A human resource prediction and scheduling method, system, device and medium under a highly uncertain production mode

Abstract

The application discloses a kind of human resource prediction and scheduling method, system, equipment and medium under highly uncertain production mode, and relates to the field of intelligent manufacturing technology.The application obtains process-level job BOM through manufacturing execution system, and constructs the mapping relationship of multilevel human resource model and process-level personnel demand by gathering;Based on historical planning data and temporary task data, differential equation fitting prediction production load is carried out by combining GM (1,1) model, and the total personnel demand of production line is dynamically balanced with workshop average load as benchmark;Finally, based on NSGA-II algorithm, personnel skill maturity and space-time collision avoidance rules are used as constraint conditions, and scheduling model with double objectives of task time and cost minimization is solved.The application realizes cross-plant multilevel linkage scheduling under the characteristics of complex electronic equipment multi-species and mixed-line production, and significantly improves the collaborative operation efficiency of agile manufacturing workshop.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, specifically to a method, system, equipment, and medium for predicting and scheduling human resources under highly uncertain production modes. Background Technology

[0002] The statements in this section are provided only as background information in connection with this disclosure and may not constitute prior art.

[0003] The manufacturing process of complex electronic equipment is characterized by multi-variety, small-batch, and mixed-line production, with assembly and debugging stages heavily reliant on multi-skilled personnel. Unlike traditional electronic equipment and machinery manufacturing, the integration of complex electronic equipment faces diverse requirements across multiple process stages and production lines, resulting in a complex, multi-layered human resource demand structure. How to scientifically predict manpower needs and achieve dynamic optimization scheduling has become a key bottleneck restricting the efficiency and quality of complex electronic equipment manufacturing.

[0004] Existing research on production scheduling for electronic equipment often treats human resources as homogeneous labor or only distinguishes between job categories, lacking consideration for the multi-level human resource elements that are differentiated across various process stages and production lines. In existing collaborative scheduling based on equipment and worker resources, the optimization objectives mainly revolve around equipment reconfiguration time and completion cycle, and the objects of the production process model are mostly based on the traditional product-defined Bill of Materials (BOM), without being refined to the process-level operations. This makes it difficult for workshops to form differentiated human resource allocation management across multiple process stages and production lines, resulting in the inability to conduct large-scale human resource allocation between production lines in multi-variety, mixed-line production processes under highly uncertain production modes.

[0005] Currently, there is no publicly available technology capable of achieving multi-workshop production line linkage scheduling and resource sharing through multi-level human resource factor prediction in uncertain production modes. For example, while the existing patent CN202410594360.9, "Dynamic Scheduling Method for Digital Twin Assembly Workshop of Complex Products Considering Personnel Allocation," solves the problem of virtual-real interaction and dynamic scheduling based on digital twin technology, it does not address the problem of multi-workshop production line linkage scheduling, nor does it resolve the lack of pre-demand prediction functionality. Another patent, CN121599395A, "Project Personnel Scheduling Management Method Combining Multi-dimensional Tag Analysis," constructs a multi-dimensional tag library, but similarly does not mention multi-level human resource demand prediction and workshop linkage scheduling technology. Summary of the Invention

[0006] The purpose of this invention is to address the problem that current electronic equipment production scheduling technologies lack consideration for multi-level human resource elements that are differentiated across multiple process stages and production lines, making it difficult to conduct large-scale pre-determining of human resource needs and multi-production line coordinated scheduling across workshops. This invention provides a method, system, equipment, and medium for human resource prediction and scheduling under highly uncertain production modes. It employs a method that uses the Manufacturing Execution System (MES) to obtain process-level BOMs to construct a common skills human resource pool mapping relationship. Based on historical planning and temporary task data combined with the GM(1,1) model, it predicts production line load using a dual-track approach. Furthermore, it utilizes the NSGA-II algorithm, which incorporates personnel skill maturity and spatiotemporal collision avoidance constraints, to construct a multi-skilled employee scheduling optimization model. This method achieves multi-level coordinated scheduling and resource pool sharing under the characteristics of complex electronic equipment production with multiple varieties, small batches, and mixed lines, significantly improving the collaborative operation efficiency and scientific allocation of human resources in agile manufacturing workshops.

[0007] The technical solution of the present invention is as follows: A human resource forecasting and scheduling method under a highly uncertain production mode, applied to the cross-workshop production line manufacturing process of complex electronic equipment, the method includes the following steps: Step S1: Obtain the process-level BOM of products in multiple workshops through the Manufacturing Execution System, and establish a BOM process table that includes the pre- and post-process relationships, required skills and manual operation cycles; through the process-level production task organization model, collect the human resource needs of the same skills required for the product manufacturing process in each workshop, build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel needs. Step S2: Evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and combine current planning data and historical temporary task data to predict the workload of temporary tasks, thereby calculating the predicted production load; Based on the predicted production load, balance the load of each workshop and production line level with the workshop average load as a dynamic benchmark, and evaluate the total personnel demand for common skills of each production line. Step S3: Based on the total personnel demand for common skills of each production line, construct a multi-skilled employee scheduling optimization model; take minimizing task planning time and minimizing the personnel demand cost for task completion as the objective function, and take the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints, solve the multi-skilled employee scheduling optimization model, and output a human resource scheduling scheme across workshop production lines.

[0008] Furthermore, in step S1, a common skills human resource pool is constructed to form a mapping relationship between a multi-level human resource model and the personnel needs at the product process level, including: Establish initial skill values ​​for multi-skilled personnel involved in manufacturing, encompassing various common skill types; Based on the obtained process-level BOM, extract the identifiers, preceding tasks, and required skills for each process task, and construct the BOM process table. The initial values ​​of employee skills are matched with the BOM process table to establish a mapping relationship that includes the correspondence between process task identifiers and the rated working hours of the personnel skill model.

[0009] Furthermore, in step S2, the formula for calculating the predicted production load is: ; in: To predict production load; The total number of tasks planned for the current month; The first of the month The working hours for each planning task; This represents the current number of personnel. For working days; The prediction coefficient is calculated as follows: ;in For the first The planning evaluation coefficient for each historical month, and , For the first The first in a historical month The actual sales time for each task For the first The first in a historical month The planning time for each task To obtain The average of the planning evaluation coefficients for each historical month. To obtain the total number of months for historical planning data; The prediction coefficient for temporary tasks is calculated as follows: ;in For the first The evaluation coefficient of temporary tasks in each historical month, and , For the first Total man-hours for temporary tasks in a historical month. To obtain The average of the evaluation coefficients for temporary tasks in each historical month and , To obtain the total number of months for historical temporary task data; By fitting a whitening differential equation to the aforementioned historical sequence data using a GM(1,1) model, the predicted production load can be obtained. The calculation. Further, in step S2, the total personnel requirements for common skills across all production lines are assessed, including: Calculate the number of employees with common skills across all production lines The calculation formula is as follows: ; in, To predict the workload of technical personnel, To predict the workload of skilled workers.

[0010] Furthermore, in step S3, the multi-skilled employee scheduling optimization model adopts the NSGA-II algorithm, and the objective function specifically includes: Minimize task scheduling time: ; Minimize the personnel required to complete the task: ; in, The total number of processes. For process Completion time; The total number of personnel involved in the dispatch. For the total number of skills, To indicate personnel Use skills Execution process 0-1 decision variables; For personnel Use skills Complete the process Time required For personnel The unit time cost.

[0011] Furthermore, the constraints specifically include: Personnel skill maturity constraints: personnel Use skills Complete the process Time required ,in For minimum standard working hours, For personnel skills Maturity; Process completion time constraints: Process Completion time ,in For process The start time, For process cycle, ; Human resource constraints for each process: Each skill requirement for each process must be performed by one person. ,in For process skills The demand for human resources; Work process constraint: At any given time, a person can only complete one type of work process. ,in To indicate personnel At any moment Use skills Execution process The state variable.

[0012] This invention also proposes a human resource forecasting and scheduling system under a highly uncertain production mode, applied to the cross-workshop production line manufacturing process of complex electronic equipment. The system includes: The mapping modeling module is used to obtain the process-level BOM of products in multiple workshops through the manufacturing execution system, and to establish a BOM process table that includes the pre- and post-process relationships, required skills and manual operation cycles. Through the process-level production task organization mode, the manpower requirements of the same skills required for the product manufacturing process in each workshop are collected to build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel requirements. The prediction and balancing module is used to evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and to predict the workload of temporary tasks by combining current planning data and historical temporary task data, thereby calculating the predicted production load; based on the predicted production load, the load of each workshop and production line is balanced using the workshop average load as a dynamic benchmark, and the total personnel demand for common skills of each production line is evaluated. The multi-production line scheduling module is used to construct a multi-skilled employee scheduling optimization model based on the total personnel demand for common skills of each production line. The objective functions are minimizing the task planning time and minimizing the personnel demand cost for task completion. The module also uses the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints to solve the multi-skilled employee scheduling optimization model and output a human resource scheduling scheme across workshop production lines.

[0013] Furthermore, the system includes a data terminal layer, a data visualization layer, and a model management layer in its logical framework; The data terminal layer includes a human resources collector, used to acquire visualized data on human resources status and terminal data on human resources composition; The model management layer includes a human resource management model, which is configured with generation task organization model strategies such as first-in-first-out, fair scheduling, capacity scheduling, and delayed scheduling.

[0014] The present invention also proposes an electronic device, comprising: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the instructions stored in the memory to perform the method described above.

[0015] The present invention also proposes a computer-readable storage medium for storing instructions that, when executed, cause the method described above to be implemented.

[0016] Compared with existing technologies, the advantages of this invention are: 1. Breaking down physical barriers in the workshop to achieve refined resource modeling. This invention uses a Manufacturing Execution System (MES) to bring the traditional Bill of Materials (BOM) down to the process level, establishing a mapping relationship between process-level production tasks and common skill human resource pools. This completely changes the previous extensive management that treated personnel as homogeneous labor, laying a refined data foundation for personnel sharing and large-scale allocation across multiple workshop production lines.

[0017] 2. Innovative dual-track forecasting mechanism to overcome the challenge of pre-demand forecasting. Addressing the pain points of "numerous order insertions and large deviations" under highly uncertain production models, this invention pioneered a dual-track forecasting model of "planning deviation + temporary tasks." By introducing the GM(1,1) model from grey forecasting theory, a highly robust continuous whitening differential equation was established with limited discrete historical samples. This scientifically and accurately predicts workshop production load and dynamically balances the number of workers on the production line, filling the business gap in existing scheduling systems that lack pre-demand forecasting capabilities.

[0018] 3. Deeply integrating industrial physical constraints, this invention outputs a globally optimal coordinated scheduling scheme. In constructing the multi-skilled employee scheduling optimization model, this invention innovatively introduces a "skill maturity inverse ratio mechanism" and a "collision prevention constraint for processes at the same time," breaking the rigid assumption that the time consumption of the same job is consistent and ensuring the absolute physical feasibility of scheduling. By solving the dual-objective conflict of minimizing time and cost through the NSGA-II algorithm, it outputs managers with optimal cross-workshop production line-level human resource coordinated scheduling instructions that balance efficiency and cost. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in the embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0020] Figure 1 A schematic diagram of a two-layer prediction model for human resource forecasting and load balancing provided in an embodiment of the present invention; Figure 2 A framework diagram of a workshop multi-production line human resource scheduling system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0022] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0023] Example 1 This embodiment provides a method for predicting and scheduling human resources under highly uncertain production modes, applied to the cross-workshop production line manufacturing process of complex electronic equipment. The execution entity of this method can be an industrial control server, cloud scheduling server, or related computing devices deployed on the Manufacturing Execution System (MES) side.

[0024] The manufacturing process of complex electronic equipment is characterized by multi-variety, small-batch, and mixed-line production, with assembly and debugging stages heavily reliant on multi-skilled personnel. Traditional scheduling often treats human resources as homogeneous labor, failing to break down tasks to the process level, thus hindering large-scale human resource allocation across production lines. To address these issues, the method in this embodiment specifically includes the following steps: Step S1: Obtain the process-level BOM of products in multiple workshops through the Manufacturing Execution System, and establish a BOM process table that includes the pre- and post-process relationships, required skills, and manual operation cycles; through the process-level production task organization model, collect the human resource needs of the same skills required for the product manufacturing process in each workshop, build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel needs.

[0025] Specifically, in a highly uncertain production model, in order to achieve refined resource planning management, step S1 above specifically includes: Establish initial skill values ​​for multi-skilled personnel involved in manufacturing, encompassing various common skill types; Based on the obtained process-level BOM, extract the identifiers, preceding tasks, and required skills for each process task, and construct the BOM process table. The initial values ​​of employee skills are matched with the BOM process table to establish a mapping relationship that includes the correspondence between process task identifiers and the rated working hours of the personnel skill model.

[0026] In this embodiment, it should be noted that in actual industrial applications, the Manufacturing Execution System (MES) defines the traditional manufacturing Bill of Materials (BOM) down to the process level. To accurately assess the manpower requirements for the product manufacturing process in each workshop, the manpower requirements are first aggregated through a process-level production task organization model.

[0027] Specifically, for multi-skilled employees in the workshop, employee numbers are assigned and their initial mastery levels of different common skills are defined (i.e., initial skill values). As shown in Table 1 below, a common task human resource model is constructed, including different skill types, their corresponding employee pools, and initial skill values. Table 1. Common Task Human Resource Model and Initial Employee Skill Values

[0028] Simultaneously, the task identifiers for each process are extracted, and a BOM (Bill of Materials) process table is constructed based on the sequential relationships of processes and the required skill constraints, as shown in Table 2 below: Table 2. BOM process table constructed based on process sequence, required skills, etc.

[0029] By combining the data in Tables 1 and 2, the manpower needs for the same type of work required for the originally isolated production and manufacturing processes in each workshop were aggregated, successfully breaking down physical space barriers and establishing a common skills human resource pool across workshops.

[0030] Step S2: Evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and combine current planning data and historical temporary task data to predict the workload of temporary tasks, thereby calculating the predicted production load; Based on the predicted production load, balance the load of each workshop and production line level with the average workshop load as a dynamic benchmark, and evaluate the total personnel demand for common skills of each production line.

[0031] Specifically, in step S2 above, the formula for calculating the predicted production load is: ; in, To predict production load, This represents the total number of tasks planned for the month. The first of the month The time required for each planning task For the current number of people, For working days; The prediction coefficient is calculated as follows: ; in For the first The planning evaluation coefficient for each historical month, and , For the first The first in a historical month The actual time spent on each task to complete the accounting process. For the first The first in a historical month The planning time for each task To obtain The average of the planning evaluation coefficients for each historical month. To obtain the total number of months for historical planning data; The prediction coefficient for temporary tasks is calculated as follows: ; in For the first The evaluation coefficient of temporary tasks in each historical month, and , For the first Total man-hours for temporary tasks in a historical month. To obtain The average of the evaluation coefficients for temporary tasks in each historical month and , To obtain the total number of months for historical temporary task data; By fitting a whitening differential equation to the aforementioned historical sequence data using a GM(1,1) model, the predicted production load can be obtained. The calculation.

[0032] Further, in step S2, the assessment yields the total personnel requirements for common skills across all production lines, including: Calculate the number of employees with common skills across all production lines The calculation formula is as follows: ; in, To predict the workload of technical personnel, To predict the workload of skilled workers.

[0033] In this embodiment, specifically, in conjunction with Figure 1 As can be seen, in the predictive analysis model on the left, this system calculates the planning evaluation coefficient by inputting historical sales data and historical planning data, and combines this with current planning data to perform predictive analysis of planning tasks, thus deriving the predicted workload of the planning tasks. Simultaneously, it calculates the temporary task evaluation coefficient by inputting historical temporary task data, and performs predictive analysis of temporary tasks to derive the predicted workload of temporary tasks. After summing both, based on... Figure 1 The architecture shown pioneered a dual-track prediction model of "planning deviation + temporary tasks".

[0034] Since historical data from workshops often exhibits nonlinearity and has a limited sample size, this embodiment introduces the GM(1,1) model from grey prediction theory. It can discover the inherent patterns of the system without requiring a large amount of historical data. Specifically, the underlying logic for deriving the prediction coefficients based on the GM(1,1) model is as follows: First, a grey differential equation is established for the discrete historical planning data and the temporary task evaluation coefficient sequence: ; Subsequently, the development coefficient was estimated through regression analysis. Ash action amount Establish the corresponding whitening differential equation:

[0035] By solving the above whitening differential equation, the time response prediction function for the evaluation coefficients is obtained:

[0036] in, The input consists of the original historical monthly evaluation coefficient data sequence (as described above). or ), This represents the sequence generated by performing a single accumulation on the original sequence. This represents a sequence generated from adjacent means. Represents a time point.

[0037] By solving and reducing the above continuous differential equations, highly robust prediction coefficients are finally obtained. and temporary task prediction coefficient Here, the predicted technician load in the formula ( This refers to the resident technical man-hours consumed within the workshop by personnel responsible for process guidance, anomaly handling, and other non-direct production tasks; it also refers to the predicted workload of skilled personnel. () refers to the available man-hours for direct production line operations.

[0038] like Figure 1 As shown in the load balancing model on the right, the algorithm combines the summarized predicted workload, current number of personnel, and number of working days to calculate the predicted production load. Then, using the average load of the workshop as a dynamic benchmark, it goes down to each production line to conduct a production line-level load assessment based on the number of working days of each production line, performs a balanced production line personnel operation, and finally outputs the total personnel demand for common skills of each production line, so as to achieve a reasonable distribution and adjustment of personnel.

[0039] Step S3: Based on the total personnel demand for common skills of each production line, construct a multi-skilled employee scheduling optimization model; take minimizing task planning time and minimizing the personnel demand cost for task completion as the objective function, and take the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints, solve the multi-skilled employee scheduling optimization model, and output a human resource scheduling scheme across workshop production lines.

[0040] Specifically, in step S3, the multi-skilled employee scheduling optimization model adopts the NSGA-II algorithm, and the objective function specifically includes: Minimize task scheduling time: ; Minimize the personnel required to complete the task: ; in, The total number of processes. For process Completion time; The total number of personnel involved in the dispatch. For the total number of skills, To indicate personnel Use skills Execution process 0-1 decision variables; For personnel Use skills Complete the process Time required For personnel The unit time cost.

[0041] The constraints specifically include: Personnel skill maturity constraints: personnel Use skills Complete the process Time required ,in For minimum standard working hours, For personnel skills Maturity; Process completion time constraints: Process Completion time ,in For process The start time, For process cycle, ; Human resource constraints for each process: Each skill requirement for each process must be performed by one person. ,in For process skills The demand for human resources; Work process constraint: At any given time, a person can only complete one type of work process. ,in To indicate personnel At any moment Use skills Execution process The state variable.

[0042] In this embodiment, it should be noted that after clarifying the common skill requirements across multiple workshops, the system enters the dynamic production scheduling phase. This embodiment employs a non-dominated sorting genetic algorithm (NSGA-II algorithm) with an elite retention strategy to solve the aforementioned multi-objective optimization problem. This breaks the rigid assumption of "consistent time consumption for the same job" in traditional scheduling (by introducing an inverse skill maturity mechanism). ), and through spatiotemporal collision avoidance constraints, ensured that on the physical timeline In this way, it is impossible for any employee to have a conflict of performing overlapping tasks.

[0043] In this embodiment, further, combined with Figure 2 As can be seen, the above scheduling process relies on the data terminal layer, data visualization layer, and model management layer in its logical framework. The underlying data terminal layer (human resource collector) includes production line node managers deployed on each production line, which can collect dynamic personnel data in real time from both time and task dimensions. Specifically, task-level status monitoring not only includes the start / completion status of regular production tasks and temporary tasks, but also more finely encompasses… Figure 2The execution status of after-sales tasks and business trip tasks, as well as the entry and exit status of personnel, are shown, thus providing the underlying algorithm with a comprehensive view of the availability of underlying human resources.

[0044] Meanwhile, the human resources organization model in the top model management layer, when executing the above-mentioned NSGA-II algorithm scheduling strategy, also configures and incorporates... Figure 2 The algorithm employs specific production task organization and scheduling strategies, such as First-In-First-Out (FIFO), fair scheduling, capacity scheduling, and delayed scheduling, to address the unique manufacturing management preferences of different workshops. The final algorithm outputs a set of Pareto optimal solutions, which are then distributed to the production task organization model for scheduling. This provides workshop managers with cross-workshop production line-level collaborative scheduling and allocation instructions that balance "shortest lead time" and "lowest cost."

[0045] Example 2 Based on the same inventive concept as Embodiment 1, this embodiment provides a human resource forecasting and scheduling system for highly uncertain production modes. This system is applied to the cross-workshop production line manufacturing process of complex electronic equipment and serves as the hardware and software implementation of the method described in Embodiment 1. Please refer to... Figure 2 The system's logical framework, from bottom to top, mainly comprises a data terminal layer, a data visualization layer, and a model management layer. The core functional architecture of the system includes: The mapping modeling module is used to obtain the process-level BOM of products in multiple workshops through the manufacturing execution system, and to establish a BOM process table that includes the pre- and post-process relationships, required skills and manual operation cycles. Through the process-level production task organization mode, the human resource needs of the same skills required for the product manufacturing process in each workshop are collected to build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel needs.

[0046] Combination Figure 2 As can be seen from the data terminal layer, this module relies on a human resources collector to acquire data. Specifically, it obtains dynamic and visual data of personnel and the constituent terminal data in real time from the time and task dimensions through production line node managers deployed on each production line. For example, it can collect the status of personnel performing production tasks, temporary tasks, after-sales tasks, and business trip tasks in a detailed manner.

[0047] The prediction and balancing module is used to evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and to predict the workload of temporary tasks by combining current planning data and historical temporary task data, thereby calculating the predicted production load; based on the predicted production load, the load of each workshop and production line is balanced using the average workshop load as a dynamic benchmark, and the total personnel demand for common skills of each production line is evaluated.

[0048] Specifically, this module incorporates a dual-track prediction algorithm based on the GM(1,1) model. It can read the limited historical data sequence collected by the aforementioned module, perform whitening differential equation fitting, and accurately calculate the predicted production load. And according to the formula Dynamically output macro-level personnel adjustment instructions for each production line.

[0049] The multi-production line scheduling module is used to construct a multi-skilled employee scheduling optimization model based on the total personnel demand for common skills of each production line. The objective functions are minimizing the task planning time and minimizing the personnel demand cost for task completion. The module also uses the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints to solve the multi-skilled employee scheduling optimization model and output a human resource scheduling scheme across workshop production lines.

[0050] Combination Figure 2 As can be seen from the model's management layer, this module internally includes a human resource management model and a production task organization model. When calling the NSGA-II algorithm to solve for multi-objective extrema, the human resource management model can also flexibly configure strategies such as First-In-First-Out (FIFO), fair scheduling, capacity scheduling, and delayed scheduling to generate the task organization model. Finally, the scheduling results are distributed to each workshop through the production task organization model, realizing an agile manufacturing closed loop of "complex products + multi-skilled personnel allocation + cross-workshop collaboration."

[0051] The human resource forecasting and scheduling system provided in this embodiment shares the same internal operating logic, formula calculation principles, and physical meaning of corresponding parameters as the method described in Embodiment 1. To avoid redundancy, further details are omitted here; please refer to the relevant descriptions in the preceding embodiments. This system effectively overcomes the shortcomings of existing scheduling technologies in considering multi-level human resource elements, achieving large-scale intelligent allocation of human resources between production lines.

[0052] Based on the same technical concept, embodiments of the present invention also provide an electronic device that can implement the human resource forecasting and scheduling method flow under a highly uncertain production mode provided in the above embodiments of the present invention. In one embodiment, the electronic device can be a server, a terminal device, or other electronic devices. Figure 3 As shown, the electronic device may include: At least one processor and a memory connected to the at least one processor. In this embodiment of the invention, the specific connection medium between the processor and the memory is not limited. Figure 3 The example used is the connection between the processor and memory via a bus. The bus... Figure 3The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. Buses can be divided into address buses, data buses, control buses, etc., but for ease of representation, [the specific bus type is not shown here]. Figure 3 The processor is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, a processor can also be called a controller; there are no restrictions on the name.

[0053] In this embodiment of the invention, the memory stores instructions executable by at least one processor. By executing the instructions stored in the memory, the at least one processor can perform a human resource forecasting and scheduling method under a highly uncertain production mode, as described above. The processor can implement... Figure 3 The functions of each module in the device shown.

[0054] The processor is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory and calling data stored in memory, it can monitor the device's various functions and process data, thereby enabling overall monitoring of the device.

[0055] In an alternative design, the processor may include one or more processing units. The processor may integrate an application processor and a modem processor, wherein the application processor primarily handles the operating system, user interface, and applications, while the modem processor primarily handles wireless communication. It is understood that the modem processor may also not be integrated into the processor. In some embodiments, the processor and memory may be implemented on the same chip; in some embodiments, they may also be implemented separately on separate chips.

[0056] The processor can be a general-purpose processor, such as a CPU, digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the human resource forecasting and scheduling method under a highly uncertain production mode disclosed in the embodiments of this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0057] Memory, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory can include at least one type of storage medium, such as flash memory, hard disk, multimedia cards, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), and electrically erasable programmable read-only memory (EPROM). Only memory (EEPROM), magnetic storage, magnetic disks, optical disks, etc. A memory is any other medium capable of carrying or storing desired program code in the form of instructions or data structures, and accessible by a computer, but is not limited thereto. The memory in embodiments of this invention can also be a circuit or any other device capable of performing storage functions for storing program instructions and / or data.

[0058] By designing and programming the processor, the code corresponding to the human resource prediction and scheduling method under a highly uncertain production mode described in the foregoing embodiments can be embedded into the chip, thereby enabling the chip to execute the steps of the method described in the foregoing embodiments during operation. How to design and program the processor is a technique well known to those skilled in the art, and will not be elaborated here.

[0059] Based on the same inventive concept, embodiments of the present invention also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform a human resource forecasting and scheduling method under a highly uncertain production mode as described above.

[0060] In some alternative embodiments, the present invention also provides a method for forecasting and scheduling human resources under highly uncertain production modes, which can also be implemented in the form of a program product including program code. When the program product is run on a device, the program code is used to cause the control device to perform the steps in the method for forecasting and scheduling human resources under highly uncertain production modes according to various exemplary embodiments of the present invention as described above.

[0061] It should be noted that although several units or sub-units of the apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the invention, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units. Furthermore, although the operation of the method of the invention is described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0062] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can be implemented in one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs) containing computer-usable program code. The form of a computer program product implemented on ROM, optical memory, etc.

[0063] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a server, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] Program code for performing the operations of this invention can be written using any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0065] In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] Example 3 This embodiment provides a specific example of monthly production scheduling and operation verification, serving as operational support and real-data verification for the human resource forecasting and scheduling method under a highly uncertain production mode described in Embodiment 1. Further description is provided below in conjunction with a specific application scenario, but the implementation of this invention is not limited thereto.

[0069] Step S1: Construct a mapping table between the human resources model and the personnel requirements at the product process level. Taking the manufacturing of several types of complex electronic equipment products as an application scenario, the process-level BOM (i.e., the PBOM process list in the original data) of each product is obtained through the manufacturing execution system. Ten common process tasks (denoted as D1 to D10) and eight personnel skill models (denoted as S1 to S8) are selected. Through the aggregation method described in Example 1, the mapping table of required rated working hours is obtained, as shown in Table 3 below.

[0070] Table 3 Mapping Table of Work Process Tasks and Personnel Skill Models and Required Standard Working Hours

[0071] The specific values ​​in Table 3 intuitively reflect the dependence of a single process on the rated working hours of personnel with different common skills (the unit can be regarded as standard working hours). With this as the underlying data support, the system successfully established a precise mapping between the multi-level human resource model and the personnel needs at the product process level.

[0072] Step S2: Human resource load forecasting and load balancing; First, taking the planned work hours of the workshop in a certain month as input, and based on the data of the past 10 months (i.e., in Example 1)... and The mean is used as the basis for analysis, and the prediction algorithm based on the GM(1,1) model described in Example 1 is used to output the prediction coefficients. With temporary task prediction coefficient The monthly task hours are predicted. Specific calculation data is shown in Table 4 below.

[0073] Table 4. Analysis of Monthly Planning Work Hours and Forecast Monthly Task Work Hours

[0074] In Table 4, the algorithm calculates highly targeted planning evaluation coefficients and temporary task evaluation coefficients for the workshop as a whole and its three independent production lines. Combined with the initial monthly planning hours, the algorithm successfully calculates the "predicted monthly task hours" (i.e., the predicted total load corresponding to the numerator in the formula of Example 1), which includes "planning deviation" and "temporary orders".

[0075] Next, based on the current total personnel distribution across all production lines in the workshop, and according to the monthly task hours predicted in Table 4 above, the personnel workload (i.e., the predicted technical / skilled personnel workload in Example 1) is assessed. Then, based on the load balancing model in Example 1, the number of personnel with common skills across all production lines is calculated. The load adjustment of each production line was carried out, and the final results are shown in Table 5 below.

[0076] Table 5. Forecasted Personnel Load and Adjusted Personnel Distribution

[0077] As shown in Table 5, the "predicted personnel planning output load" objectively exposed the extreme unevenness of the load among the production lines before balancing (for example, the load of production line 2 was as high as 11.215 h / person-day, far exceeding the 8.51 of production line 1). After applying the dynamic benchmark balancing production line load algorithm described in this invention, the system provides a scientific "adjusted personnel distribution" instruction: it recommends setting the workshop chief to 237 people, and dynamically reconfiguring the personnel of production lines 1, 2, and 3 to 132, 51, and 54 people respectively. Based on this, the system will further call the NSGA-II algorithm in step S3 to execute multi-objective coordinated scheduling accurate to the individual level.

[0078] The real data in this embodiment verifies that the present invention can achieve large-scale scientific prediction and precise allocation of human resources across workshops / production lines under uncertain production modes, effectively solving the technical bottleneck of blind scheduling and load imbalance in complex electronic equipment manufacturing.

[0079] The embodiments described above merely illustrate specific implementation methods of this application, and while the descriptions are detailed and specific, they should not be construed as limiting the scope of protection of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the technical solution of this application, and these modifications and improvements all fall within the scope of protection of this application.

[0080] This background section is provided to generally present the context of the invention. The work of the currently named inventors, the work to the extent described in this background section, and aspects of this section that did not constitute prior art at the time of application are neither expressly nor impliedly acknowledged as prior art to the invention.

Claims

1. A method for forecasting and scheduling human resources under a highly uncertain production mode, characterized in that, The method, applied to cross-workshop production line manufacturing processes for complex electronic equipment, includes the following steps: Step S1: Obtain the process-level BOM of products in multiple workshops through the Manufacturing Execution System, and establish a BOM process table that includes the pre- and post-process relationships, required skills and manual operation cycles; through the process-level production task organization model, collect the human resource needs of the same skills required for the product manufacturing process in each workshop, build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel needs. Step S2: Evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and combine current planning data and historical temporary task data to predict the workload of temporary tasks, thereby calculating the predicted production load; Based on the predicted production load, balance the load of each workshop and production line level with the workshop average load as a dynamic benchmark, and evaluate the total personnel demand for common skills of each production line. Step S3: Based on the total personnel demand for common skills of each production line, construct a multi-skilled employee scheduling optimization model; take minimizing task planning time and minimizing the personnel demand cost for task completion as the objective function, and take the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints, solve the multi-skilled employee scheduling optimization model, and output a human resource scheduling scheme across workshop production lines.

2. The method for human resource forecasting and scheduling under a highly uncertain production mode according to claim 1, characterized in that, In step S1, a common skills human resource pool is constructed to form a mapping relationship between a multi-level human resource model and the personnel needs at the product process level, including: Establish initial skill values ​​for multi-skilled personnel involved in manufacturing, encompassing various common skill types; Based on the obtained process-level BOM, extract the identifiers, preceding tasks, and required skills for each process task, and construct the BOM process table. The initial values ​​of employee skills are matched with the BOM process table to establish a mapping relationship that includes the correspondence between process task identifiers and the rated working hours of the personnel skill model.

3. The method for human resource forecasting and scheduling under a highly uncertain production mode according to claim 1, characterized in that, In step S2, the formula for predicting production load is: ； in: To predict production load; This represents the total number of tasks planned for the current month. The first of the month The working hours for each planning task; This represents the current number of personnel. For working days; The prediction coefficient is calculated as follows: ;in For the first The planning evaluation coefficient for each historical month, and , For the first The first in a historical month The actual sales time for each task For the first The first in a historical month The planning time for each task To obtain The average of the planning evaluation coefficients for each historical month. To obtain the total number of months for historical planning data; The prediction coefficient for temporary tasks is calculated as follows: ;in For the first The evaluation coefficient of temporary tasks in each historical month, and , For the first Total man-hours for temporary tasks in a historical month. To obtain The average of the evaluation coefficients for temporary tasks in each historical month and , To obtain the total number of months for historical temporary task data; By fitting a whitening differential equation to the aforementioned historical sequence data using a GM(1,1) model, the predicted production load can be obtained. The calculation.

4. The human resource forecasting and scheduling method under a highly uncertain production mode according to claim 3, characterized in that, In step S2, the total personnel requirements for common skills across all production lines are assessed, including: Calculate the number of employees with common skills across all production lines The calculation formula is as follows: ； in, To predict the workload of technical personnel, To predict the workload of skilled workers.

5. The method for human resource forecasting and scheduling under a highly uncertain production mode according to claim 1, characterized in that, In step S3, the multi-skilled employee scheduling optimization model adopts the NSGA-II algorithm, and the objective function specifically includes: Minimize task scheduling time: ; Minimize the personnel required to complete the task: ; in, The total number of processes. For process Completion time; The total number of personnel involved in the dispatch. For the total number of skills, To indicate personnel Use skills Execution process 0-1 decision variables; For personnel Use skills Complete the process Time required For personnel The unit time cost.

6. The human resource forecasting and scheduling method under a highly uncertain production mode according to claim 5, characterized in that, The constraints specifically include: Personnel skill maturity constraints: personnel Use skills Complete the process Time required ,in For minimum standard working hours, For personnel skills Maturity; Process completion time constraints: Process Completion time ,in For process The start time, For process cycle, ; Human resource constraints for each process: Each skill requirement for each process must be performed by one person. ,in For process skills The demand for human resources; Work process constraint: At any given time, a person can only complete one type of work process. ,in To indicate personnel At any moment Use skills Execution process The state variable.

7. A human resource forecasting and scheduling system under a highly uncertain production mode, characterized in that, The system, applied to cross-workshop production line manufacturing processes for complex electronic equipment, includes: The mapping modeling module is used to obtain the process-level BOM of products in multiple workshops through the manufacturing execution system, and to establish a BOM process table that includes the pre- and post-process relationships, required skills and manual operation cycles. Through the process-level production task organization mode, the manpower requirements of the same skills required for the product manufacturing process in each workshop are collected to build a common skills human resource pool, so as to form a mapping relationship between the multi-level human resource model and the product process-level personnel requirements. The prediction and balancing module is used to evaluate planning deviations based on historical planning data and historical sales data to predict the workload of planning tasks, and to predict the workload of temporary tasks by combining current planning data and historical temporary task data, thereby calculating the predicted production load; based on the predicted production load, the load of each workshop and production line is balanced using the workshop average load as a dynamic benchmark, and the total personnel demand for common skills of each production line is evaluated. The multi-production line scheduling module is used to construct a multi-skilled employee scheduling optimization model based on the total personnel demand for common skills of each production line. The objective functions are minimizing the task planning time and minimizing the personnel demand cost for task completion. The module also uses the process completion time associated with personnel skill maturity, the human resources required for the process, and the rules for personnel to execute process tasks at the same time as constraints to solve the multi-skilled employee scheduling optimization model and output a human resource scheduling scheme across workshop production lines.

8. A human resource forecasting and scheduling system under a highly uncertain production mode according to claim 7, characterized in that, The system includes a data terminal layer, a data visualization layer, and a model management layer in its logical framework; The data terminal layer includes a human resources collector, used to acquire visualized data on human resources status and terminal data on human resources composition; The model management layer includes a human resource management model, which is configured with generation task organization model strategies such as first-in-first-out, fair scheduling, capacity scheduling, and delayed scheduling.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which executes the instructions stored in the memory to perform the method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store instructions that, when executed, cause the method as described in any one of claims 1-6 to be implemented.

Images