Warehouse management information system and method based on supply chain cloud platform

Abstract

The embodiment of the invention provides a warehouse management information system and method based on a supply chain cloud platform. The method comprises the following steps: obtaining goods information and corresponding warehouse site path information; decomposing the goods atlas information into multiple pieces of sub-atlas information according to warehouse site positions; layering the sub-atlas information into goods atlas hierarchical samples; inputting the goods atlas hierarchical sample into a conditional generative adversarial neural network to obtain an output simulated goods atlas hierarchical sample; inputting the simulated goods graph hierarchical sample into a convolutional neural network for training to obtain a trained convolutional neural network; new goods information is input into the convolutional neural network, and output path information and warehouse management scheduling information are obtained.In the embodiment of the invention, dimension reduction is performed on the multi-dimensional supply chain data, so that hierarchical sample data can be obtained, the training accuracy of a virtual sample generation model is improved, and the training efficiency is improved. The scheduling information related to each warehouse with the optimal cost and the optimal path is obtained, and the management efficiency of the goods supply chain is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a warehouse management system based on a supply chain cloud platform, a warehouse management method based on a supply chain cloud platform, a computer device and a storage medium. Background Art

[0002] Supply chain management, cargo management and warehouse management play a vital role in modern business operations. Supply chain management involves all links from raw material procurement to final product delivery to consumers, including the management of logistics, information flow and capital flow. Effective supply chain management can improve the operational efficiency of enterprises, reduce costs and enhance market competitiveness. The core components of the supply chain include suppliers, manufacturers, distributors, retailers and end customers. Each link requires efficient coordination to ensure the smooth operation of the entire supply chain; warehouse management is the core component of supply chain management, responsible for key links such as storage, sorting, loading and distribution of goods. The warehouse is not only a storage place for goods, but also an important operation center, which plays a vital role in the stability and efficient operation of the supply chain. However, the efficiency of existing warehouse management still needs to be improved. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a warehouse management method based on a supply chain cloud platform, a warehouse management system based on a supply chain cloud platform, a computer device and a storage medium that overcome the above problems or at least partially solve the above problems.

[0004] In order to solve the above problems, an embodiment of the present invention discloses a warehouse management method based on a supply chain cloud platform, including:

[0005] Get the product information and the corresponding warehouse site path information;

[0006] Generate product map information according to the product information and corresponding warehouse site path information;

[0007] Decomposing the product map information into a plurality of sub-map information according to the warehouse site location;

[0008] Layering the sub-graph information into product graph layer samples;

[0009] Inputting the product graph level sample into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining an output simulated product graph level sample;

[0010] Inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network;

[0011] The new product information is input into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0012] Preferably, the product information includes product name information and product feature information; the warehouse site path information includes warehouse site location and path information; and the generating of product map information according to the product information and the corresponding warehouse site path information includes:

[0013] Determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information using path information as a connection relationship, and generate product map information.

[0014] Preferably, the sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information; the decomposing the product graph information into a plurality of sub-graph information according to the warehouse site location includes:

[0015] Extract specific warehouse site locations or specific product feature information from product map information;

[0016] Obtaining product name information and path information associated with the specific warehouse site location or specific product feature information;

[0017] Determine the specific warehouse site location or specific product feature information and product name information and path information as the first sub-graph information;

[0018] Traverse the product map information, return to the step of extracting the specific warehouse site location or specific product feature information in the product map information, and obtain the second sub-map information to the Nth sub-map information.

[0019] Preferably, the step of stratifying the sub-graph information into product graph layer samples includes:

[0020] The module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information are calculated, and a stratification operation is performed according to the module clustering coefficients to obtain a hierarchical sample of a product graph.

[0021] Preferably, the step of inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples comprises:

[0022] Setting the conditional information of the conditional generative adversarial neural network to an iteration number greater than twice the number of sub-graph information;

[0023] Applying the conditional information to the generator and discriminator of a conditional generative adversarial neural network;

[0024] The product map hierarchy samples are input into a conditional generative adversarial neural network, and the conditional generative adversarial neural network is trained to obtain output simulated product map hierarchy samples.

[0025] Preferably, the step of inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network comprises:

[0026] Calculate the cost loss coefficient through the warehouse site path information;

[0027] Adding the cost loss coefficient to the loss function of the convolutional neural network;

[0028] The simulated product atlas hierarchical samples are input into a convolutional neural network for training to obtain a trained convolutional neural network.

[0029] An embodiment of the present invention provides a warehouse management system based on a supply chain cloud platform, including:

[0030] Path information acquisition module, used to obtain product information and corresponding warehouse site path information;

[0031] A generation module, used to generate product map information according to the product information and corresponding warehouse site path information;

[0032] A decomposition module, used for decomposing the product map information into a plurality of sub-map information according to the warehouse site location;

[0033] A stratification module, used for stratifying the sub-map information into product map layer samples;

[0034] A sample output module, used to input the product graph hierarchy sample into a conditional generative adversarial neural network, train the conditional generative adversarial neural network, and obtain an output simulated product graph hierarchy sample;

[0035] A training module, used for inputting the simulated product graph layer samples into the convolutional neural network for training to obtain a trained convolutional neural network;

[0036] The scheduling module is used to input new product information into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0037] Preferably, the product information includes product name information and product feature information; the warehouse site path information includes warehouse site location and path information; and the generation module includes:

[0038] The first determination submodule is used to determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information with the path information as the connection relationship, and generate product map information.

[0039] An embodiment of the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned steps of warehouse management based on a supply chain cloud platform when executing the computer program.

[0040] An embodiment of the present invention further discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of warehouse management based on a supply chain cloud platform are implemented.

[0041] The embodiments of the present invention include the following advantages:

[0042] In an embodiment of the present invention, the warehouse management method based on the supply chain cloud platform includes: obtaining product information and corresponding warehouse site path information; generating product map information according to the product information and the corresponding warehouse site path information; decomposing the product map information into multiple sub-map information according to the warehouse site location; stratifying the sub-map information into product map hierarchical samples; inputting the product map hierarchical samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product map hierarchical samples; inputting the simulated product map hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network; inputting new product information into the convolutional neural network to obtain output path information and warehouse management scheduling information. In an embodiment of the present invention, multi-dimensional supply chain data is reduced in dimension to obtain multi-level data, which is convenient for data processing and improves data processing efficiency. Hierarchical sample data can be obtained, so that the convergence effect of the model is better, the accuracy of virtual sample generation model training is improved, and scheduling information related to each warehouse with optimal cost and optimal path is obtained, so as to improve the management efficiency of the product supply chain and reduce management costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 It is a flowchart of a warehouse management method based on a supply chain cloud platform according to an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of product map information according to an embodiment of the present invention;

[0046] Figure 3 It is a schematic diagram of decomposition of product map information in an embodiment of the present invention;

[0047] Figure 4 It is a structural block diagram of a warehouse management system embodiment based on a supply chain cloud platform according to an embodiment of the present invention;

[0048] Figure 5 The diagram is a diagram of the internal structure of a computer device according to an embodiment. DETAILED DESCRIPTION

[0049] In order to make the technical problems, technical solutions and beneficial effects solved by the embodiments of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] In a core concept of an embodiment of the present invention, first, a variety of related supply chain information is sorted out to generate supply chain-related product knowledge graph information; then the product knowledge graph information is decomposed and layered to obtain layered samples, and the multi-dimensional supply chain data is reduced in dimension to obtain multi-level data, which is convenient for data processing and improves data processing efficiency; the layered samples are input into a conditional generative adversarial neural network to obtain output virtual samples, solve the problem of small sample number, and improve the accuracy of model training; by setting a new loss function of the intelligent model, a specific neural network is obtained, and the neural network is trained through virtual samples to obtain the output scheduling information related to each warehouse with the optimal cost and path, thereby improving the management efficiency of the product supply chain and reducing management costs.

[0051] A warehouse management method based on a supply chain cloud platform provided by an embodiment of the present invention can be applied to an application environment including a terminal and a server, the server forming a cloud platform, and the terminal can be set at multiple warehouse site locations and also applied to the application environment of the terminal. Among them, the terminal communicates with the server through a network. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The operating system of the terminal may include Android, Harmony OS, IOS, Windows Phone, Windows, etc. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0052] Reference Figure 1, shows a flowchart of a warehouse management method based on a supply chain cloud platform according to an embodiment of the present invention, which may specifically include the following steps:

[0053] Step 101, obtaining product information and corresponding warehouse site path information;

[0054] In an embodiment of the present invention, the warehouse management method is applied to a supply chain cloud platform architecture. Specifically, the supply chain cloud platform architecture may include a server cloud platform and terminal devices distributed at multiple goods warehouse sites. The server cloud platform is respectively connected to the terminal devices at the multiple goods warehouse sites for processing a variety of goods information and warehouse site path information. The embodiment of the present invention does not impose further restrictions on this.

[0055] Specifically applied to the embodiments of the present invention, the product information may include product name information and product feature information. The product feature information refers to all product-related information except the product name, which may include material number, product type, product quantity, product source, product weight, product destination, etc. The embodiments of the present invention do not impose too many restrictions on this. On the other hand, corresponding to the product information is warehouse site path information. The warehouse site path information refers to the site information and other related information of each warehouse site through which the product passes. The warehouse site path information includes warehouse site location and path information. Specifically, it may include each site address, transportation routes between each site address, average warehousing rental cost, vehicle number, average warehousing labor cost, road cost, vehicle cost, sorting processing time, etc. The embodiments of the present invention do not impose too many restrictions on the types of warehouse site path information.

[0056] Step 102, generating product map information according to the product information and the corresponding warehouse site path information;

[0057] Specific as Figure 2 As shown, the product map information is generated according to the product information and the corresponding warehouse site path information, including: determining the product name information as the first entity information, determining the warehouse site location or product feature information as the second entity attribute information, connecting the first entity information and the second entity attribute information with the path information as the connection relationship, and generating the product map information;.

[0058] First, the first entity information can be determined, and then the associated second entity attribute information can be determined through the first entity information. It should be noted that the second entity attribute information can include entity information or attribute information; that is, the associated entity information or attribute information can be extracted through the first entity information, such as through the vehicle number 1 of the product name 1, the product name 2 and the site address 1 of the same vehicle number are obtained, that is, the second entity attribute information is obtained, and then the connection relationship related to the path information of the two is obtained: vehicle number 1, transportation route 1; the two are connected through the connection relationship, and finally other attribute values ​​are added, such as product destination 1, product quantity 1, product weight 1, average storage rental cost 1, etc., to form a part of the product map information.

[0059] It is worth noting that the above-mentioned method of assembling the product map information is only a specific example of an embodiment of the present invention. The product information and the corresponding warehouse site path information can also be combined and connected into product map information in other ways. The embodiment of the present invention does not impose too many restrictions on this.

[0060] Step 103, decomposing the product map information into a plurality of sub-map information according to the warehouse site location;

[0061] Further applied to the embodiment of the present invention, the sub-graph information refers to the sub-graph information containing an entity or object information or the associated connection relationship and attribute value after decomposing the product graph information;

[0062] In an embodiment of the present invention, the sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information, wherein N represents a positive integer; the decomposing the product graph information into multiple sub-graph information according to the warehouse site location includes: extracting a specific warehouse site location or specific product feature information in the product graph information; obtaining the product name information and path information associated with the specific warehouse site location or the specific product feature information; determining the specific warehouse site location or the specific product feature information and the product name information and path information as the first sub-graph information; traversing the product graph information, returning to the step of extracting the specific warehouse site location or the specific product feature information in the product graph information, and obtaining the second sub-graph information to the Nth sub-graph information.

[0063] In the embodiment of the present invention, a specific warehouse site location or specific commodity feature information in the commodity map information is first determined, and the corresponding commodity name information and connection relationship are determined based on the specific warehouse site location or specific commodity feature information, commodity name information, and path information, and the first sub-map information is formed;

[0064] like Figure 3 As shown, Figure 3 3a in the figure may be the first sub-graph information, and the connection relationship between the "product name 1" and the associated "transportation route 1," "average storage rental cost 1," "product destination 1," "product weight 1," and "product quantity 1" of the first sub-graph information is an implicit "product attribute"; Figure 3 3b in the figure may be the second sub-graph information, and the connection relationship between the "goods name 2" and the associated "transportation route 1," "transportation route 2," "goods quantity 2," and "goods destination 2" in the second sub-graph information is an implicit "goods attribute"; Figure 3 3c in the figure may be the third sub-graph information, and the connection relationship between the "site address 1" and the associated "sorting processing time 1," "road cost 1," and "average labor cost of storage 1" of the third sub-graph information is the implicit "warehouse transportation attribute;"

[0065] Furthermore, the complete product map information is traversed to extract other specific warehouse site locations or specific product feature information, product name information and path information to obtain the fourth sub-map information to the Nth sub-map information.

[0066] Step 104, stratifying the sub-graph information into product graph layer samples;

[0067] In the embodiment of the present invention, after obtaining the sub-graph information, the sub-graph information is layered into commodity graph layer samples;

[0068] Specifically, the stratification of the sub-graph information into product graph hierarchical samples includes: calculating the module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information, performing edge fusion according to the module clustering coefficients, and obtaining product graph hierarchical samples by combining edge fusion.

[0069] In the embodiment of the present invention, the module clustering coefficient refers to the ratio of the existing edges between the neighboring nodes of a certain node in the community structure between nodes to the possible existing edges. The module clustering coefficient of a certain node is calculated as follows:

[0070]

[0071] Where M represents the module clustering coefficient, T represents the number of edges between the neighboring nodes of the node, D represents the degree of the node, which is the total number of in-degree and in-degree. In-degree is the number of edges pointing to the node, and out-degree is the number of edges pointing from the node. δ represents the resolution parameter, and K a It represents the sum of the degrees of multiple nodes in the community, and m represents the total number of edges in the graph.

[0072] After obtaining the module clustering coefficient of the node, a stratification operation is performed according to the module clustering coefficient to obtain a hierarchical sample of the product map; specifically, firstly, a plurality of threshold ranges are set, and the modules with the module clustering coefficient belonging to the same threshold range are classified as the same hierarchical sample of the product map.

[0073] If the above Figure 3 The child Figure 3 The first subgraph information of a is node 1, Figure 3 The child Figure 3 The second subgraph information of b is node 2, Figure 3 The child Figure 3 The third sub-graph information of c is node 3. If the module clustering coefficient of node 1 is calculated to be 0.285, the module clustering coefficient of node 2 is 0.53, and the module clustering coefficient of node 3 is 0.31; and the first threshold range is 0-0.5, and the second threshold range is 0.5-1; then the node 1 and node 3 belong to the first threshold range, and the data corresponding to node 1 and node 3 are divided into the first product graph level sample, and the node 2 belongs to the second threshold range, and the data corresponding to node 2 is divided into the second product graph level sample; the product graph level sample includes all information corresponding to one or more sub-graph information. In an embodiment of the present invention, the multi-dimensional supply chain data is reduced in dimensionality to obtain multi-level data, which is convenient for data processing and improves data processing efficiency. Hierarchical sample data can be obtained, which makes the convergence effect of the model better and improves the accuracy of virtual sample generation model training.

[0074] Step 105, inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples;

[0075] After obtaining the product map hierarchy sample, the product map hierarchy sample can be input into a conditional generative adversarial neural network to train the conditional generative adversarial neural network to obtain an output simulated product map hierarchy sample.

[0076] Specifically, the step of inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples includes: setting the conditional information of the conditional generative adversarial neural network so that the number of iterations is greater than twice the number of sub-graph information; applying the conditional information to the generator and discriminator of the conditional generative adversarial neural network; inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples.

[0077] Specifically applied to the embodiments of the present invention, the structure of the conditional generative adversarial neural network may include a discriminator and a generator. The generator may include a deep neural network, which transforms and maps the input low-dimensional vector (such as random noise) to output high-dimensional data. It mainly includes an input layer, multiple hidden layers and an output layer. The goal of the generator is to generate as realistic as possible simulated product graph hierarchical samples to deceive the discriminator. The generator continuously optimizes its own parameters through adversarial training with the discriminator, so that the generated data distribution gradually approaches the real data distribution; and the discriminator may include an input layer, a hidden layer, various activation function layers and an output layer. The goal of the discriminator is to maximize the probability of correct classification of real data, i.e., product graph hierarchical samples, while minimizing the probability of incorrect classification of simulated product graph hierarchical samples; the embodiments of the present invention do not impose too many restrictions on the specific structure of the discriminator and the generator, as long as the effect of the embodiments of the present invention can be achieved.

[0078] Specifically, in an embodiment of the present invention, the number of iterations greater than twice the number of sub-graph information can be set as the conditional information of the conditional generative adversarial neural network, and the above-mentioned conditional information can be added to the generator and discriminator of the conditional generative adversarial neural network; the product graph hierarchy samples are input into the conditional generative adversarial neural network, and the conditional generative adversarial neural network is trained to obtain output simulated product graph hierarchy samples, thereby solving the problem of small number of samples and improving the accuracy of neural network model training.

[0079] Step 106, inputting the simulated product graph layer samples into a convolutional neural network for training to obtain a trained convolutional neural network;

[0080] In actual applications, the output of the simulated product map hierarchy sample may include one or more of the site address, the transportation routes between the site addresses, the average warehouse rental cost, the vehicle number, the average warehouse labor cost, the road cost, the vehicle cost, the sorting processing time, etc., and the input may include one or more of the material number, the type of goods, the quantity of goods, the source of goods, the weight of goods, the destination of goods, etc. The embodiment of the present invention does not impose excessive restrictions on this.

[0081] Further applied to the embodiment of the present invention, the simulated product map hierarchical samples are input into a convolutional neural network for training to obtain a trained convolutional neural network, including: calculating a cost loss coefficient through the warehouse site path information; adding the cost loss coefficient to the loss function of the convolutional neural network; inputting the simulated product map hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network.

[0082] The cost loss coefficient refers to the ratio of the predicted warehouse cost to the actual warehouse cost. The actual warehouse cost represents the sum of the average warehouse rental cost, average warehouse labor cost, road cost and vehicle cost. The cost loss coefficient can be expressed as l p ;

[0083] The loss function L of the convolutional neural network can be expressed as:

[0084]

[0085] Among them, y i represents the output of the sample, p i Represents the output of the neural network prediction, F represents the number of stratification layers of the samples, n represents the number of samples, i=1, 2, 3······n, and the loss function of the embodiment of the present invention can effectively improve the robustness of the model.

[0086] In an embodiment of the present invention, the convolutional neural network may include multiple structures such as an input layer, a convolutional layer, a pooling layer, an activation function layer, a fully connected layer and an output layer. The embodiment of the present invention does not impose too many restrictions on the composition structure of the convolutional neural network. Of course, sample data can also be trained through other supervised artificial intelligence models, and the embodiment of the present invention does not impose too many restrictions on this.

[0087] Step 107, input the new product information into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0088] In an embodiment of the present invention, after obtaining the trained convolutional neural network, new product information, such as material number, product type, product quantity, product source, product weight, product destination, etc., can be input into the trained convolutional neural network to obtain output warehouse site path information. Specifically, the warehouse management scheduling information can be generated based on the product information and the predicted output warehouse site path information. For example, based on the product weight and the warehouse site location, the number of personnel, personnel time, storage location, etc. of the warehouse site that processes the product can be determined, and the optimal cost plan for processing the corresponding product can be output to obtain the output scheduling information related to each warehouse with the optimal cost and path, thereby improving the management efficiency of the product supply chain and reducing management costs.

[0089] The warehouse management scheduling information may include the number of personnel, personnel time, storage location, etc. The embodiment of the present invention does not impose excessive restrictions on the types of warehouse management scheduling information.

[0090] In an embodiment of the present invention, a warehouse management method based on a supply chain cloud platform includes: obtaining product information and corresponding warehouse site path information; generating product map information according to the product information and the corresponding warehouse site path information; decomposing the product map information into multiple sub-map information according to the warehouse site location; stratifying the sub-map information into product map hierarchical samples; inputting the product map hierarchical samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product map hierarchical samples; inputting the simulated product map hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network; inputting new product information into the convolutional neural network to obtain output path information and warehouse management scheduling information. In an embodiment of the present invention, multi-dimensional supply chain data is reduced in dimension to obtain multi-level data, which is convenient for data processing and improves data processing efficiency. Hierarchical sample data can be obtained, so that the convergence effect of the model is better, the accuracy of virtual sample generation model training is improved, and scheduling information related to each warehouse with optimal cost and optimal path is obtained, thereby improving the management efficiency of the product supply chain and reducing management costs.

[0091] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0092] Reference Figure 4 , shows a structural block diagram of a warehouse management system based on a supply chain cloud platform according to an embodiment of the present invention, which may specifically include the following modules:

[0093] The path information acquisition module 301 is used to acquire the product information and the corresponding warehouse site path information;

[0094] A generating module 302, for generating product map information according to the product information and the corresponding warehouse site path information;

[0095] A decomposition module 303, used to decompose the product map information into a plurality of sub-map information according to the warehouse site location;

[0096] A stratification module 304, used for stratifying the sub-graph information into product graph layer samples;

[0097] The sample output module 305 is used to input the product graph level sample into the conditional generative adversarial neural network, train the conditional generative adversarial neural network, and obtain the output simulated product graph level sample;

[0098] A training module 306 is used to input the simulated product graph layer samples into a convolutional neural network for training to obtain a trained convolutional neural network;

[0099] The scheduling module 307 is used to input new product information into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0100] Preferably, the product information includes product name information and product feature information; the warehouse site path information includes warehouse site location and path information; and the generation module includes:

[0101] The first determination submodule is used to determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information with the path information as the connection relationship, and generate product map information.

[0102] Preferably, the sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information; and the decomposition module includes:

[0103] The extraction submodule is used to extract specific warehouse site locations or specific product feature information from the product map information;

[0104] An information acquisition submodule, used to acquire product name information and path information associated with the specific warehouse site location or specific product feature information;

[0105] The second determination submodule is used to determine the specific warehouse site location or specific product feature information and product name information and path information as the first sub-graph information;

[0106] The traversal submodule is used to traverse the product map information, return to the step of extracting the specific warehouse site location or specific product feature information in the product map information, and obtain the second sub-map information to the Nth sub-map information.

[0107] Preferably, the layering module comprises:

[0108] The calculation submodule is used to calculate the module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information, and perform a stratification operation according to the module clustering coefficients to obtain a hierarchical sample of a product graph.

[0109] Preferably, the sample output module includes:

[0110] Setting a submodule, used to set the conditional information of the conditional generative adversarial neural network to have a number of iterations greater than twice the number of sub-graph information;

[0111] An application submodule, used for applying the conditional information to a generator and a discriminator of a conditional generative adversarial neural network;

[0112] The first training submodule is used to input the product map hierarchy samples into a conditional generative adversarial neural network, train the conditional generative adversarial neural network, and obtain output simulated product map hierarchy samples.

[0113] Preferably, the training module includes:

[0114] A calculation submodule, used to calculate the cost loss coefficient through the warehouse site path information;

[0115] An adding submodule, used for adding the cost loss coefficient to the loss function of the convolutional neural network;

[0116] The second training submodule is used to input the simulated product map hierarchical samples into the convolutional neural network for training to obtain a trained convolutional neural network.

[0117] For the specific definition of a warehouse management system based on a supply chain cloud platform, please refer to the definition of a warehouse management method based on a supply chain cloud platform above, which will not be repeated here. Each module in the above-mentioned warehouse management system based on a supply chain cloud platform can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0118] The warehouse management system based on the supply chain cloud platform provided above can be used to execute the warehouse management method based on the supply chain cloud platform provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0119] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for simulating daylighting is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0120] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0122] Get the product information and the corresponding warehouse site path information;

[0123] Generate product map information according to the product information and corresponding warehouse site path information;

[0124] Decomposing the product map information into a plurality of sub-map information according to the warehouse site location;

[0125] Layering the sub-graph information into product graph layer samples;

[0126] Inputting the product graph level sample into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining an output simulated product graph level sample;

[0127] Inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network;

[0128] The new product information is input into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0129] Preferably, the product information includes product name information and product feature information; the warehouse site path information includes warehouse site location and path information; and the generating of product map information according to the product information and the corresponding warehouse site path information includes:

[0130] Determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information using path information as a connection relationship, and generate product map information.

[0131] Preferably, the sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information; the decomposing the product graph information into a plurality of sub-graph information according to the warehouse site location includes:

[0132] Extract specific warehouse site locations or specific product feature information from product map information;

[0133] Obtaining product name information and path information associated with the specific warehouse site location or specific product feature information;

[0134] Determine the specific warehouse site location or specific product feature information and product name information and path information as the first sub-graph information;

[0135] Traverse the product map information, return to the step of extracting the specific warehouse site location or specific product feature information in the product map information, and obtain the second sub-map information to the Nth sub-map information.

[0136] Preferably, the step of stratifying the sub-graph information into product graph layer samples includes:

[0137] The module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information are calculated, and a stratification operation is performed according to the module clustering coefficients to obtain a hierarchical sample of a product graph.

[0138] Preferably, the step of inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples comprises:

[0139] Setting the conditional information of the conditional generative adversarial neural network to an iteration number greater than twice the number of sub-graph information;

[0140] Applying the conditional information to the generator and discriminator of a conditional generative adversarial neural network;

[0141] The product map hierarchy samples are input into a conditional generative adversarial neural network, and the conditional generative adversarial neural network is trained to obtain output simulated product map hierarchy samples.

[0142] Preferably, the step of inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network comprises:

[0143] Calculate the cost loss coefficient through the warehouse site path information;

[0144] Adding the cost loss coefficient to the loss function of the convolutional neural network;

[0145] The simulated product atlas hierarchical samples are input into a convolutional neural network for training to obtain a trained convolutional neural network.

[0146] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0147] Get the product information and the corresponding warehouse site path information;

[0148] Generate product map information according to the product information and corresponding warehouse site path information;

[0149] Decomposing the product map information into a plurality of sub-map information according to the warehouse site location;

[0150] Layering the sub-graph information into product graph layer samples;

[0151] Inputting the product graph level sample into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining an output simulated product graph level sample;

[0152] Inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network;

[0153] The new product information is input into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

[0154] Preferably, the product information includes product name information and product feature information; the warehouse site path information includes warehouse site location and path information; and the generating of product map information according to the product information and the corresponding warehouse site path information includes:

[0155] Determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information using path information as a connection relationship, and generate product map information.

[0156] Preferably, the sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information; the decomposing the product graph information into a plurality of sub-graph information according to the warehouse site location includes:

[0157] Extract specific warehouse site locations or specific product feature information from product map information;

[0158] Obtaining product name information and path information associated with the specific warehouse site location or specific product feature information;

[0159] Determine the specific warehouse site location or specific product feature information and product name information and path information as the first sub-graph information;

[0160] Traverse the product map information, return to the step of extracting the specific warehouse site location or specific product feature information in the product map information, and obtain the second sub-map information to the Nth sub-map information.

[0161] Preferably, the step of stratifying the sub-graph information into product graph layer samples includes:

[0162] The module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information are calculated, and a stratification operation is performed according to the module clustering coefficients to obtain a hierarchical sample of a product graph.

[0163] Preferably, the step of inputting the product graph hierarchy samples into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining output simulated product graph hierarchy samples comprises:

[0164] Setting the conditional information of the conditional generative adversarial neural network to an iteration number greater than twice the number of sub-graph information;

[0165] Applying the conditional information to the generator and discriminator of a conditional generative adversarial neural network;

[0166] The product map hierarchy samples are input into a conditional generative adversarial neural network, and the conditional generative adversarial neural network is trained to obtain output simulated product map hierarchy samples.

[0167] Preferably, the step of inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network comprises:

[0168] Calculate the cost loss coefficient through the warehouse site path information;

[0169] Adding the cost loss coefficient to the loss function of the convolutional neural network;

[0170] The simulated product atlas hierarchical samples are input into a convolutional neural network for training to obtain a trained convolutional neural network.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0172] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0173] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0174] The embodiments of the present invention are described with reference to flowcharts and / or block diagrams of apparatuses, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction method, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0177] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0178] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the existence of other identical elements in the process, device, article or terminal device including the elements.

[0179] The above is a detailed introduction to a warehouse management method based on a supply chain cloud platform and a warehouse management system based on a supply chain cloud platform, a computer device and a storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A warehouse management method based on a supply chain cloud platform, characterized in that: include: Get the product information and the corresponding warehouse site path information; Generate product map information according to the product information and corresponding warehouse site path information; Decomposing the product map information into a plurality of sub-map information according to the warehouse site location; Layering the sub-graph information into product graph layer samples; Inputting the product graph level sample into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining an output simulated product graph level sample; Inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network; The new product information is input into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

2. The method according to claim 1, characterized in that The product information includes product name information and product feature information; The warehouse site path information includes warehouse site location and path information; the generating of product map information according to the product information and the corresponding warehouse site path information includes: Determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information using path information as a connection relationship, and generate product map information.

3. The method according to claim 2, characterized in that The sub-graph information includes first sub-graph information, second sub-graph information to Nth sub-graph information; the decomposing the product graph information into a plurality of sub-graph information according to the warehouse site location includes: Extract specific warehouse site locations or specific product feature information from product map information; Obtaining product name information and path information associated with the specific warehouse site location or specific product feature information; Determine the specific warehouse site location or specific product feature information and product name information and path information as the first sub-graph information; Traverse the product map information, return to the step of extracting the specific warehouse site location or specific product feature information in the product map information, and obtain the second sub-map information to the Nth sub-map information.

4. The method according to claim 3, characterized in that The step of stratifying the sub-graph information into product graph layer samples includes: The module clustering coefficients of the first sub-graph information and the second sub-graph information to the Nth sub-graph information are calculated, and a stratification operation is performed according to the module clustering coefficients to obtain a hierarchical sample of a product graph.

5. The method according to claim 1, characterized in that The step of inputting the product graph level sample into a conditional generative adversarial neural network, training the conditional generative adversarial neural network, and obtaining an output simulated product graph level sample includes: Setting the conditional information of the conditional generative adversarial neural network to an iteration number greater than twice the number of sub-graph information; Applying the conditional information to the generator and discriminator of a conditional generative adversarial neural network; The product map hierarchy samples are input into a conditional generative adversarial neural network, and the conditional generative adversarial neural network is trained to obtain output simulated product map hierarchy samples.

6. The method according to claim 1, characterized in that The step of inputting the simulated product graph hierarchical samples into a convolutional neural network for training to obtain a trained convolutional neural network includes: Calculate the cost loss coefficient through the warehouse site path information; Adding the cost loss coefficient to the loss function of the convolutional neural network; The simulated product atlas hierarchical samples are input into a convolutional neural network for training to obtain a trained convolutional neural network.

7. A warehouse management system based on a supply chain cloud platform, characterized in that: include: Path information acquisition module, used to obtain product information and corresponding warehouse site path information; A generation module, used to generate product map information according to the product information and corresponding warehouse site path information; A decomposition module, used for decomposing the product map information into a plurality of sub-map information according to the warehouse site location; A stratification module, used for stratifying the sub-map information into product map layer samples; A sample output module, used to input the product graph hierarchy sample into a conditional generative adversarial neural network, train the conditional generative adversarial neural network, and obtain an output simulated product graph hierarchy sample; A training module, used for inputting the simulated product graph layer samples into the convolutional neural network for training to obtain a trained convolutional neural network; The scheduling module is used to input new product information into the convolutional neural network to obtain output warehouse site path information and warehouse management scheduling information.

8. The system according to claim 7, characterized in that The product information includes product name information and product feature information; The warehouse site path information includes warehouse site location and path information; the generation module includes: The first determination submodule is used to determine the product name information as the first entity information, determine the warehouse site location or product feature information as the second entity attribute information, connect the first entity information and the second entity attribute information with the path information as the connection relationship, and generate product map information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a warehouse management method based on a supply chain cloud platform described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a warehouse management method based on a supply chain cloud platform described in any one of claims 1 to 6 are implemented.

Images