Order processing method, device, equipment and storage medium based on network model

Abstract

The embodiment of the present application discloses an order processing method, device, equipment and storage medium based on a network model. The method includes: according to the order products in the order information, the order information is divided into product order information corresponding to various order products; according to the product order information, the production tasks corresponding to the order products are determined, and the production tasks are divided into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; the link tasks and the corresponding multiple production links are input into a pre-trained order allocation model to obtain the production links and task processing sequence of the processing link tasks output by the order allocation model; according to the task processing sequence, the production link processing corresponding link tasks is controlled. Through the above technical means, the problem of low order processing efficiency caused by order backlog in the existing order processing system is solved, and the order data processing efficiency and product production efficiency are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of assembly line production, and in particular to an order processing method, device, equipment and storage medium based on a network model. Background Art

[0002] The order processing system includes two subsystems: order transaction and product production. After receiving the order sent by the order transaction subsystem, the product manufacturing subsystem controls the production line to manufacture the products corresponding to the order.

[0003] The existing product production subsystem controls the production line to produce products corresponding to the order data in the order in which the orders are received. When the order processing system receives high-concurrency orders, a large number of order tasks are waiting for the production line to process, resulting in a backlog of orders in the product production subsystem and low order processing efficiency. Summary of the invention

[0004] The embodiments of the present application provide an order processing method, device, equipment and storage medium based on a network model, which can solve the problem of low order processing efficiency caused by order backlog in the existing order processing system, and improve the order data processing efficiency and product production efficiency.

[0005] In a first aspect, an embodiment of the present application provides an order processing method based on a network model, comprising:

[0006] According to the order products in the order information, the order information is divided into product order information corresponding to various order products;

[0007] Determine the production task of the corresponding order product according to the product order information, and split the production task into link tasks corresponding to each production link according to the production links configured in the production line, where one link task corresponds to multiple production links;

[0008] Input the link tasks and the corresponding multiple production links into a pre-trained order allocation model, and obtain the production links and task processing sequence for processing the link tasks output by the order allocation model;

[0009] Control the production links to process the corresponding link tasks according to the task processing sequence.

[0010] Furthermore, the product order information includes the product type and order quantity of the ordered product;

[0011] Correspondingly, determining the production task of the corresponding order product according to the order information includes:

[0012] Determine the production steps of the ordered product according to the product type, and determine the number of executions of the production steps according to the ordered quantity;

[0013] A production task for the order product is generated according to the production steps and the corresponding execution times.

[0014] Furthermore, the production process of the production line according to the production process configured in the production line splits the production task into the process tasks corresponding to each production process respectively, including:

[0015] Splitting the production step into multiple sub-steps according to the production links configured in the production line, and determining multiple production links corresponding to each sub-step;

[0016] According to the sub-steps and the execution times, the link tasks corresponding to each sub-step are generated, and multiple production links corresponding to the link tasks are determined.

[0017] Furthermore, the step of inputting the link tasks and the corresponding multiple production links into a pre-trained order allocation model to obtain the production links and task processing sequence output by the order allocation model for processing the link tasks includes:

[0018] The link tasks and corresponding production links corresponding to all product order information are input into the order allocation model, and the order allocation model is used to determine the production link for processing the link task and the task processing sequence from the multiple production links corresponding to the link task.

[0019] Furthermore, the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, production links and task processing sequence for processing the sample link tasks, and task processing time and task processing error rate when the production link processes the sample link tasks.

[0020] Furthermore, after inputting the link tasks and the corresponding production links corresponding to all product order information into the order allocation model, it also includes:

[0021] Obtaining the task processing time and task processing error rate corresponding to the sample link tasks output by the order allocation model;

[0022] When it is determined that the task processing time or the task processing error rate meets the corresponding preset threshold, the link tasks and the task processing sequence of the production link processing are adjusted.

[0023] Furthermore, the step of controlling the production link processing corresponding link tasks according to the task processing sequence includes:

[0024] The link tasks and the task processing sequence are sent to the controller of the corresponding production link, so that the controller controls the production link to process the link tasks according to the task processing sequence.

[0025] In a second aspect, an embodiment of the present application provides an order processing device based on a network model, comprising:

[0026] An order classification module is configured to classify the order information into product order information corresponding to various order products according to the order products in the order information;

[0027] A task classification module is configured to determine the production task of the corresponding order product according to the product order information, and split the production task into link tasks corresponding to each production link according to the production links configured in the production line, and one link task corresponds to multiple production links;

[0028] A task allocation module is configured to input the link task and the corresponding multiple production links into a pre-trained order allocation model, and obtain the production link and task processing sequence for processing the link task output by the order allocation model;

[0029] The product production module is configured to control the production links to process corresponding link tasks according to the task processing sequence.

[0030] Further, the product order information includes the product type and order quantity of the order product; in the order classification module, determining the production task corresponding to the order product according to the order information includes:

[0031] Determine the production steps of the ordered product according to the product type, and determine the number of executions of the production steps according to the ordered quantity;

[0032] A production task for the order product is generated according to the production steps and the corresponding execution times.

[0033] Furthermore, in the task classification module, the production process configured according to the production line splits the production task into the process tasks corresponding to each production process, including:

[0034] Splitting the production step into multiple sub-steps according to the production links configured in the production line, and determining multiple production links corresponding to each sub-step;

[0035] According to the sub-steps and the execution times, the link tasks corresponding to each sub-step are generated, and multiple production links corresponding to the link tasks are determined.

[0036] Furthermore, in the task allocation module, the link tasks and the corresponding multiple production links are input into a pre-trained order allocation model, and the production links and task processing sequence for processing the link tasks output by the order allocation model are obtained, including:

[0037] The link tasks and corresponding production links corresponding to all product order information are input into the order allocation model, and the order allocation model is used to determine the production link for processing the link task and the task processing sequence from the multiple production links corresponding to the link task.

[0038] Furthermore, the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, production links and task processing sequence for processing the sample link tasks, and task processing time and task processing error rate when the production link processes the sample link tasks.

[0039] Furthermore, the network model-based order processing device also includes: a processing result acquisition module, configured to obtain the task processing time and task processing error rate corresponding to the sample link task output by the order allocation model; an allocation result adjustment module, configured to adjust the link tasks and task processing sequence of the production link processing when it is determined that the task processing time or the task processing error rate meets the corresponding preset threshold.

[0040] Furthermore, in the product production module, controlling the production link processing corresponding link tasks according to the task processing sequence includes:

[0041] The link tasks and the task processing sequence are sent to the controller of the corresponding production link, so that the controller controls the production link to process the link tasks according to the task processing sequence.

[0042] In a third aspect, an embodiment of the present application provides an order processing device based on a network model, including:

[0043] memory and one or more processors;

[0044] The memory is used to store one or more programs;

[0045] When the one or more programs are executed by the one or more processors, the one or more processors implement the order processing method based on the network model as described in the first aspect.

[0046] In a fourth aspect, an embodiment of the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the network model-based order processing method as described in the first aspect.

[0047] This application divides the order information into product order information corresponding to various order products according to the order products in the order information; determines the production tasks corresponding to the order products according to the product order information, and divides the production tasks into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; inputs the link tasks and the corresponding multiple production links into a pre-trained order allocation model to obtain the production links and task processing sequence of the link tasks output by the order allocation model; and controls the link tasks corresponding to the production link processing according to the task processing sequence. Through the above-mentioned technical means, the production links and task processing sequence for processing each link task are determined through a pre-trained order allocation model, the allocation mechanism of link tasks is optimized, the task processing time is shortened and the task processing error rate is reduced, order processing stagnation caused by processing errors is avoided, and order processing efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of an order processing method based on a network model provided by an embodiment of the present application;

[0049] Figure 2 This is a flowchart of determining the production task of an order product provided in an embodiment of the present application;

[0050] Figure 3 It is a flowchart of the tasks of dividing the links provided in the embodiment of the present application;

[0051] Figure 4 is a flowchart of adjusting task allocation results according to processing results provided by an embodiment of the present application;

[0052] Figure 5 It is a structural schematic diagram of an order processing device based on a network model provided by an embodiment of the present application;

[0053] Figure 6 It is a structural diagram of an order processing device based on a network model provided by an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0055] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0056] The order processing method, device, equipment and storage medium based on the network model provided by the present application are intended to divide the order information into product order information corresponding to various order products according to the order products in the order information; determine the production tasks corresponding to the order products according to the product order information, and divide the production tasks into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; input the link tasks and the corresponding multiple production links into the pre-trained order allocation model to obtain the production links and task processing sequence of the processing link tasks output by the order allocation model; and control the link tasks corresponding to the production link processing according to the task processing sequence. Compared with the traditional order processing technology, it controls the production line to produce the products corresponding to the order data in sequence according to the order received. When the order processing system receives high-concurrency orders, a large number of order tasks are waiting for the production line to process, resulting in a backlog of orders in the product production subsystem and low order processing efficiency. Based on this, the order processing method based on the network model provided by the present application is to solve the problem of low order processing efficiency caused by order backlog in the existing order processing system.

[0057] Figure 1 A flow chart of an order processing method based on a network model provided by an embodiment of the present application is given. The order processing method based on a network model provided in this embodiment can be executed by an order processing device based on a network model. The order processing device based on a network model can be implemented by software and / or hardware. The order processing device based on the network model can be composed of two or more physical entities, or can be composed of one physical entity.

[0058] Exemplarily, this embodiment provides an order processing system, including an order transaction subsystem and a product production subsystem, wherein the order transaction subsystem is used to generate corresponding order data according to the products, quantities, and delivery addresses selected by the customer on the trading platform, and send the order data to the product production subsystem. The product production subsystem is used to process the order data to control the production of corresponding products on the assembly line. Therefore, the order processing method based on the network model in this embodiment mainly runs on the product production subsystem. It can be understood that the order processing system provided in this embodiment can realize that after the customer places an order, the assembly line can be quickly controlled to produce the corresponding product, and the transaction process and the production process are linked to improve the order processing efficiency based on the network model.

[0059] This embodiment takes the product production subsystem as an example to describe the main body of the order processing method based on the network model. Figure 1 , the order processing method based on the network model specifically includes:

[0060] S110. According to order products in the order information, the order information is divided into product order information corresponding to various order products.

[0061] Among them, the order information refers to the information entered when the customer orders a product on the trading platform of the order trading subsystem, which includes information such as product type, order quantity, logistics address, and user account. In one embodiment, when a large number of customers order products from the trading platform of the order trading subsystem, the trading platform packages the information such as the product type, order quantity, logistics address, and user account ordered by each customer into order information. Since there are many orders currently traded on the trading platform, the product production subsystem receives a large amount of order information within a certain period of time. All order information received within a certain period of time is collected, and according to the product type of each order product in the order information, the order information of the order products of the same product type is collected to obtain the product order information corresponding to the order product. Among them, the product order information only includes the order information of the corresponding order product.

[0062] S120. Determine the production task of the corresponding order product according to the product order information, and split the production task into link tasks corresponding to each production link according to the production links configured in the production line. One link task corresponds to multiple production links.

[0063] Since different types of products require different raw materials and production processes, it is necessary to determine the production tasks to be performed by the production line when producing the corresponding product according to the product type. Figure 2 This is a flowchart of determining the production task of an order product provided by an embodiment of the present application. Figure 2 As shown, the steps of determining the production task of the order product specifically include S1201-S1202:

[0064] S1201. Determine the production steps of the order product according to the product type, and determine the number of execution times of the production steps according to the order quantity.

[0065] S1202. Generate a production task for the order product according to the production steps and the corresponding execution times.

[0066] Exemplarily, the production steps of a product refer to the process of producing the product by running each production link of the production line in a certain order. For example, after the production line runs production link A, production link B, production link C and production link D in sequence, product A is obtained. Then the production steps of product A are to run production link A, production link B, production link C and production link D in sequence. In one embodiment, the production steps of each product are pre-configured, and the production steps of the product order information are determined according to the product type corresponding to the product order information. According to the order quantity of each order in the product order information, the total order quantity of the product is determined, and the number of executions of the production steps is determined according to the total order quantity. After the production line is controlled to run the production steps of the execution number, the total order quantity of products can be produced. According to the execution number and the production steps, the production task of the corresponding product is generated, and the production line can control the corresponding production link to produce the corresponding total order quantity of products according to the production steps and the execution number in the production task.

[0067] Furthermore, since the production line runs the production steps in sequence through each production link to produce the corresponding product, the production tasks of the production line can be divided into link tasks of each production link according to the production link that runs the production step in the production line. Figure 3 This is a flowchart of the task division process provided by the embodiment of the present application. Figure 3 As shown, the steps of dividing the task into segments specifically include S1203-S1204:

[0068] S1203. Split the production steps into multiple sub-steps according to the production links configured in the production line, and determine the multiple production links corresponding to each sub-step.

[0069] In one embodiment, a production workshop is equipped with multiple production lines, each of which is equipped with the same production links, and each production line can produce all types of products. For example, the production workshop is equipped with 3 production lines, namely, production line ①, production line ②, and production line ③, and each production line is equipped with 6 production links, namely, production link A, production link B, production link C, production link D, production link E, and production link F. At this time, the number of each production link in the production workshop is 3. When producing product A, production links A, production link B, production link C, and production link D in production line ①, production line ②, and production line ③ can be randomly selected to cooperate in running the production steps of product A.

[0070] In this embodiment, the production steps of product A are that the production line sequentially produces raw materials through production link A, performs preliminary processing on the raw materials through production link B, performs secondary processing on the raw materials through production link C, and performs final processing on the raw materials through production link D to obtain product A. According to the production link A, production link B, production link C, production link D, production link E, and production link F configured in the production line, the production steps of product A can be divided into sub-steps that are sequentially operated in each production link, and it can be determined that sub-step A: production link A produces raw materials; sub-step B: production link B performs preliminary processing on raw materials; sub-step C: performs secondary processing on raw materials through production link C; sub-step D performs final processing on raw materials through production link D. According to the content of the sub-steps and the number of production lines configured in the production workshop, it can be determined that sub-step A corresponds to 3 production links A, sub-step B corresponds to 3 production links B, sub-step C corresponds to 3 production links C, and sub-step D corresponds to 3 production links D.

[0071] S1204. Generate the link tasks corresponding to each sub-step according to the sub-steps and the number of executions, and determine the multiple production links corresponding to the link tasks.

[0072] For example, when the production line executes a certain number of production steps, the production link also executes the corresponding number of sub-steps. According to the number of executions of the production line and the corresponding sub-steps of the production link, the link tasks that need to be completed by the production link corresponding to the sub-step when the production line produces the total ordered quantity of products can be obtained. It can be understood that the production link corresponding to the link task refers to all link tasks that can handle the link task in the production workshop, such as the production link A in production line No. 1, production line No. 2 and production line No. 3 are all production links corresponding to the production task of sub-step A.

[0073] S130, inputting the link tasks and the corresponding multiple production links into a pre-trained order allocation model, and obtaining the production links and task processing sequence of the processing link tasks output by the order allocation model.

[0074] Among them, the order allocation model refers to a neural network model used to allocate the production links of each link task. In a period of time, the order information received includes one or more order products. Whether it is one order product or multiple order products, the order allocation model will reasonably allocate the production links and task processing sequence of the processing link tasks according to the production links corresponding to the tasks of each link, so as to shorten the task processing time and reduce the task processing error rate.

[0075] In one embodiment, the order information includes only one order product, and the link tasks and corresponding multiple production links of the order product are determined according to the product order information of the order product. The link tasks and corresponding multiple production links are input into the order allocation model to obtain the production links and task processing sequence of processing each link task output by the order allocation model. In this embodiment, when the production line in the production workshop only produces one product, the order allocation model generally outputs the link tasks corresponding to the production links on the three production lines in the production workshop evenly distributed. The task processing sequence of the same production link is the same, and the task processing sequence of different production links is sorted according to the execution sequence of the sub-steps corresponding to the link tasks in the production steps.

[0076] In another embodiment, when the order information includes multiple order products, the product order information of each order product is determined, and the link tasks of the corresponding order products and the multiple production links corresponding to the link tasks are determined according to the product order information. The link tasks and the corresponding production links corresponding to all product order information are input into the order allocation model, and the production links and task processing order of the link tasks are determined from the multiple production links corresponding to the link tasks through the order allocation model. Exemplarily, it is assumed that the order information includes three order products, namely, product A, product B and product C, and the link tasks corresponding to product A include link tasks AA, link tasks AB, link tasks AC and link tasks AD. Among them, the production link corresponding to link task AA is the production link A in production lines ①, ② and ③, and the production link corresponding to link task AB is the production link B in production lines ①, ② and ③, and so on for the production links corresponding to link tasks AC and link tasks AD. The link tasks corresponding to product B include link tasks BA, link tasks BB, link tasks BE and link tasks BF, and the link tasks corresponding to product C include link tasks CC, link tasks CD, link tasks CE and link tasks CF. The production links corresponding to the link tasks of product B and product C can be deduced by analogy as for product A. The link tasks and corresponding production links of product A, product B and product C are input into the order allocation model. Under the constraint of the execution order of the sub-steps corresponding to the link tasks, the order allocation model determines the production links and task processing order of each link task according to the task amount of each link task, wherein the task amount is calculated by the time required for each execution of the corresponding sub-step and the number of executions in the link task. For example, it is assumed that the execution order of the sub-steps corresponding to the link tasks of product A is AA, AB, AC and AD, the execution order of the sub-steps corresponding to the link tasks of product B is BA, BB, BE and BF, and the execution order of the sub-steps corresponding to the link tasks of product C is CC, CD, CE and CF. The production links A in production lines ①, ② and ③ are A1, A2 and A3, the production links B are B1, B2 and B3, and the production links C are C1, C2 and C3. Link tasks AA, BA and CC are all at the top of the corresponding execution order, so the three link tasks can be processed at the same time. According to the execution order of the sub-steps corresponding to the link tasks, the processing order of the link tasks is determined. For example, the processing order of link task AB is after link task AA, the processing order of link task BB is after link task BA, and the processing order of link task CD is after link task CC. Similarly, the processing order of other link tasks can be deduced.

[0077] Furthermore, since link task AA and link task BA are processed at the same time, and the production links corresponding to the two link tasks are the same, the order allocation model needs to determine the production link for processing link task AA and link task BA according to the task amount of link task AA and link task BA. Exemplarily, assuming that the task amount of link task AA is greater than link task BA, the order allocation model determines to evenly distribute link task AA to production links A1 and A2, and to distribute link task BA to production link A3. However, link task CC has no production link conflict with link tasks AA and BA processed at the same time, and link task CC can be distributed to production links C1, C2 and C3 according to the task amount of link task CC. Similarly, link task AB and link task BB are both in the second place in the corresponding execution order, and there is a conflict in the production link. Link task AB and link task BB are distributed to production links B1, B2 and B3 according to the task amount of link task AB and link task BB. Link task BE and link task CE are both in the third place in the corresponding execution order, and there is a conflict in the production link. According to the task volume of link task BE and link task CE, link task BE and link task CE are allocated to production links E1, E2 and E3, and so on, the production links for processing link task BF and link task CF can be determined.

[0078] It should be noted that the link tasks of different products with different execution orders may also have conflicts in the production links. For example, when link task AB has been processed, according to the task processing order, link task AC needs to be processed by at least one of the production links C1, C2 and C3, but link task CC may not be processed at this time, so link task AC needs to wait for production links C1, C2 and C3 to complete link task CC. For this situation, the order allocation model can estimate the processing time of link task AA and link task AB, and allocate the task volume of production links C1, C2 and C3 to process link task CC according to the processing time, so that after link task AB is completed, production links C1, C2 and / or C3 are free to process link task AC, avoiding long waiting time for link tasks.

[0079] In one embodiment, the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, production links and task processing order for processing sample link tasks, and task processing time and task processing error rate when the production link processes sample link tasks. Exemplarily, the sample link tasks and corresponding production links of all sample product order information are input into the neural network model to obtain the result output by the neural network model. The result and the task processing time and task processing error rate when the production link processes the sample link tasks are substituted into the preset loss function to obtain the result output by the loss function. The weight coefficient of the neural network model is optimized according to the result output by the loss function. After the number of training times of the neural network model reaches a certain number, the training is completed to obtain the order allocation model. It should be noted that the above-mentioned task processing time not only includes the processing time required for the production link to process the link tasks, but also includes the waiting time for the link tasks to wait for the production link to process. The task processing error rate refers to the proportion of errors when the production link processes the link tasks. The higher the task processing error rate, the longer the task processing time, and the longer the task processing time, the more unreasonable the allocation of the corresponding link tasks. Therefore, task processing time and task processing error rate are the basis for the order allocation model to output the optimal task allocation results.

[0080] In this embodiment, Figure 4 1 is a flowchart of adjusting the task allocation result according to the processing result provided by the embodiment of the present application. Figure 4 As shown, the step of adjusting the task allocation result according to the processing result specifically includes S1301-S1302:

[0081] S1301. Obtain the task processing time and task processing error rate corresponding to the sample link tasks output by the order allocation model.

[0082] S1302: When it is determined that the task processing time or the task processing error rate meets the corresponding preset threshold, adjust the link tasks and task processing sequence of the production link processing.

[0083] Exemplarily, the task allocation results output by the order allocation model include the production links and task processing order for processing tasks at each link, and the processing results output by the order allocation model include the task processing time and task processing error rate when the production link processes the corresponding link task. The task processing time and task processing error rate output by the order allocation model can be understood as the shortest task processing time and the lowest task processing error rate required to process link tasks under the optimal task allocation as considered by the order allocation model.

[0084] However, the shortest task processing time and the lowest task processing error rate considered by the order allocation model may not necessarily meet user expectations. Exemplarily, the preset threshold can be understood as the maximum value of the task processing time and the task processing error rate expected by the user. When the task processing time output by the order allocation model is greater than the corresponding preset threshold or the task processing error rate output by the order allocation model is greater than the corresponding preset threshold, it indicates that the shortest task processing time considered by the order allocation model is too long or the lowest task processing error rate is too high, which does not meet user expectations. Therefore, when it is determined that the task processing time or the task processing error rate is greater than the corresponding preset threshold, the link tasks and task processing sequence of the production link processing are manually adjusted to optimize the task allocation results.

[0085] S140, controlling the production links to process corresponding link tasks according to the task processing sequence.

[0086] In one embodiment, the product production subsystem is equipped with a general controller, and the general controller is used to control each production link to process the corresponding link task. For example, it is assumed that each link task corresponding to product D is processed by production link A1, production link B2, production link C3 and production link D4 in sequence. After determining that production link A1 has processed the corresponding current link task, the general controller controls production link A1 to process the link task corresponding to the product ordering information. Among them, the current link task can be understood as the link task that is still being processed when the production link receives the link task of a certain product. Further, after production link A1 processes the link task corresponding to the product ordering information for a period of time and determines that production link B2 has processed the corresponding current link task, production link B2 is controlled to process the link task corresponding to the product ordering information. Similarly, the subsequent control process is that according to the task processing order of each link task of product D, after the previous production link processes the link task corresponding to the product ordering information for a period of time and the current round of production links processes the corresponding current link task, the current round of production links is controlled to process the link task corresponding to the product ordering information. It should be noted that the link task corresponding to the product ordering information that has been waiting for a period of time to be processed by the previous production link is because the current round of production link needs to process the products output by the previous production link.

[0087] In another embodiment, each production link in the product production subsystem is configured with a controller, and a communication connection is established between the master controller and the controller. The master controller sends the link task and the task processing sequence to the controller of the corresponding production link, so that the controller controls the production link to process the link task according to the task processing sequence. Exemplarily, after the controller receives the link task and the task processing sequence corresponding to the managed production link, if the production link that the controller is responsible for is the first in the task processing sequence, then after determining that the production link has processed the current link task, the corresponding production link is controlled to start processing the corresponding link task. After processing the link task for a period of time, according to the task processing sequence of the link task of the same product, a notification message is sent to the controller of the next production link to inform the controller of the next production link that it can start processing the corresponding link task. If the production link that the controller is responsible for is not the first in the task processing sequence, after determining that the corresponding production link has processed the current link task and receiving the notification message sent by the controller of the previous production link, the corresponding production link is controlled to start processing the corresponding link task, and after processing the link task for a period of time, a notification message is sent to the controller of the next production link.

[0088] In summary, the order processing method based on the network model provided in the embodiment of the present application divides the order information into product order information corresponding to various order products according to the order products in the order information; determines the production tasks corresponding to the order products according to the product order information, and divides the production tasks into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; inputs the link tasks and the corresponding multiple production links into the pre-trained order allocation model to obtain the production links and task processing sequence of the link tasks output by the order allocation model; and controls the link tasks corresponding to the production link processing according to the task processing sequence. Through the above-mentioned technical means, the production links and task processing sequence of processing each link task are determined by the pre-trained order allocation model, the allocation mechanism of link tasks is optimized, the task processing time is shortened and the task processing error rate is reduced, the order processing stagnation caused by processing errors is avoided, and the order processing efficiency is improved.

[0089] Based on the above embodiments, Figure 5 A schematic diagram of a network model-based order processing device provided by an embodiment of the present application. Figure 5 The network model-based order processing device provided in this embodiment specifically includes: an order classification module 21, a task classification module 22, a task allocation module 23 and a product production module 24.

[0090] The order classification module is configured to classify the order information into product order information corresponding to various order products according to the order products in the order information;

[0091] The task classification module is configured to determine the production tasks of the corresponding order products according to the product order information, and split the production tasks into link tasks corresponding to each production link according to the production links configured in the production line, and one link task corresponds to multiple production links;

[0092] The task allocation module is configured to input the link tasks and the corresponding multiple production links into the pre-trained order allocation model, and obtain the production links and task processing sequence of the processing link tasks output by the order allocation model;

[0093] The product production module is configured to control the production links to process corresponding link tasks according to the task processing sequence.

[0094] Based on the above embodiment, the product order information includes the product type and order quantity of the order product; in the order classification module, determining the production task corresponding to the order product according to the order information includes:

[0095] Determine the production steps for the order product based on the product type, and determine the number of times the production step is executed based on the order quantity;

[0096] Generate production tasks for order products based on production steps and corresponding execution times.

[0097] On the basis of the above embodiment, in the task classification module, the production line splits the production tasks into the link tasks corresponding to each production link according to the production links configured in the production line, including:

[0098] Split the production steps into multiple sub-steps according to the production links configured in the production line, and determine the multiple production links corresponding to each sub-step;

[0099] According to the sub-steps and the number of executions, the link tasks corresponding to each sub-step are generated, and multiple production links corresponding to the link tasks are determined.

[0100] On the basis of the above embodiment, in the task allocation module, the link tasks and the corresponding multiple production links are input into the pre-trained order allocation model, and the production links and task processing sequence of the processing link tasks output by the order allocation model are obtained, including:

[0101] The link tasks and corresponding production links corresponding to all product order information are input into the order allocation model, and the order allocation model is used to determine the production link for processing the link task and the task processing sequence from the multiple production links corresponding to the link tasks.

[0102] Based on the above embodiments, the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, production links and task processing sequence for processing sample link tasks, and task processing time and task processing error rate when the production link processes sample link tasks.

[0103] On the basis of the above embodiments, the order processing device based on the network model also includes: a processing result acquisition module, which is configured to obtain the task processing time and task processing error rate corresponding to the sample link tasks output by the order allocation model; an allocation result adjustment module, which is configured to adjust the link tasks and task processing order of the production link processing when it is determined that the task processing time or the task processing error rate meets the corresponding preset threshold.

[0104] On the basis of the above embodiment, in the product production module, the corresponding link tasks of the production link processing are controlled according to the task processing sequence, including:

[0105] The link tasks and task processing sequence are sent to the controller of the corresponding production link, so that the controller controls the production link to process the link tasks according to the task processing sequence.

[0106] In summary, the order processing device based on the network model provided in the embodiment of the present application divides the order information into product order information corresponding to various order products according to the order products in the order information; determines the production tasks corresponding to the order products according to the product order information, and divides the production tasks into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; inputs the link tasks and the corresponding multiple production links into the pre-trained order allocation model to obtain the production links and task processing sequence of the link tasks output by the order allocation model; and controls the link tasks corresponding to the production link processing according to the task processing sequence. Through the above-mentioned technical means, the production links and task processing sequence for processing each link task are determined by the pre-trained order allocation model, the allocation mechanism of the link tasks is optimized, the task processing time is shortened and the task processing error rate is reduced, the order processing stagnation caused by processing errors is avoided, and the order processing efficiency is improved.

[0107] The network model-based order processing device provided in the embodiment of the present application can be used to execute the network model-based order processing method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0108] The present application embodiment provides an order processing device based on a network model, referring to Figure 6The order processing device based on the network model includes: a processor 31, a memory 32, a communication module 33, an input device 34 and an output device 35. The number of processors in the order processing device based on the network model can be one or more, and the number of memories in the order processing device based on the network model can be one or more. The processor, memory, communication module, input device and output device of the order processing device based on the network model can be connected through a bus or other methods.

[0109] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the order processing method based on the network model described in any embodiment of the present application (for example, the order classification module 21, the task classification module 22, the task allocation module 23 and the product production module 24 in the order processing device based on the network model). The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0110] The communication module 33 is used for data transmission.

[0111] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory, that is, realizes the above-mentioned order processing method based on the network model.

[0112] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0113] The network model-based order processing device provided above can be used to execute the network model-based order processing method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0114] An embodiment of the present application also provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to execute an order processing method based on a network model. The order processing method based on the network model includes: dividing the order information into product order information corresponding to various order products according to the order products in the order information; determining the production tasks corresponding to the order products according to the product order information, and splitting the production tasks into link tasks corresponding to each production link according to the production links configured by the production line, and one link task corresponds to multiple production links; inputting the link tasks and the corresponding multiple production links into a pre-trained order allocation model to obtain the production links and task processing sequence of the link tasks output by the order allocation model; and controlling the production links to process the corresponding link tasks according to the task processing sequence.

[0115] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0116] Of course, the storage medium containing computer executable instructions provided in the embodiments of the present application is not limited to the order processing method based on the network model as described above, and can also execute related operations in the order processing method based on the network model provided in any embodiment of the present application.

[0117] The network model-based order processing apparatus, device and storage medium provided in the above embodiments can execute the network model-based order processing method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the network model-based order processing method provided in any embodiment of the present application.

[0118] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. An order processing method based on a network model, characterized in that: include: According to the order products in the order information, the order information is divided into product order information corresponding to various order products; Determine the production task of the corresponding order product according to the product order information, and split the production task into link tasks corresponding to each production link according to the production links configured in the production line, where one link task corresponds to multiple production links; Input the link tasks and the corresponding multiple production links into a pre-trained order allocation model to obtain the production links and task processing sequence for processing the link tasks output by the order allocation model, wherein the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, production links and task processing sequence for processing the sample link tasks, and task processing time and task processing error rate when the production link processes the sample link tasks; Control the production links to process the corresponding link tasks according to the task processing sequence.

2. The method according to claim 1, characterized in that The product order information includes the product type and order quantity of the ordered product; Correspondingly, determining the production task of the corresponding order product according to the order information includes: Determine the production steps of the ordered product according to the product type, and determine the number of executions of the production steps according to the ordered quantity; A production task for the order product is generated according to the production steps and the corresponding execution times.

3. The method according to claim 2, characterized in that The production process of the production line is configured according to the production process of the production line. The production tasks are divided into the process tasks corresponding to each production process, including: Splitting the production step into multiple sub-steps according to the production links configured in the production line, and determining multiple production links corresponding to each sub-step; According to the sub-steps and the execution times, the link tasks corresponding to each sub-step are generated, and multiple production links corresponding to the link tasks are determined.

4. The method according to claim 1, characterized in that The step of inputting the link tasks and the corresponding multiple production links into a pre-trained order allocation model to obtain the production links and task processing sequence output by the order allocation model for processing the link tasks includes: The link tasks and corresponding production links corresponding to all product order information are input into the order allocation model, and the order allocation model is used to determine the production link for processing the link task and the task processing sequence from the multiple production links corresponding to the link task.

5. The method according to claim 1, characterized in that After all the link tasks and corresponding production links corresponding to the product order information are input into the order allocation model, the following is further included: Obtaining the task processing time and task processing error rate corresponding to the sample link tasks output by the order allocation model; When it is determined that the task processing time or the task processing error rate meets the corresponding preset threshold, the link tasks and the task processing sequence of the production link processing are adjusted.

6. The method according to claim 1, characterized in that The step of controlling the production step processing corresponding step tasks according to the task processing sequence includes: The link tasks and the task processing sequence are sent to the controller of the corresponding production link, so that the controller controls the production link to process the link tasks according to the task processing sequence.

7. An order processing device based on a network model, characterized in that: include: An order classification module is configured to classify the order information into product order information corresponding to various order products according to the order products in the order information; A task classification module is configured to determine the production task of the corresponding order product according to the product order information, and split the production task into link tasks corresponding to each production link according to the production links configured in the production line, and one link task corresponds to multiple production links; A task allocation module is configured to input the link tasks and the corresponding multiple production links into a pre-trained order allocation model, and obtain the production links and task processing sequence for processing the link tasks output by the order allocation model, wherein the order allocation model is obtained by training a preset neural network model through multiple groups of sample data, each group of the sample data includes sample link tasks corresponding to multiple sample product order information and production links corresponding to the sample link tasks, the production links and task processing sequence for processing the sample link tasks, and the task processing time and task processing error rate when the production link processes the sample link tasks; The product production module is configured to control the production links to process corresponding link tasks according to the task processing sequence.

8. An electronic device, characterized in that: include: memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the order processing method based on the network model as described in any one of claims 1-6.

9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the order processing method based on the network model as described in any one of claims 1-6 when executed by a computer processor.

Images