An efficient intelligent warehousing and transportation system and method

Abstract

The present invention provides an efficient intelligent warehousing and transportation system and method. The system includes an Internet of Things module, a data transmission module, a preliminary navigation module, a navigation optimization module, an integrated processing module, an intelligent allocation module, and an energy efficiency monitoring and optimization module. The Internet of Things module is deployed in a gridding and two-dimensional coordinate system manner to ensure that each area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of the goods. The preliminary processing performed by the data transmission module ensures the quality of the data and provides high-quality input for subsequent data processing and analysis. The automated deployment and data processing flow greatly reduces the errors caused by human operation and improves the reliability of the system. The technical problems of poor accuracy, slow response speed and low efficiency of the existing warehousing and transportation system are solved, and the technical effect of realizing warehousing and transportation with high efficiency, high speed and high accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an efficient intelligent warehousing and transportation system and method. Background Art

[0002] Traditional warehousing and transportation systems usually include shelves, conveyor belts, forklifts, and manual operation systems, etc., relying on manual handling, fixed shelf layouts, and simple barcode systems. However, with the rapid development of e-commerce and retail industries, this traditional approach has gradually become inefficient, error-prone, and requires a lot of manpower. In the early stage of automation, some simple automated equipment such as automatic forklifts and conveyor belts were used, but human intervention was still required. Warehouse management systems and software solutions were used to track inventory, orders, and shipments. However, their degree of automation was limited. Early smart warehousing adopted some solutions based on sensors and preliminary AI technologies, but there may still be problems with equipment compatibility, system response speed, and limited data processing capabilities.

[0003] There are many research methods for intelligent warehousing and transportation. The "202310223596.0" "Intelligent Warehousing and Transportation Management Equipment and System" proposed by Li Yongchun et al. mainly includes: including a transport storage structure and a transport conduction structure. The transport storage structure is movably connected to the upper limit of the transport conduction structure. The transport storage structure can store goods and change its own height to adapt to the transport conduction structure for storage work. The transport conduction structure can transport goods and cooperate with the transport conduction structure to coordinate transport storage operations with the transport storage structure. The track inside the transport conduction structure can be adjusted. The transport storage structure includes a linkage lifting component and a load-bearing driven component. The upper end of the load-bearing driven component is movably connected to the linkage lifting component. The linkage lifting component is used for the storage of goods, and the load-bearing driven component carries the bottom of the linkage lifting component. Through the overall setting of the transport storage structure and the transport conduction structure, the transportation work of intelligent warehousing and transportation is realized.

[0004] However, in the process of implementing the technical solution of the invention in the above application embodiment, the inventors of the present application found that the above technology has at least the following technical problems: the existing warehousing and transportation system has poor accuracy, slow response speed and low efficiency. Summary of the invention

[0005] The embodiments of the present application provide an efficient intelligent warehousing and transportation system and method, thereby solving the technical problems of poor accuracy, slow response speed and low efficiency of existing warehousing and transportation systems, and achieving the technical effect of realizing warehousing and transportation with high efficiency, high speed and high accuracy.

[0006] This application provides an efficient intelligent warehousing and transportation system and method. Specifically, it includes the following technical solutions:

[0007] An efficient intelligent warehousing and transportation system includes the following parts:

[0008] Internet of Things module, data transmission module, preliminary navigation module, navigation optimization module, integrated processing module, intelligent allocation module, energy efficiency monitoring and optimization module;

[0009] The IoT module tracks the real-time location and status of the goods in the warehouse and immediately uploads these data for use by subsequent modules;

[0010] The data transmission module receives the commodity location and status information data from the IoT module, and transmits the data using optimization technology to provide commodity data for subsequent modules;

[0011] The preliminary navigation module provides preliminary path navigation for warehouse staff or robots based on the commodity data received from the data transmission module;

[0012] The navigation optimization module senses the navigation path given by the preliminary navigation module and the real-time obstacle information in the warehouse, monitors obstacles or other robots and personnel on the path in real time, and adjusts the path in real time to prevent collisions when necessary;

[0013] The integrated processing module integrates the commodity data from the data transmission module, the navigation path data from the preliminary navigation module, and the real-time working status data from the navigation optimization module, performs comprehensive processing and analysis, further optimizes inventory management, predicts inventory demand and transportation strategies, and provides strategic recommendations for warehousing and transportation;

[0014] The intelligent allocation module performs automatic and intelligent storage allocation of commodities according to the storage and transportation strategy suggestions from the integrated processing module;

[0015] The energy efficiency monitoring and optimization module uses energy management algorithms to collect and analyze energy consumption data of various activities in the warehouse from the Internet of Things module and the navigation optimization module in real time, and automatically adjusts the overall energy consumption in the warehouse according to the analysis results to optimize energy consumption.

[0016] An efficient intelligent warehousing and transportation method comprises the following steps:

[0017] S1. Deploy the IoT module to ensure that each area is within the monitoring range, initialize the IoT module to ensure that the module can accurately track and identify the real-time location and status of the goods, configure the data transmission module to ensure stable reception of data from the IoT module, and perform preliminary processing;

[0018] S2. Based on the real-time commodity data stream provided by the data transmission module, the optimal pickup path is calculated to obtain a preliminary navigation path. According to the preliminary navigation path and the real-time obstacle information of the warehouse, obstacle detection and path adjustment are performed to obtain an optimized safe navigation path;

[0019] S3. Based on the commodity data and the real-time working status data of the navigation optimization module, comprehensive processing and analysis are carried out to further optimize inventory management, predict inventory demand and transportation strategies, and provide strategic recommendations for warehousing and transportation for the next module;

[0020] S4. Collect the energy consumption data of various activities in the warehouse obtained by the Internet of Things module and the navigation optimization module, analyze the overall energy consumption of the warehouse, optimize the equipment, and obtain energy efficiency reports and energy consumption optimization plans.

[0021] Preferably, the step S2 further includes:

[0022] In order to obtain a preliminary navigation path, real-time data acquisition and warehouse space network construction are carried out, and based on the spatial fluctuation diffusion method of real-time data, all possible paths from the starting point to the target point are simulated to obtain a preliminary navigation path.

[0023] Preferably, the step S2 further includes:

[0024] In order to avoid dynamic obstacle problems, a dynamic space unit adjustment algorithm is introduced to dynamically detect obstacles in the space unit and dynamically adjust the fluctuation path; the initial navigation path is optimized;

[0025] Based on the above dynamic obstacle adjustment results, spatial path fusion technology is used to solve the fluctuating paths generated by multiple targets and obtain the optimized best navigation path.

[0026] Preferably, the step S4 further includes:

[0027] When analyzing energy consumption data, a dynamic energy efficiency flow clustering algorithm is used for data analysis.

[0028] Preferably, the step S4 further includes:

[0029] When performing data analysis, a sliding time window is used to perform statistics and feature extraction on local areas of the data stream; when performing data analysis, a dynamic threshold is set to find abnormal points or sudden energy consumption peaks in the energy consumption data and capture abnormal fluctuations.

[0030] Preferably, the step S4 further includes:

[0031] When performing data analysis, an optimized clustering algorithm is used.

[0032] Beneficial effects:

[0033] The multiple technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0034] 1. This application deploys the IoT module through gridding and a two-dimensional coordinate system to ensure that every area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of the goods. The preliminary processing performed by the data transmission module, such as outlier detection, unit conversion, and data denoising, ensures the quality of the data and provides high-quality input for subsequent data processing and analysis. The automated deployment and data processing process greatly reduces errors caused by human operations and improves the reliability of the system.

[0035] 2. This application utilizes the spatial fluctuation diffusion algorithm to efficiently simulate all possible paths from the starting point to the target point, greatly improving the efficiency of path planning. Due to the introduction of the dynamic spatial unit adjustment algorithm, even if there are dynamic obstacles in the warehouse (such as moving shelves or robots), the solution can adjust the navigation path in real time to ensure that the path is always optimal. By utilizing the spatial fluctuation diffusion method and spatial path fusion technology, it can not only effectively handle multi-target path problems, but also maintain the accuracy of the path in a variety of situations.

[0036] 3. This application adopts a dynamic energy efficiency flow clustering algorithm to ensure efficient processing and analysis of large amounts of real-time energy consumption data, reduce the burden on central processing, and better capture the local characteristics and abnormal fluctuations of energy consumption data. By using clustering algorithms and feature engineering, it can reveal the underlying structure and patterns of energy consumption data, identify energy consumption patterns associated with specific warehouse operations, and provide in-depth insights for energy efficiency analysis.

[0037] 4. The technical solution of the present application can effectively solve the technical problems of poor accuracy, slow response speed and low efficiency of the existing warehousing and transportation system. In addition, the above system or method has undergone a series of effect surveys. The deployment of the Internet of Things module in the form of gridding and a two-dimensional coordinate system can ensure that every area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of the goods. The preliminary processing performed by the data transmission module, such as outlier detection, unit conversion and data denoising, ensures the quality of the data and provides high-quality input for subsequent data processing and analysis. The automated deployment and data processing process greatly reduces the errors caused by human operations and improves the reliability of the system. The spatial fluctuation diffusion algorithm can efficiently simulate all the processes from the starting point to the target point. Possible paths greatly improve the efficiency of path planning. Due to the introduction of the dynamic spatial unit adjustment algorithm, even if there are dynamic obstacles in the warehouse (such as moving shelves or robots), the solution can adjust the navigation path in real time to ensure that the path is always optimal. By utilizing the spatial fluctuation diffusion method and spatial path fusion technology, it can not only effectively handle multi-target path problems, but also maintain the accuracy of the path in various situations; the dynamic energy efficiency flow clustering algorithm is adopted to ensure the efficient processing and analysis of a large amount of real-time energy consumption data, reduce the burden of central processing, and better capture the local characteristics and abnormal fluctuations of energy consumption data. The clustering algorithm and feature engineering can reveal the potential structure and pattern of energy consumption data, identify the energy consumption pattern related to specific warehouse operations, and provide in-depth insights for energy efficiency analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a module diagram of the efficient intelligent warehousing and transportation system described in this application;

[0039] Figure 2 The present invention is a flowchart of an efficient intelligent warehousing and transportation method for this application. DETAILED DESCRIPTION

[0040] The embodiments of the present application provide an efficient intelligent warehousing and transportation system and method to solve the technical problems of poor accuracy, slow response speed and low efficiency of the existing warehousing and transportation systems in the prior art. The overall idea is as follows:

[0041] It includes an Internet of Things module, a data transmission module, a preliminary navigation module, a navigation optimization module, an integrated processing module, an intelligent allocation module, and an energy efficiency monitoring and optimization module; the Internet of Things module is directly connected to the data transmission module to provide it with real-time commodity data; the data transmission module supplies stable commodity data to the preliminary navigation module and the integrated processing module; the path information of the preliminary navigation module is used by the navigation optimization module to avoid any collision; the navigation optimization module provides safe working environment information to the integrated processing module; the strategy recommendations of the integrated processing module are executed by the intelligent allocation module; finally, based on the energy consumption data of various activities in the warehouse of the Internet of Things module and the navigation module, the energy efficiency monitoring and optimization module is used for analysis to obtain the optimal energy consumption; the Internet of Things module is deployed in a gridded and two-dimensional coordinate system manner to ensure that every area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of the goods, the preliminary processing performed by the data transmission module, such as outlier detection, unit conversion and data denoising, The quality of the data is ensured, providing high-quality input for subsequent data processing and analysis. The automated deployment and data processing process greatly reduces errors caused by human operations and improves the reliability of the system. The spatial fluctuation diffusion algorithm can efficiently simulate all possible paths from the starting point to the target point, greatly improving the efficiency of path planning. Due to the introduction of the dynamic spatial unit adjustment algorithm, even if there are dynamic obstacles in the warehouse (such as moving shelves or robots), the solution can adjust the navigation path in real time to ensure that the path is always optimal. By using the spatial fluctuation diffusion method and spatial path fusion technology, it can not only effectively handle multi-target path problems, but also maintain the accuracy of the path in various situations. The dynamic energy efficiency flow clustering algorithm is adopted to ensure the efficient processing and analysis of a large amount of real-time energy consumption data, reduce the burden of central processing, and better capture the local characteristics and abnormal fluctuations of energy consumption data. The clustering algorithm and feature engineering can reveal the potential structure and pattern of energy consumption data, identify energy consumption patterns related to specific warehouse operations, and provide in-depth insights for energy efficiency analysis.

[0042] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0043] Refer to the attached Figure 1 , an efficient intelligent warehousing and transportation system described in this application includes the following parts:

[0044] Internet of Things module, data transmission module, preliminary navigation module, navigation optimization module, integrated processing module, intelligent allocation module, energy efficiency monitoring and optimization module;

[0045] The IoT module tracks the real-time location and status of the goods in the warehouse and immediately uploads these data for use by subsequent modules;

[0046] The data transmission module receives the commodity location and status information data from the IoT module, and uses optimization technology to efficiently transmit data, ensuring that signal interference and data delay are reduced, and providing stable, high-speed, and real-time commodity data for subsequent modules;

[0047] The preliminary navigation module provides preliminary path navigation for warehouse staff or robots based on the stable, high-speed, real-time commodity data received from the data transmission module;

[0048] The navigation optimization module senses the navigation path provided by the preliminary navigation module and other real-time obstacle information in the warehouse. This module monitors obstacles or other robots and personnel on the path in real time, and makes real-time adjustments to the path when necessary to prevent collisions.

[0049] The integrated processing module integrates the commodity data from the data transmission module, the navigation path data from the preliminary navigation module, and the real-time working status data from the navigation optimization module, performs comprehensive processing and analysis, further optimizes inventory management, predicts inventory demand and transportation strategies, and provides warehousing and transportation strategy recommendations for the next module;

[0050] The intelligent allocation module performs automatic and intelligent storage allocation of goods based on the storage and transportation strategy recommendations from the integrated processing module to ensure that the space is optimally used;

[0051] The energy efficiency monitoring and optimization module uses energy management algorithms to collect and analyze energy consumption data of various activities in the warehouse from the IoT module and the navigation module in real time, and automatically adjusts the lighting, robot speed, air conditioning, etc. in the warehouse to optimize energy consumption based on the analysis results;

[0052] The connection between modules

[0053] The IoT module directly communicates with the data transmission module to provide it with real-time commodity data;

[0054] The data transmission module supplies stable commodity data to the preliminary navigation module and the integrated processing module;

[0055] The path information from the preliminary navigation module is used by the navigation optimization module to avoid any collisions;

[0056] The navigation optimization module provides safe working environment information to the integrated processing module;

[0057] The strategy recommendations of the integrated processing module are implemented by the intelligent allocation module;

[0058] Finally, based on the energy consumption data of various activities in the warehouse from the IoT module and the navigation optimization module, the energy efficiency monitoring and optimization module is used to analyze the energy consumption to obtain the optimal energy consumption;

[0059] Refer to the attached Figure 2 , an efficient intelligent warehousing and transportation method described in this application comprises the following steps:

[0060] S1. Deploy the IoT module to ensure that each area is within the monitoring range, initialize the IoT module to ensure that the module can accurately track and identify the real-time location and status of the goods, configure the data transmission module to ensure stable reception of data from the IoT module, and perform preliminary processing;

[0061] First, equipment deployment is performed to determine the key locations in the warehouse. The warehouse is divided by a two-dimensional grid method. For each grid, its center point is used as the potential deployment of the IoT module. The warehouse is regarded as a coordinate plane P(x, y), where x is the width of the warehouse and y is the length of the warehouse. Through the above method, all possible key location points can be obtained:

[0062] P = {(x 1 ,y 1 ), (x 2 ,y 2 ),…,(x n ,y n )}

[0063] Using the total area of ​​the warehouse and the monitoring area of ​​a single IoT module, the number of modules required and their layout can be estimated;

[0064] According to the above location points, select a suitable location to place the IoT module, and use the nearest neighbor search algorithm to verify and ensure that each area A i All have at least one device covered:

[0065] A i ={(x,y)|distance((x,y),(x i ,y i ))≤r}

[0066] Among them, r is the effective monitoring radius of the IoT module;

[0067] Use the Euclidean distance formula to calculate the distance between each point and its nearest module, ensuring that this distance does not exceed the effective monitoring radius r of the module;

[0068] Furthermore, for data synchronization, a hash function is used to assign a unique identifier ID to each IoT module. i,When the module is activated, it starts to send its status and location information to the ,main server periodically;

[0069] The received data is formatted into a structured data format using the JSON encoding method. For example, each data entry can be represented as:

[0070] D i ={ID i ,Status,Position,Timestamp}

[0071] Among them, ID i It is the module identifier, Status indicates the status of the product (such as on the shelf, off the shelf, etc.), Position indicates the current location of the product, and Timestamp is the timestamp of the data entry;

[0072] Data structuring usually does not involve mathematical operations, but involves parsing, classifying, and storing raw data;

[0073] Furthermore, the data transmission module first establishes a stable network connection with all IoT modules, and can use the TCP / IP protocol and its three-way handshake mechanism to ensure the stability of the connection;

[0074] After receiving the data from each IoT module, the data transmission module will perform preliminary processing to ensure the quality of the data, which can be expressed by the following formula:

[0075] D′ i =f(D i )

[0076] Among them, D′ i is the processed data, f is a pair of input data D i A set of operations for cleaning and formatting. This function contains multiple sub-operations, such as outlier detection, unit conversion, and data denoising;

[0077] For each data entry D i , apply f, remove irrelevant or redundant information to optimize data storage and transmission, and obtain the output result D′={D′ 1 , D′ 2 , ..., D′ n}, where D′ is the processed stable, high-speed, real-time data stream of commodity location and status, providing the data basis for preliminary navigation;

[0078] This application deploys the IoT module through gridding and a two-dimensional coordinate system to ensure that every area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of goods. The preliminary processing performed by the data transmission module, such as outlier detection, unit conversion, and data denoising, ensures the quality of the data and provides high-quality input for subsequent data processing and analysis. The automated deployment and data processing process greatly reduces errors caused by human operations and improves the reliability of the system.

[0079] S2. Based on the real-time commodity data stream provided by the data transmission module, the optimal pickup path is calculated to obtain a preliminary navigation path. According to the preliminary navigation path and the real-time obstacle information of the warehouse, obstacle detection and path adjustment are performed to obtain an optimized safe navigation path;

[0080] In order to obtain the preliminary navigation path, real-time data acquisition and warehouse space network construction are carried out. First, the location and status information of the goods are obtained in real time based on the real-time commodity data stream provided by the data transmission module.

[0081] The entire warehouse is divided into cubic space units of equal size according to a certain size (such as 1m x 1m x 1m); finally, a status value is assigned to each space unit according to the location and status data of the goods, such as whether there are goods, whether there are obstacles, and the type of goods. The specific formula is as follows:

[0082] S={s ijk |1≤i,j,k≤n}

[0083] Among them, S represents the three-dimensional space of the entire warehouse, where each s ijk Represents the state of a space unit, indicating whether the space unit is occupied, whether there are obstacles, etc. Usually, s ijk It is 0 or 1, where 0 means no obstacle and 1 means there is an obstacle; n represents the number of spatial units;

[0084] Furthermore, based on the spatial fluctuation diffusion method of real-time data, all possible paths from the starting point to the target point are simulated to obtain a preliminary navigation path: according to the real-time commodity location, the fluctuation source is set, such as the location of the commodity that needs to be picked up; using the diffusion algorithm, the propagation of the fluctuation in the warehouse space is simulated, and the fluctuation will diffuse to the surrounding 8 adjacent space units, and the intensity will decrease with the distance; when the fluctuation reaches the target location or encounters an obstacle, the current path and fluctuation intensity are recorded. The specific implementation formula is as follows:

[0085]

[0086] w ijk (t+1)=α×w ijk(t)+(1-α)×avg_neighbour(w ijk (t))

[0087] Where W(t) is the total fluctuation intensity of the entire warehouse at time t; w ijk (t) is the space unit s at time t ijk The fluctuation intensity is measured by the sensor; w ijk (t+1) is the number of cells in the warehouse at s at time t+1. ijk The fluctuation intensity of the spatial unit of the position; avg_neighbour(w ijk (t)) represents the spatial unit w at time t. ijk (t) is the average value of the fluctuation intensity of all adjacent spatial units around it; α is an attenuation factor, which represents the decreasing degree of fluctuation, and its value is between 0 and 1, which is obtained by empirical method; finally, by artificially setting the threshold δ, the fluctuations with a total intensity greater than the threshold are screened out, and finally the preliminary navigation path is obtained, that is, the set P of some possible paths from the starting point to the target point.

[0088] However, because there are many dynamic obstacles in the warehouse, such as workers or robots, in order to avoid the dynamic obstacle problem, a dynamic space unit adjustment algorithm is introduced to dynamically detect obstacles in the space unit and dynamically adjust the fluctuation path; first, the state of each space unit is monitored in real time by sensors, and moving obstacles (such as other robots, moving shelves, etc.) are detected; when it is detected that the state of a space unit has changed, such as the goods are taken away, its fluctuation intensity is adjusted so that it cannot be passed by the fluctuation, and finally the path is recalculated according to the adjusted fluctuation intensity; the specific formula is as follows:

[0089] w′ ijk (t) = w ijk (t)×(1-β×obstacle ijk )

[0090] Among them, w′ ijk (t) is the spatial unit s at time t after considering obstacles. ijk Adjusted volatility intensity; obstacle ijk is a function, when the space unit s ijk When there is an obstacle or the product is taken away, it returns 1, otherwise it returns 0; β is a blocking factor, which is used to adjust the impact of obstacles or changes in product status on the fluctuation intensity, and is obtained based on empirical methods; the dynamically adjusted fluctuation intensity is applied to the spatial fluctuation diffusion method to obtain the updated partial possible path set P′;

[0091] Based on the dynamic obstacle adjustment results, the spatial path fusion technology is used to solve the fluctuating paths generated by multiple targets and obtain an optimized optimal navigation path. First, for tasks with multiple target locations, the spatial fluctuation diffusion method is performed separately. Then, the paths from different starting points to their respective target points are fused to ensure that all target points can be effectively accessed. Finally, the path length and fluctuation intensity are used as weights to optimize the fused path. The specific formula is as follows:

[0092]

[0093] Among them, length(p) is the length of path p, λ is a weight factor used to adjust the relative importance of path length and fluctuation intensity in optimization, between 0 and 1, and is a preset parameter; W(p) represents the total fluctuation intensity on path p. This is an indicator to measure the quality of a path. The greater the fluctuation intensity, the more likely the path is to be the best path;

[0094] The above process not only combines the three-dimensional structure and fluctuation model of the warehouse in the warehouse navigation path selection, but also incorporates the real-time commodity location and status information, allowing the robot to navigate efficiently and accurately.

[0095] This application uses the spatial fluctuation diffusion algorithm to efficiently simulate all possible paths from the starting point to the target point, greatly improving the efficiency of path planning. Due to the introduction of the dynamic spatial unit adjustment algorithm, even if there are dynamic obstacles in the warehouse (such as moving shelves or robots), the solution can adjust the navigation path in real time to ensure that the path is always optimal. By utilizing the spatial fluctuation diffusion method and spatial path fusion technology, it can not only effectively handle multi-target path problems, but also maintain the accuracy of the path in various situations.

[0096] S3. Based on the commodity data and the real-time working status data of the navigation optimization module, comprehensive processing and analysis are carried out to further optimize inventory management, predict inventory demand and transportation strategies, and provide strategic recommendations for warehousing and transportation for the next module;

[0097] Based on the commodity data and the real-time working status data of the navigation optimization module, the complete implementation process of further optimizing inventory management and predicting inventory demand and transportation strategy through comprehensive processing and analysis is as follows:

[0098] First, in order to ensure the quality and integrity of the data, a unified data interface is used to collect product data from different modules, preliminary navigation path data, and real-time working status data of the navigation optimization module. After such collection, data cleaning is performed to remove abnormal, redundant, or irrelevant data. This stage ensures that subsequent analysis and strategy formulation are based on the cleaned integrated data set;

[0099] Subsequently, the inbound and outbound status of goods is monitored in real time to gain an in-depth understanding of the real-time changes in inventory. At the same time, the storage cycle of goods is analyzed to distinguish between goods with long and short storage cycles. These analyses provide detailed information for subsequent inventory layout and management, forming a complete current inventory status report;

[0100] Based on the current inventory status, we further predict inventory demand. Here, we use time series analysis to predict future inventory demand based on past historical data. At the same time, we combine machine learning models such as decision trees and random forests to make more accurate inventory demand forecasts and obtain a predicted inventory demand report.

[0101] Next, we will optimize the transportation strategy in detail. We will analyze the current navigation path data to identify possible bottlenecks or inefficient areas to ensure efficient transportation. We will determine the most appropriate transportation mode based on the predicted inventory demand, such as batch or single-piece transportation. We will further optimize the navigation path, especially for those products with urgent demand, to ensure that they reach their destination in the shortest possible time.

[0102] Finally, a comprehensive warehousing and transportation strategy is developed by comprehensively considering the current inventory status, predicted inventory demand, and optimized transportation strategy. In order to verify the actual effect and applicability of this strategy, strategy verification will also be carried out, which may include simulation or small-scale experiments to ensure that the strategy recommendations provided are both practical and effective.

[0103] The above process ensures that the warehousing and transportation systems are comprehensively and meticulously optimized based on real-time data monitoring and prediction, achieving efficient intelligent warehousing and transportation.

[0104] S4. Collect the energy consumption data of various activities in the warehouse obtained by the IoT module and the navigation module, analyze the overall energy consumption of the warehouse, optimize the equipment, and obtain energy efficiency reports and energy consumption optimization plans.

[0105] In an efficient intelligent warehousing and transportation system, in order to monitor and optimize energy efficiency, data collection is first carried out; energy consumption monitoring points are deployed in key equipment such as robots, conveyor belts, automatic shelves, etc. and warehouse areas. To ensure real-time performance, low-power Bluetooth technology is used to synchronize data with the central data management system. Subsequently, edge computing technology is used to obtain the working status of the equipment in real time and perform preliminary processing. This not only reduces the burden of central processing, but also ensures the timeliness of data. The main product of this stage is a real-time energy consumption data stream and its preliminary processing report;

[0106] Furthermore, the dynamic energy efficiency flow clustering algorithm is used for data analysis:

[0107] First, data preprocessing; based on the real-time energy consumption data stream X = {x 1 , x 2 , ..., x t}, t represents the total number of data streams, available x i represents any element in X; in order to ensure that the algorithm can handle data of different sizes and reduce the impact of extreme values, the data needs to be z-score standardized, and the mean μ and standard deviation σ of the data are calculated using the following formula:

[0108]

[0109]

[0110] Normalize each data point to:

[0111]

[0112] In order to smooth existing data based on past data, reduce noise and capture trends, the double exponential smoothing method is used as follows:

[0113] z i =αs i +(1-α)(z i-1 +b i-1 )

[0114] Where, the sliding speed b i for:

[0115] b i =β(S i -S i-1 )+(1-β)b i-1

[0116] Among them, α and β are the smoothing parameters of data smoothing and speed, respectively, which are obtained by empirical method.

[0117] Furthermore, in order to capture the local characteristics of energy consumption, such as seasonal or periodic changes, a sliding time window W is used. j =[z j-n+1 , ..., z j ]. Where n is the window length, so that statistics and feature extraction can be performed on the local area of ​​the data stream;

[0118] In particular, the feature extraction, for each window W j , calculate the statistic μ j , σ j And Skewness:

[0119]

[0120] Among them, Skewness measures the skewness of data distribution, which can help understand the distribution of data within the window;

[0121] Furthermore, in order to find abnormal points or sudden energy consumption peaks from the energy consumption data and capture abnormal fluctuations, a dynamic threshold is set. The dynamic threshold is defined as:

[0122]

[0123] Where k is a constant. The above formula determines the abnormal threshold by considering the standard deviation and skewness. If (z j >θ j ), then mark it as an abnormal point; get the non-abnormal data set Z′;

[0124] Furthermore, in order to further understand the pattern and source of energy consumption, a clustering operation is performed on Z′: first, the cluster centers are initialized, and the K_means++ method is used to ensure the rationality of the initial centers; next, the cluster centers are optimized; in order to give more importance to the previous and next relationships in the time series data, a time weight factor ω is introduced, and the weight is adjusted as follows:

[0125] ω=1+λ×R(s,t)

[0126] Among them, R(s, t) is the autocorrelation function, which measures the correlation between data points s and t at lag t. Through the autocorrelation function, the time series characteristics of the data can be taken into account;

[0127] The above optimized process is introduced into the conventional clustering algorithm to obtain an optimized clustering algorithm. Further, a set of cluster labels are obtained for each time window. The labels reveal the potential structure and pattern in the energy consumption data stream. For example, a cluster center may correspond to a specific warehouse operation (such as unloading, loading or robot navigation). Understanding these patterns is the key to building energy efficiency analysis reports.

[0128] Further, clustering post-processing and feature engineering; Extract cluster features: Calculate feature vectors for each cluster, which include average energy consumption, energy consumption fluctuation rate, maximum energy consumption value and minimum energy consumption value in the cluster; Time series features: Use energy consumption values ​​of the previous few time windows to construct lag features, which help capture short-term trends in energy efficiency; Frequency domain analysis: Perform Fourier transform on energy consumption time series to extract several frequencies with the largest energy, which helps capture periodic patterns in energy efficiency;

[0129] Based on the clustering results, a multivariate linear regression model was constructed using existing technology to describe the relationship between energy efficiency and various factors;

[0130] Specifically, the energy efficiency pattern was analyzed using the following multiple linear regression model:

[0131] Y=β 0 +β 1 X 1 +β 2 X 2 +…+β m X m

[0132] Among them, Y represents energy consumption; β 0 To β m represents the regression parameters obtained by experiments; X represents the factors in various clusters and other factors extracted from feature engineering; the performance of the model is evaluated using the existing cross-validation method, and the quality of the model is evaluated based on the prediction error of the model and other statistical indicators;

[0133] In particular, a report is generated, based on the comparison between the model prediction and the actual data, to generate an energy efficiency report. The report not only includes the prediction of energy consumption trends, but also provides early warnings for possible abnormal points in the future; in addition, based on the coefficients of the model, the main factors affecting energy efficiency can be identified, thereby providing operational recommendations for warehouse management;

[0134] The above technical solution describes in detail how to extract meaningful information from real-time energy consumption data streams and analyze it using advanced algorithms to better manage and optimize the energy efficiency of warehouses;

[0135] Furthermore, according to the classification and analysis reports obtained above, the automatic adjustment of the equipment begins. In this process, fuzzy logic or neural network technology can be used. When the energy consumption exceeds the predetermined threshold, the IoT technology can be combined to automatically adjust the equipment status or inform the staff through the intelligent notification system, so as to achieve real-time energy efficiency management; in addition, the genetic algorithm or ant colony algorithm can be used to formulate and implement the best energy-saving strategy, so as to ensure that the equipment operates in the best state while meeting the energy-saving requirements;

[0136] Furthermore, energy efficiency reports are generated; in order to fully understand and share the energy consumption of the warehouse, cloud storage and big data technology are used to summarize all collected energy consumption data. These data are visualized through data visualization tools such as Tableau or PowerBI to show the changing trend of energy consumption and form an interactive and dynamic energy efficiency report. This report not only provides a clear view for management, but also builds an AI-based adaptive system that can provide further energy-saving suggestions, and continuously learn and gradually improve.

[0137] This application adopts a dynamic energy efficiency flow clustering algorithm to ensure efficient processing and analysis of large amounts of real-time energy consumption data, reduce the burden on central processing, and better capture the local characteristics and abnormal fluctuations of energy consumption data. By using clustering algorithms and feature engineering, the potential structure and patterns of energy consumption data can be revealed, and energy consumption patterns related to specific warehouse operations can be identified, providing in-depth insights for energy efficiency analysis.

[0138] In summary, an efficient intelligent warehousing and transportation system and method described in this application are completed.

[0139] Effect research:

[0140] The technical solution of the present application can effectively solve the technical problems of poor accuracy, slow response speed and low efficiency of the existing warehousing and transportation system. In addition, the above-mentioned system or method has undergone a series of effect surveys. The deployment of the Internet of Things module in the form of gridding and a two-dimensional coordinate system can ensure that every area of ​​the warehouse is monitored with high precision, which helps to accurately track and identify the real-time location and status of the goods. The preliminary processing performed by the data transmission module, such as outlier detection, unit conversion and data denoising, ensures the quality of the data and provides high-quality input for subsequent data processing and analysis. The automated deployment and data processing process greatly reduces the errors caused by human operations and improves the reliability of the system. The spatial fluctuation diffusion algorithm can efficiently simulate all possible locations from the starting point to the target point. Energy path, greatly improving the efficiency of path planning. Due to the introduction of dynamic spatial unit adjustment algorithm, even if there are dynamic obstacles in the warehouse (such as moving shelves or robots), the solution can adjust the navigation path in real time to ensure that the path is always optimal. By utilizing the spatial fluctuation diffusion method and spatial path fusion technology, it can not only effectively handle multi-target path problems, but also maintain the accuracy of the path in various situations; the dynamic energy efficiency flow clustering algorithm is adopted to ensure the efficient processing and analysis of a large amount of real-time energy consumption data, reduce the burden of central processing, and better capture the local characteristics and abnormal fluctuations of energy consumption data. The clustering algorithm and feature engineering can reveal the potential structure and pattern of energy consumption data, identify the energy consumption pattern related to specific warehouse operations, and provide in-depth insights for energy efficiency analysis.

[0141] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0143] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0144] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An efficient intelligent warehousing and transportation method, characterized in that: The following steps are involved: S1. Deploy the IoT module to ensure that each area is within the monitoring range, initialize the IoT module to ensure that the module can accurately track and identify the real-time location and status of the goods, configure the data transmission module to ensure stable reception of data from the IoT module, and perform preliminary processing; S2. Based on the real-time commodity data stream provided by the data transmission module, the optimal pickup path is calculated, and the real-time data acquisition and warehouse space network is constructed. Based on the spatial fluctuation diffusion method of real-time data, all possible paths from the starting point to the target point are simulated to obtain a preliminary navigation path. The spatial fluctuation diffusion method based on real-time data is used to simulate the propagation of fluctuations in the warehouse space. The specific implementation formula is as follows: w ijk (t+1)=α×w ijk (t)+(1-α)×avg_neighbour(w ijk (t)) Where W(t) is the total fluctuation intensity of the entire warehouse at time t; w ijk (t) is the space unit s at time t ijk The fluctuation intensity of i, j, k is between 1 and n, s ijk is 0 or 1, where 0 means no obstacle and 1 means there is an obstacle; n represents the number of spatial units; w ijk (t+1) is the number of cells in the warehouse at s at time t+1. ijk The fluctuation intensity of the spatial unit of the position; avg_neighbour(w ijk (t)) represents the spatial unit w at time t. ijk (t) is the average value of the fluctuation intensity of all adjacent spatial units around it; α is the attenuation factor, representing the decreasing degree of fluctuation; According to the preliminary navigation path and real-time obstacle information of the warehouse, obstacle detection and path adjustment are carried out, and a dynamic space unit adjustment algorithm is introduced to dynamically detect obstacles in the space unit and dynamically adjust the fluctuation path; the initial navigation path is optimized; the state of each space unit is monitored in real time, and moving obstacles are detected; when a change in the state of the space unit is detected, the fluctuation intensity is adjusted, and the path is recalculated according to the adjusted fluctuation intensity; the specific formula is as follows: w i ′ jk (t)=w ijk (t)×(1-β×obstacle ijk ) Among them, w i ′ jk (t) is the time t, after obstacle detection, the spatial unit s ijk Adjusted volatility intensity; obstacle ijk is a function, when the space unit s ijk It returns 1 if there is an obstacle or the product is taken away, otherwise it returns 0; β is the blocking factor; Based on the above dynamic obstacle adjustment results, spatial path fusion technology is used to solve the fluctuating paths generated by multiple targets to obtain the optimized best navigation path; S3. Based on the commodity data and the real-time working status data of the navigation optimization module, comprehensive processing and analysis are carried out to further optimize inventory management, predict inventory demand and transportation strategies, and provide strategic recommendations for warehousing and transportation for the next module; S4. Collect the energy consumption data of various activities in the warehouse obtained by the IoT module and the navigation optimization module, analyze the overall energy consumption of the warehouse, and optimize the equipment. When analyzing the energy consumption data, use the dynamic energy efficiency flow clustering algorithm to perform data analysis; In the process of implementing the dynamic energy efficiency flow clustering algorithm, data preprocessing is performed to process data of different sizes and reduce the impact of extreme values ​​based on the real-time energy consumption data stream of various activities in the warehouse, and the data is z-score standardized and quadratically smoothed; Use a sliding time window to perform statistics and feature extraction on the local area of ​​the data stream; in order to find outliers or energy consumption peaks from the energy consumption data, capture abnormal fluctuations, set a dynamic threshold, and obtain a non-abnormal data set; perform clustering operations on the non-abnormal data set, initialize and optimize the clustering center, and introduce the optimization process into the conventional clustering algorithm to obtain an optimized clustering algorithm, and obtain a set of cluster labels for each time window; Perform clustering post-processing and feature engineering to extract clustering features and obtain clustering results. Based on the clustering results, build a multivariate linear regression model to perform energy efficiency pattern analysis to obtain energy efficiency reports and energy consumption optimization plans.

2. An efficient intelligent warehousing and transportation system, applied to an efficient intelligent warehousing and transportation method as claimed in claim 1, characterized in that: Includes the following parts: Internet of Things module, data transmission module, preliminary navigation module, navigation optimization module, integrated processing module, intelligent allocation module, energy efficiency monitoring and optimization module; The IoT module tracks the real-time location and status of the goods in the warehouse and immediately uploads these data for use by subsequent modules; The data transmission module receives the commodity location and status information data from the IoT module, and transmits the data using optimization technology to provide commodity data for subsequent modules; The preliminary navigation module provides preliminary path navigation for warehouse staff or robots based on the commodity data received from the data transmission module; The navigation optimization module senses the navigation path given by the preliminary navigation module and the real-time obstacle information in the warehouse, monitors obstacles or other robots and personnel on the path in real time, and adjusts the path in real time to prevent collisions; The integrated processing module integrates the commodity data from the data transmission module, the navigation path data from the preliminary navigation module, and the real-time working status data from the navigation optimization module, performs comprehensive processing and analysis, further optimizes inventory management, predicts inventory demand and transportation strategies, and provides strategic recommendations for warehousing and transportation; The intelligent allocation module performs automatic and intelligent storage allocation of commodities according to the storage and transportation strategy suggestions from the integrated processing module; The energy efficiency monitoring and optimization module uses energy management algorithms to collect and analyze energy consumption data of various activities in the warehouse from the Internet of Things module and the navigation optimization module in real time, and automatically adjusts the overall energy consumption in the warehouse to optimize energy consumption based on the analysis results.

Images