and related data on energy usage is collected. The target data exists in the form of time series, and the energy consumption at multiple time points is recorded. Moving average and exponential smoothing methods are applied to smooth the energy consumption data to reduce the interference of accidental fluctuations, analyze the long-term trend and seasonal pattern of energy consumption, identify the key factors affecting energy consumption, including improper settings of lighting and temperature control systems or outdated equipment, and record the key factors and trends of energy consumption, which provides a clear energy usage overview and improvement points for warehouse management, and provides a basis for the subsequent formulation of energy-saving strategies.

[0128] In the energy-saving strategy submodule, based on energy consumption information, a linear programming algorithm is used to identify energy-saving improvement points and formulate energy-saving measures. By converting the energy-saving goal into an optimization problem, the total energy consumption cost is minimized. The constraints include lighting intensity, indoor temperature standards and electricity usage restrictions. By analyzing energy consumption information, including the operating data of the lighting system and temperature control equipment, a linear programming algorithm is used to determine the optimal lighting brightness, temperature settings and electricity usage plan to reduce energy consumption, generate energy-saving measures plans, and formulate adjustment plans, including adjusting the brightness of lighting during working hours, optimizing temperature control settings and improving electricity usage plans, to reduce energy consumption and maintain high efficiency of warehouse operations.

[0129] In the effect evaluation submodule, based on the energy-saving measures planning, energy efficiency comparative analysis is carried out through the effect evaluation model. The actual effect of the energy-saving measures is evaluated by using the historical energy usage data and the energy usage data after the implementation of the energy-saving measures. The energy usage data before and after the implementation of the energy-saving measures are collected. The control group test or regression analysis technology is applied to analyze the changes in energy consumption before and after the energy-saving measures, quantify the energy-saving effect, evaluate the effectiveness of the energy-saving measures, identify the reasons why the energy-saving effect is not obvious, provide a basis for the subsequent adjustment of the energy-saving strategy, generate energy-saving adjustment strategies, analyze the effect evaluation results of the energy-saving measures, including energy-saving rate, cost savings and improvement plans, and provide the warehouse management with proof of the benefits of implementing energy-saving measures and subsequent optimization directions.

[0130] See also Figure 2 and Fig.10 ,The cost control module includes a cost analysis submodule, a saving strategy submodule, and a benefit prediction submodule;

[0131] The cost analysis submodule uses cost-benefit analysis methods based on energy-saving adjustment strategies to analyze the costs and economic benefits of various warehousing activities, identify key areas for cost optimization, including labor cost analysis, energy use assessment, and equipment depreciation calculation, and generate comprehensive cost-benefit analysis results;

[0132] The saving strategy submodule uses linear programming, integer programming and random optimization techniques based on the comprehensive cost-benefit analysis results to generate a saving strategy optimization plan through detailed management and intelligent adjustment, including optimizing human resource allocation, reducing energy consumption and extending equipment service life;

[0133] The benefit forecasting submodule is based on the optimization plan of the saving strategy and adopts time series analysis technology. By building a prediction model and using historical data and market dynamics, it estimates the economic benefits after the implementation of the strategy and generates a cost control optimization plan.

[0134] In the cost analysis submodule, based on labor cost, energy consumption and equipment depreciation data, the cost-benefit analysis method is used to conduct a comprehensive evaluation of the data, identify the optimization area of ​​cost control, evaluate the relationship between the input of multiple costs and the economic benefits generated by the corresponding activities, establish the strategic basis for cost optimization, and identify the key areas of cost optimization through quantitative analysis, including the efficient use of human resources, ways to reduce energy consumption, and strategies to extend the service life of equipment. The corresponding relationship between labor cost and work efficiency, the corresponding relationship between energy use and energy-saving potential, and the balance point between equipment depreciation and renewal cycle are analyzed to generate comprehensive cost-benefit analysis results, clearly point out the potential for cost savings and optimization direction, identify key areas for cost savings, and provide accurate decision-making support for the subsequent formulation of cost-saving strategies.

[0135] In the saving strategy submodule, based on the comprehensive cost-benefit analysis results, linear programming, integer programming and stochastic optimization techniques are used to develop a saving strategy optimization plan. The cost saving goal is converted into an optimization problem, including an objective function and a series of constraints. The objective function aims to maximize cost savings or minimize total costs, while the constraints ensure the rationality of resource allocation and the feasibility of operations. Linear programming is used to solve continuous resource allocation problems, and integer programming is used to deal with discrete decision-making problems, including staffing, labor costs and work efficiency. Stochastic optimization technology is used to cope with the uncertainty of demand and supply, accurately adjust human resource allocation, reduce energy consumption, extend equipment life, ensure warehouse operation efficiency, maximize cost savings, generate a saving strategy optimization plan, provide specific cost control measures and operating guidelines for warehouse management, and optimize the cost structure.

[0136] In the benefit forecasting submodule, based on the optimization plan of the saving strategy, the time series analysis technology is used to build a forecasting model. The historical data and market dynamics are used to estimate the economic benefits after the implementation of the strategy, including cost savings and return on investment. The historical cost data and related market dynamic information are collected and formatted as a time series. The autoregressive moving average model and the seasonally adjusted autoregressive integral moving average model are used to perform trend and seasonal analysis on the data, predict future cost changes and savings benefits, quantify the long-term benefits of the saving strategy, provide decision makers with an economic rationality assessment of the implementation strategy, generate a cost control optimization plan, and guide warehouse management to make more scientific and forward-looking decisions in cost control.

[0137] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A smart warehouse cargo dispatching device, characterized in that: The device includes a dynamic priority adjustment module, an adaptive classification storage module, a cargo flow optimization module, a resource allocation module, a fault analysis and maintenance module, a behavior monitoring module, an energy management module, and a cost control module; The dynamic priority adjustment module uses a support vector machine algorithm based on cargo feature information to analyze the relationship between cargo features and warehouse operation efficiency, uses a decision tree method to logically summarize the analysis results, adjusts cargo scheduling priorities based on cargo attributes and warehouse status, and generates scheduling priority indicators; The adaptive classification storage module uses a convolutional neural network algorithm based on the dispatch priority index to identify the type and characteristics of goods, applies a genetic algorithm to analyze the volume, weight and dispatch priority index of goods, optimizes the storage location of goods, and generates a storage optimization plan; The cargo flow optimization module is based on the storage optimization plan, adopts a linear programming algorithm to formulate cargo storage and outbound paths, uses a network flow analysis algorithm to analyze cargo types, storage locations and destinations, optimizes the process of cargo movement within the warehouse, and generates a process optimization strategy; The resource allocation module is based on process optimization strategy, adopts autoregressive integral moving average model, analyzes historical warehouse data, estimates the inflow and outflow trend of goods, uses recurrent neural network to analyze seasonal changes and random fluctuations in goods demand, adjusts human and warehouse resource allocation, and generates resource allocation plan; The fault analysis and maintenance module is based on the resource allocation plan and uses a long short-term memory network to analyze the operating data of the storage equipment, including temperature, humidity, and vibration, identify the correlation and fault signs in the data, plan the maintenance and repair schedule of the equipment, reduce the risk of unexpected downtime, optimize the maintenance cycle and equipment reliability, and generate maintenance warning information; The behavior monitoring module uses computer vision technology and behavior recognition algorithms based on maintenance warning information to identify operator behavior patterns, including handling postures and the use of safety equipment. It analyzes behavior data through anomaly detection algorithms to identify safety hazards, provide safety warnings to management, and generate safety monitoring information. The energy management module uses energy consumption pattern analysis algorithms based on security monitoring information to analyze warehouse energy usage data and energy-saving improvement points, including power consumption, lighting and temperature control equipment, apply dynamic energy adjustment strategies, adjust energy distribution and use, and generate energy-saving adjustment strategies; The cost control module is based on energy-saving adjustment strategies, adopts cost-benefit analysis methods and dynamic cost optimization algorithms, analyzes the cost benefits of multiple warehousing activities, including labor costs, energy costs, equipment depreciation and small and medium-sized warehouse site information, and generates cost optimization plans through detailed management and intelligent adjustment.

2. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The scheduling priority indicators include the cargo emergency response level, destination distance weight, and access frequency score; the storage optimization plan includes cargo classification labels, recommended storage areas, and cargo access path optimization plan; the process optimization strategy includes cargo handling paths, cargo picking serialization plan, and cargo in and out of storage timing scheduling information; the resource allocation plan includes human resource dynamic allocation information, warehouse space utilization forecast, and automated equipment scheduling plan; the maintenance warning information includes equipment failure probability assessment, expected maintenance time point, and pre-maintenance operation plan; the safety monitoring information includes unsafe behavior detection records, potential safety risk areas, and proposals for improved safety measures; the energy-saving adjustment strategy includes energy consumption optimization area, energy-saving operation plan, and expected energy-saving effect evaluation; the cost optimization results include cost savings area analysis results, operating cost reduction strategies, and long-term cost-effectiveness forecast information.

3. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The dynamic priority adjustment module includes a feature weight submodule, an algorithm application submodule, and a priority calculation submodule; The feature weight submodule uses a principal component analysis algorithm based on the cargo feature information to analyze the basic features of the cargo, including volume, weight, and access frequency, assign weights to the basic features, identify the priorities of multiple cargo features, and generate feature weight information; The algorithm application submodule uses a support vector machine algorithm based on feature weight information to analyze the relationship between cargo features and warehouse operating efficiency, determine cargo scheduling priorities, optimize warehouse resource allocation and operating efficiency, and generate a priority association model; The priority calculation submodule uses a decision tree algorithm based on a priority association model to analyze the priority of target goods through the weight of goods characteristics and the current state of the warehouse, improve the efficiency of goods scheduling, reduce warehouse resource consumption, and generate a scheduling priority index.

4. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The adaptive classification storage module includes an image analysis submodule, a type recognition submodule, and a position decision submodule; The image analysis submodule uses image preprocessing technology to optimize the image quality of goods based on the scheduling priority index, applies edge detection algorithm, extracts key visual features of goods, and generates visual feature data; The type recognition submodule uses a convolutional neural network model based on visual feature data to analyze the visual features of cargo images, including shape, color, and size, classify the cargo into multiple categories, optimize the efficiency and accuracy of cargo classification, and generate cargo classification information; The location decision submodule is based on cargo classification information and adopts genetic algorithm to analyze the convenience and safety of cargo access through cargo key features and warehouse layout information, matches cargo storage locations, optimizes the allocation and utilization of warehouse space resources, and generates a storage optimization plan.

5. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The cargo flow optimization module includes a path planning submodule, a picking strategy submodule, and a timing management submodule; The path planning submodule uses the Dijkstra algorithm based on the storage optimization solution to analyze the road grid and obstacles inside the warehouse, calculate the path between the cargo storage location in the warehouse and the exit, optimize the cargo transportation route, and generate the shortest path planning; The picking strategy submodule is based on the shortest path planning and uses the queuing theory algorithm to analyze the waiting time and processing time of the goods picking process, refine the goods picking sequence and picking window, reduce the goods picking congestion, and generate a picking efficiency optimization strategy; The timing management submodule is based on the picking efficiency optimization strategy and adopts the critical path method to perform timing management on the entire process of goods out of the warehouse, identify the key steps and time bottlenecks of the goods out of the warehouse process, optimize the operation sequence and time arrangement, reduce the goods out of the warehouse time, and generate a process optimization strategy.

6. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The resource allocation module includes a trend analysis submodule, a demand forecasting submodule, and a resource allocation submodule; The trend analysis submodule is based on the process optimization strategy and adopts the autoregressive integral moving average model to analyze the historical warehouse data, including the inflow and outflow records of goods and seasonal demand changes, identify the flow trend of goods, and generate trend analysis information; The demand forecasting submodule uses a long short-term memory network based on trend analysis information to analyze and forecast cargo demand, including market dynamics, changes in consumer behavior, holidays and seasonal changes, optimize warehouse resource allocation, and generate demand forecast analysis; The resource allocation submodule uses a linear programming algorithm based on demand forecast analysis to optimize the allocation of human resources and storage space, match cargo demand with warehouse resource capacity, optimize storage and transportation costs, and generate a resource allocation plan.

7. The intelligent warehouse cargo dispatching device according to claim 1 is characterized in that: The fault analysis and maintenance module includes a data analysis submodule, a fault prediction submodule, and a maintenance planning submodule; The data analysis submodule analyzes the operation data of storage equipment, including temperature, humidity, and vibration, based on the resource allocation plan, using outlier processing and data normalization, identifies equipment operation rules and abnormal traces, and generates a standardized equipment data set; The fault prediction submodule is based on the normalized equipment data set, combined with the equipment historical operation data, and uses the long short-term memory network to analyze the relationship between multi-source data through the equipment historical operation data, identify fault signals and equipment fault points, and generate fault prediction information; The maintenance planning submodule uses a priority queuing algorithm based on fault prediction information to analyze fault severity and urgency, develop equipment maintenance and repair plans, including the sequence and schedule of warehouse equipment maintenance, optimize the overall maintenance process, reduce operational interruptions, and generate maintenance warning information.

8. The intelligent warehouse cargo dispatching device according to claim 1 is characterized by: The behavior monitoring module includes a behavior analysis submodule, a safety assessment submodule, and a risk identification submodule; The behavior analysis submodule uses a convolutional neural network to analyze monitoring video data based on maintenance warning information, identify operator behavior patterns, including handling postures and use of safety equipment, and generate behavior feature information; The safety assessment submodule uses an isolation forest algorithm based on behavioral feature information to analyze the behavioral features of operators, identify behaviors that lead to safety accidents, optimize risk identification, reduce safety hazards, and generate safety risk assessment information; The risk identification submodule uses the risk matrix assessment method based on the security risk assessment information to analyze the environment and safety specifications of warehouse operations, identify abnormal behavior levels, match preventive measures and response strategies, and generate security monitoring information.

9. The intelligent warehouse cargo dispatching device according to claim 1, characterized in that: The energy management module includes a consumption analysis submodule, an energy-saving strategy submodule, and an effect evaluation submodule; The consumption analysis submodule uses trend analysis technology based on security monitoring information to analyze warehouse energy usage data, including power consumption, lighting system usage efficiency, and energy consumption patterns of temperature control equipment, identify key factors of energy consumption, and generate energy consumption information; The energy-saving strategy submodule uses a linear programming algorithm based on energy consumption information to identify energy-saving improvement points and formulate energy-saving measures, including adjusting the settings of lighting and temperature control systems, optimizing power usage plans, reducing energy consumption, and generating energy-saving measures plans; The effect evaluation submodule is based on energy-saving measure planning, and through the effect evaluation model, uses energy efficiency comparison analysis to analyze the energy usage data affected by energy-saving measures, evaluate the actual effects of energy-saving measures, optimize energy-saving effects, and generate energy-saving adjustment strategies.

10. The intelligent warehouse cargo dispatching device according to claim 1, characterized in that: The cost control module includes a cost analysis submodule, a savings strategy submodule, and a benefit prediction submodule; The cost analysis submodule adopts cost-benefit analysis method based on energy-saving adjustment strategy to analyze the cost and economic benefits of various warehousing activities, identify key areas of cost optimization, including labor cost analysis, energy use evaluation and equipment depreciation calculation, and generate comprehensive cost-benefit analysis results; The saving strategy submodule generates a saving strategy optimization plan based on the comprehensive cost-benefit analysis results, using linear programming, integer programming and random optimization techniques, through detailed management and intelligent adjustment, including optimizing human resource allocation, reducing energy consumption and extending equipment service life; The benefit prediction submodule is based on the saving strategy optimization plan, adopts time series analysis technology, builds a prediction model, uses historical data and market dynamics, estimates the economic benefits after the strategy is implemented, and generates a cost control optimization plan.

Images