E-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning

Abstract

The present invention discloses a method for e-commerce intelligent warehousing optimization and dynamic scheduling based on deep learning, comprising the following steps: S1, collecting data in the warehousing environment and performing standardization processing; S2, learning the standardized data and predicting future order demand; S3, building a MoE-Transformer model and using the MoE-Transformer model to optimize SKU storage locations; S4, dividing order tasks, sorting them according to task priorities, and performing task allocation; S5, building a warehousing environment topology map, using an improved GAT to calculate the paths of execution units, and performing path optimization and dynamic adjustment; S6, updating the parameters of the MoE-Transformer model and the improved GAT, optimizing task generation and task allocation, and optimizing inventory layout and storage partitioning. The present invention utilizes the MoE-Transformer model and the improved GAT to achieve e-commerce warehousing SKU storage optimization, task scheduling, and path planning, with the advantages of intelligence, self-adaptation, efficient collaboration, and dynamic optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce intelligent warehousing optimization and scheduling, and in particular to an e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning. Background Art

[0002] With the rapid development of the e-commerce industry, the scale and complexity of e-commerce warehousing systems are increasing, requiring warehouses to efficiently handle large volumes of order and inventory data. Traditional e-commerce warehousing systems often rely on manual operations and fixed-rule task scheduling. This approach has significant limitations when faced with dynamic factors such as order fluctuations, inventory management, and equipment status changes. Traditional warehouse scheduling systems typically use rule-based path planning and task allocation methods, which cannot flexibly adapt to real-time changes in the warehouse environment, resulting in low efficiency and wasted resources.

[0003] In traditional e-commerce warehouse management, SKU storage locations are often arranged based on historical experience and, once set, are not easily changed. This fixed storage layout often leads to improper storage locations for high-frequency items when faced with demand fluctuations and order changes, increasing picking time and costs. Furthermore, traditional methods often fail to account for inter-inventory correlations and are unable to intelligently predict which items should be stored closer together and which should be distributed in different areas to improve overall picking efficiency.

[0004] Task scheduling is another key issue in warehouse management. Traditional task scheduling methods typically rely on static rules or manual experience to determine the execution order of picking tasks. This can easily lead to resource conflicts and inefficiencies when multiple tasks occur simultaneously. For example, multiple automated picking robots, robotic arms, and human pickers may be performing tasks in the warehouse at the same time. Due to the lack of a dynamic scheduling mechanism, they may encounter path conflicts, resulting in delayed task execution and wasted warehouse resources. Irrational task scheduling not only affects warehouse operational efficiency but also increases equipment idle time and energy consumption.

[0005] Existing warehouse path planning methods also have certain shortcomings. Traditional path planning algorithms, such as Dijkstra and A*, primarily calculate optimal paths based on static network models and are suitable for scenarios with relatively fixed equipment and environmental conditions. However, in the dynamic and complex e-commerce warehousing environment, path planning needs to take into account multiple factors, such as real-time order demand, the warehouse's environmental conditions, the urgency of the task, and the real-time status of the equipment. Existing path planning algorithms lack the ability to respond to these dynamic factors in real time, which can easily lead to path conflicts among equipment within the warehouse, affecting overall operational efficiency.

[0006] In recent years, with the development of deep learning and reinforcement learning technologies, the application of artificial intelligence in e-commerce warehousing has gradually increased. Deep learning technology, by automatically extracting features and learning underlying patterns in data, has been widely used in fields such as image recognition and natural language processing. However, in e-commerce warehousing systems, traditional deep learning methods rely primarily on historical data for static predictions and lack real-time adaptability to changes in the warehousing environment. For example, factors such as inventory status, order demand, and equipment location exhibit significant dynamic changes over time, and existing deep learning models often ignore the temporal relationships between these factors, limiting the accuracy and practicality of model predictions.

[0007] Furthermore, deep learning-based task scheduling and path planning face challenges in practical applications, including massive data volumes and high computational complexity. In e-commerce warehousing environments, the volume of information involved, including tasks, equipment, and paths, is enormous, and traditional deep learning models often struggle to efficiently process this massive data. While emerging technologies such as graph neural networks and graph attention networks offer significant advantages in processing graph-structured data, their application in e-commerce warehousing environments is still in the exploratory stage.

[0008] Therefore, existing technologies suffer from the following shortcomings: First, warehouse layout optimization methods lack intelligence and cannot dynamically adjust to real-time order demand and inventory status; second, existing task scheduling methods rely too much on static rules and cannot adapt to the ever-changing warehouse environment, leading to resource conflicts and low efficiency; third, path planning methods fail to fully consider dynamic factors and cannot optimize paths in real time, which makes path conflicts prone to occur and affects warehouse efficiency. Therefore, how to provide an e-commerce intelligent warehouse optimization and dynamic scheduling method based on deep learning is an urgent problem that those skilled in the art need to solve. Summary of the Invention

[0009] One objective of the present invention is to propose an e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning. The present invention uses deep learning technology to dynamically optimize SKU storage locations, task scheduling, and path planning, thereby improving the overall efficiency and flexibility of the warehousing system. By combining MoE-Transformer and improved GAT, dynamic adjustment of the warehousing environment and optimization of path conflicts are achieved, thereby improving the operational efficiency of the e-commerce warehousing system.

[0010] According to an embodiment of the present invention, a method for e-commerce intelligent warehousing optimization and dynamic scheduling based on deep learning includes the following steps:

[0011] S1. Collect inventory status data, historical order data, equipment location information, task execution records, and warehouse environment variables in the warehouse environment, and standardize the collected data to generate standardized data;

[0012] S2. Use the Transformer model to learn from standardized data, predict future order demand, and adjust replenishment strategies based on inventory status data.

[0013] S3. Build a MoE-Transformer model and use it to optimize SKU storage locations based on future order requirements, adjusting the storage locations of products.

[0014] S4. Based on future order demand, optimized inventory status, and SKU storage locations, order tasks are divided, sorted according to task priority, and assigned;

[0015] S5. Based on the task allocation results, a warehouse environment topology map is constructed. The paths of the execution units are calculated using the improved GAT. A path optimization objective function is constructed. Path optimization and dynamic adjustment are performed according to the path optimization objective function.

[0016] S6. Based on the long-term storage environment operation data, update the parameters of the MoE-Transformer model and the improved GAT to optimize task generation and task allocation, while optimizing inventory layout and storage partitioning.

[0017] Optionally, the data includes inventory status data, historical order data, equipment location information, task execution records and warehouse environment variables.

[0018] Optionally, the S3 specifically includes:

[0019] S31. Constructing a SKU storage optimization input data set, wherein the SKU storage optimization input data set includes an order demand prediction matrix, a SKU access frequency matrix, and storage area information;

[0020] S32. Calculate the storage area status matrix and SKU storage optimization feature matrix:

[0021] S={s1,s2,...,s n};

[0022]

[0023] Among them, S represents the storage area state matrix, X t represents the SKU storage optimization feature matrix, s n Indicates the storage location of SKUn in the current warehouse, f k,t represents the SKU access frequency matrix, represents the order demand forecast matrix, Indicates storage area z j Available storage capacity, Indicates the current position of the SKU k To storage area z j The shortest path distance, z j Indicates storage area information;

[0024] S33. Constructing a MoE-Transformer model, wherein the MoE-Transformer model includes an MoE layer, a gating network, and a Transformer network. The MoE layer is composed of multiple expert networks, and the gating network is used to select the most suitable expert network.

[0025] S34. Input the SKU storage optimization feature matrix into the MoE-Transformer model to obtain the output H Trans ;

[0026] S35. Predict SKU storage locations, set optimization targets, and use Adam for model training:

[0027]

[0028]

[0029] in, represents the optimization goal, represents the probability distribution of SKU in each storage area, W s and b s Represents the trainable parameters, y k,j Indicates the actual storage area. represents the predicted value, C j Represents the storage capacity of the storage area, λ represents the regularization parameter, θ represents all trainable parameters of the model, α represents the learning rate, represents the gradient of the optimization target, m and n represent the number and location of storage areas respectively, and softmax represents the activation function;

[0030] S36. Determine the final SKU storage location:

[0031]

[0032] Among them, S t+1 Indicates the final SKU storage location.

[0033] Optionally, the S34 specifically includes:

[0034] S341. Input the SKU storage optimization feature matrix into the expert network to obtain a single expert network output:

[0035] M e (X t )=ReLU(We1 X t +b e1 );

[0036] H e =ReLU(W e2 M e +b e2 );

[0037] Among them, H e represents the output of the expert network, M e represents the expert network, X t represents the SKU storage optimization feature matrix, W e1 、b e1 、W e2 and b e2 Represents trainable parameters;

[0038] S342. Output the weight of each expert network through the gating network:

[0039] G(X t )=softmax(W g X t +b g );

[0040] Among them, G(X t ) represents the weight of each expert network, W g and b g represents the gating network parameters;

[0041] S343. Calculate the output of the MoE layer:

[0042]

[0043] Among them, H MoE Represents the output of the MoE layer;

[0044] S344. Use the multi-head attention mechanism to calculate the output of the Transformer network:

[0045] Q=W q H MoE ,K=W k H MoE ,V=W v H MoE ;

[0046]

[0047] H Trans =LN(ReLU(W t Z+b t ));

[0048] Among them, Z represents the output of the multi-head attention mechanism, LN represents layer normalization, Q, K and V represent the vectors of query, key and value, and W q 、W k and W v The weight matrix representing the query, key, and value, d k represents the dimension of the query vector Q, H Trans Represents the final output of the Transformer network, LN represents layer normalization, and W t and b t Represents the Transformer network parameters.

[0049] Optionally, the execution unit includes an AGV, a robotic arm, and a manual picker.

[0050] Optionally, the S5 specifically includes:

[0051] S51. Construct a warehouse environment topology graph G = (V, E) and define a path weight matrix. V in the warehouse environment topology graph represents a set of key nodes in the warehouse, and E in the warehouse environment topology graph represents an edge set of accessible paths within the warehouse:

[0052] W i,j =d i,j +βC i,j +γL i,j ;

[0053] Among them, W i,j Represents the path weight matrix, which is the cost from path i to path j, d i,j represents the Euclidean distance between path i and path j, C i,j Indicates the channel congestion level between path i and path j, L i,j represents the historical path usage frequency from path i to path j, β and γ represent the adjustment weights of path congestion and historical usage rate;

[0054] S52. Generate a task path request for the execution unit based on the SKU storage location and the execution unit status:

[0055]

[0056] Among them, P R Represents the path request set, e p,t represents the current position of execution unit p at time t, Indicates that SKUk is in storage area z j The storage coordinates of It means "any";

[0057] S53, using the improved GAT to calculate path features and generate a node feature matrix;

[0058] S54. Calculate the optimal path score:

[0059]

[0060] Among them, P score (i,j) represents the optimal path score, W (l) represents the feature weight calculated by the improved GAT at layer l, represents the updated representation of node i at layer l, T i,j represents the time weight from path i to path j, represents the frequency of use of path i to path j in historical tasks, ω1, ω2 and ω3 represent trainable path scoring weight parameters, L represents the number of layers of the improved GAT, C i,j represents the channel congestion degree between path i and path j, e i,j represents edge features, W2 represents the trainable weight matrix;

[0061] S55. Calculate the optimal path based on the optimal path score:

[0062] P optimal =argmin P ∑ (i,j)∈P P score (i,j);

[0063] Among them, P optimal represents the path with the minimum cost in the path set P, argmin represents the variable value that makes the function achieve the minimum value, and P represents the path set;

[0064] S56. Construct a path optimization objective function and dynamically adjust the path according to the path optimization objective function:

[0065]

[0066] P' optimal =P optimal ∪{(i′,j′)|C i',j' <θ};

[0067] in, represents the path optimization objective function, represents the path conflict cost of execution unit p at time t, λ1 represents the path conflict adjustment coefficient, P' optimal represents the set of optimized paths, θ represents the path switching cost threshold, C i',j' represents the channel congestion degree between path i' and path j', {} represents a set, ∪ represents the "and" operation, W i,j represents the path weight matrix;

[0068] S57. Output the final optimized path set:

[0069] P * =P' optimal ;

[0070] Among them, P * Represents the final optimized path set.

[0071] Optionally, the S53 specifically includes:

[0072] S531. Constructing the input of graph neural network:

[0073]

[0074] Among them, H (0) represents the initial node feature matrix, represents the initial features of node i, V represents the key node set in the warehouse, include:

[0075] Node type t i : Storage area t i =1, picking station t i =2, conveyor belt interface t i =3, Shipping port t i =4;

[0076] Node coordinate x i ,y i : The absolute position of the node in the warehouse layout;

[0077] Channel width w i : The width of the path where the node is located;

[0078] Picking point flow f i : The historical frequency of picking tasks at the node's location;

[0079] Historical task completion time τ i : reflects the average time required to execute the task at this point in the past;

[0080] S532, constructing an edge feature matrix;

[0081] E i,j ={e i,j |(i,j)∈E};

[0082] Among them, E i,j represents the edge feature matrix, which is the feature of path i to path j. E represents the edge set of the accessible path inside the warehouse. i,j include:

[0083] Physical distance di,j : The Euclidean distance between path i and path j;

[0084] Path channel congestion weight C i,j : The congestion level of the channel between path i and path j;

[0085] Path usage frequency L i,j : The historical path usage frequency from path i to path j;

[0086] Path accessibilitya i,j :If the path is passable, then a i,j =1, otherwise a i,j =0;

[0087] S533. Initialize node feature matrix embedding:

[0088]

[0089] Among them, x i represents the original features of node i, represents the initial embedding matrix, represents the bias term;

[0090] S534, using the multi-head attention mechanism to calculate the information interaction between nodes:

[0091]

[0092] in, represents the attention weight of the h-th attention head between path i and path j, W h represents the trainable parameter matrix of the h-th attention head, represents the features of node j of the lth attention head, represents the feature of node k of the lth attention head, a h represents the parameter vector of attention calculation, T represents the transpose operation, || represents the vector concatenation operation, N(i) represents the set of neighbor nodes of node i, LeakyReLU represents the activation function, and exp represents the natural exponential function;

[0093] S535, update the node representation and obtain the node feature matrix H (L) :

[0094]

[0095] in, represents the updated representation of node i after calculation in layer l+1, H represents the number of attention heads, σ represents the nonlinear activation function, and H (L) Represents the node feature matrix calculated by the final L layer.

[0096] The beneficial effects of the present invention are:

[0097] First, in terms of task scheduling, the present invention uses a deep learning model to intelligently divide order tasks, and sort and allocate them based on task priority. Compared with the traditional fixed rule scheduling method, the present invention can optimize tasks based on the urgency of the order, inventory distribution, and the status of the execution unit, effectively avoiding task accumulation and resource waste, and improving the overall throughput of the warehousing system. In addition, the present invention introduces an improved GAT for path optimization. Compared with the static path planning method, the present invention can dynamically calculate the optimal picking path of the execution unit, calculate the path weight in combination with the warehouse environment topology map, and adaptively adjust the path selection through the attention mechanism to reduce path conflicts and channel congestion, thereby improving the efficiency and stability of task execution.

[0098] Secondly, in terms of path optimization, the present invention breaks through the limitation of traditional path planning algorithms that only consider static weights. It combines multi-dimensional data such as historical path utilization, channel congestion, and equipment operating status to dynamically adjust the path weight matrix and calculate the optimal path score based on the improved GAT. This method introduces a multi-head attention mechanism in the path search process, so that path selection can more accurately adapt to the real-time warehousing environment. In addition, the present invention realizes dynamic adjustment of path conflicts by constructing a path optimization objective function, ensuring that multiple execution units will not experience path congestion or resource competition during task execution, thereby improving the overall operational efficiency of the warehousing system.

[0099] Finally, the present invention also optimizes the MoE-Transformer and the improved GAT model through long-term warehouse environment operation data, so that the system can continuously learn and optimize task generation, task allocation and path planning strategies. Compared with the existing warehouse management system, the present invention provides a more adaptive intelligent method, which can dynamically adjust the warehouse layout, task scheduling and path optimization strategies in the case of a constantly changing warehouse environment, thereby improving the degree of automation and intelligence of the warehouse system. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0101] Figure 1 This is a flowchart of an e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning proposed by the present invention;

[0102] Figure 2 This is a flow chart of path optimization based on improved GAT for an e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning proposed by the present invention. DETAILED DESCRIPTION

[0103] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0104] refer to Figure 1 and Figure 2 , a deep learning-based e-commerce intelligent warehousing optimization and dynamic scheduling method, including the following steps:

[0105] S1. Collect inventory status data, historical order data, equipment location information, task execution records, and warehouse environment variables in the warehouse environment, and standardize the collected data to generate standardized data;

[0106] S2. Use the Transformer model to learn from standardized data, predict future order demand, and adjust replenishment strategies based on inventory status data.

[0107] S3. Build a MoE-Transformer model and use it to optimize SKU storage locations based on future order requirements, adjusting the storage locations of products.

[0108] S4. Based on future order demand, optimized inventory status, and SKU storage locations, order tasks are divided, sorted according to task priority, and assigned;

[0109] S5. Based on the task allocation results, a warehouse environment topology map is constructed. The paths of the execution units are calculated using the improved GAT. A path optimization objective function is constructed. Path optimization and dynamic adjustment are performed according to the path optimization objective function.

[0110] S6. Based on the long-term storage environment operation data, update the parameters of the MoE-Transformer model and the improved GAT to optimize task generation and task allocation, while optimizing inventory layout and storage partitioning.

[0111] In this embodiment, the data includes inventory status data, historical order data, equipment location information, task execution records and warehouse environment variables.

[0112] In this embodiment, S3 specifically includes:

[0113] S31. Constructing a SKU storage optimization input data set, wherein the SKU storage optimization input data set includes an order demand prediction matrix, a SKU access frequency matrix, and storage area information;

[0114] S32. Calculate the storage area status matrix and SKU storage optimization feature matrix:

[0115] S={s1,s2,...,s n};

[0116]

[0117] Among them, S represents the storage area state matrix, X t represents the SKU storage optimization feature matrix, s n Indicates the storage location of SKUn in the current warehouse, f k,t represents the SKU access frequency matrix, represents the order demand forecast matrix, Indicates storage area z j Available storage capacity, Indicates the current position of the SKU k To storage area z j The shortest path distance, z j Indicates storage area information;

[0118] S33. Constructing a MoE-Transformer model, wherein the MoE-Transformer model includes an MoE layer, a gating network, and a Transformer network. The MoE layer is composed of multiple expert networks, and the gating network is used to select the most suitable expert network.

[0119] S34. Input the SKU storage optimization feature matrix into the MoE-Transformer model to obtain the output H Trans ;

[0120] S35. Predict SKU storage locations, set optimization targets, and use Adam for model training:

[0121]

[0122] in, represents the optimization goal, represents the probability distribution of SKU in each storage area, W s and b s Represents the trainable parameters, y k,j Indicates the actual storage area. represents the predicted value, C j Represents the storage capacity of the storage area, λ represents the regularization parameter, θ represents all trainable parameters of the model, α represents the learning rate, represents the gradient of the optimization target, m and n represent the number and location of storage areas respectively, and softmax represents the activation function;

[0123] S36. Determine the final SKU storage location:

[0124]

[0125] Among them, S t+1 Indicates the final SKU storage location.

[0126] In this embodiment, the S34 specifically includes:

[0127] S341. Input the SKU storage optimization feature matrix into the expert network to obtain a single expert network output:

[0128] M e (X t )=ReLU(W e1 X t +b e1 );

[0129] H e =ReLU(W e2 M e +b e2 );

[0130] Among them, H e represents the output of the expert network, M e represents the expert network, X t represents the SKU storage optimization feature matrix, W e1 、b e1 、W e2 and b e2 Represents trainable parameters;

[0131] S342. Output the weight of each expert network through the gating network:

[0132] G(X t )=softmax(W g X t +b g );

[0133] Among them, G(X t ) represents the weight of each expert network, W g and b g Represents the gate network parameters, and softmax represents the activation function;

[0134] S343. Calculate the output of the MoE layer:

[0135]

[0136] Among them, H MoE Represents the output of the MoE layer;

[0137] S344. Use the multi-head attention mechanism to calculate the output of the Transformer network:

[0138] Q=W q H MoE ,K=W k H MoE ,V=W v H MoE ;

[0139]

[0140] H Trans =LN(ReLU(W t Z+b t ));

[0141] Among them, Z represents the output of the multi-head attention mechanism, LN represents layer normalization, Q, K and V represent the vectors of query, key and value, and W q 、W k and W v The weight matrix representing the query, key, and value, d k represents the dimension of the query vector Q, H Trans Represents the final output of the Transformer network, LN represents layer normalization, and W t and b t Represents the Transformer network parameters.

[0142] In this embodiment, the execution unit includes an AGV, a robotic arm, and a manual picker.

[0143] In this embodiment, the S5 specifically includes:

[0144] S51. Construct a warehouse environment topology graph G = (V, E) and define a path weight matrix. V in the warehouse environment topology graph represents a set of key nodes in the warehouse, and E in the warehouse environment topology graph represents an edge set of accessible paths within the warehouse:

[0145] W i,j =d i,j +βC i,j +γL i,j ;

[0146] Among them, W i,j Represents the path weight matrix, which is the cost from path i to path j, d i,j represents the Euclidean distance between path i and path j, C i,j Indicates the channel congestion level between path i and path j, L i,jrepresents the historical path usage frequency from path i to path j, β and γ represent the adjustment weights of path congestion and historical usage rate;

[0147] S52. Generate a task path request for the execution unit based on the SKU storage location and the execution unit status:

[0148]

[0149] Among them, P R Represents the path request set, e p,t represents the current position of execution unit p at time t, Indicates that SKUk is in storage area z j The storage coordinates of It means "any";

[0150] S53, using the improved GAT to calculate path features and generate a node feature matrix;

[0151] S54. Calculate the optimal path score:

[0152]

[0153] Among them, P score (i,j) represents the optimal path score, W (l) represents the feature weight calculated by the improved GAT at layer l, represents the updated representation of node i at layer l, T i,j represents the time weight from path i to path j, represents the frequency of use of path i to path j in historical tasks, ω1, ω2 and ω3 represent trainable path scoring weight parameters, L represents the number of layers of the improved GAT, C i,j represents the channel congestion degree between path i and path j, e i,j represents edge features, W2 represents the trainable weight matrix;

[0154] S55. Calculate the optimal path based on the optimal path score:

[0155] P optimal =argmin P ∑ (i,j)∈P P score (i,j);

[0156] Among them, P optimal represents the path with the minimum cost in the path set P, argmin represents the variable value that makes the function achieve the minimum value, and P represents the path set;

[0157] S56. Construct a path optimization objective function and dynamically adjust the path according to the path optimization objective function:

[0158]

[0159] P' optimal =P optimal ∪{(i′,j′)|C i',j' <θ};

[0160] in, represents the path optimization objective function, represents the path conflict cost of execution unit p at time t, λ1 represents the path conflict adjustment coefficient, P' optimal represents the set of optimized paths, θ represents the path switching cost threshold, C i',j' represents the channel congestion degree between path i' and path j', {} represents a set, ∪ represents the "and" operation, W i,j represents the path weight matrix;

[0161] S57. Output the final optimized path set:

[0162] P * =P' optimal ;

[0163] Among them, P * Represents the final optimized path set.

[0164] In this embodiment, the S53 specifically includes:

[0165] S531. Constructing the input of graph neural network:

[0166]

[0167] Among them, H (0) represents the initial node feature matrix, represents the initial features of node i, V represents the key node set in the warehouse, include:

[0168] Node type t i : Storage area t i =1, picking station t i =2, conveyor belt interface t i =3, Shipping port t i =4;

[0169] Node coordinate x i ,y i : The absolute position of the node in the warehouse layout;

[0170] Channel width w i : The width of the path where the node is located;

[0171] Picking point flow f i : The historical frequency of picking tasks at the node's location;

[0172] Historical task completion time τ i : reflects the average time required to execute the task at this point in the past;

[0173] S532, constructing an edge feature matrix;

[0174] E i,j ={e i,j |(i,j)∈E};

[0175] Among them, E i,j represents the edge feature matrix, which is the feature of path i to path j. E represents the edge set of the accessible path inside the warehouse. i,j include:

[0176] Physical distance d i,j : The Euclidean distance between path i and path j;

[0177] Path channel congestion weight C i,j : The congestion level of the channel between path i and path j;

[0178] Path usage frequency L i,j : The historical path usage frequency from path i to path j;

[0179] Path accessibilitya i,j :If the path is passable, then a i,j =1, otherwise a i,j =0;

[0180] S533. Initialize node feature matrix embedding:

[0181]

[0182] Among them, x i represents the original features of node i, represents the initial embedding matrix, represents the bias term;

[0183] S534, using the multi-head attention mechanism to calculate the information interaction between nodes:

[0184]

[0185] in, represents the attention weight of the h-th attention head between path i and path j, W h represents the trainable parameter matrix of the h-th attention head, represents the features of node j of the lth attention head, represents the feature of node k of the lth attention head, a h represents the parameter vector of attention calculation, T represents the transpose operation, || represents the vector concatenation operation, N(i) represents the set of neighbor nodes of node i, LeakyReLU represents the activation function, and exp represents the natural exponential function;

[0186] S535, update the node representation and obtain the node feature matrix H (L) :

[0187]

[0188] in, represents the updated representation of node i after calculation in layer l+1, H represents the number of attention heads, σ represents the nonlinear activation function, and H (L) Represents the node feature matrix calculated by the final L layer.

[0189] Example 1:

[0190] To verify the feasibility of the present invention, it was applied to an e-commerce intelligent warehousing center. This warehouse processes over 30,000 orders daily, stores 50,000 SKUs, and has a storage area of ​​approximately 8,000 square meters. The automated execution unit includes 300 automated guided vehicles (AGVs), 100 robotic arms, and several manual pickers. However, in actual operation, the warehouse faced problems such as an unreasonable SKU storage layout, inefficient task scheduling, and severe path planning conflicts. These issues resulted in extended order fulfillment times, limited warehouse throughput, and impacted overall operational efficiency.

[0191] In this warehousing environment, the present invention performs SKU storage optimization based on MoE-Transformer and combines it with improved GAT for path optimization to improve the operational efficiency of the warehouse. First, the present invention uses Transformer to predict future order demand and dynamically optimizes SKU storage locations, so that high-frequency SKUs have better storage locations, reducing associated storage conflicts between SKUs, thereby shortening the picking path and reducing the walking distance of automated guided vehicles and manual pickers. Secondly, the present invention combines improved GAT to calculate the optimal picking path of the execution unit in the warehouse environment, dynamically adjusts the path weight, avoids automated guided vehicle path conflicts, and improves equipment coordination efficiency. Finally, through long-term data accumulation, the model parameters are continuously optimized to achieve intelligent upgrades of the warehousing system.

[0192] During implementation, the invention was deployed in the core business system of the e-commerce warehouse and tested in real-world operations for six months. During the testing period, several key metrics were collected, including SKU picking time, order fulfillment time, path conflict rate, and equipment utilization, and compared with traditional warehouse scheduling methods.

[0193] Table 1 Experimental data comparison table

[0194]

[0195]

[0196] From the perspective of SKU storage optimization, the present invention optimizes the SKU access frequency and storage areas through the MoE-Transformer model, reducing the storage areas of high-frequency SKUs from 4.2 to 2.1, reducing the dispersion of SKUs in the warehouse, and improving picking efficiency. At the same time, the optimized SKU storage strategy reduces the average order picking time from 28.5 minutes to 19.3 minutes, a decrease of 32.3%, effectively shortening the order processing time. In addition, due to the more reasonable SKU storage location, the average length of the picking path is reduced from 22 meters to 13 meters, a reduction of 37.8%, reducing the driving distance of pickers and automatic guided vehicles in the warehouse and improving order fulfillment efficiency.

[0197] In terms of path planning, traditional automated guided vehicle path scheduling methods have path conflict problems, especially during peak hours, when the path conflict rate is as high as 12.4%, causing the automated guided vehicles to frequently get blocked during picking tasks, affecting the warehouse throughput capacity. The present invention uses an improved GAT for dynamic path optimization and combines it with a multi-head attention mechanism to calculate the optimal path, which reduces the path conflict rate to 4.6%, a reduction of 63.1%, and improves the stability of AGV task scheduling in a warehouse environment. At the same time, the average waiting time of the automated guided vehicle is reduced from 3.5 minutes to 1.8 minutes, a reduction of 48.6%, indicating that the optimized path planning method significantly reduces the equipment waiting time and makes the automated guided vehicle task scheduling smoother.

[0198] In terms of task scheduling, the present invention combines order priority, execution unit status and other information to allocate tasks, which increases the task completion rate from 72.3% to 88.7%, an increase of 19.4%, fully utilizing warehouse resources and reducing task backlogs. At the same time, the utilization rate of execution units has also increased significantly, from the original 72.3% to 88.7%, an increase of 16.4%, further demonstrating that the optimization of intelligent task scheduling plays a significant role in improving the efficiency of automated guided vehicles and manual pickers. The average daily order throughput of the optimized warehousing system increased from 30,000 orders to 38,500 orders, an increase of 28.3%, indicating that task scheduling and path optimization have a positive impact on the overall throughput capacity of the warehouse.

[0199] In terms of order processing capacity during peak periods, before the optimization of the present invention, the warehouse's order throughput during big promotions could only be maintained at 25,000 orders / day, and the throughput capacity was lower than that of normal days. However, after adopting the optimized scheduling and path planning of the present invention, the average daily order processing volume during peak periods increased to 35,000 orders / day, an increase of 36.9%, indicating that the optimization strategy of the present invention has a strong ability to relieve the pressure on the warehousing system during peak periods and can better adapt to order fluctuations. In addition, under the condition of intensive automated guided vehicle tasks during peak periods, the optimized scheduling strategy of the present invention reduces the average waiting time of automated guided vehicles from 3.5 minutes to 1.8 minutes, a decrease of 48.6%, which greatly reduces the inefficiency of execution units caused by task accumulation.

[0200] In terms of cost and economic benefits, traditional warehousing operations result in high operating costs and labor intervention costs due to path conflicts and inefficient task scheduling. This invention reduces unnecessary equipment operation and labor costs through intelligent scheduling, resulting in a 11.8% reduction in the warehouse's overall operating costs, a 9.4% decrease in order fulfillment costs, and a 6.2% increase in overall profit margins. Furthermore, due to the significant reduction in order fulfillment time, the user experience has been optimized, with customer satisfaction ratings increasing from 4.2 / 5 to 4.57 / 5, an 8.7% increase. This demonstrates that the optimized warehousing system not only improves efficiency but also enhances the quality of e-commerce logistics services.

[0201] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A method for e-commerce intelligent warehousing optimization and dynamic scheduling based on deep learning, characterized in that: The steps include: S1. Collect data in the storage environment and standardize the collected data to generate standardized data; S2. Use the Transformer model to learn from standardized data, predict future order demand, and adjust replenishment strategies based on inventory status data. S3. Build a MoE-Transformer model and use it to optimize SKU storage locations based on future order requirements, adjusting the storage locations of products. S4. Based on future order demand, optimized inventory status, and SKU storage locations, order tasks are divided, sorted according to task priority, and assigned; S5. Based on the task allocation results, a warehouse environment topology map is constructed. The paths of the execution units are calculated using the improved GAT. A path optimization objective function is constructed. Path optimization and dynamic adjustment are performed according to the path optimization objective function. S6. Based on the long-term storage environment operation data, update the parameters of the MoE-Transformer model and the improved GAT to optimize task generation and task allocation, while optimizing inventory layout and storage partitioning; The S5 specifically includes: S51. Construct a warehouse environment topology graph G = (V, E) and define a path weight matrix. V in the warehouse environment topology graph represents a set of key nodes in the warehouse, and E in the warehouse environment topology graph represents an edge set of accessible paths within the warehouse: W i,j =d i,j +βC i,j +γL i,j ; Among them, W i,j Represents the path weight matrix, which is the cost from path i to path j, d i,j represents the Euclidean distance between path i and path j, C i,j Indicates the channel congestion level between path i and path j, L i,j represents the historical path usage frequency from path i to path j, β and γ represent the adjustment weights of path congestion and historical usage rate; S52. Generate a task path request for the execution unit based on the SKU storage location and the execution unit status: Among them, P R Represents the path request set, e p,t represents the current position of execution unit p at time t, Indicates that SKU k is in storage area z j The storage coordinates of It means "any"; S53, using the improved GAT to calculate path features and generate a node feature matrix; S54. Calculate the optimal path score: Among them, P score (i,j) represents the optimal path score, W (l) represents the feature weight calculated by the improved GAT at layer l, represents the updated representation of node i at layer l, T i,j represents the time weight from path i to path j, represents the frequency of use of path i to path j in historical tasks, ω1, ω2 and ω3 represent trainable path scoring weight parameters, L represents the number of layers of the improved GAT, C i,j represents the channel congestion degree between path i and path j, e i,j represents edge features, W2 represents the trainable weight matrix; S55. Calculate the optimal path based on the optimal path score: P optimal =argmin P ∑ (i,j)∈P P score (i,j); Among them, P optimal represents the path with the minimum cost in the path set P, argmin represents the variable value that makes the function achieve the minimum value, and P represents the path set; S56. Construct a path optimization objective function and dynamically adjust the path according to the path optimization objective function: in, represents the path optimization objective function, represents the path conflict cost of execution unit p at time t, λ1 represents the path conflict adjustment coefficient, P′ optimal represents the set of optimized paths, θ represents the path switching cost threshold, C i′,j′ represents the channel congestion degree between path i′ and path j′, {} represents a set, ∪ represents the “and” operation, W i,j represents the path weight matrix; S57. Output the final optimized path set: P * =P′ optimal ; Among them, P * Represents the final optimized path set; The S53 specifically includes: S531. Constructing the input of graph neural network: Among them, H (0) represents the initial node feature matrix, represents the initial features of node i, V represents the key node set in the warehouse, include: Node type t i : Storage area t i =1, picking station t i =2, conveyor belt interface t i =3, Shipping port t i =4; Node coordinate x i ,y i : The absolute position of the node in the warehouse layout; Channel width w i : The width of the path where the node is located; Picking point flow f i : The historical frequency of picking tasks at the node's location; Historical task completion time τ i : reflects the average time required to execute the task at this point in the past; S532, constructing an edge feature matrix; HAVE BEEN i,j ={e i,j |(i,j)∈E}; Among them, E i,j represents the edge feature matrix, which is the feature of path i to path j. E represents the edge set of the accessible path inside the warehouse. i,j include: Physical distance d i,j : Euclidean distance between path i and path j; Path channel congestion weight C i,j : The congestion level of the channel between path i and path j; Path usage frequency L i,j : The historical path usage frequency from path i to path j; Path accessibilitya i,j :If the path is passable, then a i,j =1, otherwise a i,j =0; S533. Initialize node feature matrix embedding: Among them, x i represents the original features of node i, represents the initial embedding matrix, represents the bias term; S534, using the multi-head attention mechanism to calculate the information interaction between nodes: in, represents the attention weight of the h-th attention head between path i and path j, W h represents the trainable parameter matrix of the h-th attention head, represents the features of node j of the lth attention head, represents the feature of node k of the lth attention head, a h represents the parameter vector of attention calculation, T represents the transpose operation, || represents the vector concatenation operation, N(i) represents the set of neighbor nodes of node i, LeakyReLU represents the activation function, and exp represents the natural exponential function; S535, update the node representation and obtain the node feature matrix H (L) : in, represents the updated representation of node i after calculation in layer l+1, H represents the number of attention heads, σ represents the nonlinear activation function, and H (L) Represents the node feature matrix calculated by the final L layer.

2. The e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning according to claim 1 is characterized in that: The data includes inventory status data, historical order data, equipment location information, task execution records and warehouse environment variables.

3. The e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning according to claim 1 is characterized in that: The S3 specifically includes: S31. Constructing a SKU storage optimization input data set, wherein the SKU storage optimization input data set includes an order demand prediction matrix, a SKU access frequency matrix, and storage area information; S32. Calculate the storage area status matrix and SKU storage optimization feature matrix: S={s1,s2,...,s n }; Among them, S represents the storage area state matrix, X t represents the SKU storage optimization feature matrix, s n Indicates the storage location of SKUn in the current warehouse, f k,t represents the SKU access frequency matrix, represents the order demand forecast matrix, Indicates storage area z j Available storage capacity, Indicates the current position of the SKU k To storage area z j The shortest path distance, z j Indicates storage area information; S33. Constructing a MoE-Transformer model, wherein the MoE-Transformer model includes an MoE layer, a gating network, and a Transformer network. The MoE layer is composed of multiple expert networks, and the gating network is used to select the most suitable expert network. S34. Input the SKU storage optimization feature matrix into the MoE-Transformer model to obtain the output H Trans ; S35. Predict SKU storage locations, set optimization targets, and use Adam for model training: in, represents the optimization goal, represents the probability distribution of SKU in each storage area, W s and b s Represents the trainable parameters, y k,j Indicates the actual storage area. represents the predicted value, C j Represents the storage capacity of the storage area, λ represents the regularization parameter, θ represents all trainable parameters of the model, α represents the learning rate, represents the gradient of the optimization objective; S36. Determine the final SKU storage location: Among them, S t+1 Indicates the final SKU storage location.

4. The e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning according to claim 2 is characterized in that: The S34 specifically includes: S341. Input the SKU storage optimization feature matrix into the expert network to obtain a single expert network output: M e (X t )=ReLU(W e1 X t +b e1 ): A e =ReLU(W e2 M e +b e2 ); Among them, H e represents the output of the expert network, M e represents the expert network, X t represents the SKU storage optimization feature matrix, W e1 、b e1 、W e2 and b e2 Represents trainable parameters; S342. Output the weight of each expert network through the gating network: G(X t )=softmax(W g X t +b g ); Among them, G(X t ) represents the weight of each expert network, W g and b g Represents the gate network parameters, and softmax represents the activation function; S343. Calculate the output of the MoE layer: Among them, H MoE Represents the output of the MoE layer; S344. Use the multi-head attention mechanism to calculate the output of the Transformer network: Q=W q H MoE ,K=W k H MoE ,V=W v H MoE ; H Trans =LN(ReLU(W t Z+b t )); Among them, Z represents the output of the multi-head attention mechanism, LN represents layer normalization, Q, K and V represent the vectors of query, key and value, and W q 、W k and W v The weight matrix representing the query, key, and value, d k represents the dimension of the query vector Q, H Trans Represents the final output of the Transformer network, LN represents layer normalization, and W t and b t Represents the Transformer network parameters.

5. The e-commerce intelligent warehousing optimization and dynamic scheduling method based on deep learning according to claim 4 is characterized in that: The execution unit includes AGV, robotic arms and manual pickers.

Images