Quality inspection task scheduling method and system based on hybrid multi-objective game
By inputting task, equipment, and employee information into a multi-objective game model, the scheduling scheme of the quality inspection workshop is optimized, which solves the shortcomings of multi-objective optimization in traditional methods and improves scheduling efficiency and quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-04-03
AI Technical Summary
Traditional quality inspection workshop scheduling methods are difficult to meet the needs of multiple objectives simultaneously in multi-objective optimization problems, resulting in insufficient scheduling efficiency and quality.
A quality inspection task scheduling method based on hybrid multi-objective game theory is adopted. By using task information, equipment information and employee information as multi-objective inputs to pre-set a multi-objective game model, the balance between multiple objectives is sought, and a game equilibrium solution is generated to optimize the scheduling scheme.
It effectively solves the shortcomings of traditional scheduling methods in multi-objective optimization problems, improves the scheduling efficiency and quality of the quality inspection workshop, and avoids the deterioration of other objectives caused by single-objective optimization.
Smart Images
Figure CN121787764A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a quality inspection task scheduling method and system based on hybrid multi-objective game theory. Background Technology
[0002] In modern manufacturing quality standard management, the quality inspection workshop is responsible for conducting quality inspections on products completed on the production line. For example, the standard measurement and quality inspection laboratory conducts a series of electrical and environmental protection quality tests on electricity meters, terminal data acquisition devices, etc., to ensure that products entering the market meet mandatory national standards and functional requirements. However, with the changing and diverse nature of customer samples and testing tasks, the scheduling of testing tasks in the quality inspection workshop has become increasingly complex and challenging. This process not only needs to ensure the accuracy of the tests but also needs to complete the testing tasks within a limited time. Efficient scheduling is crucial for improving production efficiency, reducing costs, and ensuring product quality.
[0003] Traditional scheduling methods mainly focus on scenarios such as production lines and freight scheduling. The constraints and resource scheduling are quite different, and in multi-objective optimization problems, it is often difficult to meet the needs of multiple objectives at the same time, so they cannot effectively solve multi-objective optimization problems in quality inspection workshop scheduling. Summary of the Invention
[0004] This application provides a quality inspection task scheduling method and system based on hybrid multi-objective game theory. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.
[0005] In a first aspect, embodiments of this application provide a quality inspection task scheduling method based on hybrid multi-objective game theory, applied to a server, the method comprising: Receive the quality inspection workshop scheduling request sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. Task information, equipment information, and employee information are used as multi-objective inputs in a pre-defined multi-objective game model; Output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display; the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee for each inspection task.
[0006] Optionally, the preset multi-objective game model includes an initial strategy allocation component, a strategy update component, an equilibrium state determination component, and a game equilibrium solution generation component; The pre-set multi-objective game model uses task information, equipment information, and employee information as multi-objective inputs, including: The initial policy allocation component assigns an initial policy to each task to be tested, each testing device, and each employee; The policy update component updates the initial policy based on task information, device information, and employee information to obtain the updated policy. The equilibrium state determination component determines whether an equilibrium state has been reached based on the update strategy. When the equilibrium solution generation component reaches an equilibrium state, it updates the strategy as the equilibrium solution.
[0007] Optionally, an initial strategy may be assigned to each task to be tested, each testing device, and each employee, including: Based on the equipment information, identify each available detection device that is currently idle; Based on employee information, identify each available employee who is currently idle; Each available testing device and each available employee can be arranged and combined to obtain multiple pairs of available device-available employee combinations; Each pair of available devices and available staff is assigned to each task to be tested, thus obtaining the initial strategy for each task to be tested; Based on the task information, determine the task arrival order and task allocation order for each task to be detected; According to the arrival order of each task to be detected, each task to be detected is assigned to each detection device to obtain the initial strategy of each detection device; According to the task assignment order of each task to be tested, each task to be tested is assigned to each employee, and the initial strategy of each employee is obtained.
[0008] Optionally, based on task information and device information, the initial policy is updated to obtain an updated policy, including: Determine the actual completion time and expected completion time of each task to be tested from the task information and equipment information; Based on the actual completion time and the expected completion time, calculate the expected benefit of each task to be detected under the initial strategy of each task to be detected; From the initial strategy of each task to be tested, the target available device-available employee combination that maximizes expected revenue is obtained as the updated strategy for each task to be tested; wherein, the formula for calculating the expected revenue of the initial strategy for each task to be tested is:
[0009] in, It is the first Expected benefits of each task to be tested It is the first The actual completion time of each task to be tested. It is the first The expected completion time for each task to be tested.
[0010] Optionally, based on task information and device information, the initial policy is updated to obtain an updated policy, including: Obtain the actual working time and total available time for each testing device from the equipment information; Based on the actual working time and total available time of each testing device, calculate the utilization rate of each testing device under the initial strategy of each testing device; When the utilization rate has not reached its maximum, the priority of each task in the initial strategy of each detection device is determined from the task information; Based on the priority of each task, the execution order of each task in the initial strategy of each detection device is adjusted, and the utilization rate of each detection device is recalculated until the utilization rate reaches its maximum, thus obtaining the updated strategy for each detection device; among which, The formula for calculating the utilization rate of each testing device under the initial strategy of each testing device is:
[0011] in, It is the first The first testing device in the Utilization rate of each testing device under the initial strategy. It is the first The actual working time of each testing device It is the first Total available time for each testing device.
[0012] Optionally, based on task information, equipment information, and employee information, the initial strategy is updated to obtain an updated strategy, including: From the employee information, obtain the working hours of each employee and the average working hours of all employees; Calculate the working hours of each employee under each employee's initial strategy, based on each employee's working hours and the average working hours of all employees. When the working time exceeds the preset time threshold, retrieve the urgency and working time limit of each task in each employee's initial strategy from the task information. Based on the urgency of each task and time constraints, the execution order of tasks in each employee's initial strategy is adjusted, and each employee's working time is recalculated until the working time is less than or equal to a preset time threshold, resulting in an updated strategy for each employee. The formula for calculating each employee's working time under each employee's initial strategy is as follows:
[0013] in, It is the first The working hours of each employee under each employee's initial strategy. It is the first The working hours of each employee It is the average working hours of all employees. It refers to the number of employees.
[0014] Optionally, the update strategy includes the target available device-available employee combination that maximizes the expected benefit of each task to be inspected, the task execution order of each inspection device, and the task processing order of each employee; Based on the update strategy, determine whether an equilibrium state has been reached, including: The target expected benefit for each test task is determined based on the target available equipment-available staff combination that maximizes the expected benefit for each test task. The target utilization rate of each testing device is determined based on the task execution sequence of each testing device; Determine the target working time for each employee based on the order in which they handle their tasks; An equilibrium state is determined when the target expected revenue of each task to be tested meets the preset revenue constraint threshold, the target utilization rate of each testing device meets the preset utilization rate constraint threshold, and the target working time of each employee meets the preset time constraint threshold.
[0015] Optionally, the method also includes: If the target expected revenue of each task to be tested does not meet the preset revenue constraint threshold, or the target utilization rate of each testing device does not meet the preset utilization rate constraint threshold, or the target working time of each employee does not meet the preset time constraint threshold, then an unbalanced state is determined.
[0016] Optionally, the method also includes: If an equilibrium state is not reached, continue to execute the steps of updating the initial strategy based on task information, equipment information, and employee information until an equilibrium state is reached.
[0017] Secondly, embodiments of this application provide a quality inspection task scheduling system based on hybrid multi-objective game theory, the system comprising: The quality inspection workshop scheduling request receiving module is used to receive quality inspection workshop scheduling requests sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. The multi-objective game model processing module is used to input task information, equipment information, and employee information as multi-objective inputs into the preset multi-objective game model. The game equilibrium solution output module is used to output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display. The game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee for each inspection task.
[0018] The technical solutions provided in this application embodiment may include the following beneficial effects: In this embodiment, a multi-objective game model is preset by taking task information, equipment information and employee information as multi-objective inputs. The preset multi-objective game model can consider multiple objectives at the same time, thereby seeking a balance among multiple objectives to find the optimal scheduling scheme. This avoids the problem of other objectives being deteriorated due to single-objective optimization in traditional methods. It can effectively solve the shortcomings of traditional scheduling methods in multi-objective optimization problems and improve the scheduling efficiency and quality of the quality inspection workshop.
[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0021] Figure 1 This is a flowchart illustrating a quality inspection task scheduling method based on hybrid multi-objective game theory provided in an embodiment of this application. Figure 2 This is a schematic diagram of the model structure of a preset multi-objective game model provided in an embodiment of this application; Figure 3A This is a schematic diagram of a user-defined configuration UI provided in an embodiment of this application; Figure 3B This is a schematic diagram of another user-defined configuration UI provided in an embodiment of this application; Figure 3C This is a schematic diagram of another user-defined configuration UI provided in an embodiment of this application; Figure 4 This is a schematic diagram of the interaction between a client and a server provided in an embodiment of this application; Figure 5 This is a UI diagram of a client displaying the game result, provided in an embodiment of this application. Figure 6 This is a schematic block diagram of a quality inspection task scheduling process based on a hybrid multi-objective game, provided in an embodiment of this application. Figure 7 This is a schematic diagram of the structure of a quality inspection task scheduling system based on hybrid multi-objective game theory provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0022] The following description and accompanying drawings fully illustrate specific embodiments of this application to enable those skilled in the art to practice them.
[0023] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.
[0024] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0025] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.
[0026] Currently, the scheduling of the quality inspection workshop mainly adopts traditional scheduling methods.
[0027] The applicant of this application recognizes that traditional scheduling methods often struggle to simultaneously satisfy the needs of multiple objectives in multi-objective optimization problems.
[0028] To address the aforementioned problems, this application provides a quality inspection task scheduling method and system based on hybrid multi-objective game theory, thereby resolving the issues present in the related technical problems. In the embodiments of this application, task information, equipment information, and employee information are used as multi-objective inputs to a pre-defined multi-objective game model. This model can simultaneously consider multiple objectives, seeking a balance among them to find the optimal scheduling scheme. This avoids the problem of single-objective optimization leading to the deterioration of other objectives in traditional methods, effectively solving the shortcomings of traditional scheduling methods in multi-objective optimization problems and improving the scheduling efficiency and quality of the quality inspection workshop. Exemplary embodiments are described in detail below.
[0029] The following will be combined with the appendix Figure 1 - Appendix Figure 6 This application provides a detailed description of the quality inspection task scheduling method based on hybrid multi-objective game theory, as provided in its embodiments. This method can be implemented using a computer program and can run on a quality inspection task scheduling system based on the von Neumann architecture and hybrid multi-objective game theory. The computer program can be integrated into applications or run as a standalone utility application.
[0030] Please see Figure 1 This document provides a flowchart illustrating a quality inspection task scheduling method based on a hybrid multi-objective game theory approach, applicable to the server side. For example... Figure 1 As shown, the method in this application embodiment includes the following steps: S101, the server receives the quality inspection workshop scheduling request sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. In this system, the server is the computer system or software that provides the service. For example, the server could be an application running on a server, such as a web-based API service. The client is the computer system or software that initiates requests, interacting with the server, sending requests, and receiving responses. A quality inspection workshop scheduling request is a request sent by the client to the server, requesting the server to perform scheduling operations in the quality inspection workshop. Task information includes data related to each task to be inspected, including the task ID, priority, expected completion time, and actual completion time. Equipment information includes data related to each testing device in the quality inspection workshop, including the device ID, type, total available time, and actual working time. Employee information includes data related to each employee in the quality inspection workshop, including the employee ID, working hours, and average working hours.
[0031] In some embodiments of this application, the client constructs a JSON object containing task information, device information, and employee information, and sends it to the server via an HTTP POST request. The server uses a web framework to receive the HTTP POST request and parses the JSON data in the request to obtain the task information, device information, and employee information carried in the request.
[0032] For example, a quality inspection workshop needs to schedule the following two tasks: Task 1: Task ID is T001, priority is 1, expected completion time is 10:00 on September 4, 2025, actual completion time is 12:00 on September 4, 2025.
[0033] Task 2: Task ID is T002, priority is 2, expected completion time is 11:00 on September 4, 2025, actual completion time is 13:00 on September 4, 2025.
[0034] The quality inspection workshop has the following two testing devices, and their information is as follows: Device 1: Device ID is D001, type is X-ray, total available time is 8 hours, actual working time is 4 hours.
[0035] Device 2: Device ID is D002, type is CT, total available time is 8 hours, actual working time is 3 hours.
[0036] The quality inspection workshop has the following two employees, whose information is as follows: Employee 1: Employee ID is E001, working hours are 6 hours, average working hours are 7 hours.
[0037] Employee 2: Employee ID is E002, working hours are 5 hours, average working hours are 7 hours.
[0038] The client packages the above information into a JSON object and sends it to the server via an HTTP POST request. Upon receiving the request, the server parses the JSON data to obtain the task information, device information, and employee information carried in the request.
[0039] For example Figure 4 As shown, the user displays this through client 120. Figure 3A Select task information, displayed through the client. Figure 3B Select device information, displayed through the client. Figure 3C Select employee information. The user clicks... Figure 3C The "Submit Scheduling Request" function can generate a quality inspection workshop scheduling request and send it to the server 110.
[0040] S102, the server uses task information, equipment information and employee information as multi-objective inputs into the preset multi-objective game model; Among them, the pre-defined multi-objective game model is an optimization model based on game theory, used to handle the conflict and coordination problems between multiple objectives. In this model, each objective (such as task completion time, equipment utilization, employee working hours, etc.) is regarded as a participant, and each participant has its own set of strategies and payoff functions.
[0041] For example Figure 2 As shown, the preset multi-objective game model includes an initial strategy allocation component, a strategy update component, an equilibrium state determination component, and a game equilibrium solution generation component.
[0042] In some embodiments of this application, the specific process of using task information, device information, and employee information as multi-objective inputs in a pre-defined multi-objective game model includes: an initial strategy allocation component allocating an initial strategy for each task to be detected, each detection device, and each employee; a strategy update component updating the initial strategy based on the task information, device information, and employee information to obtain an updated strategy; an equilibrium state determination component determining whether an equilibrium state has been reached based on the updated strategy; and a game equilibrium solution generation component using the updated strategy as the game equilibrium solution if an equilibrium state has been reached.
[0043] In some embodiments of this application, the specific process of assigning an initial strategy to each task to be tested, each testing device, and each employee includes: determining each available testing device currently in an idle state based on device information; determining each available employee currently in an idle state based on employee information; arranging and combining each available testing device and each available employee to obtain multiple pairs of available device-available employee combinations; assigning each pair of available device-available employee combinations to each task to be tested to obtain an initial strategy for each task to be tested; determining the task arrival order and task assignment order for each task to be tested based on task information; assigning each task to each testing device according to the task arrival order to obtain an initial strategy for each testing device; and assigning each task to each employee according to the task assignment order to obtain an initial strategy for each employee.
[0044] In this context, "available testing equipment" refers to testing equipment that is currently idle, and "available staff" refers to staff that are currently idle. The available equipment-available staff combination involves arranging and combining each available testing device with each available staff member to form multiple equipment-staff pairs.
[0045] In one possible implementation, the device information is traversed, and the `current_status` field of each device is checked to filter out devices that are currently idle. Similarly, the employee information is traversed, and the `current_status` field of each employee is checked to filter out employees that are currently idle. Using nested loops, each available detection device is combined with each available employee to generate multiple device-employee pairs. Each available device-employee pair is assigned to each task to be detected, resulting in an initial strategy for each task. Tasks are sorted according to the `expected_completion_time` field in the task information to obtain the task arrival order. Tasks are also sorted according to the `priority` field in the task information to obtain the task assignment order. Each task to be detected is assigned to each detection device according to the task arrival order, generating an initial strategy for each detection device. Finally, each task to be detected is assigned to each employee according to the task assignment order, generating an initial strategy for each employee. Examples of multiple device-employee pairs are shown in Table 1.
[0046] Table 1
[0047] In some embodiments of this application, the specific process of updating the initial strategy based on task information and device information to obtain the updated strategy includes: determining the actual completion time and expected completion time of each task to be detected from the task information and device information; calculating the expected benefit of each task to be detected under the initial strategy of each task to be detected based on the actual completion time and expected completion time; obtaining the target available device-available employee combination with the highest expected benefit from the initial strategies of each task to be detected as the updated strategy of each task to be detected; wherein, the formula for calculating the expected benefit under the initial strategy of each task to be detected is:
[0048] in, It is the first Expected benefits of each task to be tested It is the first The actual completion time of each task to be tested. It is the first The expected completion time for each task to be tested.
[0049] In some embodiments of this application, the specific process of updating the initial strategy based on task information and device information to obtain the updated strategy includes: obtaining the actual working time and total available time of each detection device from the device information; calculating the utilization rate of each detection device under the initial strategy of each detection device based on the actual working time and total available time of each detection device; when the utilization rate has not reached the maximum, determining the priority of each task in the initial strategy of each detection device from the task information; adjusting the execution order of each task in the initial strategy of each detection device according to the priority of each task, and recalculating the utilization rate of each detection device until the utilization rate reaches the maximum, thereby obtaining the updated strategy of each detection device; wherein, the calculation formula for the utilization rate of each detection device under the initial strategy of each detection device is:
[0050] in, It is the first The first testing device in the Utilization rate of each testing device under the initial strategy. It is the first The actual working time of each testing device It is the first Total available time for each testing device.
[0051] In some embodiments of this application, the specific process of updating the initial strategy based on task information, device information, and employee information to obtain the updated strategy includes: obtaining the working time of each employee and the average working time of all employees from the employee information; calculating the working time of each employee under each employee's initial strategy based on the working time of each employee and the average working time of all employees; when the working time is greater than a preset time threshold, obtaining the urgency and working time limit of each task in each employee's initial strategy from the task information; adjusting the execution order of each task in each employee's initial strategy according to the urgency and working time limit of each task, and recalculating the working time of each employee until the working time is less than or equal to the preset time threshold, thereby obtaining the updated strategy for each employee; wherein, the formula for calculating the working time of each employee under each employee's initial strategy is:
[0052] in, It is the first The working hours of each employee under each employee's initial strategy. It is the first The working hours of each employee It is the average working hours of all employees. It refers to the number of employees.
[0053] The update strategy includes the target available equipment-available staff combination that maximizes the expected benefit of each testing task, the task execution order of each testing device, and the task processing order of each staff member.
[0054] In some embodiments of this application, the specific process of determining whether an equilibrium state has been reached based on the update strategy includes: determining the target expected revenue of each task to be tested based on the target available device-available employee combination that maximizes the expected revenue of each task to be tested; determining the target utilization rate of each testing device based on the task execution order of each testing device; determining the target working time of each employee based on the task processing order of each employee; and determining that an equilibrium state has been reached when the target expected revenue of each task to be tested meets a preset revenue constraint threshold, the target utilization rate of each testing device meets a preset utilization rate constraint threshold, and the target working time of each employee meets a preset time constraint threshold.
[0055] In some embodiments of this application, if the target expected revenue of each task to be tested does not meet the preset revenue constraint threshold, or the target utilization rate of each testing device does not meet the preset utilization rate constraint threshold, or the target working time of each employee does not meet the preset time constraint threshold, it is determined that an equilibrium state has not been reached.
[0056] In some embodiments of this application, if an equilibrium state is not reached, the step of updating the initial strategy based on task information, device information, and employee information continues until an equilibrium state is reached.
[0057] S103, the server outputs the game equilibrium solution corresponding to the quality inspection workshop scheduling request and sends it to the client for display; the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee for each inspection task.
[0058] In this context, the game equilibrium solution is the optimal scheduling strategy calculated using a game theory model in a multi-objective optimization problem. This solution achieves a relatively balanced state of reward for all tasks, equipment, and employees.
[0059] In some embodiments of this application, the server uses a preset multi-objective game model to calculate the optimal allocation strategy for each task based on task information, equipment information, and employee information. The game equilibrium solution includes the equipment and employee information allocated to each task. The server formats the calculated game equilibrium solution into JSON format data. The server sends the response data back to the client via an HTTP response. The client receives the response data returned by the server and displays it to the user. The client displays the results, for example... Figure 5 As shown.
[0060] In one possible implementation, after receiving the request, the server calculates the game equilibrium solution using a pre-defined multi-objective game model. Assume the calculation result is as follows: Task 1: Assign to device 1 (D001) and employee 1 (E001).
[0061] Task 2: Assign to device 2 (D002) and employee 2 (E002).
[0062] The server formats the game equilibrium solution into JSON data and sends this JSON data back to the client via an HTTP response. Upon receiving the response data, the client displays it to the user. The displayed content is as follows: Task 1: Assigned equipment: Equipment 1 (D001, X-ray), Assigned staff: Staff 1 (E001, working hours 6 hours).
[0063] Task 2: Assigned equipment: Equipment 2 (D002, CT), Assigned staff: Staff 2 (E002, working hours 5 hours).
[0064] For example Figure 6 As shown, Figure 6 This application provides a schematic flowchart of a quality inspection task scheduling process based on a hybrid multi-objective game theory. First, it receives a quality inspection workshop scheduling request from a client. This request carries task information for each task to be inspected, equipment information for each inspection device in the workshop, and employee information for each employee. Then, a pre-defined multi-objective game model assigns an initial strategy to each task, each inspection device, and each employee. Based on the task information, equipment information, and employee information, the pre-defined multi-objective game model updates the initial strategy to obtain an updated strategy. Next, based on the updated strategy, the pre-defined multi-objective game model determines whether an equilibrium state has been reached. If so, the updated strategy is taken as the game equilibrium solution; otherwise, the process continues, resuming the steps of updating the initial strategy based on the task information, equipment information, and employee information to obtain the updated strategy.
[0065] In this embodiment, a multi-objective game model is preset by taking task information, equipment information and employee information as multi-objective inputs. The preset multi-objective game model can consider multiple objectives at the same time, thereby seeking a balance among multiple objectives to find the optimal scheduling scheme. This avoids the problem of other objectives being deteriorated due to single-objective optimization in traditional methods. It can effectively solve the shortcomings of traditional scheduling methods in multi-objective optimization problems and improve the scheduling efficiency and quality of the quality inspection workshop.
[0066] The following are system embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of this application.
[0067] Please see Figure 7 This illustration shows a schematic diagram of a quality inspection task scheduling system based on a hybrid multi-objective game theory, provided in an exemplary embodiment of this application. This quality inspection task scheduling system based on a hybrid multi-objective game theory can be implemented as all or part of an electronic device through software, hardware, or a combination of both. System 1 includes a quality inspection workshop scheduling request receiving module 10, a multi-objective game model processing module 20, and a game equilibrium solution output module 30.
[0068] The quality inspection workshop scheduling request receiving module 10 is used to receive the quality inspection workshop scheduling request sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. The multi-objective game model processing module 20 is used to input task information, equipment information and employee information as multi-objective inputs into the preset multi-objective game model; The game equilibrium solution output module 30 is used to output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display; wherein, the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee corresponding to each inspection task.
[0069] It should be noted that the quality inspection task scheduling system based on hybrid multi-objective game theory provided in the above embodiments is only illustrated by the division of the above functional modules when executing the quality inspection task scheduling method based on hybrid multi-objective game theory. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the quality inspection task scheduling system based on hybrid multi-objective game theory and the quality inspection task scheduling method embodiment provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.
[0070] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0071] In this embodiment, a multi-objective game model is preset by taking task information, equipment information and employee information as multi-objective inputs. The preset multi-objective game model can consider multiple objectives at the same time, thereby seeking a balance among multiple objectives to find the optimal scheduling scheme. This avoids the problem of other objectives being deteriorated due to single-objective optimization in traditional methods. It can effectively solve the shortcomings of traditional scheduling methods in multi-objective optimization problems and improve the scheduling efficiency and quality of the quality inspection workshop.
[0072] This application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the quality inspection task scheduling method based on hybrid multi-objective game provided in the above-described method embodiments.
[0073] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the quality inspection task scheduling method based on hybrid multi-objective game theory described in the above-described method embodiments.
[0074] Please see Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.
[0075] The communication bus 1002 is used to realize the connection and communication between these components.
[0076] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.
[0077] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).
[0078] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip, without being integrated into the processor 1001.
[0079] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage system located remotely from the aforementioned processor 1001. Figure 8 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a quality inspection task scheduling application based on a hybrid multi-objective game.
[0080] exist Figure 8In the illustrated electronic device 1000, the user interface 1003 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 1001 can be used to call the quality inspection task scheduling application based on hybrid multi-objective game stored in the memory 1005, and specifically perform the following operations: Receive the quality inspection workshop scheduling request sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. Task information, equipment information, and employee information are used as multi-objective inputs in a pre-defined multi-objective game model; Output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display; the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee for each inspection task.
[0081] In one embodiment, when the processor 1001 executes a preset multi-objective game model that takes task information, device information, and employee information as multi-objective inputs, it specifically performs the following operations: The initial policy allocation component assigns an initial policy to each task to be tested, each testing device, and each employee; The policy update component updates the initial policy based on task information, device information, and employee information to obtain the updated policy. The equilibrium state determination component determines whether an equilibrium state has been reached based on the update strategy. When the equilibrium solution generation component reaches an equilibrium state, it updates the strategy as the equilibrium solution.
[0082] In one embodiment, when the processor 1001 assigns an initial strategy for each task to be detected, each detection device, and each employee, it specifically performs the following operations: Based on the equipment information, identify each available detection device that is currently idle; Based on employee information, identify each available employee who is currently idle; Each available testing device and each available employee can be arranged and combined to obtain multiple pairs of available device-available employee combinations; Each pair of available devices and available staff is assigned to each task to be tested, thus obtaining the initial strategy for each task to be tested; Based on the task information, determine the task arrival order and task allocation order for each task to be detected; According to the arrival order of each task to be detected, each task to be detected is assigned to each detection device to obtain the initial strategy of each detection device; According to the task assignment order of each task to be tested, each task to be tested is assigned to each employee, and the initial strategy of each employee is obtained.
[0083] In one embodiment, when the processor 1001 executes the process of updating the initial policy based on task information and device information to obtain the updated policy, it specifically performs the following operations: Determine the actual completion time and expected completion time of each task to be tested from the task information and equipment information; Based on the actual completion time and the expected completion time, calculate the expected benefit of each task to be detected under the initial strategy of each task to be detected; From the initial strategy of each task to be tested, the target available device-available employee combination that maximizes expected revenue is obtained as the updated strategy for each task to be tested; wherein, the formula for calculating the expected revenue of the initial strategy for each task to be tested is:
[0084] in, It is the first Expected benefits of each task to be tested It is the first The actual completion time of each task to be tested. It is the first The expected completion time for each task to be tested.
[0085] In one embodiment, when the processor 1001 executes the process of updating the initial policy based on task information and device information to obtain the updated policy, it specifically performs the following operations: Obtain the actual working time and total available time for each testing device from the equipment information; Based on the actual working time and total available time of each testing device, calculate the utilization rate of each testing device under the initial strategy of each testing device; When the utilization rate has not reached its maximum, the priority of each task in the initial strategy of each detection device is determined from the task information; Based on the priority of each task, the execution order of each task in the initial strategy of each detection device is adjusted, and the utilization rate of each detection device is recalculated until the utilization rate reaches its maximum, thus obtaining the updated strategy for each detection device; among which, The formula for calculating the utilization rate of each testing device under the initial strategy of each testing device is:
[0086] in, It is the first The first testing device in the Utilization rate of each testing device under the initial strategy. It is the first The actual working time of each testing device It is the first Total available time for each testing device.
[0087] In one embodiment, when the processor 1001 updates the initial policy based on task information, device information, and employee information to obtain the updated policy, it specifically performs the following operations: From the employee information, obtain the working hours of each employee and the average working hours of all employees; Calculate the working hours of each employee under each employee's initial strategy, based on each employee's working hours and the average working hours of all employees. When the working time exceeds the preset time threshold, retrieve the urgency and working time limit of each task in each employee's initial strategy from the task information. Based on the urgency of each task and time constraints, the execution order of tasks in each employee's initial strategy is adjusted, and each employee's working time is recalculated until the working time is less than or equal to a preset time threshold, resulting in an updated strategy for each employee. The formula for calculating each employee's working time under each employee's initial strategy is as follows:
[0088] in, It is the first The working hours of each employee under each employee's initial strategy. It is the first The working hours of each employee It is the average working hours of all employees. It refers to the number of employees.
[0089] In one embodiment, when the processor 1001 executes the operation based on the update policy to determine whether an equilibrium state has been reached, it specifically performs the following operations: The target expected benefit for each test task is determined based on the target available equipment-available staff combination that maximizes the expected benefit for each test task. The target utilization rate of each testing device is determined based on the task execution sequence of each testing device; Determine the target working time for each employee based on the order in which they handle their tasks; An equilibrium state is determined when the target expected revenue of each task to be tested meets the preset revenue constraint threshold, the target utilization rate of each testing device meets the preset utilization rate constraint threshold, and the target working time of each employee meets the preset time constraint threshold.
[0090] In one embodiment, the processor 1001 also performs the following operations: If the target expected revenue of each task to be tested does not meet the preset revenue constraint threshold, or the target utilization rate of each testing device does not meet the preset utilization rate constraint threshold, or the target working time of each employee does not meet the preset time constraint threshold, then an unbalanced state is determined.
[0091] In one embodiment, the processor 1001 also performs the following operations: If an equilibrium state is not reached, continue to execute the steps of updating the initial strategy based on task information, equipment information, and employee information until an equilibrium state is reached.
[0092] In this embodiment, a multi-objective game model is preset by taking task information, equipment information and employee information as multi-objective inputs. The preset multi-objective game model can consider multiple objectives at the same time, thereby seeking a balance among multiple objectives to find the optimal scheduling scheme. This avoids the problem of other objectives being deteriorated due to single-objective optimization in traditional methods. It can effectively solve the shortcomings of traditional scheduling methods in multi-objective optimization problems and improve the scheduling efficiency and quality of the quality inspection workshop.
[0093] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program for scheduling quality inspection tasks based on hybrid multi-objective game theory can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium for the program for scheduling quality inspection tasks based on hybrid multi-objective game theory can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.
[0094] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.
Claims
1. A quality inspection task scheduling method based on hybrid multi-objective game theory, characterized in that, Applied to the server side, the method includes: Receive a quality inspection workshop scheduling request sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. The task information, equipment information, and employee information are used as multi-objective inputs into a preset multi-objective game model; Output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display; wherein, the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee corresponding to each inspection task.
2. The method according to claim 1, characterized in that, The preset multi-objective game model includes an initial strategy allocation component, a strategy update component, an equilibrium state determination component, and a game equilibrium solution generation component. The pre-defined multi-objective game model, which uses the task information, equipment information, and employee information as multi-objective inputs, includes: The initial strategy allocation component allocates an initial strategy for each task to be tested, each testing device, and each employee; The strategy update component updates the initial strategy based on the task information, the device information, and the employee information to obtain an updated strategy. The equilibrium state determination component determines whether an equilibrium state has been reached based on the update strategy. When the game equilibrium solution generation component reaches an equilibrium state, it uses the updated strategy as the game equilibrium solution.
3. The method according to claim 2, characterized in that, The initial strategy allocation for each task to be tested, each testing device, and each employee includes: Based on the device information, determine each available detection device that is currently idle; Based on the employee information, determine each available employee that is currently idle; Each available testing device and each available employee are arranged and combined to obtain multiple pairs of available device-available employee combinations; Each available device-available employee pair is assigned to each task to be tested to obtain an initial strategy for each task to be tested; Based on the task information, determine the task arrival order and task allocation order of each task to be detected; According to the arrival order of each task to be detected, each task to be detected is assigned to each detection device to obtain the initial strategy of each detection device; According to the task allocation order of each task to be detected, each task to be detected is assigned to each employee to obtain the initial strategy of each employee.
4. The method according to claim 3, characterized in that, Based on the task information and the device information, the initial policy is updated to obtain an updated policy, including: From the task information and equipment information, determine the actual completion time and expected completion time of each task to be detected; Based on the actual completion time and the expected completion time, calculate the expected benefit of each task to be detected under the initial strategy of each task to be detected; From the initial strategy of each task to be tested, the target available device-available employee combination that maximizes expected return is obtained as the update strategy for each task to be tested; wherein, the formula for calculating the expected return on the initial strategy of each task to be tested is: in, It is the first Expected benefits of each task to be tested It is the first The actual completion time of each task to be tested. It is the first The expected completion time for each task to be tested.
5. The method according to claim 3, characterized in that, Based on the task information and the device information, the initial policy is updated to obtain an updated policy, including: From the device information, obtain the actual working time and total available time of each testing device; Based on the actual working time and total available time of each testing device, calculate the utilization rate of each testing device under the initial strategy of each testing device; When the utilization rate has not reached its maximum, the priority of each task in the initial strategy of each detection device is determined from the task information; Based on the priority of each task, the execution order of each task in the initial strategy of each detection device is adjusted, and the utilization rate of each detection device is recalculated until the utilization rate reaches its maximum, thus obtaining the updated strategy for each detection device; wherein, The formula for calculating the utilization rate of each detection device under the initial strategy of each detection device is as follows: in, It is the first The first testing device in the Utilization rate of each testing device under the initial strategy. It is the first The actual working time of each testing device It is the first Total available time for each testing device.
6. The method according to claim 3, characterized in that, The step of updating the initial strategy based on the task information, the device information, and the employee information to obtain an updated strategy includes: From the employee information, obtain the working hours of each employee and the average working hours of all employees; Based on the working time of each employee and the average working time of all employees, calculate the working time of each employee under the initial strategy of each employee; When the working time exceeds a preset time threshold, the urgency and working time limit of each task in the initial strategy of each employee are obtained from the task information. Based on the urgency and time constraints of each task, the execution order of each task in each employee's initial strategy is adjusted, and the working time of each employee is recalculated until the working time is less than or equal to a preset time threshold, thus obtaining an updated strategy for each employee; wherein, the formula for calculating the working time of each employee under each employee's initial strategy is: in, It is the first The working hours of each employee under the initial strategy for each employee. It is the first The working hours of each employee It is the average working hours of all employees. It refers to the number of employees.
7. The method according to claim 3, characterized in that, The update strategy includes the target available equipment-available staff combination that maximizes the expected benefit of each task to be tested, the task execution order of each testing device, and the task processing order of each employee; The step of determining whether an equilibrium state has been reached based on the update strategy includes: The target expected revenue for each task to be tested is determined based on the target available equipment-available staff combination that maximizes the expected revenue for each task to be tested. The target utilization rate of each testing device is determined based on the task execution order of each testing device; Based on the task processing order of each employee, determine the target working time for each employee; An equilibrium state is determined when the target expected revenue of each task to be tested meets a preset revenue constraint threshold, the target utilization rate of each testing device meets a preset utilization rate constraint threshold, and the target working time of each employee meets a preset time constraint threshold.
8. The method according to claim 7, characterized in that, The method further includes: If the target expected revenue of each task to be tested does not meet the preset revenue constraint threshold, or the target utilization rate of each testing device does not meet the preset utilization rate constraint threshold, or the target working time of each employee does not meet the preset time constraint threshold, it is determined that an equilibrium state has not been reached.
9. The method according to claim 2, characterized in that, The method further includes: If an equilibrium state is not reached, continue executing the step of updating the initial strategy based on the task information, the device information, and the employee information until an equilibrium state is reached.
10. A quality inspection task scheduling system based on hybrid multi-objective game theory, characterized in that, The system includes: The quality inspection workshop scheduling request receiving module is used to receive quality inspection workshop scheduling requests sent by the client. The quality inspection workshop scheduling request carries the task information of each task to be tested, the equipment information of each testing device in the quality inspection workshop, and the employee information of each employee. A multi-objective game model processing module is used to input the task information, the equipment information, and the employee information as multi-objective inputs into a preset multi-objective game model; The game equilibrium solution output module is used to output the game equilibrium solution corresponding to the quality inspection workshop scheduling request and send it to the client for display; wherein, the game equilibrium solution includes the equipment information of the target inspection equipment and the employee information of the target employee corresponding to each inspection task.