Multi-layer workshop resource control method and device, electronic equipment and storage medium

Abstract

The embodiments of the present application provide a multi-layer workshop resource control method and device, electronic device and storage medium, which belong to the field of artificial intelligence technology. The method includes: obtaining the total workshop resources and workshop performance targets of the multi-layer workshop; allocating resources for the total workshop resources to obtain single-layer workshop resources; based on the pre-built target performance evaluation model, the workshop performance target and the single-layer workshop resources, allocating resources for the workshop production line to obtain a production line resource allocation plan; based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop, allocating resources for the single-layer workshop to obtain a workshop resource allocation plan; based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop, allocating resources for the multi-layer workshop. The embodiments of the present application can improve and reduce the computational complexity of multi-layer workshop resource control.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a multi-layer workshop resource control method and device, electronic equipment and storage medium. Background Art

[0002] At present, the common multi-layer workshop resource control method is to use computer software to simulate the resource allocation of the multi-layer workshop, perform simulation modeling, obtain the workshop simulation model, and then use the workshop simulation model to allocate resources to achieve the preset performance goals. For example, when the performance goal of the workshop is to minimize the average production cycle, and the workshop resources are workshop workers, workshop workstations and workshop transport vehicles, the workshop workers, workshop workstations and workshop transport vehicles are allocated through the workshop simulation model of the workshop, and the workshop average production cycle of the workshop after each allocation is calculated, and then the allocation plan of workshop workers, workshop workstations and workshop transport vehicles with the smallest workshop average production cycle is selected. However, this method requires the entire workshop to be simulated as a whole and the performance data of the entire workshop is calculated at the same time. When there are many workshops, the calculation difficulty increases, which makes the calculation complexity of the multi-layer workshop resource control larger, resulting in a decrease in the efficiency of the multi-layer workshop resource control. Therefore, how to reduce the calculation complexity of the multi-layer workshop resource control has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a multi-layer workshop resource control method and device, electronic device and storage medium, aiming to reduce the computational complexity of multi-layer workshop resource control.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a multi-layer workshop resource control method, the method comprising:

[0005] Obtaining total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, each of the single-layer workshops includes multiple workshop production lines, and the workshop performance targets are used to represent the performance targets that need to be achieved after resource allocation for the multi-layer workshops;

[0006] Allocating resources to the total resources of the workshop to obtain single-layer workshop resources, wherein the single-layer workshop resources are used to represent the resources allocated to the single-layer workshop;

[0007] Based on the pre-built target performance evaluation model, the workshop performance target and the single-layer workshop resources, resources are allocated for the workshop production line to obtain a production line resource allocation plan;

[0008] Based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop, resources are allocated for the single-layer workshop to obtain a workshop resource allocation plan;

[0009] Based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop, resources are allocated to the multi-layer workshop.

[0010] In some embodiments, the workshop production line includes a starting production line, a middle production line and a tail production line, and the resource allocation for the workshop production line is performed based on the pre-built target performance evaluation model, the workshop performance target and the single-layer workshop resources to obtain a production line resource allocation plan, including:

[0011] Based on the single-layer workshop resources, the workshop performance target and the target performance evaluation model, resources are allocated to the starting production line to obtain a starting production line allocation plan;

[0012] Based on the initial production line allocation plan and the single-layer workshop resources, the production line resources of the middle row of production lines are calculated to obtain the allocatable resources of the middle row of production lines;

[0013] Based on the allocatable resources of the middle production line, the workshop performance target and the target performance evaluation model, allocating resources to the middle production line to obtain an allocation plan for the middle production line;

[0014] Determine the last production line allocation plan of the last production line based on the middle production line allocation plan and the allocatable resources of the middle production line;

[0015] The production line resource allocation plan is determined based on the starting production line allocation plan, the middle row production line allocation plan and the end production line allocation plan.

[0016] In some embodiments, allocating resources to the starting production line based on the single-layer workshop resources, the workshop performance target, and the target performance evaluation model to obtain a starting production line allocation plan includes:

[0017] Based on the pre-built production line balancer and the single-layer workshop resources, determine the initial resource allocation plan of the starting production line, wherein the production line balancer is used to adjust the resource allocation between the workshop production lines;

[0018] Based on the target performance evaluation model and the initial resource allocation plan, a performance evaluation is performed on the starting production line to obtain initial production line performance data;

[0019] Based on the production line balancer and the single-layer workshop resources, adjusting the initial resource allocation plan to obtain an updated resource allocation plan;

[0020] Based on the target performance evaluation model and the updated resource allocation scheme, a performance evaluation is performed on the starting production line to obtain updated production line performance data;

[0021] Determine the target production line resource allocation direction of the starting production line based on the initial resource allocation plan, the updated resource allocation plan, the initial production line performance data, the updated production line performance data and the workshop performance target;

[0022] Based on the resource allocation direction of the target production line and the production line balancer, resources are adjusted for the starting production line to obtain the starting production line allocation plan.

[0023] In some embodiments, determining the target production line resource allocation direction of the starting production line based on the initial resource allocation plan, the updated resource allocation plan, the initial production line performance data, the updated production line performance data, and the workshop performance target includes:

[0024] Compare the initial resource allocation plan with the updated resource allocation plan to obtain the production line resource allocation direction of the starting production line, wherein the production line resource allocation direction indicates an increase or decrease in resources of the starting production line;

[0025] Compare the initial production line performance data with the updated production line performance data to obtain the production line performance change direction of the starting production line, wherein the production line performance change direction indicates whether the performance of the starting production line is approaching or moving away from the workshop performance target;

[0026] If the direction of the production line performance change indicates that the performance of the starting production line is approaching the workshop performance target, the production line resource allocation direction is used as the target production line resource allocation direction;

[0027] If the direction of the production line performance change indicates that the performance of the starting production line is moving away from the workshop performance target, the opposite direction of the production line resource allocation direction is used as the target production line resource allocation direction.

[0028] In some embodiments, allocating resources to the multi-layer workshop based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop includes:

[0029] Based on the workshop resource allocation plan and the total resources of the workshop, resources are allocated to the single-layer workshop to obtain actual resources of the single-layer workshop;

[0030] Based on the production line resource allocation plan and the actual resources of the single-layer workshop, resources are allocated to the workshop production line.

[0031] In some embodiments, the resource allocation for the single-layer workshop is performed based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop to obtain the workshop resource allocation plan, including:

[0032] Based on the target performance evaluation model and the production line resource allocation plan, a performance evaluation is performed on the single-layer workshop to obtain initial workshop performance data;

[0033] Based on the pre-built workshop balancer and the total resources of the workshop, the resources of the single-layer workshop are readjusted to obtain a readjusted resource allocation plan, wherein the workshop balancer is used to adjust the resource allocation between the single-layer workshops;

[0034] Based on the resource reallocation plan, resources are reallocated to the production line of the workshop to obtain a production line resource reallocation plan;

[0035] Based on the target performance evaluation model and the production line resource readjustment plan, a performance evaluation is performed on the single-layer workshop to obtain performance data of the readjustment workshop;

[0036] Determine the target workshop resource allocation direction of the single-layer workshop based on the production line resource allocation plan, the production line resource readjustment plan, the initial workshop performance data, the readjusted workshop performance data and the workshop performance target;

[0037] Based on the target workshop resource allocation direction and the workshop balancer, resources are adjusted for the single-layer workshop to obtain the workshop resource allocation plan.

[0038] In some embodiments, the training method of the target performance evaluation model includes:

[0039] Acquiring resource allocation data and workshop performance data of the multi-layer workshop;

[0040] Inputting the resource allocation data into a preset initial performance evaluation model for forward propagation to obtain estimated workshop performance data;

[0041] Calculating a loss value between the estimated workshop performance data and the workshop performance data using a preset loss function;

[0042] If the loss value is greater than a preset loss threshold, the loss value and the estimated workshop performance data are input into the initial performance evaluation model for back propagation to obtain the target performance evaluation model.

[0043] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a multi-layer workshop resource control device, the device comprising:

[0044] A workshop resource acquisition module, used to acquire the total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, and the single-layer workshop includes multiple workshop production lines;

[0045] A workshop total resource allocation module, used for allocating workshop resources to the total resources of the workshop to obtain single-layer workshop resources;

[0046] A production line resource allocation module, used to allocate resources for the workshop production line based on a pre-built target performance evaluation model, the workshop performance target and the single-layer workshop resources, and obtain a production line resource allocation plan;

[0047] A workshop resource allocation module, configured to allocate resources for the single-layer workshop based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop, and obtain a workshop resource allocation plan;

[0048] The workshop resource allocation module is used to allocate resources to the multi-layer workshop based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop.

[0049] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0050] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0051] The multi-layer workshop resource control method and device, electronic device and storage medium proposed in the present application obtain the single-layer workshop resources of each single-layer workshop by allocating resources to the total resources of the workshop, and then allocate resources to the workshop production line according to the pre-constructed target performance evaluation model, workshop performance goals and single-layer workshop resources to obtain the production line resource allocation plan. According to the target performance evaluation model, the production line resource allocation plan, the workshop performance goals and the total resources of the workshop, the resources of the single-layer workshop are allocated to obtain the workshop resource allocation plan, thereby decomposing the resource allocation problem of the multi-layer workshop into the resource allocation problem of the workshop production line, thereby reducing the modeling difficulty of the multi-layer workshop, and the computational complexity of the resource control of the multi-layer workshop is also reduced accordingly. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of a multi-layer workshop resource control method provided in an embodiment of the present application;

[0053] Figure 2 is a flow chart of a target performance evaluation model training method provided in an embodiment of the present application;

[0054] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.

[0055] Figure 4 yes Figure 3 Flow chart of step S301 in FIG.

[0056] Figure 5 yes Figure 4 Flow chart of step S405 in FIG.

[0057] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0058] Figure 7 yes Figure 1 Flow chart of step S105 in FIG.

[0059] Figure 8 It is a structural schematic diagram of a multi-layer workshop resource control device provided in an embodiment of the present application;

[0060] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is 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 application and are not used to limit the present application.

[0062] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0064] First, some nouns involved in this application are analyzed:

[0065] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0066] At present, the common multi-layer workshop resource control method is to use computer software to simulate the resource allocation of the multi-layer workshop, perform simulation modeling, obtain the workshop simulation model, and then use the workshop simulation model to allocate resources to achieve the preset performance goals. For example, when the performance goal of the workshop is to minimize the average production cycle, and the workshop resources are workshop workers, workshop workstations and workshop transport vehicles, the workshop workers, workshop workstations and workshop transport vehicles are allocated through the workshop simulation model of the workshop, and the workshop average production cycle of the workshop after each allocation is calculated, and then the allocation plan of workshop workers, workshop workstations and workshop transport vehicles with the smallest workshop average production cycle is selected. However, this method requires the entire workshop to be simulated as a whole and the performance data of the entire workshop is calculated at the same time. When there are many workshops, the calculation difficulty increases, which makes the calculation complexity of the multi-layer workshop resource control larger, resulting in a decrease in the efficiency of the multi-layer workshop resource control. Therefore, how to reduce the calculation complexity of the multi-layer workshop resource control has become a technical problem that needs to be solved urgently.

[0067] Based on this, the embodiments of the present application provide a multi-layer workshop resource control method and device, an electronic device and a storage medium, aiming to reduce the computational complexity of multi-layer workshop resource control.

[0068] The recommendation method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the recommendation method in the embodiments of the present application is described.

[0069] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0070] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The multi-layer workshop resource control method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The multi-layer workshop resource control method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services; the software can be an application that implements the multi-layer workshop resource control method, etc., but is not limited to the above forms.

[0072] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0073] Figure 1 is an optional flow chart of the multi-layer workshop resource control method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0074] Step S101, obtaining the total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, each single-layer workshop includes multiple workshop production lines, and the workshop performance targets are used to represent the performance targets that need to be achieved after resource allocation in the multi-layer workshop;

[0075] Step S102, performing resource allocation on the total resources of the workshop to obtain single-layer workshop resources, wherein the single-layer workshop resources are used to represent the resources allocated to the single-layer workshop;

[0076] Step S103, based on the pre-built target performance evaluation model, workshop performance target and single-layer workshop resources, resources are allocated for the workshop production line to obtain a production line resource allocation plan;

[0077] Step S104, based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop, resources are allocated for the single-layer workshop to obtain a workshop resource allocation plan;

[0078] Step S105, allocating resources to multi-layer workshops based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop.

[0079] In steps S101 to S105 shown in the embodiment of the present application, the total resources of the workshop are obtained by acquiring the resource data of the multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, and each single-layer workshop includes multiple workshop production lines. After determining the workshop performance goals, the total resources of the workshop are allocated to obtain the single-layer workshop resources, and then according to the pre-constructed target performance evaluation model, workshop performance goals and single-layer workshop resources, resources are allocated for all workshop production lines to obtain the production line resource allocation plan. Furthermore, according to the above-mentioned target performance evaluation model, workshop performance goals, production line resource allocation plan and total workshop resources, resources are allocated for all single-layer workshops to obtain the workshop resource allocation plan. Finally, according to the workshop resource allocation plan, production line resource allocation plan and total workshop resources, resources are allocated for the multi-layer workshops. Therefore, this application allocates resources to the total resources of the workshop to obtain the single-layer workshop resources of each single-layer workshop, and then allocates resources to the workshop production line according to the pre-built target performance evaluation model, workshop performance goals and single-layer workshop resources to obtain the production line resource allocation plan. According to the target performance evaluation model, the production line resource allocation plan, the workshop performance goals and the total resources of the workshop, the single-layer workshop is allocated resources to obtain the workshop resource allocation plan, thereby decomposing the resource allocation problem of multi-layer workshops into the resource allocation problem of workshop production lines, thereby reducing the modeling difficulty and computational complexity of multi-layer workshops and improving the speed of resource regulation in multi-layer workshops.

[0080] In one application scenario, taking the allocation of resources of a multi-layer production workshop to minimize the average production cycle of the workshop as an example, the fixed resource data of the workshop, such as the number of workers, the number of workstations, the size of the buffer zone, etc. in the multi-layer production workshop, that is, the total resources of the production workshop, is obtained, and the workshop performance target of the multi-layer production workshop is clarified as minimizing the average production cycle. The number of workers, the number of workstations, the size of the buffer zone, etc. in the multi-layer production workshop is allocated to obtain the number of resources such as the number of workers, the number of workstations, the size of the buffer zone, etc. in each single-layer production workshop, that is, the resources of the single-layer production workshop. Furthermore, according to the average production cycle prediction model trained in advance, the resources of the above-mentioned single-layer production workshop, and the workshop performance with the minimum average production cycle as the target, the production line of each single-layer production workshop is allocated resources to obtain the resource allocation method of all production workshop production lines. The plan is the production line resource allocation plan, which includes the production line worker allocation plan, the production line workstation allocation plan and the production line buffer allocation plan, etc. Secondly, according to the above-mentioned average production cycle prediction model, the above-mentioned total resources of the production workshop, the above-mentioned production line resource allocation plan and the above-mentioned workshop performance goals, resources are allocated for each single-layer workshop to obtain the resource allocation plan of each single-layer production workshop, that is, the workshop resource allocation plan, wherein the workshop resource allocation plan includes the workshop worker allocation plan, the workshop workstation allocation plan and the workshop buffer allocation plan, etc. Finally, according to the resource allocation plan of each single-layer production workshop, the resource allocation plan of each production workshop production line and the total resources of the multi-layer production workshop, resources are allocated for the multi-layer production workshop to obtain the resource allocation plan that minimizes the average production cycle of the multi-layer production workshop.

[0081] In step S101 of some embodiments, a multi-layer workshop refers to a combination of workshops containing multiple layers of interrelated single-layer workshops, and the total workshop resources refer to the number of fixed resources in the multi-layer workshop, for example, the number of workshop workers, the number of workshop workstations, and the size of the workshop buffer. The workshop performance target refers to the performance index that the multi-layer workshop is expected to achieve after resource allocation. This application obtains the total workshop resources by counting the number of resources in the multi-layer workshop, and then determines the workshop performance target of the multi-layer workshop according to the performance expectation index of the multi-layer workshop proposed by the workshop manager.

[0082] It should be noted that, in one embodiment of the present application, a multi-layer workshop is composed of a plurality of interrelated single-layer workshops, and each single-layer workshop is composed of a plurality of interrelated workshop production lines.

[0083] It is also important to know that the resources contained in the workshop production line and the single-layer workshop are the same, and the resources contained in the single-layer workshop and the multi-layer workshop are the same. For example, the resources in the multi-layer workshop include workers, workstations and buffers, etc., then the resources in the single-layer workshop contained in the multi-layer workshop also include workers, workstations and buffers.

[0084] In step S102 of some embodiments, the single-layer workshop resources represent the resource data of the single-layer workshop. After the total workshop resources of the multi-layer workshop are obtained, the total workshop resources are randomly allocated to obtain the resource data of each single-layer workshop, that is, the single-layer workshop resources.

[0085] It should be noted that, in one embodiment of the present application, a workshop balancer may be used for initial resource allocation.

[0086] In step S103 of some embodiments, the target performance evaluation model refers to a model used to evaluate the performance of a multi-layer workshop, wherein the performance of the multi-layer workshop may be values ​​such as the average production cycle or the total production output. It should be noted that in the embodiments of the present application, the target performance evaluation model is a trained performance evaluation model to reduce the model training time of the multi-layer workshop resource control and improve the efficiency of the multi-layer workshop resource control.

[0087] Specifically, see Figure 2 In some embodiments, the training method of the target performance evaluation model in step S103 may include but is not limited to steps S201 to S204:

[0088] Step S201, obtaining resource allocation data and workshop performance data of multi-layer workshops;

[0089] Step S202, inputting the resource allocation data into a preset initial performance evaluation model for forward propagation to obtain estimated workshop performance data;

[0090] Step S203, using a preset loss function to calculate the loss value between the estimated workshop performance data and the workshop performance data;

[0091] Step S204: If the loss value is greater than a preset loss threshold, the loss value and the estimated workshop performance data are input into the initial performance evaluation model for back propagation to obtain a target performance evaluation model.

[0092] In step S201 of some embodiments, resource allocation data refers to the allocation scheme of allocable resources in a multi-layer workshop, wherein the allocable resources may be workshop workers, workshop workstations, workshop transport vehicles, and workshop buffers, etc. Workshop performance data refers to the performance data of a multi-layer workshop when the resource allocation scheme of the multi-layer workshop is the above resource allocation data. The present application can use simulation software to simulate a multi-layer workshop to obtain a simulated workshop, and then run the simulated workshop based on the resource allocation data to obtain workshop performance data corresponding to the resource allocation data. It should be noted that the resource allocation data can be obtained by randomly adjusting the number of resources in the multi-layer workshop. In addition, the present application can also search for historical resource allocation schemes and historical performance data of a multi-layer workshop as resource allocation data and workshop performance data, wherein the historical resource allocation scheme refers to the resource allocation scheme used by a multi-layer workshop no more than one month from the current time, and the historical performance data refers to the performance data of a multi-layer workshop under the historical resource allocation scheme.

[0093] In step S202 of some embodiments, the initial performance evaluation model refers to a prediction model whose model parameters have not been adjusted. The present application uses the pre-built initial performance evaluation model to forward propagate the input resource allocation data to obtain the estimated workshop performance data.

[0094] In step S203 of some embodiments, the loss function may be a mean square error loss function, a cross entropy loss function, etc., which is mainly used to calculate the gap between the estimated workshop performance data and the workshop performance data. The present application may use a mean square error loss function to calculate the gap between the estimated workshop performance data and the workshop performance data to obtain a loss value.

[0095] In step S204 of some embodiments, the loss threshold is the maximum difference between the estimated workshop performance data and the workshop performance data set in advance. When the loss value is greater than the loss threshold set in advance, the application inputs the loss value and the estimated workshop performance data output by the initial performance evaluation model into the initial performance evaluation model for back propagation to obtain the target performance evaluation model, and adjusts the parameters of the initial performance evaluation model so that the estimated workshop performance output by the initial performance evaluation model is closer to the workshop performance data, thereby improving the precision and accuracy of the target performance evaluation model.

[0096] It should be noted that common back-propagation algorithms include gradient descent method, stochastic gradient descent method, etc. In one embodiment of the present application, the gradient descent method is used to perform back-propagation of the initial performance evaluation model.

[0097] In steps S201 to S204 shown in this embodiment, resource allocation data and workshop performance data of the multi-layer workshop are obtained, and then the obtained resource allocation data is input into the initial performance evaluation model for forward propagation to obtain estimated workshop performance data, and the loss value between the estimated workshop performance data and the workshop performance data is calculated. When the loss value is greater than a preset loss threshold, the loss value and the estimated workshop performance data are input into the initial performance evaluation model for back propagation to obtain a target performance evaluation model, so that the target performance evaluation model can accurately predict the workshop performance data of the multi-layer workshop under various resource allocation data, thereby reducing the simulation of the multi-layer workshop and improving the efficiency of resource regulation of the multi-layer workshop.

[0098] It should be noted that in step S103 of some embodiments, when the total amount of resources is a single-layer workshop resource, the target performance evaluation model can be used to allocate resources to the workshop production lines one by one so that the performance data of each workshop production line can reach the workshop performance target.

[0099] It should be noted that when allocating resources to the workshop production lines, the workshop production lines can be divided into the starting production line, the middle column production line and the last production line, among which the starting production line refers to the first workshop production line to which resources are allocated in the current single-layer workshop, the last production line refers to the last workshop production line to which resources are allocated in the current single-layer workshop, and the middle column production line refers to the workshop production line in the current single-layer workshop except the starting production line and the last production line.

[0100] For details, see Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S305:

[0101] Step S301, based on the single-layer workshop resources, workshop performance targets and target performance evaluation model, resources are allocated to the starting production line to obtain a starting production line allocation plan;

[0102] Step S302, based on the initial production line allocation plan and the single-layer workshop resources, the production line resources of the middle row of production lines are calculated to obtain the allocatable resources of the middle row of production lines;

[0103] Step S303, based on the allocatable resources of the middle production line, the workshop performance target and the target performance evaluation model, allocate resources to the middle production line to obtain an allocation plan for the middle production line;

[0104] Step S304, determining the last production line allocation plan of the last production line based on the middle production line allocation plan and the allocatable resources of the middle production line;

[0105] Step S305, determining a production line resource allocation plan based on the start production line allocation plan, the middle row production line allocation plan and the end production line allocation plan.

[0106] In step S301 of some embodiments, a target performance evaluation model is used to evaluate the resource allocation combination of the starting production line under the constraints of single-layer workshop resources to obtain multiple evaluation results. An evaluation result that meets the workshop performance target is selected from the multiple evaluation results as the target evaluation result, and the resource allocation combination corresponding to the target evaluation result is used as the resource allocation plan for the starting production line to obtain the allocation plan for the starting production line.

[0107] It is important to know that the starting production line is the first workshop production line in a single-layer workshop to allocate resources, so the range of resources available to the starting production line can be between zero and the single-layer workshop resources.

[0108] See also Figure 4 In some embodiments, step S301 may include but is not limited to steps S401 to S406:

[0109] Step S401, based on the pre-built production line balancer and the resources of the single-layer workshop, determine the initial resource allocation plan of the starting production line, wherein the production line balancer is used to adjust the resource allocation between the workshop production lines;

[0110] Step S402, based on the target performance evaluation model and the initial resource allocation plan, the performance of the starting production line is evaluated to obtain initial production line performance data;

[0111] Step S403, based on the production line balancer and the single-layer workshop resources, the initial resource allocation plan is adjusted to obtain an updated resource allocation plan;

[0112] Step S404, based on the target performance evaluation model and the updated resource allocation plan, the starting production line is evaluated for performance to obtain updated production line performance data;

[0113] Step S405, determining the target production line resource allocation direction of the starting production line based on the initial resource allocation plan, the updated resource allocation plan, the initial production line performance data, the updated production line performance data and the workshop performance target;

[0114] Step S406: Based on the resource allocation direction of the target production line and the production line balancer, the resources of the starting production line are adjusted to obtain a starting production line allocation plan.

[0115] In step S401 of some embodiments, the production line balancer is used to adjust the resource allocation between each workshop production line in a single-layer workshop. For example, the resources of a single-layer workshop include 10 workshop workers, 10 workshop workstations and 10 workshop transport vehicles. When the production line resources of the starting production line are 2 workshop workers, 1 workshop workstation and 2 workshop transport vehicles, the resources of the middle production line and the last production line are 8 workshop workers, 9 workshop workstations and 8 workshop transport vehicles. After adjusting the resources through the production line balancer, the production line resources of the starting production line can be 3 workshop workers, 2 workshop workstations and 2 workshop transport vehicles. At this time, the resources of the middle production line and the last production line are 7 workshop workers, 8 workshop workstations and 8 workshop transport vehicles. The initial resource allocation plan refers to the resource allocation plan when the starting production line performs the first resource allocation. Under the constraints of the single-layer workshop resources, this application uses the production line balancer to randomly allocate resources to the starting production line to obtain an initial resource allocation plan.

[0116] In step S402 of some embodiments, resource data in the initial resource allocation scheme is input into the target performance evaluation model, so that performance data of the starting production line under the initial resource allocation scheme, ie, initial production line performance data, can be obtained.

[0117] In step S403 of some embodiments, after obtaining the initial production line performance data of the starting production line under the initial resource allocation plan, in order to determine whether the initial production line performance data reaches the workshop performance target, it is also necessary to adjust the resource allocation plan of the starting production line, that is, use the production line balancer to adjust the resource allocation of the initial resource allocation plan under the constraints of the single-layer workshop resources, and obtain an updated resource allocation plan after the resource allocation adjustment.

[0118] In step S404 of some embodiments, a method for performing a performance evaluation on the starting production line based on a target performance evaluation model and an updated resource allocation plan to obtain updated production line performance data is similar to a method for performing a performance evaluation on the starting production line based on a target performance evaluation model and an initial resource allocation plan to obtain initial production line performance data, and therefore is not described in detail herein.

[0119] In step S405 of some embodiments, the target production line resource allocation direction of the starting production line is determined based on the change direction between the initial resource allocation plan and the updated resource allocation plan, the change direction between the initial production line performance data and the updated production line performance data and the workshop performance target.

[0120] Specifically, see Figure 5 In some embodiments, step S405 may include but is not limited to steps S501 to S504:

[0121] Step S501, comparing the initial resource allocation plan with the updated resource allocation plan to obtain the production line resource allocation direction of the starting production line, wherein the production line resource allocation direction indicates an increase or decrease in resources of the starting production line;

[0122] Step S502, comparing the initial production line performance data with the updated production line performance data to obtain the production line performance change direction of the starting production line, wherein the production line performance change direction indicates whether the performance of the starting production line is approaching or moving away from the workshop performance target;

[0123] Step S503: if the direction of the production line performance change indicates that the performance of the starting production line is approaching the workshop performance target, the production line resource allocation direction is used as the target production line resource allocation direction;

[0124] Step S504: If the direction of the production line performance change indicates that the performance of the starting production line is moving away from the workshop performance target, the opposite direction of the production line resource allocation direction is used as the target production line resource allocation direction.

[0125] In step S501 of some embodiments, the allocated quantities of various resources in the initial resource allocation plan are compared with the allocated quantities of various resources in the updated resource allocation plan to determine whether the resources of the starting production line are increased or decreased, thereby obtaining the production line resource allocation direction of the starting production line. For example, when the initial resource allocation plan indicates that the resources allocated to the starting production line include 3 workshop workers, 3 workshop workstations and 3 vehicle workshop transport vehicles, and the updated resource allocation plan indicates that the resources allocated to the starting production line include 4 workshop workers, 4 workshop workstations and 4 vehicle workshop transport vehicles, by comparing the changes in the quantities of various resources in the starting production line, it is determined that various resources of the starting production line have increased, and the increase of various resources is used as the production line resource allocation direction of the starting production line.

[0126] In step S502 of some embodiments, the initial production line performance data of the starting production line under the initial resource allocation scheme is compared with the updated production line performance data of the starting production line under the updated resource allocation scheme to determine whether the performance data of the starting production line is approaching the workshop performance target, thereby obtaining the direction of production line performance change of the starting production line. For example, when the workshop performance target is to minimize the average production cycle, and the initial production line performance data indicates that the average production cycle of the starting production line is 30s, and the updated production line performance data indicates that the average production cycle of the starting production line is 28s, by comparing the changes in the average production cycle duration of the starting production line, it is determined that the performance data of the starting production line is approaching the workshop performance target, and the direction of production line performance change of the starting production line is taken as the approach of the performance data of the starting production line to the workshop performance target.

[0127] In step S503 of some embodiments, when the direction of production line performance change indicates that the performance of the starting production line is approaching the workshop performance target, it indicates that the production line resource allocation direction of the starting production line is consistent with the workshop performance target. Therefore, the production line resource allocation direction is used as the target production line resource allocation direction of the starting production line.

[0128] In step S504 of some embodiments, when the direction of the production line performance change indicates that the performance of the starting production line is far away from the workshop performance target, it indicates that the production line resource allocation direction of the starting production line is inconsistent with the workshop performance target. Therefore, the opposite direction of the production line resource allocation direction is used as the target production line resource allocation direction of the starting production line.

[0129] In steps S501 to S504 illustrated in the present embodiment, by comparing the initial resource allocation plan with the updated resource allocation plan, the production line resource allocation direction of the starting production line at the current moment is clarified, and then the initial production line performance data with the updated production line performance data are compared to determine the direction of change in production line performance of the starting production line at the current moment. When the direction of change in production line performance indicates that the performance of the starting production line is approaching the workshop performance target, the production line resource allocation direction is used as the target production line resource allocation direction of the starting production line. When the direction of change in production line performance indicates that the performance of the starting production line is far away from the workshop performance target, the opposite direction of the production line resource allocation direction is used as the target production line resource allocation direction of the starting production line, thereby helping the production line balancer to clarify the direction of adjustment of the resource allocation plan of the starting production line, thereby reducing the resource allocation time of the production line and improving the resource allocation efficiency of the production line.

[0130] In step S406 of some embodiments, after obtaining the target production line resource allocation direction of the starting production line, the production line balancer is used to adjust the resources of the starting production line in the target production line resource allocation direction, thereby ensuring that the starting production line quickly reaches the workshop performance target and improving the allocation efficiency of the production line.

[0131] In steps S401 to S406 illustrated in the present embodiment, the target production line resource allocation direction of the starting production line is determined by comparing the initial production line performance data of the starting production line under the initial resource allocation plan with the updated production line performance data of the starting production line under the updated resource allocation plan. Then, according to the target production line resource allocation direction and the production line balancer, the resources of the starting production line are adjusted to obtain the starting production line allocation plan of the starting production line. The starting production line allocation plan can satisfy the starting production line to achieve the workshop performance goals under the constraints of single-layer workshop resources, thereby ensuring that the workshop performance goals of the multi-layer workshop are achieved.

[0132] In step S302 of some embodiments, after the initial resource allocation plan is obtained, the initial resource allocation plan is applied according to the starting production line allocation plan to calculate the production line resources used by the starting production line, and then the production line resources used by the starting production line are subtracted from the single-layer workshop resources to obtain the remaining production line resources for the middle column production lines, that is, the allocatable resources for the middle column production lines.

[0133] In step S303 of some embodiments, based on the allocatable resources of the middle column production lines, the workshop performance objectives and the target performance evaluation model, a method for allocating resources to the middle column production lines to obtain an allocation plan for the middle column production lines is similar to a method for allocating resources to the starting production lines to obtain an allocation plan for the starting production lines based on the single-layer workshop resources, the workshop performance objectives and the target performance evaluation model, and therefore is not described in detail.

[0134] In step S304 of some embodiments, the resources of each single-layer workshop are fixed. Therefore, after determining the allocated resources of the starting production line and the middle column production lines, it is only necessary to use the remaining resources in the single-layer workshop as the resources of the last production line, that is, to subtract the resources used in the allocation plan of the middle column production line from the allocatable resources of the middle column production line to obtain the resources of the last production line, and then determine the allocation plan of the last production line based on the resources of the last production line.

[0135] In step S305 of some embodiments, the starting production line allocation plan and the middle column production line allocation plan both meet the workshop performance goals. Therefore, by merging the starting production line allocation plan, the middle column production line allocation plan and the end production line allocation plan, it can be ensured that the obtained production line resource allocation plan is a resource allocation plan that meets the workshop performance goals under the constraints of single-layer workshop resources.

[0136] In steps S301 to S305 shown in this embodiment, based on the workshop performance target, resources are allocated to the starting production line in the workshop production line to obtain a starting production line allocation plan, based on the workshop performance target, resources are allocated to the middle column production lines in the workshop production line to obtain a middle column production line allocation plan, based on the single-layer workshop resources, the starting production line allocation plan and the middle column production line allocation plan, the end production line allocation plan is determined, and then the starting production line allocation plan, the middle column production line allocation plan and the end production line allocation plan are merged to ensure that the workshop production line can achieve the workshop performance target under the constraints of the single-layer workshop resources.

[0137] In step S104 of some embodiments, after obtaining the production line resource allocation plan for all workshop production lines, the resources of each single-layer workshop can be adjusted, and the resource allocation plan of all workshop production lines after the single-layer workshop resource adjustment can be calculated. The production line resource allocation plan is then compared with the resource allocation plan of all workshop production lines after the single-layer workshop resource adjustment to clarify the resource allocation direction of the workshop, thereby ensuring that the allocation of workshop resources can enable the performance of the multi-layer workshop to quickly reach the workshop performance target.

[0138] Specifically, see Figure 6 In some embodiments, step S104 includes but is not limited to steps S601 to S606:

[0139] Step S601, based on the target performance evaluation model and the production line resource allocation plan, a single-layer workshop is evaluated for performance to obtain initial workshop performance data;

[0140] Step S602, based on the pre-built workshop balancer and the total resources of the workshop, the resources of the single-layer workshop are readjusted to obtain a readjusted resource allocation plan, wherein the workshop balancer is used to adjust the resource allocation between the single-layer workshops;

[0141] Step S603, based on the resource readjustment plan, readjust the resources of the workshop production line to obtain a production line resource readjustment plan;

[0142] Step S604, based on the target performance evaluation model and the production line resource readjustment plan, a performance evaluation is performed on the single-layer workshop to obtain the readjustment workshop performance data;

[0143] Step S605, determining the target workshop resource allocation direction of the single-layer workshop based on the production line resource allocation plan, the production line resource readjustment plan, the initial workshop performance data, the readjusted workshop performance data and the workshop performance target;

[0144] Step S606: Based on the target workshop resource allocation direction and the workshop balancer, resources are adjusted for the single-layer workshop to obtain a workshop resource allocation plan.

[0145] In step S601 of some embodiments, after obtaining the production line resource allocation plan for all workshop production lines, the target performance evaluation model is used to perform performance evaluation on each single-layer workshop, and the initial workshop performance data of each single-layer workshop can be obtained.

[0146] In step S602 of some embodiments, based on the pre-built workshop balancer and the total resources of the workshop, the resources of the single-layer workshop are readjusted to obtain the readjusted resource allocation plan. The method is similar to the method of step S403 and is not repeated here.

[0147] In step S603 of some embodiments, after obtaining the resource readjustment plan for each single-layer workshop, resources are readjusted for the workshop production lines contained in each single-layer workshop to obtain a production line resource readjustment plan. Specifically, the method for readingjusting resources for the workshop production lines is similar to the method of step S103, so it is not repeated here.

[0148] In step S604 of some embodiments, a performance evaluation is performed on a single-layer workshop based on a target performance evaluation model and a production line resource realignment plan. The method for obtaining performance data of the realigned workshop is similar to the method in step S601 and is not described in detail herein.

[0149] In step S605 of some embodiments, the method for determining the target workshop resource allocation direction of a single-layer workshop based on the production line resource allocation plan, the production line resource readjustment plan, the initial workshop performance data, the readjusted workshop performance data and the workshop performance goals is similar to the method of step S405, so it is not repeated here.

[0150] In step S606 of some embodiments, after obtaining the target workshop resource allocation direction of the single-layer workshop, the workshop balancer is used to adjust the resources of the single-layer workshop in the target workshop resource allocation direction, thereby ensuring that the single-layer workshop quickly reaches the workshop performance target and improving the allocation efficiency of the single-layer workshop.

[0151] In steps S601 to S606 shown in this embodiment, by performing multiple resource allocations on the single-layer workshop, the target workshop resource allocation direction of the single-layer workshop is determined, and then the resources of the single-layer workshop are adjusted according to the target workshop resource allocation direction and the workshop balancer to obtain a workshop resource allocation plan, so that the workshop resource allocation plan can achieve the workshop performance target and improve the accuracy of workshop resource allocation. Furthermore, by hierarchically calculating the workshop resource allocation plan of each single-layer workshop in the multi-layer workshop, the computational complexity of the multi-layer workshop resource control can be reduced, thereby improving the efficiency of the multi-layer workshop resource control.

[0152] In step S105 of some embodiments, after obtaining the workshop resource allocation plan for each single-layer workshop and the production line resource allocation plan for each workshop production line, the total resources of the workshop are allocated according to the workshop resource allocation plan and the production line resource allocation plan to ensure that the resource allocation for multi-layer workshops can achieve the workshop performance goals.

[0153] See also Figure 7 In some embodiments, step S105 may include but is not limited to steps S701 to S702:

[0154] Step S701, based on the workshop resource allocation plan and the total resources of the workshop, resources are allocated to the single-layer workshop to obtain the actual resources of the single-layer workshop;

[0155] Step S702: Allocate resources to the workshop production lines based on the production line resource allocation plan and the actual resources of the single-layer workshop.

[0156] In step S701 of some embodiments, resource allocation data of each single-layer workshop, ie, actual resources of the single-layer workshop, is obtained by allocating total workshop resources of the multi-layer workshop among single-layer workshops according to a workshop resource allocation plan.

[0157] In step S702 of some embodiments, by allocating actual resources of a single-layer workshop among workshop production lines according to a production line resource allocation plan, resource allocation data for each workshop production line can be obtained, thereby achieving resource allocation for multi-layer workshops.

[0158] In steps S701 to S702 shown in this embodiment, the total workshop resources of the multi-layer workshop are allocated among the single-layer workshops according to the workshop resource allocation plan to obtain the actual resources of the single-layer workshop, and then the actual resources of the single-layer workshop are allocated among the workshop production lines according to the production line resource allocation plan, thereby ensuring that the resource allocation of the multi-layer workshop can achieve the workshop performance target.

[0159] The embodiment of the present application allocates resources to the total resources of the workshop to obtain the single-layer workshop resources of each single-layer workshop, and then allocates resources to the workshop production line according to the pre-constructed target performance evaluation model, workshop performance goals and single-layer workshop resources to obtain a production line resource allocation plan. According to the target performance evaluation model, the production line resource allocation plan, the workshop performance goals and the total resources of the workshop, the resources of the single-layer workshop are allocated to obtain a workshop resource allocation plan, thereby decomposing the resource allocation problem of the multi-layer workshop into the resource allocation problem of the workshop production line, thereby reducing the difficulty of modeling the multi-layer workshop, and reducing the computational complexity of the resource control of the multi-layer workshop.

[0160] See also Figure 8 The embodiment of the present application also provides a multi-layer workshop resource control device, which can implement the above-mentioned multi-layer workshop resource control method, and the device includes:

[0161] The workshop resource acquisition module 801 is used to acquire the total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, and the single-layer workshop includes multiple workshop production lines;

[0162] The workshop total resource allocation module 802 is used to allocate workshop total resources to obtain single-layer workshop resources;

[0163] The production line resource allocation module 803 is used to allocate resources for the workshop production line based on the pre-built target performance evaluation model, workshop performance target and single-layer workshop resources to obtain a production line resource allocation plan;

[0164] The workshop resource allocation module 804 is used to allocate resources for a single-layer workshop based on the target performance evaluation model, the production line resource allocation plan, the workshop performance target and the total resources of the workshop to obtain a workshop resource allocation plan;

[0165] The workshop resource allocation module 805 is used to allocate resources to multi-layer workshops based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop.

[0166] The specific implementation of the multi-layer workshop resource control device is basically the same as the specific implementation of the multi-layer workshop resource control method described above, and will not be repeated here.

[0167] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned multi-layer workshop resource control method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0168] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0169] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0170] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the multi-layer workshop resource control method of the embodiment of this application;

[0171] Input / output interface 903, used to implement information input and output;

[0172] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0173] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0174] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0175] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned multi-layer workshop resource control method is implemented.

[0176] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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 combinations thereof.

[0177] The multi-layer workshop resource control method, multi-layer workshop resource control device, electronic device and storage medium provided in the embodiments of the present application obtain the single-layer workshop resources of each single-layer workshop by allocating resources to the total resources of the workshop, and then allocate resources to the workshop production line according to the pre-constructed target performance evaluation model, workshop performance goals and single-layer workshop resources to obtain the production line resource allocation plan. According to the target performance evaluation model, the production line resource allocation plan, the workshop performance goals and the total resources of the workshop, the resources of the single-layer workshop are allocated to obtain the workshop resource allocation plan, thereby decomposing the resource allocation problem of the multi-layer workshop into the resource allocation problem of the workshop production line, thereby reducing the modeling difficulty of the multi-layer workshop, and the computational complexity of the resource control of the multi-layer workshop is also reduced accordingly.

[0178] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0179] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0180] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0182] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0183] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0184] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0185] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0187] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0188] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A multi-layer workshop resource control method, characterized in that: The method comprises: Obtaining the total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, each of which includes multiple workshop production lines, and the workshop performance targets are used to represent the performance targets that need to be achieved after the multi-layer workshops are allocated resources, and the workshop production lines include the starting production line, the middle production line, and the end production line; Allocating resources to the total resources of the workshop to obtain single-layer workshop resources, wherein the single-layer workshop resources are used to represent the resources allocated to the single-layer workshop; Based on the single-layer workshop resources, the workshop performance objectives and the target performance evaluation model, resources are allocated to the starting production line to obtain a starting production line allocation plan; Based on the initial production line allocation plan and the single-layer workshop resources, the production line resources of the middle row of production lines are calculated to obtain the allocatable resources of the middle row of production lines; Based on the allocatable resources of the middle production line, the workshop performance target and the target performance evaluation model, allocating resources to the middle production line to obtain an allocation plan for the middle production line; Determine the last production line allocation plan of the last production line based on the middle production line allocation plan and the allocatable resources of the middle production line; Determine a production line resource allocation plan based on the starting production line allocation plan, the middle row production line allocation plan, and the last production line allocation plan; Based on the target performance evaluation model and the production line resource allocation plan, a performance evaluation is performed on the single-layer workshop to obtain initial workshop performance data; Based on a pre-built workshop balancer and the total resources of the workshop, resources of the single-layer workshop are readjusted to obtain a readjusted resource allocation plan, wherein the workshop balancer is used to adjust resource allocation between the single-layer workshops; Based on the resource reallocation plan, resources are reallocated to the production line of the workshop to obtain a production line resource reallocation plan; Based on the target performance evaluation model and the production line resource readjustment plan, a performance evaluation is performed on the single-layer workshop to obtain performance data of the readjustment workshop; Determine the target workshop resource allocation direction of the single-layer workshop based on the production line resource allocation plan, the production line resource readjustment plan, the initial workshop performance data, the readjusted workshop performance data and the workshop performance target; Based on the target workshop resource allocation direction and the workshop balancer, adjusting resources for the single-layer workshop to obtain a workshop resource allocation plan; Based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop, resources are allocated to the multi-layer workshop.

2. The method according to claim 1, characterized in that: The method of allocating resources to the starting production line based on the single-layer workshop resources, the workshop performance target and the target performance evaluation model to obtain a starting production line allocation plan includes: Based on the pre-built production line balancer and the single-layer workshop resources, determine the initial resource allocation plan of the starting production line, wherein the production line balancer is used to adjust the resource allocation between the workshop production lines; Based on the target performance evaluation model and the initial resource allocation plan, a performance evaluation is performed on the starting production line to obtain initial production line performance data; Based on the production line balancer and the single-layer workshop resources, adjusting the initial resource allocation plan to obtain an updated resource allocation plan; Based on the target performance evaluation model and the updated resource allocation scheme, a performance evaluation is performed on the starting production line to obtain updated production line performance data; Determine the target production line resource allocation direction of the starting production line based on the initial resource allocation plan, the updated resource allocation plan, the initial production line performance data, the updated production line performance data and the workshop performance target; Based on the resource allocation direction of the target production line and the production line balancer, resources are adjusted for the starting production line to obtain the starting production line allocation plan.

3. The method according to claim 2, characterized in that The determining the target production line resource allocation direction of the starting production line based on the initial resource allocation plan, the updated resource allocation plan, the initial production line performance data, the updated production line performance data and the workshop performance target includes: Compare the initial resource allocation plan with the updated resource allocation plan to obtain the production line resource allocation direction of the starting production line, wherein the production line resource allocation direction indicates an increase or decrease in resources of the starting production line; Comparing the initial production line performance data with the updated production line performance data to obtain the production line performance change direction of the starting production line, wherein the production line performance change direction indicates whether the performance of the starting production line is approaching or moving away from the workshop performance target; If the direction of the production line performance change indicates that the performance of the starting production line is approaching the workshop performance target, the production line resource allocation direction is used as the target production line resource allocation direction; If the direction of the production line performance change indicates that the performance of the starting production line is moving away from the workshop performance target, the opposite direction of the production line resource allocation direction is used as the target production line resource allocation direction.

4. The method according to any one of claims 1 to 3, characterized in that: The allocating resources to the multi-layer workshop based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop includes: Based on the workshop resource allocation plan and the total resources of the workshop, resources are allocated to the single-layer workshop to obtain actual resources of the single-layer workshop; Based on the production line resource allocation plan and the actual resources of the single-layer workshop, resources are allocated to the workshop production line.

5. The method according to any one of claims 1 to 3, characterized in that: The training method of the target performance evaluation model includes: Acquiring resource allocation data and workshop performance data of the multi-layer workshop; Inputting the resource allocation data into a preset initial performance evaluation model for forward propagation to obtain estimated workshop performance data; Calculating a loss value between the estimated workshop performance data and the workshop performance data using a preset loss function; If the loss value is greater than a preset loss threshold, the loss value and the estimated workshop performance data are input into the initial performance evaluation model for back propagation to obtain the target performance evaluation model.

6. A multi-layer workshop resource control device, characterized in that: The device comprises: A workshop resource acquisition module, used to acquire the total workshop resources and workshop performance targets of a multi-layer workshop, wherein the multi-layer workshop includes multiple single-layer workshops, each of which includes multiple workshop production lines, and the workshop performance targets are used to characterize the performance targets that need to be achieved after the multi-layer workshops are allocated resources, and the workshop production lines include the starting production line, the middle production line, and the end production line; A workshop total resource allocation module, used to allocate workshop resources to the total resources of the workshop to obtain single-layer workshop resources; A production line resource allocation module, configured to allocate resources to the starting production line based on the single-layer workshop resources, the workshop performance objectives and the target performance evaluation model to obtain a starting production line allocation plan; calculate the production line resources of the middle column production lines based on the starting production line allocation plan and the single-layer workshop resources to obtain allocatable resources for the middle column production lines; allocate resources to the middle column production lines based on the allocatable resources for the middle column production lines, the workshop performance objectives and the target performance evaluation model to obtain a middle column production line allocation plan; determine the end production line allocation plan for the end production line based on the middle column production line allocation plan and the allocatable resources for the middle column production lines; and determine a production line resource allocation plan based on the starting production line allocation plan, the middle column production line allocation plan and the end production line allocation plan; A workshop resource allocation module, used for performing performance evaluation on the single-layer workshop based on the target performance evaluation model and the production line resource allocation plan to obtain initial workshop performance data, and for realigning resources on the single-layer workshop based on a pre-built workshop balancer and the total resources of the workshop to obtain a realigned resource allocation plan, wherein the workshop balancer is used to adjust resource allocation between the single-layer workshops, and for realigning resources on the workshop production line based on the realigned resource allocation plan to obtain a production line resource realignment plan, and for performing performance evaluation on the single-layer workshop based on the target performance evaluation model and the production line resource realignment plan to obtain realigned workshop performance data, and for determining a target workshop resource allocation direction for the single-layer workshop based on the production line resource allocation plan, the production line resource realignment plan, the initial workshop performance data, the realigned workshop performance data and the workshop performance target, and for adjusting resources on the single-layer workshop based on the target workshop resource allocation direction and the workshop balancer to obtain a workshop resource allocation plan; The workshop resource allocation module is used to allocate resources to the multi-layer workshop based on the workshop resource allocation plan, the production line resource allocation plan and the total resources of the workshop.

7. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the multi-layer workshop resource control method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the multi-layer workshop resource control method according to any one of claims 1 to 5 is implemented.

Images