Production planning device, production planning method and program

Abstract

To make it possible to generate feasible production plans that achieve productivity-related targets, and also to develop workers' proficiency.SOLUTION: A production planning device includes: a proficiency-predicting model generation unit that generates proficiency-predicting model information for predicting a change in productivity-related proficiency of a worker who performs work processes pertaining to production of a product, on the basis of a work record of the worker; and a plan generation unit that uses the proficiency-predicting model information to predict the change in proficiency according to a result of assigning the work processes to the worker, and that generates a production plan, according to which the work processes and a schedule for work implementation have been assigned to the worker, such that the worker's proficiency will be developed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a production planning device, a production planning method, and a program. [Background technology]

[0002] Conventional production schedulers create production plans using standard work times established for each product process. However, work times vary depending on the skill level of each worker, resulting in variations in work times compared to the standard work time for each worker. This creates the problem of deviations from the work plan for each worker, preventing production from proceeding according to the original plan.

[0003] Furthermore, conventional production schedulers do not have a production planning function that takes into account the proficiency level of workers, so on-site managers assign work to each worker based on their own evaluation to ensure work quality.As a result, the evaluation of proficiency level is not quantified, and the evaluation of each worker varies depending on the on-site manager, which creates the issue of defective products occurring when workers are not assigned appropriate work.

[0004] Additionally, on-site managers manually create training plans to develop the proficiency of each worker, and reducing the amount of time required to create these plans is also an issue.

[0005] Patent Document 1 discloses a technology for creating a production plan by conducting a production process simulation using standard work times based on performance data of similar products produced in the past, and proficiency transition data showing that a preset proficiency level changes over time when a worker engages in a certain task.

[0006] Specifically, the document states that, regarding the production process support method, "a product similar to the new product is selected from performance data for each product previously produced in the target production process, and prediction data for the new product's standard work time, standard work man-hours, work difficulty and parts procurement time, worker fatigue level, and worker proficiency is calculated based on the performance data, and a production process simulation is performed in advance for the new product's production process based on the prediction data, and a production plan is created based on the results." [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-133664 Summary of the Invention [Problem to be solved by the invention]

[0008] As mentioned above, the technology in Patent Document 1 creates a production plan based on a prior simulation that takes into account past performance data of similar products, the proficiency of workers, etc. However, the technology in this document does not take into consideration the development of worker proficiency when creating a production plan.

[0009] Therefore, even if the technology of Patent Document 1 is used, it is difficult to create a production plan that allows for the achievement of production efficiency and yield targets while simultaneously cultivating the proficiency of workers.

[0010] The present invention has been made in view of the above-mentioned problems, and has an object to generate a feasible production plan that achieves productivity targets while also fostering worker proficiency. [Means for solving the problem]

[0011] The present application includes multiple means for solving at least part of the above-mentioned problems, examples of which are as follows: A production planning device according to one aspect of the present invention for solving the above-mentioned problems includes: a proficiency prediction model generation unit that generates proficiency prediction model information that predicts changes in proficiency related to the productivity of a worker who performs work processes related to the manufacture of a product, based on the work performance of the worker, and a plan generation unit that uses the proficiency prediction model information to predict changes in proficiency depending on the results of allocating work processes to the worker, and generates a production plan in which the work processes and work execution schedules are allocated to the worker so that the proficiency of the worker is developed. [Effects of the Invention]

[0012] According to the present invention, it is possible to generate a feasible production plan that achieves productivity targets while also fostering worker proficiency. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an example of a schematic configuration of a production planning device. [Figure 2] FIG. 10 is a diagram showing an example of work performance information. [Figure 3] FIG. 10 is a graph illustrating the relationship between the proficiency level of productivity and task feature amounts based on proficiency level prediction model information. [Figure 4] FIG. 10 is a diagram showing an example of skill development plan information. [Figure 5] FIG. 10 is a diagram showing an example of production volume information. [Figure 6] FIG. 10 is a diagram showing an example of process plan candidate information. [Figure 7] FIG. 2 is a diagram showing an example of production plan information. [Figure 8] FIG. 10 is a diagram showing the gap between the current proficiency level and the proficiency level at the target value. [Figure 9] FIG. 10 is a flow diagram illustrating an example of a production plan generation process. [Figure 10] FIG. 10 is a diagram illustrating an example of a production plan formulation process that takes into account a training plan for a worker. [Figure 11] FIG. 10 is a diagram showing an example of a screen on which information indicating predicted changes in proficiency level is displayed. [Figure 12] FIG. 1 is a diagram illustrating an example of a hardware configuration of a production planning device. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0015] FIG. 1 is a diagram showing an example of the schematic configuration of a production planning device 100 according to this embodiment. The production planning device 100 generates proficiency prediction model information that outputs predicted values ​​of worker proficiency, such as production efficiency (production throughput) and yield rate, and uses the proficiency prediction model information to create a production plan that minimizes the gap between the current proficiency of workers in a product work process and the target proficiency. Such a production planning device 100 creates an optimal production plan while taking into account a worker training plan.

[0016] As shown in the figure, the production planning device 100 includes a processing unit 110, a storage unit 120, an input unit 130, an output unit 140, and a communication unit 150.

[0017] First, a description will be given of the storage unit 120. The storage unit 120 is a functional unit that stores various types of information used in the processing executed by the production planning device 100. The storage unit 120 also stores information generated by the production planning device 100.

[0018] Specifically, the memory unit 120 has work performance information 121, proficiency prediction model information 122, proficiency development plan information 123, product information 124, production quantity information 125, worker information 126, process plan candidate information 127, and production plan information 128.

[0019] FIG. 2 is a diagram showing an example of work performance information 121. The work performance information 121 registers various information related to the work performance of each worker. Specifically, the work performance information 121 registers the following work characteristics: product type, process type, number of parts, maximum part height, and product size. The product type is information that identifies the product type, and for example, a product ID is registered. The process type is information that identifies the content of the work process, and for example, a process ID is registered. The number of parts is the number of parts that make up the product. The product size is registered information that indicates the size of the product.

[0020] Furthermore, the work performance information 121 registers the worker, the work time, and whether or not the work was redone as the work performance. Note that a worker ID that identifies the worker is registered for the worker. Furthermore, the work time is registered as the time taken for the work specified by the process type. Furthermore, the whether or not the work was redone is registered as information indicating whether or not redone occurred when the work specified by the process type was performed.

[0021] The work performance information 121 is used to generate skill level prediction model information 122 that predicts the skill level of each worker.

[0022] The proficiency prediction model information 122 is an information model used to quantitatively evaluate the proficiency of productivity, such as the production efficiency and yield rate of a worker, and to predict how the proficiency will change depending on the work process performed by the worker. Note that the proficiency prediction model information 122 is generated for each worker.

[0023] Fig. 3 is a graph showing the relationship between the proficiency level of productivity and task feature amounts based on the proficiency level prediction model information 122. Specifically, Fig. 3(a) to (c) are examples showing changes in the proficiency level of a certain worker's production efficiency over time. Fig. 3(d) to (f) are examples showing changes in the proficiency level of the yield rate of the same worker over time.

[0024] The horizontal axis in Figures 3(a) to (f) represents task features. Task features are multidimensional features (parameters) that indicate the characteristics of the products and task processes on which the worker worked, such as the product type, process type, number of parts, maximum part height, and product size, and are expressed as two-dimensional features through dimensionality reduction. Therefore, the width along the horizontal axis is proportional to the number of product types and task processes on which the worker worked.

[0025] The vertical axes in Figures 3(a) to (c) represent the proficiency level of production efficiency. Production efficiency is proportional to the production throughput per unit of work time. In other words, by using these graphs showing the relationship between production efficiency and task feature quantities, it is possible to calculate the work time required to perform a task of the process type indicated by a certain task feature quantity from the production efficiency value corresponding to that task feature quantity. The vertical axes in Figures 3(d) to (f) represent the proficiency level of yield rate. The yield rate is proportional to the number of tasks performed without rework. In other words, by using these graphs showing the relationship between yield rate and task feature quantities, it is possible to calculate the yield rate when a task of the process type indicated by that task feature quantity is performed from the yield rate value corresponding to that task feature quantity.

[0026] A graph showing the relationship between proficiency and work feature quantities related to productivity is generated by inputting various parameters of work performance information 121 at the time of generation (current time) (such as the product type, work type, number of parts, maximum part height, product size, work time, and whether or not rework is required, which are registered in work performance information 121) into proficiency prediction model information 122.

[0027] 3(a) and 3(d) show the relationship between the proficiency level of the worker and the task feature amount at the current time t1. When various parameters of the task performance information 121 generated according to the tasks performed after t1 are input into the model information, a graph is generated showing the relationship between the proficiency level and the task feature amount related to the worker's productivity at each time point (t2, tn, etc.) according to the content of the task performance.

[0028] 3 is an example, and the relationship between proficiency and task feature quantities is not limited to this. For example, task feature quantities may include parameters related to the worker (e.g., worker ID, etc.).

[0029] 4 is a diagram showing an example of the proficiency development plan information 123. As shown in the figure, the proficiency development plan is expressed by a graph showing the relationship between the target proficiency values ​​related to productivity, such as production efficiency and yield rate, of each worker at each point in time (e.g., tn, tn+1, tn+2, etc.) beyond the current point in time (e.g., t1) and in the future, and task feature quantities.

[0030] Figures 4(a) to (c) are examples of a training plan for a certain worker's production efficiency shown in chronological order. Figures 4(d) to (f) are examples of a training plan for a certain worker's yield rate shown in chronological order. The definitions of the task feature quantity on the horizontal axis and the production efficiency or yield rate on the vertical axis are the same as in Figure 3, so detailed explanations will be omitted.

[0031] Such proficiency development plan information 123 is calculated by inputting target values ​​of proficiency related to productivity into proficiency prediction model information 122 corresponding to each worker. Specifically, the site manager inputs target values ​​for each worker, such as target work time and target yield rate for each time point beyond (in the future) the present time point (e.g., t1) (e.g., future time points tn+1, tn+2 in increments of one to three months), together with parameters of work feature quantities such as product type and work process, into proficiency prediction model information 122, thereby generating the proficiency development plan information 123. Note that the value of production efficiency is proportional to the production throughput per unit time, and is therefore calculated by inputting target work time in association with product type and work process into proficiency prediction model information 122.

[0032] Returning to Fig. 1, information about various products is registered in product information 124. Specifically, various information corresponding to the registered information in work performance information 121, such as product ID, component parts, number of parts, maximum part height, product size, and work processes performed in manufacturing the product, is registered in product information 124.

[0033] Such product information 124 is used to generate work performance information 121 corresponding to the work performed by the worker.

[0034] 5 is a diagram showing an example of the production volume information 125. The production volume information 125 is information indicating the planned production quantity of a product for each period. Specifically, the product ID 125a of the production volume information 125 is information for identifying the product to be produced. Furthermore, the monthly production volume 125b is information indicating the planned production quantity of the target product for a specified target period.

[0035] The production volume information 125 is referenced, for example, when a site manager sets a target value for the proficiency of each worker. The site manager sets a target value for the proficiency of each worker related to productivity up to a predetermined time by referring to the production volume information 125. Specifically, the site manager sets a target value for the proficiency of each worker at each time point with reference to the planned production volume of the product, and inputs the target value into the proficiency prediction model information 122 to calculate the proficiency development plan information 123 for each worker. The production volume information 125 is also used in the production plan generation process described below.

[0036] Returning to Fig. 1, the worker information 126 contains various information related to the worker. Specifically, the worker information 126 stores various information such as a worker ID for identifying the worker, scheduled work dates and times, and work results.

[0037] FIG. 6 is a diagram showing an example of the process plan candidate information 127. The process plan candidate information 127 is information in which work candidates capable of performing each work are assigned to each work process according to their proficiency levels related to productivity. Specifically, the product ID 127a in the process plan candidate information 127 is information for identifying the product to be manufactured. The part ID 127b is information for identifying the parts that make up the product. The process ID 127c is information for identifying each process. The work candidate ID 127d is information for identifying work candidates who have the proficiency level to perform the work of the associated process ID 127c. Note that the work candidate ID 127d is registered with at least one work candidate associated with one process ID.

[0038] Such process plan candidate information 127 is generated when a production plan generation process, which will be described later, is executed. After the production plan generation process is executed, a worker identified by the formulated production plan is assigned to the worker candidate ID 127d of the process plan candidate information 127, and the process plan information is updated.

[0039] FIG. 7 is a diagram showing an example of production plan information 128. The production plan information 128 contains information indicating the timing of product production, such as the date and time, start time, and end time of each process in product manufacturing. Specifically, the product ID 128a in the production plan information 128 is information for identifying the product to be manufactured. The part ID 128b is information for identifying the parts that make up the product. The process ID 128c is information for identifying the process. The worker ID 128d is information for identifying the worker performing the work content of the associated process ID 128c. The date and time 128e is information indicating the date and time of a specific process, such as assembling the part identified by the associated part ID 128b, in the manufacture of the product identified by the associated product ID 128a. The estimated start time 128f is information indicating the estimated start time of the process identified by the associated process ID 128c. The estimated end time 128g is information indicating the estimated end time of the process.

[0040] The production plan information 128 is generated when a production plan generation process, which will be described later, is executed.

[0041] Next, we will explain the processing unit 110. The processing unit 110 is a functional unit that performs various processes executed by the production planning device 100. As shown in Fig. 1, the processing unit 110 has a work record generation unit 111, a proficiency prediction model generation unit 112, a training plan calculation unit 113, a proficiency gap calculation unit 114, an allocation candidate specification unit 115, and a plan generation unit 116.

[0042] The work record generation unit 111 is a functional unit that generates work record information 121. Specifically, when each worker performs the assigned work process, the work record generation unit 111 uses product information 124 and worker information 126 to generate work record information 121 including the details of the work that was performed.

[0043] The proficiency prediction model generation unit 112 is a functional unit that generates proficiency prediction model information 122. Specifically, the proficiency prediction model generation unit 112 uses the work performance information 121 to generate the proficiency prediction model information 122 for predicting how proficiency related to worker productivity will change over time by machine learning or statistical analysis techniques. Note that the method for generating the proficiency prediction model information 122 is not particularly limited, and any known technique may be used, such as deep learning (particularly, LSTM: Long Short Term Memory) using multivariate time series data as input, or a regression method that uses explanatory variables including information about time as input and predicts a target variable (production efficiency, yield rate).

[0044] The training plan calculation unit 113 is a functional unit that calculates proficiency training plan information 123. Specifically, the training plan calculation unit 113 inputs the target values ​​of each worker acquired via the input unit 130 into proficiency prediction model information 122, thereby calculating proficiency training plan information 123 that shows, in a graph, the proficiency related to productivity of each worker at each time point in the training plan (for example, time points tn, tn+1, tn+2, etc.).

[0045] More specifically, the training plan calculation unit 113 acquires, via the input unit 130, dates indicating each time point (for example, t1) beyond (in the future) (for example, future times tn, tn+1, tn+2, etc., in increments of one to three months), product types and work processes, and the corresponding target work time and target yield rate for each worker. In addition, the training plan calculation unit 113 inputs the acquired information into proficiency prediction model information 122, thereby calculating proficiency training plan information 123, which graphs the proficiency related to productivity at each time point (for example, tn, tn+1, tn+2, etc.) of the training plan for each worker.

[0046] The proficiency gap calculation unit 114 is a functional unit that calculates the gap between the current proficiency level related to productivity and the proficiency level at the target value. Specifically, the proficiency gap calculation unit 114 uses the proficiency prediction model information 122 to generate a graph showing the proficiency level related to the worker's productivity at the current time and the proficiency level at the target value related to the productivity, and calculates the gap between the two by comparing them. Note that the proficiency level at the target value may be calculated using information calculated by the training plan calculation unit 113.

[0047] FIG. 8 is a diagram showing the gap between the current proficiency level and the proficiency level at a target value. As shown in the figure, there is a gap between the current proficiency level related to productivity (the illustrated example shows the case of production efficiency, but it may also be the yield rate) and the proficiency level at a target value set by the site manager. The proficiency gap calculation unit 114 identifies the gap, which is the difference between the two. Note that the proficiency gap calculation unit 114 may calculate the size of the gap between the two in a certain task feature amount, or may calculate the average value of the differences between the two in each task feature amount as the gap.

[0048] Such proficiency gaps are used to generate a production plan that takes training plans into account. As will be described later, a production plan is generated that allocates work processes to each worker so as to minimize the size of the gaps, making it possible to create a production plan that takes training plans into account, such that the target proficiency level is achieved after a predetermined period of time.

[0049] The allocation candidate specification unit 115 is a functional unit that specifies, as work candidate workers, workers to whom each work process can be assigned according to the worker's level of proficiency. Specifically, the allocation candidate specification unit 115 specifies the product type and quantity (physical amount) to be produced, for example, from the production quantity information 125. The allocation candidate specification unit 115 also specifies the work processes required to manufacture the product using the product information 124. The allocation candidate specification unit 115 also calculates the work time set (allowable) for each work process of the product based on the manufacturing period specified from the production quantity information 125. The allocation candidate specification unit 115 also specifies the lower limit of the yield rate, which is set in advance for each product, from predetermined setting information (not shown) stored in the storage unit 120.

[0050] The allocation candidate specification unit 115 also specifies workers with proficiency that meet the calculated operation time and specified yield rate, based on the operation time and yield rate obtained from a proficiency graph (for example, the graph in FIG. 3) obtained by inputting current operation performance information 121 into proficiency prediction model information 122. The allocation candidate specification unit 115 also generates process plan candidate information 127 in which at least one operation candidate is associated with each process ID.

[0051] The plan generating unit 116 is a functional unit that generates various types of plan information. Specifically, the plan generating unit 116 executes a production plan generation process to generate production plan information 128 that takes into account a training plan for workers.

[0052] The processing unit 110 has been described above.

[0053] The input unit 130 is a functional unit that accepts input of instructions and information from a user (operator) of the production planning device 100 via an input device included in the production planning device 100. The input unit 130 also accepts input of instructions and information from an external device 200 via the communication unit 150.

[0054] The output unit 140 is a functional unit that generates output information (including display information) and displays the display information on an output device (for example, a display) that the production planning device 100 or the external device 200 has.

[0055] The communication unit 150 is a functional unit that performs information communication with the external device 200. Specifically, the communication unit 150 transmits and receives various information to and from the external device 200 via a network (communication line network) N such as the Internet or a LAN (Local Area Network).

[0056] An example of the schematic configuration (functional blocks) of the production planning device 100 has been described above.

[0057] [Explanation of operation] Next, the production plan generation process executed by the production planning device 100 will be described.

[0058] 9 is a flow diagram showing an example of the production plan generation process. The production plan generation process is a process for generating (drafting) optimal production plan information 128 that takes into account a training plan for workers by generating production plan information 128 that minimizes the gap between the worker's current proficiency level in terms of productivity and the proficiency level at a target value.

[0059] The production plan generation process is started, for example, when the production planning device 100 is started.

[0060] When the process starts, the plan generating unit 116 determines whether it is time to create a production plan and a development plan (step S010). Specifically, the plan generating unit 116 determines whether it is time to create a production plan or a development plan, such as a preset weekly or monthly schedule.

[0061] If it is determined that the timing for planning has arrived (Yes in step S010), the plan generating unit 116 proceeds to step S020. On the other hand, if it is determined that the timing for planning has not arrived (No in step S010), the plan generating unit 116 executes the process of step S010 again.

[0062] In step S020, the proficiency prediction model generation unit 112 generates proficiency prediction model information 122 at the current time point for each worker. Specifically, the proficiency prediction model generation unit 112 identifies the worker ID of each worker using the worker information 126. Furthermore, the proficiency prediction model generation unit 112 generates the proficiency prediction model information 122 for each worker by a predetermined method such as regression analysis, using the work performance information 121 in which the worker ID is registered.

[0063] Next, the plan generating unit 116 uses the generated skill level prediction model information 122 to execute a process of creating a production plan that takes into account the training plan for the workers (step S030).

[0064] FIG. 10 is a diagram showing an example of a production plan formulation process that takes into account a training plan for a worker. First, the training plan calculation unit 113 accepts input of a target value for proficiency (step S031). Specifically, the training plan calculation unit 113 displays screen information for accepting input of the target value on an output device (display) via the output unit 140. The training plan calculation unit 113 also accepts input of dates for each point in time on the training plan (for example, dates indicating each point in time in the future in increments of one to three months), a worker ID, a product type and work process, and target values ​​for the product type and work process (for example, a target work time and a target yield rate) via the input unit 130.

[0065] Next, the training plan calculation unit 113 calculates a training plan for proficiency (step S032). Specifically, the training plan calculation unit 113 inputs information related to the received target value into proficiency prediction model information 122 for the corresponding worker, thereby calculating proficiency training plan information 123 indicating proficiency related to productivity at each time point on the training plan.

[0066] Next, the proficiency gap calculation unit 114 calculates the gap between the current proficiency level related to productivity and the target proficiency level (step S033). Specifically, the proficiency gap calculation unit 114 calculates the gap between the graph of the proficiency level related to the worker's productivity at the current time, which is generated using the proficiency prediction model information 122, and the graph showing the target proficiency level at a predetermined time point, which is indicated in the proficiency development plan information 123.

[0067] The proficiency gap calculation unit 114 may calculate the gap between the proficiency gap corresponding to a certain task feature (for example, a task feature corresponding to a product type and task process received from the site manager as a target value) and the current proficiency, or may calculate the gap as the average value of the difference between the two for each task feature.

[0068] Next, the allocation candidate specification unit 115 calculates the work processes required for the specified manufacturing period and the set (allowable) work time and yield rate for each process (step S034). Specifically, the allocation candidate specification unit 115 specifies the product type and quantity (quantity) to be produced during the manufacturing period specified from, for example, the production quantity information 125, and specifies the work processes required to manufacture the product and the number of such processes using the product information 124. The allocation candidate specification unit 115 also calculates the work time to be set for each work process of the product based on the manufacturing period. The allocation candidate specification unit 115 also specifies the lower limit of the yield rate that is preset for each product from the storage unit 120.

[0069] Next, the allocation candidate identification unit 115 generates process plan candidate information 127 in which work candidates who can perform the work are assigned to each work process (step S035). Specifically, the allocation candidate identification unit 115 identifies workers with proficiency levels that satisfy the calculated work time and the identified yield rate from a graph (a graph showing the relationship between proficiency levels related to productivity such as production efficiency and work feature amounts) generated using the proficiency prediction model information 122, and generates process plan candidate information 127 in which the work candidates are associated with each process ID 127c.

[0070] Next, the plan generating unit 116 generates production plan information 128 so as to minimize the gap between each worker (step S036). Specifically, the plan generating unit 116 uses the process plan candidate information 127 to perform initial allocation in which work processes are allocated to work candidates (if multiple work candidates are associated with one work process, an arbitrary one work candidate).

[0071] The plan generation unit 116 also generates work performance prediction information that indicates the work performance when the work processes assigned to each work candidate are performed by a certain point in the training plan. Specifically, the plan generation unit 116 uses product information 124 to identify the characteristics (product type, process type, number of parts, etc.) of the work processes assigned to each work candidate, and generates work performance prediction information that includes the work characteristics and the predicted work time and whether or not rework is required, which are calculated by statistical analysis using each work candidate's past work performance information 121. Note that the work performance prediction information has the same items as the work performance information 121.

[0072] The plan generation unit 116 also inputs the work performance prediction information into the proficiency prediction model information 122 to obtain a prediction graph (for example, the graph shown in FIG. 3) showing time-series changes in proficiency related to productivity. The plan generation unit 116 also calculates a prediction gap in the initial allocation based on the difference between the prediction graph showing the proficiency when the work process for which initial allocation has been performed is carried out and the graph showing the proficiency of the target value. The plan generation unit 116 also identifies the gap reduction amount for each work candidate by subtracting the prediction gap in the initial allocation from the gap calculated in step S033.

[0073] The plan generation unit 116 also calculates the predicted gap for each candidate worker while changing the candidate worker to whom the work process is assigned, and repeatedly performs a simulation to identify the degree of gap reduction. The plan generation unit 116 also identifies a combination of a work process with a larger degree of reduction identified and a candidate worker to whom the work process is assigned.

[0074] In this way, by identifying a combination of a work process and a candidate worker to whom that work process is to be assigned, a combination that minimizes the gap between the current proficiency level and the target proficiency level is identified, i.e., a combination of a work process that brings the current proficiency level closer to the target proficiency level and a candidate worker to whom that work process is to be assigned is identified.

[0075] The method for identifying the optimal combination through such simulation may be a known optimization method such as a metaheuristic method.

[0076] Furthermore, the plan generating unit 116 generates process plan information in which the work candidate in the identified combination is assigned to the work process.

[0077] Furthermore, the plan generation unit 116 calculates the date and time when each work process will be performed using the production quantity information 125, worker information 126, and process plan information, and generates production plan information 128 that includes the timing of performing each work process. Note that any known technology may be used to generate a production plan using a process plan.

[0078] After generating the production plan information 128, the plan generating unit 116 ends this flow and proceeds to step S040 in FIG.

[0079] The processing of steps S031 to S036 may be performed, for example, by a group of workers who are pre-assigned to each production line in a factory.

[0080] In step S040, the output unit 140 outputs screen information showing a predicted change in the productivity proficiency level.

[0081] 11 is a diagram showing an example screen 250 on which information indicating predicted changes in proficiency level is displayed. Note that the example screen 250 in this example displays a worker selection area 251 that displays target workers in a selectable manner, and a radar chart display area 252 that displays a radar chart of proficiency levels.

[0082] The proficiency radar chart displayed in the radar chart display area 252 shows predicted changes in proficiency related to the productivity of the worker selected in the worker selection area 251. Specifically, the radar chart has the items of production efficiency, quality, and experience. The radar chart also forms graphs of actual values, predicted values, and target values ​​for each base date 253.

[0083] The graph of actual results indicates the proficiency level as of a reference date for the actual results (in the illustrated example, January 5, 2022, e.g., the present time). The graph of actual results is generated based on a graph (e.g., the graph in FIG. 3(a)) obtained by inputting the work performance information 121 of the worker generated up to the reference date for the actual results into the proficiency prediction model information 122. Specifically, the scale of the graph for production efficiency corresponds to, for example, the average value of the production efficiency on the vertical axis in FIG. 3(a). The scale of the graph for quality corresponds to, for example, the average value of the yield rate on the vertical axis in FIG. 3(d). The experience corresponds to the quantity of work performance information 121 generated up to the reference date, i.e., the amount of work performed by the selected worker.

[0084] Furthermore, the graph of predicted values ​​shows the proficiency predicted on the reference date of the predicted values ​​(in the illustrated example, February 5, 2022). Specifically, the scale of each item on the graph of predicted values ​​is calculated based on, for example, the production efficiency, yield rate, and work performance information 121 (including work performance prediction information) at a first time point in the proficiency development plan information 123 (for example, time point tn in FIGS. 4(a) and (d) or time point tn+1 in FIGS. 4(b) and (e)).

[0085] The target value graph also shows the target proficiency predicted on the target value reference date (in the illustrated example, March 31, 2022). Specifically, the scale of each item on the target value graph is calculated based on the production efficiency, yield rate, and work performance information 121 (including work performance prediction information) at a second time point in the development plan information (for example, time point tn+2 in FIGS. 4(c) and 4(f)).

[0086] Returning to Fig. 9, the explanation will be made. Next, the input unit 130 determines whether or not a correction instruction has been received (step S050). Specifically, the input unit 130 determines whether or not a correction instruction has been received from, for example, a site manager via a predetermined correction instruction receiving screen displayed on the output device by the output unit 140. Note that correction instructions include, for example, an instruction to change a target value for a worker or an instruction to change a work process assigned to a worker.

[0087] If it is determined that a correction instruction has been received (Yes in step S050), input unit 130 proceeds to step S030. In step S030, the production plan creation process is performed again, reflecting the correction instruction.

[0088] On the other hand, if it is determined that a correction instruction has not been received (No in step S050), the output unit 140 outputs the generated production plan information 128 to the output device (step S060), and ends this flow.

[0089] The production plan generation process has been described above.

[0090] Such a production planning device 100 can generate a feasible production plan that achieves productivity targets while also fostering worker proficiency. That is, the production planning device 100 can formulate a production plan that simultaneously optimizes a training-related KPI (Key Performance Indicator), which is indicated by the gap between the current proficiency level and the target proficiency level, and productivity-related KPIs, such as production efficiency and yield rate. Productivity-related KPIs may include, for example, delivery deadline compliance. Similar to KPIs such as production efficiency, the delivery deadline compliance KPI may be calculated by executing a production plan generation process based on a graph generated using, for example, worker work performance information and proficiency prediction model information.

[0091] Furthermore, the production planning device 100 can predict changes in the proficiency of each worker by generating proficiency prediction model information related to the productivity of each worker. Therefore, the production planning device 100 can calculate a training plan according to the characteristics of each worker to achieve a target proficiency.

[0092] Furthermore, the production planning device 100 can calculate the gap between the current proficiency level of each worker and the target proficiency level, and generate a process plan and a production plan in which work processes are assigned to appropriate workers so as to reduce (minimize) the gap. Therefore, the production planning device 100 can create a production plan that takes into account the training of each worker.

[0093] Furthermore, the production planning device 100 calculates the work time and yield rate for each worker using the proficiency prediction model information, and identifies workers with a proficiency level that satisfies the work time and yield rate required for the product work process as work candidates. Therefore, the production planning device 100 can select workers who have a low risk of delays in product manufacturing or quality defects, and can also create a production plan that allows for the training of these workers.

[0094] The present invention is not limited to the above embodiment, and various modifications are possible. For example, the production planning device 100 according to a first modification executes re-planning of the production plan when a predetermined production change event occurs.

[0095] Specifically, in step S010 of the production plan generation process, the plan generation unit 116 also determines whether a production fluctuation event has occurred, such as a worker's absence or lateness, or an order for the manufacture of a product type that requires urgent action.

[0096] If it is determined that such a production fluctuation event has occurred, the plan generation unit 116 performs the processes of steps S020 to S060 to generate production plan information 128 corresponding to the production fluctuation event. For example, if the production fluctuation event is a worker's absence or lateness, the production planning unit generates worker proficiency prediction model information 122, proficiency development plan information 123, and process plan candidate information 127 using worker information 126 excluding that worker, and then re-creates the production plan information 128 using each of these pieces of information.

[0097] Furthermore, for example, when a production fluctuation event is an order for manufacturing a product type that requires an urgent response, the plan generating unit 116 re-creates the production plan information 128 using the production quantity information 125 that reflects the product type and the order quantity.

[0098] According to the production planning device 100 of the first modified example, even when an order is received for the manufacture of a product type that requires an urgent response or when a worker is absent, it is possible to quickly regenerate production plan information 128 that takes into account the worker training plan.

[0099] Furthermore, the plan generation unit 116 of the production planning device 100 according to the second modified example uses the process plan information or the proposed production plan information 128 to generate configuration information for the production lines in which workers appropriate for the work processes to be performed on each production line are assigned.

[0100] Specifically, the plan generation unit 116 can generate configuration information for a production line in which appropriate workers are assigned by allocating workers to each production line based on the work processes assigned to each worker and the various work processes that have been assigned to each production line in advance.

[0101] According to such a production planning device 100, it is possible to generate configuration information in which workers, to whom work processes taking into consideration the training plan, are allocated to appropriate production lines in each production line in a factory.

[0102] The above describes the modified example of the production planning device 100.

[0103] 12 is a diagram showing an example of the hardware configuration of the production planning device 100. As shown in the figure, the production planning device 100 has an input device 310, an output device 320, a processing device 330, a main memory device 340, an auxiliary memory device 350, a communication device 360, and a bus 370 that electrically interconnects these devices.

[0104] The input device 310 is, for example, a touch panel, a keyboard, a mouse, etc. The output device 320 is a display device such as a liquid crystal display or an organic display.

[0105] The processing device 330 is, for example, a central processing unit (CPU). The main storage device 340 is a memory device such as a random access memory (RAM) or a read only memory (ROM).

[0106] The auxiliary storage device 350 is a non-volatile storage device capable of storing digital information, such as a so-called hard disk drive, a solid state drive (SSD), or a flash memory.

[0107] The communication device 360 ​​is a wired communication device that performs wired communication via a network cable, or a wireless communication device that performs wireless communication via an antenna.

[0108] An example of the hardware configuration of the production planning device 100 has been described above.

[0109] The processing unit 110 of the production planning device 100 is realized by a program that causes the processing device 330 to perform processing. This program is stored in the main storage device 340 or the auxiliary storage device 350, and is loaded onto the main storage device 340 and executed by the processing device 330 when the program is executed.

[0110] The input unit 130 is realized by an input device 310. The output unit 140 is realized by an output device 320. The storage unit 120 is realized by a main storage device 340, an auxiliary storage device 350, or a combination of these. The communication unit 150 is realized by a communication device 360.

[0111] Furthermore, the above-described configurations, functions, processing unit 110, processing means, etc. of the production planning device 100 may be partially or entirely realized in hardware, for example, by designing them as integrated circuits. The above-described configurations and functions may also be realized in software, with a processor interpreting and executing programs that realize the respective functions. Information such as programs, tables, and files that realize the respective functions can be stored in storage devices such as memory, hard disks, and SSDs, or in recording media such as IC cards, SD cards, and DVDs.

[0112] Furthermore, the present invention is not limited to the above-described embodiments and modifications, and includes various modifications within the scope of the same technical concept. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0113] In addition, in the above explanation, the control lines and information lines are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0114] 100... Production planning device, 110... Processing unit, 111... Work performance generation unit, 112... Skill level prediction model generation unit, 113... Training plan calculation unit, 114... Skill level gap calculation unit, 115... Allocation candidate identification unit, 116... Plan generation unit, 120... Storage unit, 121... Work performance information, 122... Skill level prediction model information, 123... Skill level training plan information, 124... Product information, 1 25...Production quantity information, 126...Worker information, 127...Process plan candidate information, 128...Production plan information, 130...Input section, 140...Output section, 150...Communication section, 200...External device, 310...Input device, 320...Output device, 330...Processing device, 340...Main memory device, 350...Auxiliary memory device, 360...Communication device, 370...Bus, N...Network

Claims

1. a proficiency prediction model generation unit that generates proficiency prediction model information that predicts changes in proficiency related to the productivity of a worker based on the work performance of the worker performing a work process related to the manufacture of the product; a plan generation unit that uses the proficiency prediction model information to predict changes in proficiency depending on the results of allocation of work processes to the workers, and generates a production plan in which the work processes and work execution schedules are allocated to the workers so that the proficiency of the workers is developed; a proficiency gap calculation unit that calculates a gap that is a difference between a current proficiency level obtained by inputting the work performance of the worker into the proficiency prediction model information and a target proficiency level obtained by inputting a target work time or a target yield rate of the worker into the proficiency prediction model information, The plan generation unit A production plan is generated that simultaneously optimizes a KPI (Key Performance Indicator) related to training, which is indicated by the gap between the current proficiency level of the worker and the target proficiency level, and a KPI related to productivity. A production planning device characterized by:

2. 2. The production planning device according to claim 1, If a production fluctuation event occurs due to the aforementioned worker or product order, The plan generation unit The production plan is generated using worker information in which the workers other than the worker causing the problem are registered, or production volume information in which the planned production volume by period reflecting the ordered product causing the problem is registered. A production planning device characterized by:

3. 2. The production planning device according to claim 1, The plan generation unit Based on the work processes assigned to the workers using the proficiency prediction model information and the work processes performed in each production line that manufactures products, configuration information of the production line in which the workers are assigned to each production line is generated. A production planning device characterized by:

4. 2. The production planning device according to claim 1, calculating an individual target proficiency for each worker by inputting the target work time or target yield rate of the worker for the work process into the proficiency prediction model information; a development plan calculation unit that calculates a development plan based on the time-series change in the target proficiency level A production planning device characterized by:

5. 2. The production planning device according to claim 1, The system further includes an allocation candidate specifying unit that specifies candidates for workers who can fulfill the work time required in the work process related to the manufacturing of the product, based on the work time obtained by inputting the work performance of the workers into the proficiency prediction model information. A production planning device characterized by:

6. 6. The production planning device according to claim 5, The allocation candidate specifying unit Candidates for workers who satisfy a required yield rate in a work process related to the manufacturing of the product are identified based on a yield rate obtained by inputting the work performance of the workers into the proficiency prediction model information. A production planning device characterized by:

7. A production planning method executed by a production planning device, The production planning device a proficiency prediction model generation step of generating proficiency prediction model information for predicting a change in proficiency related to the productivity of a worker based on the work performance of the worker performing a work process related to the manufacture of the product; a plan generation step of predicting a change in proficiency according to a result of allocation of work processes to the workers using the proficiency prediction model information, and generating a production plan in which the work processes and work execution schedules are allocated to the workers so that the proficiency of the workers is developed; a proficiency gap calculation step of calculating a gap that is a difference between a current proficiency level obtained by inputting the work performance of the worker into the proficiency prediction model information and a target proficiency level obtained by inputting a target work time or a target yield rate of the worker into the proficiency prediction model information; In the plan generation step, generating a production plan that simultaneously optimizes a KPI (Key Performance Indicator) related to training indicated by the gap between the current proficiency level of the worker and the target proficiency level, and a KPI related to productivity; A production planning method comprising:

8. A program that causes a computer to function as a production planning device, The computer a proficiency prediction model generation unit that generates proficiency prediction model information that predicts changes in proficiency related to the productivity of a worker based on the work performance of the worker performing a work process related to the manufacture of the product; a plan generation unit that uses the proficiency prediction model information to predict changes in proficiency depending on the results of allocation of work processes to the workers, and generates a production plan in which the work processes and work execution schedules are allocated to the workers so that the proficiency of the workers is developed; a proficiency gap calculation unit that calculates a gap that is a difference between a current proficiency level obtained by inputting the work performance of the worker into the proficiency prediction model information and a target proficiency level obtained by inputting a target work time or a target yield rate of the worker into the proficiency prediction model information, In the processing of the plan generation unit, A production plan is generated that simultaneously optimizes a KPI (Key Performance Indicator) related to training, which is indicated by the gap between the current proficiency level of the worker and the target proficiency level, and a KPI related to productivity. A program characterized by:

Images