Warehouse logistics management system based on artificial intelligence

By using an AI-based warehouse logistics management system, the system can monitor and optimize the warehouse environment and inventory in real time, and dynamically schedule goods. This solves the shortcomings of existing systems in managing complex environments and order demands, and achieves efficient and intelligent warehouse logistics management.

CN119027030AInactive Publication Date: 2024-11-26SHENZHEN ZICHUAN SOFTWARE CO LTD

Patent Information

Application Number
CN202411309637.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing warehouse and logistics management systems are inadequate in handling complex and ever-changing warehousing environments and order demands. They lack comprehensive data support and intelligent analysis, resulting in inaccurate inventory management, inefficient logistics scheduling, and difficulty in dynamically responding to environmental changes and order demands.

Method used

The warehouse logistics management system adopts an artificial intelligence-based approach, including an environmental perception module, an inventory management module, a dynamic scheduling module, an automatic picking module, and a data processing and decision support module. It utilizes multiple sensors to monitor environmental data in real time, and combines machine learning and big data analysis to achieve intelligent inventory management and dynamic scheduling optimization. The system also provides real-time data display and operation instructions through a user interaction module.

Benefits of technology

It improves the accuracy of warehouse environment monitoring and the level of intelligence in inventory management, dynamically optimizes warehouse layout and logistics scheduling, enhances the overall efficiency and flexibility of warehouse management, reduces manual intervention and inventory loss, and improves the response speed and accuracy of logistics scheduling.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027030A_ABST
    Figure CN119027030A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of logistics management, in particular to a warehouse logistics management system based on artificial intelligence, which comprises an environment sensing module, an inventory management module, a dynamic scheduling module, an automatic sorting module, a data processing and decision support module and a user interaction module, the inventory management module monitors and analyzes the inventory state in real time by using an artificial intelligence algorithm, the dynamic scheduling module dynamically optimizes the storage layout and the warehouse-in and warehouse-out sequence based on a reinforcement learning algorithm, and the automatic sorting module realizes efficient sorting and carrying of goods through robot control and a path planning algorithm. The data processing and decision support module comprehensively analyzes the data generated by each module and provides optimization decision support, the user interaction module provides real-time data display and system monitoring functions for users, and the intelligent level and response capability of warehouse logistics management are significantly improved through cooperative work of multiple modules.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a warehouse logistics management system based on artificial intelligence. Background Art

[0002] With the rapid development of global e-commerce, the competition in the logistics industry is becoming increasingly fierce, and warehouse management has become a key link in supply chain management. The demand for intelligent and automated warehouse logistics management systems has also increased. Enterprises hope to improve the efficiency of warehouse management, reduce manual intervention, and achieve full-scale automated operations by introducing artificial intelligence technology. Warehouse management not only involves the dispatching of goods in and out of the warehouse, but also includes dynamic monitoring of inventory, real-time perception of the warehouse environment, and automated execution of picking operations. These factors play an important role in improving the overall operational efficiency of the logistics system, reducing operating costs, and improving customer service levels.

[0003] However, most of the existing warehouse logistics management systems rely on traditional automation technology, which has many deficiencies in dealing with complex and changeable warehouse environments and order requirements. First, the monitoring of the warehouse environment is usually limited to simple temperature and humidity control, lacking comprehensive data support and intelligent analysis, making it difficult to effectively prevent inventory losses caused by environmental changes. Secondly, inventory management relies on manual or semi-automatic monitoring methods, which is prone to lagging or inaccurate inventory data, resulting in inventory backlogs or out-of-stocks. The optimization and execution of logistics scheduling mainly rely on fixed rules and cannot dynamically respond to changes in the warehouse environment and order requirements, resulting in low scheduling efficiency. Summary of the invention

[0004] Based on the above objectives, the present invention provides a warehouse logistics management system based on artificial intelligence.

[0005] A warehouse logistics management system based on artificial intelligence, including an environment perception module, an inventory management module, a dynamic scheduling module, an automatic picking module, a data processing and decision support module and a user interaction module, wherein;

[0006] The environmental perception module is equipped with multiple sensors for real-time collection of environmental data in the warehouse, including temperature, humidity, light and air quality;

[0007] The inventory management module is used to monitor and manage the inventory status in the warehouse in real time, analyze the inventory data using artificial intelligence algorithms, automatically generate inventory replenishment suggestions, and realize automatic replenishment through connection with the supply chain system;

[0008] The dynamic scheduling module is connected to the inventory management module and is used to dynamically optimize the warehouse layout and the order of entry and exit according to the inventory status and order requirements;

[0009] The automatic picking module includes a robot control unit, which is linked with the dynamic scheduling module to perform automatic picking and handling operations of goods;

[0010] The data processing and decision support module is connected to the environment perception module, the inventory management module and the dynamic scheduling module, and is used to process and analyze the data generated by the modules, use big data analysis and machine learning algorithms, provide decision support, and continuously optimize the operation strategy;

[0011] The user interaction module is used to realize information interaction between users and the system, and provides real-time data display, system monitoring and operation instruction input functions. Users can view the system operation status through this module and adjust the warehouse management strategy.

[0012] Optionally, the environment perception module specifically includes:

[0013] Temperature sensors: installed at key locations in the warehouse, such as entrances and exits, the middle of shelves, and cold storage areas, to monitor temperature data in the warehouse in real time;

[0014] Humidity sensors: They are placed in different areas of the warehouse, especially near goods that are susceptible to humidity, to monitor humidity data in real time.

[0015] Light sensor: installed on the ceiling of the warehouse and in corners with uneven light to monitor the light intensity data in the warehouse;

[0016] Air quality sensors: Deployed at warehouse vents and central locations to monitor air quality indicators in real time, including PM2.5 concentration and carbon dioxide concentration.

[0017] Optionally, the inventory management module includes:

[0018] Inventory monitoring unit: Install RFID readers or QR code scanning devices on each shelf and storage area in the warehouse to track the storage location and inventory quantity of each item in real time. The data is automatically updated and uploaded to the central database to achieve real-time monitoring of inventory;

[0019] Inventory Analysis Unit: Uses machine learning algorithms to dynamically analyze inventory data, predict inventory demand, and generate replenishment recommendations;

[0020] Automatic replenishment unit: Through integration with the supply chain system, replenishment orders are automatically generated and sent, combined with inventory analysis results to ensure timely replenishment and avoid insufficient or excessive inventory accumulation.

[0021] Optionally, the inventory analysis unit specifically includes:

[0022] Data preprocessing: Collect and organize historical inventory data and order data in the warehouse system, including timestamps, inventory levels, and order quantities, and perform preprocessing, including missing value processing, outlier detection, and data smoothing;

[0023] Time series decomposition: Perform time series decomposition on inventory data and decompose the time series into trend, seasonality and residual;

[0024] Model selection and training: The machine learning algorithm selects the autoregressive integrated moving average model to predict inventory demand, and uses historical inventory data and order data to train the autoregressive integrated moving average model. The basic formula of the autoregressive integrated moving average model is expressed as:

[0025] y t =c+φ1y t―1 +φ2y t―2 +…+θ1∈ t―1 +θ2∈ t―2 +∈ t ;

[0026] Among them, y t is the actual value of the time series, c is a constant term, φ i is the autoregressive coefficient, θ i is the moving average coefficient, ∈ t is the error term;

[0027] Inventory demand forecasting: Use the trained autoregressive integrated moving average model to predict future inventory demand;

[0028] Generate replenishment suggestions: Generate replenishment suggestions based on predicted inventory requirements.

[0029] Optionally, the dynamic scheduling module specifically includes:

[0030] Warehouse layout optimization unit: dynamically optimizes the storage location of goods inside the warehouse based on inventory data and order requirements;

[0031] Inbound and outbound order optimization unit: dynamically generates inbound and outbound order based on real-time orders and inventory status;

[0032] Scheduling execution unit: issues the optimized warehouse layout and warehousing and warehousing order to relevant execution equipment, including automatic picking robots and transportation equipment.

[0033] Optionally, the automatic picking module specifically includes:

[0034] Robot control unit: controls the automatic picking robot to perform picking and handling operations according to the instructions of the dynamic scheduling module to ensure efficient completion of tasks;

[0035] Path planning unit: Generates the optimal path for the picking robot through the Dijkstra algorithm, avoids obstacles, and reduces path length and handling time.

[0036] Optionally, the data processing and decision support module specifically includes:

[0037] Data preprocessing unit: cleans, formats and standardizes data from environment perception, inventory management and dynamic scheduling modules;

[0038] Big data analysis unit: conducts in-depth analysis of pre-processed data, using K-means clustering algorithm and linear regression model to identify patterns and trends in the data, providing strong data support for warehouse management;

[0039] Decision support unit: Based on the analysis results and combined with machine learning algorithms, it generates optimization decision suggestions for warehouse management, including inventory adjustment, scheduling optimization and environmental control strategies, and continuously optimizes the decision model according to the operation of the system.

[0040] Optionally, the big data analysis unit specifically includes:

[0041] Define clustering features: Select the features to be clustered, including inventory level, order volume, inbound frequency, and outbound frequency;

[0042] Select the number of clusters k: Use the elbow method to select the k value. The elbow method formula is expressed as:

[0043]

[0044] Among them, C i is the i-th cluster, μ i is the centroid of the ith cluster, x j is the jth data point belonging to the i-th cluster;

[0045] Perform K-means clustering: Use the selected k value to perform K-means clustering on the data. The goal is to divide the data into k clusters so that the data points in the same cluster are as similar as possible and the data points in different clusters are as different as possible. The K-means objective function is expressed as:

[0046]

[0047] Among them, J is the objective function value, which represents the sum of the squares of the distances from the data points in the cluster to the centroid;

[0048] Result analysis: After clustering, analyze each cluster to identify data groups with similar characteristics. For example, analyze which warehouses with different inventory levels have similar order patterns in a specific time period. These patterns may reflect seasonal demand or other factors that affect inventory levels.

[0049] Application of linear regression model: Select relevant independent variables (such as time, order volume, inventory level) and dependent variables (such as inventory demand, inbound and outbound frequency) to construct a regression model data set;

[0050] Build a regression model to build a linear regression model with the dependent variable v (such as predicted inventory demand) as the target and the independent variables x1, x2, ..., x n To input features, fit the model, and identify the linear relationship between independent variables and dependent variables, the linear regression model formula is expressed as:

[0051] y=β0+β1x1+β2x2+…+β n x n +∈;

[0052] Where y is the dependent variable (such as predicted inventory demand), β0 is the intercept, which represents the value of the dependent variable when all independent variables are zero, β1, β2, ..., β n is the regression coefficient, which indicates the influence of each variable on the dependent variable, x1, x2, ..., x n is the independent variable (such as time, order volume, etc.), ∈ is the error term, which represents the part not explained by the model;

[0053] Model evaluation: The R-squared formula is used to evaluate the model's fitting effect:

[0054]

[0055] Among them, y i is the actual value, is the model prediction value, is the mean of the actual values;

[0056] Model analysis: Based on the regression coefficient of the linear regression model, identify which factors (independent variables) have a significant impact on inventory demand, thereby identifying the trend and pattern of inventory changes;

[0057] Comprehensive application: Through cluster analysis, groups with similar inventory behaviors in the warehouse can be identified. These groups can represent the inventory pattern or demand pattern in a specific time period. Through regression analysis, the impact of independent variables on inventory demand can be quantified, and the long-term trend and seasonal fluctuations of inventory changes can be identified.

[0058] Optionally, the decision support unit specifically includes:

[0059] Inventory adjustment strategy: Generate inventory adjustment suggestions, including replenishment plans and inventory transfers, based on the inventory demand predicted by the inventory analysis unit;

[0060] Scheduling optimization: Based on the results of the warehouse layout optimization unit and the storage order optimization unit, an optimized scheduling strategy is generated, including the optimal storage order and storage location of the goods;

[0061] Environmental control strategy: Generate environmental control strategy through machine learning algorithm.

[0062] Optionally, the user interaction module specifically includes:

[0063] Real-time data display: The real-time environment data, inventory status, order processing progress and operation status of the warehouse are displayed through a visual interface. It supports a variety of data chart forms, such as line charts, bar charts and pie charts, which can intuitively display various indicators of warehouse management;

[0064] Operation instruction input: allows users to input operation instructions through a visual interface and manually adjust operating parameters, including inventory management, scheduling and environmental control settings. It supports multi-user authority management to ensure the security of system operations.

[0065] Beneficial effects of the present invention:

[0066] The present invention uses multiple sensors of the environment perception module to enable the system to monitor the temperature, humidity, light intensity and air quality in the warehouse in real time. It not only provides a reliable basis for the formulation of environmental control strategies, but also is closely integrated with the inventory management module. It analyzes inventory data through artificial intelligence algorithms, automatically generates inventory replenishment suggestions, and integrates with the supply chain system to achieve automatic replenishment. The system effectively reduces the workload of manual monitoring and management, improves the accuracy of warehouse environment monitoring and the intelligent level of inventory management, avoids inventory losses and replenishment delays caused by environmental factors, and thus improves the overall efficiency of warehouse management.

[0067] In the present invention, the dynamic scheduling module dynamically optimizes the warehouse layout and the order of goods in and out of the warehouse according to the real-time inventory status and order requirements through the reinforcement learning algorithm, and works in conjunction with the robot control unit and the path planning unit in the automatic picking module to achieve the optimal goods picking and transportation path. The optimal path generated by the Dijkstra algorithm reduces the path length and transportation time, and improves the response speed and accuracy of logistics scheduling. It can not only quickly adapt to changes in the storage environment, but also adjust the scheduling strategy in real time according to actual conditions, significantly improving the operational efficiency and flexibility of warehousing logistics.

[0068] In the present invention, the data processing and decision support module uses big data analysis and machine learning algorithms to clean, analyze and provide decision support for data from the environmental perception, inventory management and dynamic scheduling modules. Through the K-means clustering algorithm and linear regression model, the system can identify the patterns and trends in the warehouse and provide data support for inventory adjustment, scheduling optimization and environmental control strategies. At the same time, the user interaction module provides an intuitive visual interface, and users can monitor the system status in real time and enter operating instructions, further enhancing the ease of use and management efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0071] Figure 2 The figure is a flowchart of an inventory management module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0073] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0074] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0075] like Figure 1-Figure 2 As shown, a warehouse logistics management system based on artificial intelligence includes an environment perception module, an inventory management module, a dynamic scheduling module, an automatic picking module, a data processing and decision support module and a user interaction module, wherein;

[0076] The environmental perception module is equipped with multiple sensors to collect real-time environmental data in the warehouse, including temperature, humidity, light and air quality;

[0077] The inventory management module is used to monitor and manage the inventory status in the warehouse in real time, analyze inventory data using artificial intelligence algorithms, automatically generate inventory replenishment suggestions, and realize automatic replenishment through connection with the supply chain system;

[0078] The dynamic scheduling module is connected to the inventory management module to dynamically optimize the warehouse layout and the order of inbound and outbound storage according to the inventory situation and order requirements, and generate the optimal scheduling plan through the reinforcement learning algorithm to ensure the fast and accurate processing of goods;

[0079] The automatic picking module includes a robot control unit, which is linked with the dynamic scheduling module to perform automatic picking and handling operations of goods;

[0080] The data processing and decision support module connects the environmental perception module, inventory management module and dynamic scheduling module to process and analyze the data generated by the modules, using big data analysis and machine learning algorithms to provide decision support and continuously optimize the operation strategy;

[0081] The user interaction module is used to realize information interaction between users and the system, and provides real-time data display, system monitoring and operation instruction input functions. Users can use this module to view the system operation status and adjust the warehouse management strategy.

[0082] The environmental perception module specifically includes:

[0083] Temperature sensors: installed at key locations in the warehouse, such as entrances and exits, the middle of shelves, and cold storage areas, to monitor temperature data in the warehouse in real time and transmit the temperature data to the data processing and decision support module for environmental control analysis;

[0084] Humidity sensors: They are placed in different areas of the warehouse, especially near goods that are susceptible to humidity. They are used to monitor the humidity data of the warehouse in real time and transmit the data to the data processing and decision support module to maintain appropriate humidity conditions.

[0085] Light sensor: installed on the ceiling of the warehouse and in corners with uneven light, used to monitor the light intensity data in the warehouse to ensure that the light level is appropriate and avoid insufficient or excessive light that affects the quality of goods;

[0086] Air quality sensors: deployed at warehouse vents and central locations to monitor air quality indicators in real time, including PM2.5 concentration and carbon dioxide concentration, to ensure good air circulation in the warehouse and provide data support for the health and safety of the storage environment;

[0087] By deploying a variety of sensors in key areas of the warehouse, the environmental perception module can comprehensively and accurately monitor various parameters of the storage environment, providing reliable basic data for subsequent data processing and environmental control.

[0088] The inventory management module includes:

[0089] Inventory monitoring unit: Install RFID readers or QR code scanning devices on each shelf and storage area in the warehouse to track the storage location and inventory quantity of each item in real time. The data is automatically updated and uploaded to the central database to achieve real-time monitoring of inventory;

[0090] Inventory Analysis Unit: Uses machine learning algorithms to dynamically analyze inventory data, predict inventory demand, and generate replenishment recommendations;

[0091] Automatic replenishment unit: Through integration with the supply chain system, replenishment orders are automatically generated and sent, combined with inventory analysis results to ensure timely replenishment and avoid insufficient or excessive inventory accumulation;

[0092] The inventory management module realizes accurate management and automatic replenishment of inventory in the warehouse through real-time monitoring and intelligent analysis, providing a guarantee for the efficient operation of warehouse logistics management.

[0093] The inventory analysis unit specifically includes:

[0094] Data preprocessing: Collect and organize historical inventory data and order data in the warehouse system, including timestamps, inventory levels, and order quantities, and perform preprocessing, including missing value processing, outlier detection, and data smoothing;

[0095] (1) Missing value processing: Linear interpolation is used to fill the gaps caused by missing data. The linear interpolation formula is expressed as:

[0096]

[0097] in, is the estimate of missing values, y t―1 is the known data point before the missing value, y t+1 is the known data point after the missing value, and t is the timestamp of the missing data point;

[0098] (2) Outlier detection: The 3σ principle is used to identify and process outliers in time series data. The 3σ detection formula is expressed as:

[0099] Outlier condition: |y t ―μ|>3σ;

[0100] Among them, y t is the time series data point, μ is the mean of the data, and σ is the standard deviation of the data;

[0101] Outliers are processed by replacing them with values ​​such as the mean or median. The outlier replacement formula is:

[0102] or

[0103] (3) Data smoothing: Exponential smoothing is used to reduce noise in time series and make data easier to analyze. The formula for exponential smoothing is:

[0104]

[0105] in, is the smoothed value at time t, y t is the actual value at time t, α is the smoothing coefficient, usually between 0 and 1, is the smoothed value at time t-1;

[0106] Time series decomposition: Perform time series decomposition on inventory data and decompose the time series into trend, seasonality and residual;

[0107] Trend: reflects the long-term trend of inventory levels, which can be obtained by fitting a simple linear regression model;

[0108] Seasonality: reflects the periodic fluctuations in inventory data, such as seasonal demand changes. The seasonal component can be extracted by moving average or fast Fourier transform;

[0109] Residual: The part that remains after trend and seasonal factors are eliminated, representing random fluctuations or unpredictable factors;

[0110] Model selection and training: The machine learning algorithm selects the autoregressive integrated moving average model to predict inventory demand, and uses historical inventory data and order data to train the autoregressive integrated moving average model. The basic formula of the autoregressive integrated moving average model is expressed as:

[0111] y t =c+φ1y t―1 +φ2y t―2 +…+θ1∈ t―1 +θ2∈ t―2 +∈ t ;

[0112] Among them, y t is the actual value of the time series, c is a constant term, φ i is the autoregressive coefficient, θ i is the moving average coefficient, ∈ t is the error term;

[0113] Inventory demand forecasting: Use the trained autoregressive integrated moving average model to predict future inventory demand. The forecast includes estimating the inventory level in a certain period of time in the future and identifying possible inventory shortages or surpluses.

[0114] Generate replenishment suggestions: Generate replenishment suggestions based on predicted inventory demand, including:

[0115] (1) Safety stock calculation: Set the minimum safety stock level and calculate the required replenishment quantity based on the forecasted inventory demand;

[0116] (2) Automatically generate replenishment orders: Automatically generate replenishment orders based on replenishment suggestions and automatically send orders to suppliers through integration with the supply chain management system;

[0117] In actual operation, as new inventory data continues to accumulate, the time series model is retrained regularly and the parameters of the forecasting model are adjusted dynamically to ensure the accuracy and timeliness of the forecast. Through dynamic adjustment and model updates, the system can adapt to changing market demand and seasonal fluctuations, thereby optimizing the replenishment strategy.

[0118] The dynamic scheduling module specifically includes:

[0119] Warehouse layout optimization unit: Combine inventory data and order requirements to dynamically optimize the storage location of goods inside the warehouse. The algorithm uses a reinforcement learning model to continuously improve the warehouse layout, reduce the cargo handling path, and improve operational efficiency. The process of establishing a reinforcement learning model includes the following steps:

[0120] (1) Define the state space: The state space represents all possible states of the warehouse layout. For example, the state can represent the occupancy of the shelves, the location of the goods, and other environmental factors that affect the efficiency of the operation.

[0121] s t represents the warehouse layout status at time t;

[0122] (2) Define the action space: The action space represents all possible actions that the warehouse system can take. For example, an action is to move a certain product from one shelf to another, or to change the order of the products.

[0123] a t represents the action taken at time t, such as adjusting the position of the goods;

[0124] (3) Reward function: The reward function evaluates the quality of each action. The goal is to maximize the long-term reward. The reward is defined based on indicators such as the transport distance and the operation time.

[0125] r t Indicates that in state s t Next, perform action a t The immediate reward obtained is negatively correlated with the length of the transport path and the work efficiency;

[0126] (4) State transfer function: P(s t+1 |s t ,a t ), which represents the probability of the system transitioning from one state to another after performing a certain action;

[0127] (5) Value function: used to estimate the expected reward that can be obtained in the future under a certain state;

[0128] V(s) represents the expected cumulative reward in state s;

[0129] (6) Q-learning formula: The Q-learning algorithm finds the optimal strategy for each state-action pair through repeated iterations to maximize the long-term reward. The Q function formula is expressed as:

[0130]

[0131] Among them, Q(s t ,a t ) is in state s t Take action a t The Q value (i.e. expected return), α is the learning rate, which controls the magnitude of each update, r t is the immediate reward, γ is the discount factor, which represents the present value weight of future rewards, usually 0≤γ≤1, max a′ Q(s t+1 ,a′) means in the next state s t+1 The maximum Q value of taking the optimal action;

[0132] In-and-out order optimization unit: dynamically generates in-and-out order based on real-time orders and inventory status, and uses reinforcement learning models to optimize the scheduling process to ensure fast and accurate order processing and reduce in-and-out time;

[0133] Scheduling execution unit: Sends the optimized warehouse layout and warehousing order to relevant execution equipment, including automatic picking robots and transportation equipment, to ensure the efficient execution of the scheduling plan;

[0134] The dynamic scheduling module ensures the optimal storage location and order of entry and exit of goods within the warehouse through intelligent algorithms and real-time optimization, greatly improving the efficiency and accuracy of warehousing operations.

[0135] The automatic picking module specifically includes:

[0136] Robot control unit: controls the automatic picking robot to perform picking and handling operations of goods according to the instructions of the dynamic scheduling module to ensure efficient completion of tasks;

[0137] Path planning unit: Generate the optimal path for the picking robot through the Dijkstra algorithm, avoid obstacles, reduce path length and handling time, and ensure the efficiency and safety of the picking process. The specific steps are as follows:

[0138] (1) Input definition: define the warehouse floor plan and obstacle locations, divide the warehouse into grids, and define the starting point (starting location) and the end point (target location);

[0139] (2) Cost function design: Define the movement cost w(u,v) between each grid. The Dijkstra algorithm formula is expressed as:

[0140] d[v]=min{d[u]+w(u,v)};

[0141] Where d[v] is the shortest path cost from the starting point to node v, d[u] is the shortest path cost from the starting point to node u, and w(u,v) is the edge weight or path cost from node u to node v;

[0142] (3) Path search: Search the optimal path through the algorithm to obtain the path sequence from the starting point to the end point;

[0143] The automatic picking module effectively improves the efficiency and accuracy of picking operations through intelligent control and path optimization, providing solid support for the efficient operation of warehousing logistics.

[0144] The data processing and decision support modules specifically include:

[0145] Data preprocessing unit: cleans, formats and standardizes data from environment perception, inventory management and dynamic scheduling modules to ensure high quality and consistency of data and provide a reliable basis for subsequent analysis, including:

[0146] Missing value filling:

[0147] in, is the estimated value of the missing value, x j is the known data point in the data set, and n is the number of known data points in the data set;

[0148] Timestamp alignment: T i =align(T i , Δt);

[0149] Among them, T i is the timestamp of the data point, Δt is the time interval specified by the system, and align is the alignment function that aligns the timestamp to the nearest time interval;

[0150] Min-max normalization:

[0151] Among them, x i ′ is the standardized data, x i is the original data, min(x), max(x) are the minimum and maximum values ​​of the data set;

[0152] Big data analysis unit: conducts in-depth analysis of pre-processed data, using K-means clustering algorithm and linear regression model to identify patterns and trends in the data, providing strong data support for warehouse management;

[0153] Decision support unit: Based on the analysis results and combined with machine learning algorithms, it generates optimization decision suggestions for warehouse management, including inventory adjustment, scheduling optimization and environmental control strategies, and continuously optimizes the decision model according to the operation of the system;

[0154] The data processing and decision support module ensures the scientificity and efficiency of warehousing logistics management through in-depth analysis of multi-source data and intelligent decision support, and provides data-driven support for the continuous optimization of the system.

[0155] The big data analysis unit specifically includes:

[0156] Define clustering features: Select the features to be clustered, including inventory level, order volume, inbound frequency, and outbound frequency. These features are used to define the location of data points in multidimensional space.

[0157] Select the number of clusters k: Selecting the appropriate number of clusters k is a key step in K-means clustering. The elbow method is used to select the appropriate k. This method calculates the sum of squares of clustering errors under different k values ​​and finds the position where the error reduction is significantly slowed down as the optimal k value. The elbow method formula is expressed as:

[0158]

[0159] Among them, C i is the i-th cluster, μ i is the centroid of the ith cluster, x j is the jth data point belonging to the i-th cluster;

[0160] Perform K-means clustering: Use the selected k value to perform K-means clustering on the data. The goal is to divide the data into k clusters so that the data points in the same cluster are as similar as possible and the data points in different clusters are as different as possible. The K-means objective function is expressed as:

[0161]

[0162] Among them, J is the objective function value, which represents the sum of the squares of the distances from the data points in the cluster to the centroid;

[0163] Result analysis: After clustering, analyze each cluster to identify data groups with similar characteristics. For example, analyze which warehouses with different inventory levels have similar order patterns in a specific time period. These patterns may reflect seasonal demand or other factors that affect inventory levels.

[0164] Application of linear regression model: Select relevant independent variables (such as time, order volume, inventory level) and dependent variables (such as inventory demand, inbound and outbound frequency) to construct a regression model data set;

[0165] Build a regression model: Build a linear regression model with the dependent variable y (such as predicted inventory demand) as the target and the independent variables x1, x2,…, x n To input features, fit the model, and identify the linear relationship between independent variables and dependent variables, the linear regression model formula is expressed as:

[0166] y=β0+β1x1+β2x2+…+β n x n +∈;

[0167] Where y is the dependent variable (such as predicted inventory demand), β0 is the intercept, which represents the value of the dependent variable when all independent variables are zero, β1, β2, …, β n is the regression coefficient, which indicates the influence of each variable on the dependent variable, x1, x2,…, x nis the independent variable (such as time, order volume, etc.), ∈ is the error term, which represents the part not explained by the model;

[0168] Model evaluation: The R-squared formula is used to evaluate the model's fitting effect:

[0169]

[0170] Among them, y i is the actual value, is the model prediction value, is the mean of the actual values;

[0171] Model analysis: Based on the regression coefficient of the linear regression model, identify which factors (independent variables) have a significant impact on inventory demand, thereby identifying the trend and pattern of inventory changes;

[0172] Comprehensive application: Through cluster analysis, groups with similar inventory behaviors in the warehouse can be identified. These groups can represent the inventory pattern or demand pattern in a specific time period. Through regression analysis, the impact of independent variables on inventory demand can be quantified, and the long-term trend and seasonal fluctuations of inventory changes can be identified.

[0173] The decision support unit specifically includes:

[0174] Inventory adjustment strategy: Generate inventory adjustment suggestions, including replenishment plans and inventory transfers, based on the inventory demand predicted by the inventory analysis unit;

[0175] Scheduling optimization: Based on the results of the warehouse layout optimization unit and the storage order optimization unit, an optimized scheduling strategy is generated, including the optimal storage order and storage location of the goods;

[0176] Environmental control strategy: Generate environmental control strategy through machine learning algorithm. The specific steps are as follows:

[0177] Data preparation: Collect historical data related to the storage environment, including storage conditions, control output data, and environmental data collected by the environmental perception module, and perform standardized processing;

[0178] Model construction: Build a support vector machine model and use historical data to train the model. The regression function of the support vector machine is expressed as:

[0179]

[0180] Where f(x) is the predicted environmental control output (such as heater power, air conditioning set temperature, etc.), α is the Lagrange multiplier corresponding to the weight of the support vector, and y i is the category label of the support vector, K(x i,x) is the kernel function, which represents the mapping of input data in high-dimensional space, and b is the bias term used to adjust the decision boundary;

[0181] Generation of environmental control strategies: Input the current environmental data (such as temperature, humidity, light intensity, etc.) into the trained support vector machine model, and the model will output the corresponding environmental control strategies, including:

[0182] Heater power setting: Based on the current temperature and the target temperature, the model outputs the optimal power setting for the heater;

[0183] Air conditioning set temperature: Based on the current temperature and humidity, the model predicts the air conditioning set temperature;

[0184] Humidifier / dehumidifier working status: Based on the humidity data, the model predicts whether the humidifier or dehumidifier needs to be started.

[0185] The user interaction module specifically includes:

[0186] Real-time data display: The real-time environment data, inventory status, order processing progress and operation status of the warehouse are displayed through a visual interface. It supports a variety of data chart forms, such as line charts, bar charts and pie charts, which can intuitively display various indicators of warehouse management;

[0187] Operation instruction input: allows users to input operation instructions through a visual interface and manually adjust operating parameters, including inventory management, scheduling and environmental control settings. It supports multi-user authority management to ensure the security of system operations.

[0188] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0189] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A warehouse logistics management system based on artificial intelligence, characterized in that: It includes environment perception module, inventory management module, dynamic scheduling module, automatic picking module, data processing and decision support module and user interaction module, among which; The environmental perception module is equipped with multiple sensors for real-time collection of environmental data in the warehouse, including temperature, humidity, light and air quality; The inventory management module is used to monitor and manage the inventory status in the warehouse in real time, analyze the inventory data using artificial intelligence algorithms, automatically generate inventory replenishment suggestions, and realize automatic replenishment through connection with the supply chain system; The dynamic scheduling module is connected to the inventory management module and is used to dynamically optimize the warehouse layout and the order of entry and exit according to the inventory status and order requirements; The automatic picking module includes a robot control unit, which is linked with the dynamic scheduling module to perform automatic picking and handling operations of goods; The data processing and decision support module is connected to the environment perception module, the inventory management module and the dynamic scheduling module, and is used to process and analyze the data generated by the modules, use big data analysis and machine learning algorithms, provide decision support, and continuously optimize the operation strategy; The user interaction module is used to realize information interaction between users and the system, and provides real-time data display, system monitoring and operation instruction input functions. Users can view the system operation status through this module and adjust the warehouse management strategy.

2. According to claim 1, a warehouse logistics management system based on artificial intelligence is characterized in that: The environment perception module specifically includes: Temperature sensor: used to monitor the temperature data in the warehouse in real time; Humidity sensor: used to monitor humidity data in the warehouse in real time; Light sensor: used to monitor light intensity data in the warehouse; Air quality sensor: Real-time monitoring of air quality indicators, including PM2.5 concentration and carbon dioxide concentration.

3. The artificial intelligence-based warehouse logistics management system according to claim 2 is characterized in that: The inventory management module includes: Inventory monitoring unit: Install RFID readers or QR code scanning devices on each shelf and storage area in the warehouse to track the storage location and inventory quantity of each item in real time. The data is automatically updated and uploaded to the central database to achieve real-time monitoring of inventory; Inventory Analysis Unit: Uses machine learning algorithms to dynamically analyze inventory data, predict inventory demand, and generate replenishment recommendations; Automatic replenishment unit: Through integration with the supply chain system, replenishment orders are automatically generated and sent, combined with inventory analysis results to ensure timely replenishment and avoid insufficient or excessive inventory accumulation.

4. The artificial intelligence-based warehouse logistics management system according to claim 3 is characterized in that: The inventory analysis unit specifically includes: Data preprocessing: Collect and organize historical inventory data and order data in the warehouse system, including timestamps, inventory levels, and order quantities, and perform preprocessing, including missing value processing, outlier detection, and data smoothing; Time series decomposition: Perform time series decomposition on inventory data and decompose the time series into trend, seasonality and residual; Model selection and training: The machine learning algorithm selects the autoregressive integrated moving average model to predict inventory demand, and uses historical inventory data and order data to train the autoregressive integrated moving average model. The basic formula of the autoregressive integrated moving average model is expressed as: y t =c+φ1y t―1 +φ2y t―2 +…+θ1∈ t―1 +θ2∈ t―2 +∈ t ; Among them, y t is the actual value of the time series, c is a constant term, φ i is the autoregressive coefficient, θ i is the moving average coefficient, ∈ t is the error term; Inventory demand forecasting: Use the trained autoregressive integrated moving average model to predict future inventory demand; Generate replenishment suggestions: Generate replenishment suggestions based on predicted inventory requirements.

5. The artificial intelligence-based warehouse logistics management system according to claim 4 is characterized in that: The dynamic scheduling module specifically includes: Warehouse layout optimization unit: dynamically optimizes the storage location of goods inside the warehouse based on inventory data and order requirements; Inbound and outbound order optimization unit: dynamically generates inbound and outbound order based on real-time orders and inventory status; Scheduling execution unit: issues the optimized warehouse layout and warehousing and warehousing order to relevant execution equipment, including automatic picking robots and transportation equipment.

6. The artificial intelligence-based warehouse logistics management system according to claim 5 is characterized in that: The automatic picking module specifically includes: Robot control unit: controls the automatic picking robot to perform picking and handling operations of goods according to the instructions of the dynamic scheduling module; Path planning unit: Generates the optimal path for the picking robot through the Dijkstra algorithm, avoids obstacles, and reduces path length and handling time.

7. The artificial intelligence-based warehouse logistics management system according to claim 6 is characterized in that: The data processing and decision support module specifically includes: Data preprocessing unit: cleans, formats and standardizes data from environment perception, inventory management and dynamic scheduling modules; Big Data Analysis Unit: Performs in-depth analysis on pre-processed data, using K-means clustering algorithm and linear regression model to identify patterns and trends in the data; Decision support unit: Based on the analysis results and combined with machine learning algorithms, it generates optimization decision suggestions for warehouse management, including inventory adjustment, scheduling optimization and environmental control strategies, and continuously optimizes the decision model according to the operation of the system.

8. The artificial intelligence-based warehouse logistics management system according to claim 7 is characterized in that: The big data analysis unit specifically includes: Define clustering features: Select the features to be clustered, including inventory level, order volume, inbound frequency, and outbound frequency; Select the number of clusters k: Use the elbow method to select the k value. The elbow method formula is expressed as: Among them, C i is the i-th cluster, μ i is the centroid of the ith cluster, x j is the jth data point belonging to the i-th cluster; Perform K-means clustering: Use the selected k value to perform K-means clustering on the data. The K-means objective function is expressed as: Among them, J is the objective function value, which represents the sum of the squares of the distances from the data points in the cluster to the centroid; Result analysis: After clustering, each cluster is analyzed to identify data groups with similar characteristics; Application of linear regression model: select relevant independent and dependent variables and construct regression model data set; Establish a regression model: Construct a linear regression model, with the dependent variable as the target and the independent variable as the input feature, fit the model, and identify the linear relationship between the independent variable and the dependent variable. The linear regression model formula is expressed as: y=β0+β1x1+β2x2+…+β n x n +∈; Among them, y is the dependent variable, β0 is the intercept, which represents the value of the dependent variable when all independent variables are zero, β1,β2,…,β n is the regression coefficient, which indicates the influence of each variable on the dependent variable, x1, x2,…, x n is the independent variable, ∈ is the error term, which represents the part not explained by the model; Model evaluation: The R-squared formula is used to evaluate the model's fitting effect: Among them, y i is the actual value, is the model prediction value, is the mean of the actual values; Comprehensive application: Through cluster analysis, groups with similar inventory behaviors in the warehouse can be identified, and through regression analysis, long-term trends and seasonal fluctuations in inventory changes can be identified.

9. The artificial intelligence-based warehouse logistics management system according to claim 8, characterized in that: The decision support unit specifically includes: Inventory adjustment strategy: Generate inventory adjustment suggestions, including replenishment plans and inventory transfers, based on the inventory demand predicted by the inventory analysis unit; Scheduling optimization: Based on the results of the warehouse layout optimization unit and the storage order optimization unit, an optimized scheduling strategy is generated, including the optimal storage order and storage location of the goods; Environmental control strategy: Generate environmental control strategy through machine learning algorithm.

10. The artificial intelligence-based warehouse logistics management system according to claim 9, characterized in that: The user interaction module specifically includes: Real-time data display: Display the warehouse's real-time environmental data, inventory status, order processing progress and operation status through a visual interface; Operation instruction input: Allows users to enter operation instructions through a visual interface and manually adjust operating parameters, including inventory management, scheduling and environmental control settings.

Citation Information

Patent Citations

  • Warehouse logistics intelligent management method, device and equipment and storage medium

    CN116502785A

  • Warehouse logistics management system

    CN117217662A

  • Biological feed warehouse management system and method

    CN117236855A

  • Intelligent storage shelf and control system

    CN117709855A

Cited By

  • Goods dispatching and distribution management system suitable for stocker vertical warehouse

    CN119349075A

  • A goods dispatching and distribution management system suitable for a stacker vertical warehouse

    CN119349075B

  • Automatic driving vehicle dynamic pick-up management system based on multi-modal large model

    CN119659668A

  • Mobile robot performance system popularity racking method based on improved TabNet algorithm

    CN119670985A

  • Neural network-based medicine cold chain inventory optimization method and system

    CN119721914A