Production planning device, production planning method, and program

Abstract

To develop an in-house production transition plan and a production plan that ensure the skill level of a worker for in-house production according to a procurement risk of components.SOLUTION: A production planning device includes: a prediction model generation unit which generates a procurement risk prediction model that predicts a time-series change in a procurement risk on the basis of the procurement records of components or the like and a proficiency prediction model that predicts a time-series change in the proficiency of a worker on the basis of the work result; an in-house production transition plan generation unit which specifies an overlapping period in which a period where the procurement risk increases and a period where the proficiency reduces overlap each other by using the procurement risk prediction model and proficiency prediction model and generates an in-house production transition plan in which components with the overlapping period are registered; and a production plan generation unit which uses the procurement risk prediction model and proficiency prediction model to calculate the combination of the in-house production transition period in which the production efficiency and procurement risk according to the proficiency of the worker are optimized and the work allocation to the worker, and devises a production plan based on the in-house production transition period and the work allocation.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] In the manufacturing industry, for example, there are procurement risks such as supply chain interruptions and delivery delays due to geopolitical risks, and if such risks occur, it may lead to production stoppages and reduced throughput in the company. In order to deal with such procurement risks, manufacturing companies need to constantly check procurement performance information such as the price and delivery date of outsourced parts, and take prompt measures when procurement risks increase.

[0003] One of the countermeasures to the rising prices and long delivery times of outsourced parts is to switch to another outsourcing supplier if there are many potential suppliers in the trading market. On the other hand, if there are few potential suppliers or there are concerns about the quality of the supplier, it becomes necessary to produce the parts in-house. However, depending on the parts and work, it can be difficult to switch to in-house production if the company's level of expertise is low.

[0004] Incidentally, Patent Document 1 discloses a method for appropriately calculating the planned in-house production quantity and the planned outsourced production quantity as a method for determining whether to produce parts in-house or outsource. Specifically, Patent Document 1 describes a "parts production management system for managing generic parts a and special order parts b used in a product, comprising: (a) a storage unit for storing inventory information; (b) a manufacturing facility information acquisition unit for acquiring manufacturing facility information; (c) an order-related information acquisition unit for acquiring order-related information; and (d) a planned production quantity xp of generic parts a produced by in-house manufacturing facility A so as to minimize total cost C. (A,a) , Custom-made parts xp manufactured at in-house manufacturing facility A (A,b) , the planned production quantity of generic part a manufactured by external manufacturing facility B is xp (B,a) , the planned production quantity of special order part b produced by external manufacturing facility B is xp (B,b) and (e) a production plan creation unit that calculates the production schedule and updates the schedule. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2019-66956 A Summary of the Invention [Problem to be solved by the invention]

[0006] The technology in Patent Document 1 calculates the planned numbers of parts to be produced in-house and outsourced based on the number of parts in stock, the stock of materials to make the parts, and the operating status of in-house and external equipment, and then makes a decision on whether to produce in-house or outsource and draws up a production plan taking into account the stock levels.

[0007] However, the technology in this document does not take into account the skill level of the workers, making it difficult to predict changes in the production capacity of parts. In addition, the technology in this document does not take into account information that affects the procurement situation, such as the price and delivery date of the outsourcing, making it difficult to predict future changes in the planned number of outsourced productions. For these reasons, the technology in this document has the problem that it is difficult to take measures when the procurement risk of outsourced parts increases.

[0008] The present invention has been made in consideration of the above-mentioned problems, and aims to devise an in-house production switching plan and production plan that ensures the proficiency of workers for in-house production in-house, in accordance with the procurement risk of parts. [Means for solving the problem]

[0009] The present application includes a plurality of means for solving at least a 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 prediction model generation unit that generates a procurement risk prediction model that predicts a time-series change in the procurement risk of a part based on the procurement record of the part and a trading market state, and a proficiency prediction model that predicts a time-series change in the proficiency of a worker based on the work record of the worker, an internal production switching plan generation unit that uses the procurement risk prediction model and the proficiency prediction model to identify an overlapping period when a period when the procurement risk increases and a period when the proficiency decreases overlap, and generates an internal production switching plan in which the part having the overlapping period is registered, and a production plan generation unit that uses the procurement risk prediction model and the proficiency prediction model to calculate a production efficiency according to the proficiency of the worker and an internal production switching time that optimizes the procurement risk, and a combination of work allocations to the worker, and creates a production plan based on the internal production switching time and work allocations. Effect of the Invention

[0010] According to the present invention, it is possible to develop an in-house production switching plan and a production plan that ensures the proficiency of workers for in-house production in accordance with the procurement risk of parts. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a schematic configuration of a production planning system. [Diagram 2] FIG. 11 is a diagram showing an example of procurement record information. [Diagram 3] FIG. 2 is a diagram showing an example of trading market information. [Figure 4] FIG. 11 is a diagram showing an example of work performance information. [Diagram 5] FIG. 13 is a graph illustrating an example of a relationship between procurement risk and procurement feature amount. [Figure 6] 11 is a graph illustrating an example of a relationship between skill level and task feature amount. FIG. [Figure 7] FIG. 11 is a diagram showing an example of production quantity information. [Figure 8] FIG. 11 is a diagram illustrating an example of product information. [Figure 9] FIG. 13 is a diagram showing an example of an input screen for product information. [Figure 10] FIG. 11 is a diagram showing an example of worker information. [Figure 11] FIG. 13 is a diagram showing an example of in-house production switching plan information. [Figure 12] FIG. 2 is a diagram showing an example of production plan information. [Figure 13] FIG. 11 is a flow diagram illustrating an example of a production plan generation process. [Figure 14] FIG. 13 is a diagram showing an example of an image of an in-house production switching plan. [Figure 15] FIG. 11 is a flow diagram illustrating an example of a production planning process. [Figure 16] FIG. 13 is a diagram showing an example of an output screen. [Figure 17] FIG. 11 is a diagram showing an example of screen information. [Figure 18] FIG. 1 is a diagram showing an example of an image of procurement and supply of materials used for outsourced parts. [Figure 19] FIG. 11 is a diagram showing an example of procurement record information according to the second embodiment. [Figure 20] FIG. 2 is a diagram illustrating an example of a hardware configuration of a production planning device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0013] First Embodiment The production planning device of this embodiment is a device that generates (draws up) a production plan, and in particular, takes into consideration the procurement risk of parts and the proficiency of workers, optimizing the timing of in-house production switchover and the production plan so as to satisfy the desired procurement risk and production efficiency.

[0014] Specifically, the production planning device uses a procurement risk prediction model for predicting time-series changes in the procurement risk of parts, and a proficiency prediction model for predicting time-series changes in the proficiency of workers' productivity, to identify parts for which the period when procurement risk increases and the period when proficiency decreases overlap, as parts that should be switched from outsourcing to in-house production.

[0015] In addition, the production planning device optimizes the timing of switching to in-house production and the production plan by repeatedly calculating (simulating) the combination of the timing of switching to in-house production and the work allocation after the timing of switching to in-house production so as to satisfy the desired procurement risk and production efficiency.

[0016] With such a production planning device, it is possible to create an in-house production switching plan and a production plan that ensures the proficiency of workers for in-house production in accordance with the procurement risks of parts.

[0017] <Overview of the Production Planning System 1000> 1 is a diagram showing an example of a schematic configuration of a production planning system 1000 including a production planning device 100 according to this embodiment. As shown in the figure, the production planning system 1000 has the production planning device 100 and an external device 200, and these devices are communicatively connected via a network N. Note that the network N is, for example, a public network such as the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network).

[0018] <Details of the production planning device 100> The production planning device 100 is a device that generates (creates) a production plan. As shown in the figure, the production planning device 100 has a processing unit 110, a storage unit 120, an input unit 140, an output unit 150, and a communication unit 160.

[0019] The processing unit 110 is a functional unit that performs various processes executed by the production planning device 100. The processing unit 110 has a prediction model generation unit 111, an internal production switchover plan generation unit 112, and a production plan generation unit 113 as individual functional units that execute each process.

[0020] The prediction model generation unit 111 is a functional unit that performs processing to generate an information model. Specifically, the prediction model generation unit 111 generates a procurement risk prediction model and a skill prediction model. The generation processing of these information models will be described later.

[0021] The in-house production switching plan generating unit 112 is a functional unit that performs processing to generate an in-house production switching plan. Specifically, the in-house production switching plan generating unit 112 predicts time-series changes in procurement risk and worker proficiency using a procurement risk prediction model and a proficiency prediction model, and identifies parts for which both procurement risk and proficiency exceed predetermined thresholds at the same time (same year and month). The in-house production switching plan generating unit 112 also identifies the identified parts as target parts for switching from outsourcing to in-house production, and generates an in-house production switching plan in which the identified parts are registered. The in-house production switching plan generating unit 112 also registers the calculated in-house production switching time in the in-house production switching plan information.

[0022] The production plan generation unit 113 is a functional unit that generates (drafts) a production plan for a product. Specifically, the production plan generation unit 113 repeatedly calculates a combination of work assignments to each worker so as to achieve the desired production efficiency and procurement risk while changing the internal production switching timing, thereby drafting an optimized production plan that maximizes production efficiency and minimizes procurement risk.

[0023] Next, a description will be given of the storage unit 120. The storage unit 120 is a functional unit that stores various information used in the processes executed by the production planning device 100. The storage unit 120 also stores information generated by the production planning device 100.

[0024] Specifically, the memory unit 120 stores procurement performance information 121, trading market information 122, work performance information 123, procurement risk prediction model 124, proficiency prediction model 125, production quantity information 126, product information 127, worker information 128, in-house production switchover plan information 129, and production plan information 130.

[0025] 2 is a diagram showing an example of procurement record information 121. Information on procurement records when outsourced parts were procured in the past is registered in procurement record information 121. Specifically, procurement record information 121 has records in which product number 121a, part number 121b, order date and time 121c, order quantity 121d, arrival date and time 121e, arrival quantity 121f, approved quantity 121g, and price 121h are associated with each other.

[0026] The product number 121a, part number 121b, order date and time 121c, order quantity 121d, arrival date and time 121e, arrival quantity 121f, and price 121h are information indicating the number of the product manufactured using the corresponding outsourced part, the part (outsourced part), outsourced order date and time, ordered quantity, arrival date and time, arrival quantity, and price of the ordered part, respectively. The pass number 121g is information indicating the number of parts without defects among the arrived parts, that is, the yield.

[0027] 3 is a diagram showing an example of the market information 122. The market information 122 stores information about available parts that are published in an electronic market or the like. Specifically, the market information 122 stores records in which a part number 122a, a supplier 122b, an information acquisition date and time 122c, a transaction price 122d, a standard delivery date 122e, and a transaction number 122f are associated with each other.

[0028] The part number 122a, supplier 122b, information acquisition date and time 122c, transaction price 122d, standard delivery date 122e, and transaction quantity 122f are information indicating the number of a procurable part, the supplier, the information acquisition date and time, the transaction price, the standard delivery date, and the transaction quantity, respectively.

[0029] Such procurement record information 121 and trading market information 122 are used to generate a procurement risk prediction model 124 that predicts the procurement risk of each part.

[0030] 4 is a diagram showing an example of the work performance information 123. Work performance related to the manufacture of products is registered in the work performance information 123. Specifically, the work performance information 123 has records in which a product number 123a, a part number 123b, a process number 123c, a work type 123d, a worker number 123e, a work start date and time 123f, a work end date and time 123g, an input quantity 123h, a pass quantity 123i, and a work feature quantity 123j are associated with each other.

[0031] The product number 123a, part number 123b, process number 123c, work type 123d, worker number 123e, work start date and time 123f, work end date and time 123g, input quantity 123h, and pass quantity 123i are information indicating the number of the manufactured product, the number of parts used in the product, the process number, the type of work, the worker number, the start and end dates and times of the work, the number of manufactured products, and the yield, respectively. The work feature amount 123j is information indicating the length, mass, hole diameter, etc. of the parts used in the product, and is information that affects productivity such as work time and work pass rate.

[0032] Such work performance information 123 is used to generate a skill level prediction model 125 that predicts the skill level of each worker.

[0033] Next, the procurement risk prediction model 124 will be described. The procurement risk prediction model 124 is an information model used to predict how procurement risk will change depending on procurement performance and market conditions. Specifically, the procurement risk prediction model 124 outputs a procurement risk according to procurement feature quantities that indicate the characteristics of the procurement status (e.g., order status, etc.) of outsourced parts and the market conditions (e.g., transaction price, number of transactions, etc.).

[0034] More specifically, the procurement risk prediction model 124 takes procurement performance information 121 and trading market information 122 as input, and outputs a procurement risk expressed by predetermined indicators such as the delivery date overrun amount (amount exceeding the required delivery date), the price overrun amount (amount exceeding the required price), and the part acceptance rate (yield).

[0035] Since the change and degree of procurement risk differs for each part, the procurement risk prediction model 124 is generated for each part and stored in the storage unit 120.

[0036] FIG. 5 is a graph showing an example of the relationship between procurement risk and procurement feature. The illustrated example shows a time series of changes from time t1 to tn in the amount of delivery delay (procurement risk) for the procurement feature of a certain part (part number: A04). The horizontal axis shows the procurement feature, which is a multidimensional feature (parameter) indicating characteristics such as the order conditions and trading market conditions at the time of procurement, expressed as a two-dimensional feature by dimensionality reduction. The vertical axis is procurement risk, which in the illustrated example shows the amount of delay relative to the requested delivery date.

[0037] The indicators of procurement risk are not limited to the aforementioned delivery time overruns, price overruns, and part acceptance rate. For example, the required lead time, the number of potential transactions, or the amount of supply (transactions) that exceeds the required lead time may be used as an indicator of procurement risk. Furthermore, it is not necessary to use procurement risks corresponding to all of these indicators, and in the process described below, at least one of these indicators may be used.

[0038] In this way, the procurement risk prediction model 124 can output procurement risks at different times corresponding to various procurement features.

[0039] Next, the proficiency prediction model 125 will be described. The proficiency prediction model 125 is an information model used to predict how proficiency related to worker productivity, such as work time and work success rate, will change. Specifically, the proficiency prediction model 125 outputs proficiency corresponding to each work feature amount when the status of the work performance (for example, the parts used in the work or the features of the work process) is taken as the work feature amount.

[0040] More specifically, the proficiency prediction model 125 receives the work performance information 123 as an input and outputs a proficiency expressed by a predetermined index such as work time or work success rate (yield). Note that it is not necessary to use the proficiency corresponding to all of these indexes, and in the process described below, it is sufficient to use at least one of these indexes.

[0041] Since the change in proficiency and the degree of change vary from worker to worker, the proficiency prediction model 125 is generated for each worker and stored in the storage unit 120.

[0042] 6 is a graph showing an example of the relationship between proficiency and task feature amount. In particular, the illustrated example shows a time series of changes from time t1 to tn in task feature amount of a certain worker.

[0043] The horizontal axis indicates the task feature, which is expressed as a two-dimensional feature by dimension reduction of multidimensional feature (parameter) indicating the features of the parts and work process that the worker worked on. The vertical axis indicates the skill level of the task, and in the illustrated example, indicates the task time.

[0044] In this way, the skill level prediction model 125 can output skill levels at different times corresponding to various task feature amounts.

[0045] 7 is a diagram showing an example of the production quantity information 126. The production quantity information 126 registers the planned production date and quantity of each product to be produced in the future. Specifically, the production quantity information 126 has records in which a product number 126a, a production date 126b, and a quantity 126c are associated with each other.

[0046] The product number 126a, production date 126b, and quantity 126c are information indicating the identification number of a product to be produced in the future, the planned production date, and the production quantity, respectively.

[0047] 8 is a diagram showing an example of product information 127. Information about parts that constitute a product is registered in product information 127. Specifically, product information 127 has a record in which product number 127a, part ID 127b, part number 127c, part name 127d, and order type 127e are associated with each other.

[0048] The product number 127a, part ID 127b, part number 127c, part name 127d and order type 127e are information indicating the product identification number, part identification ID, part identification number, part name and order type, i.e., whether each part is an in-house produced part or an outsourced part whose production is outsourced to an external company.

[0049] FIG. 9 is a diagram showing an example of an input screen for product information 127. The "File Load" button is a button for inputting an instruction to load product information 127. When the button is pressed, a file selection screen for product information 127 is displayed, and the result of loading the specified file is displayed on this screen. The "Product" field displays the product number of product information 127 corresponding to the loaded file. The "Parts Configuration" field displays a list of part numbers, part names, and order types of all parts that constitute the product. The "Product Image" field displays an image of the product or part. For example, when file information that displays the shape of each part, such as 3D-CAD, exists, the shape state of the product is displayed using the shape file of each part. The "Register button" is a button for inputting an instruction when the user registers the product information 127 after checking the list of parts and the shape state of the product. When the Register button is pressed, the product information 127 is stored in the product information 127 of the storage unit 120.

[0050] 10 is a diagram showing an example of worker information 128. The worker information 128 is information about a worker who manufactures a product. Specifically, the worker information 128 has a record in which a worker number 128a and a scheduled work date 128b are associated with each other.

[0051] The worker number 128a and the scheduled work date 128b are information indicating a number for identifying a worker and a scheduled date on which the worker is available to work, respectively.

[0052] FIG. 11 is a diagram showing an example of the in-house production switching plan information 129. The in-house production switching plan information 129 registers information on target parts to be switched to in-house production. Specifically, the in-house production switching plan information 129 registers target parts that may become difficult to procure and in-house production in the future due to changes in procurement risk and worker proficiency, target products in which the target parts are used, and the timing of switching to in-house production for parts whose procurement type in the product information 127 is outsourced. More specifically, the in-house production switching plan information 129 has records in which product numbers 129a, part numbers 129b, and in-house production switching times 129c are associated with each other.

[0053] The product number 129a, the part number 129b, and the in-house production switching timing 129c are information indicating the identification number of the product (target product) in which the target part to be switched to in-house production is installed (used), the identification number of the target part, and the timing of switching to in-house production, respectively.

[0054] Such in-house production changeover plan information 129 is generated and updated in the in-house production changeover plan generation process and the production plan formulation process described below.

[0055] 12 is a diagram showing an example of the production plan information 130. The production plan information 130 registers information related to the overall plan for products to be produced in the future. Specifically, the production plan information 130 has records in which a product number 130a, a production month 130b, a quantity 130c, a part number 130d, a process number 130e, and a worker number 130f are associated with each other.

[0056] In addition, product number 130a, production month 130b, quantity 130c, part number 130d, process number 130e, and worker number 130f are information indicating the product identification number, the year and month of production of the product, the quantity of the product to be produced, the part identification number, the identification number of each process in production, and the worker identification number, respectively.

[0057] Such production plan information 130 is generated by a production plan generation process, which will be described later.

[0058] The storage unit 120 has been described above.

[0059] Returning to Fig. 1, the explanation will be given. The input unit 140 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 provided in the production planning device 100. The input unit 140 also accepts input of instructions and information from an external device 200 via the communication unit 160.

[0060] The output unit 150 is a functional unit that generates output information (including display information) and displays the display information on an output device (for example, a display) provided in the production planning device 100 or the external device 200.

[0061] The communication unit 160 is a functional unit that performs information communication with the external device 200. For example, the communication unit 160 receives various information stored in the storage unit 120, an instruction to execute a production plan generation process, and the like from the external device 200 via the network N. In addition, for example, the communication unit 160 transmits (outputs) a production plan generated by the production planning device 100 and its screen information to the external device 200 via the network N.

[0062] An example of the schematic configuration (functional blocks) of the production planning device 100 has been described above.

[0063] <Details of production plan generation process> Next, a production plan generating process executed by the production planning device 100 will be described.

[0064] 13 is a flow diagram showing an example of the production plan generation process. This process is started when the processing unit 110 receives an instruction to execute the production plan generation process from the operator of the production planning device 100 via the input unit 140, for example.

[0065] When the process starts, the prediction model generation unit 111 acquires information on parts for which "outsourcing" is registered in the ordering type of the product information 127 from the procurement record information 121 and the trading market information 122, and generates a procurement risk prediction model 124 (step S10). The storage unit 120 also stores the generated procurement risk prediction model 124.

[0066] Next, the prediction model generation unit 111 acquires information on parts for which "outsourcing" is registered in the ordering type of the product information 127 from the work result information 123, and generates a proficiency prediction model 125 (step S20). In addition, the storage unit 120 stores the generated proficiency prediction model 125.

[0067] Next, the in-house production switching plan generating unit 112 acquires the procurement risk prediction model 124 and the proficiency prediction model 125 from the storage unit 120, and generates an in-house production switching plan. In addition, the storage unit 120 stores the generated in-house production switching plan (Step S30).

[0068] Next, the production plan generating unit 113 acquires the procurement risk prediction model 124, the proficiency prediction model 125, the production quantity information 126, the worker information 128, and the internal production switching plan information 129 from the storage unit 120, and creates a production plan (step S40). The storage unit 120 also stores the generated production plan in the production plan information 130. The output unit 150 also acquires the production plan information 130 from the storage unit 120, and outputs (displays) it on a display. The output unit 150 may generate display information (screen information) of the production plan generated by the production planning device 100, such as the production plan information 130, and output (transmit) the display information to the external device 200 via the communication unit 160.

[0069] Furthermore, after performing the process of step S40, the production plan generating process ends the process of this flow.

[0070] <Details of the generation process of the procurement risk prediction model 124> The process of generating the procurement risk prediction model 124 (step S10) will now be described in detail.

[0071] First, the prediction model generation unit 111 identifies parts whose order type is registered as “outsourcing” from the product information 127. In addition, the prediction model generation unit 111 extracts records related to the identified parts from the procurement history information 121 and the market trading information 122, respectively.

[0072] In addition, the prediction model generation unit 111 uses the extracted procurement performance information 121 and trading market information 122 for each part to generate a procurement risk prediction model 124 for predicting how the procurement risk of each outsourced part will change over time, using well-known techniques such as machine learning and statistical analysis.

[0073] The amount of overdue delivery, which is one of the indicators of procurement risk, uses, for example, the difference between the order date and time 121c and the arrival date and time 121e in procurement history information 121 as the delivery date. Also, the part pass rate, which is one of the indicators of procurement risk, is calculated, for example, as the ratio of the number of passed parts 121g to the number of arrivals 121f in procurement history information 121, and this is used.

[0074] The method for generating the procurement risk prediction model 124 is not particularly limited, and any known technology 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 time-related information as input and predicts objective variables (delivery deadlines, price overruns, part acceptance rates).

[0075] In this manner, the prediction model generation unit 111 uses the procurement performance information 121 and the trading market information 122 to generate the procurement risk prediction model 124 and stores it in the memory unit 120 .

[0076] <Details of the generation process of the proficiency prediction model 125> The process of generating the skill level prediction model 125 (step S20) will now be described in detail.

[0077] First, the prediction model generation unit 111 identifies parts whose order type is registered as “outsourcing” from the product information 127. In addition, the prediction model generation unit 111 extracts records related to the identified parts from the work performance information 123.

[0078] In addition, the prediction model generation unit 111 uses the extracted work performance information 123 for each part to generate a proficiency prediction model 125 for predicting how the proficiency of a worker will change over time through known techniques such as machine learning and statistical analysis.

[0079] For example, the difference between the work start date and time 123f and the work end date and time 123g in the work performance information 123 is used as the work time, which is one of the indices of proficiency. Also, for example, the work pass rate, which is one of the indices of proficiency, is calculated as the ratio of the number of passes 123i to the number of inputs 123h in the work performance information 123, and this is used.

[0080] The method for generating the proficiency prediction model 125 is not particularly limited, and any known technology 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 related to time as input and predicts objective variables (work time, work success rate).

[0081] In this way, the prediction model generation unit 111 generates the skill level prediction model 125 using the work result information 123 and stores it in the storage unit 120.

[0082] <Details of the in-house production switching plan generation process> The in-house production switching plan generation process (step S30) will be described in detail.

[0083] First, the in-house production switchover plan generating unit 112 identifies records of parts for which "outsourcing" is registered in the order type from the product information 127. Furthermore, for the identified part, the in-house production switchover plan generating unit 112 calculates the time-series procurement risk of the part using the procurement history information 121, the trading market information 122, and the procurement risk prediction model 124 corresponding to the part. Specifically, the in-house production switchover plan generating unit 112 inputs information registered in each item of the procurement history information 121 and the trading market information 122 for the identified part into the procurement risk prediction model 124, and obtains an output of information indicating the time-series procurement risk of each part.

[0084] Furthermore, the in-house production switchover plan generating unit 112 identifies records of parts for which "outsourcing" is registered in the arrangement type from the product information 127. Furthermore, the in-house production switchover plan generating unit 112 calculates the time-series proficiency of each worker for the identified parts, using the work performance information 123 and the proficiency prediction model 125 for each worker. Specifically, the in-house production switchover plan generating unit 112 inputs information registered in each item of the work performance information 123 for the identified parts into the proficiency prediction model 125, and obtains an output of information indicating the time-series proficiency of each worker.

[0085] The in-house production switchover plan generating unit 112 also compares the production date when the time series prediction value of the procurement risk is equal to or greater than a predetermined threshold with the production date when the time series prediction value of the proficiency is less than a predetermined threshold. If the same production date exists for both that exceeds the threshold, the in-house production switchover plan generating unit 112 generates in-house production switchover plan information 129 that registers the part number of the part (target part) and the product number of the product (target product) that uses the part.

[0086] Figure 14 is a diagram showing an example of an image of a switching to in-house production plan. As shown in the figure, for parts that have a period (parts shown with diagonal lines) where both the procurement risk exceeds the threshold (period above the threshold) and the worker proficiency falls below the threshold (period below the threshold) overlap, the worker proficiency has already declined by the time the procurement risk exceeds the threshold, making it difficult to switch to in-house production.

[0087] Therefore, in the production plan generation process described below, the production plan generation unit 113 creates a production plan that reflects an optimized in-house production switchover timing that minimizes the procurement risk and maximizes the production efficiency during the period from the present to the time when both the procurement risk and the proficiency exceed the thresholds. That is, at the time of step S30, the target parts that need to be switched to in-house production are registered in the in-house production switchover plan information 129, and the in-house production switchover timing is specified when the production plan is created and registered in the in-house production switchover plan information 129.

[0088] <Details of production planning process> 15 is a flow diagram showing an example of a production planning process. When the process is started, the production plan generating unit 113 identifies the work type and the work feature amount for the target part registered in the internal production switching plan information 129 from the work result information 123 (step S41).

[0089] Next, the production plan generating unit 113 provisionally sets an arbitrary in-house production switching time for the target part (step S42). Specifically, the production plan generating unit 113 provisionally sets an arbitrary in-house production switching time with an initial value being a later time (for example, the month before the month in which the times when the thresholds are exceeded overlap) that is within the period from the present to the time when both the procurement risk and the proficiency exceed the thresholds.

[0090] Next, the production plan generating unit 113 sets a desired production efficiency and a procurement risk threshold value (for example, a minimum value of the desired production efficiency, etc.) in the current production line (step S43).

[0091] Next, the production plan generating unit 113 calculates the work allocation to each worker after the provisionally set internal production switching time and the production efficiency (throughput) of the product at that time (step S44). Note that, for example, the number of products produced (number of completed products) per unit time or the product acceptance rate is used as an index of the production efficiency.

[0092] Specifically, the production plan generating unit 113 allocates any work (for example, each work process in the manufacture of a product using the target part) to each worker, taking into consideration the scheduled work dates registered in the worker information 128. In addition, the production plan generating unit 113 inputs the work type and work feature amount of the allocated work to the proficiency prediction model 125 corresponding to each worker, and obtains an output of the work time and the work pass rate for each worker.

[0093] Furthermore, the production plan generating unit 113 calculates the production efficiency of products manufactured using the target parts, using the work time and work success rate of each worker acquired via the proficiency prediction model 125. The production plan generating unit 113 repeatedly executes a simulation to obtain the production efficiency while changing the combination of work assignments to each worker.

[0094] In addition, the production plan generation unit 113 calculates the production efficiency for all combinations of work allocation at the provisionally set internal production switchover time, and then changes the provisionally set internal production switchover time (for example, to a time brought forward from the present) and calculates the production efficiency in that case in a similar manner.

[0095] The production plan generating unit 113 sequentially changes the provisionally set internal production switching time up to the present time, and obtains the production efficiency corresponding to each combination of work assignment at each time. After obtaining the production efficiency of each work assignment at each internal production switching time, the production plan generating unit 113 transitions to step S45.

[0096] Next, the production plan generating unit 113 calculates a procurement risk (step S45). Since the arrangement type of the product information 127 related to the target part is changed from outsourcing to in-house production, the production plan generating unit 113 recalculates the procurement risk when the target part is changed to in-house production.

[0097] Specifically, the production plan generating unit 113 uses a procurement risk prediction model 124 corresponding to the target part to calculate a procurement risk (such as a delivery delay amount) corresponding to the procurement feature after the provisionally set internal production switchover time. Since the target part is to be internally produced, the procurement feature is input with the order quantity of the target part in the target product set to 0 (zero) and the order quantity of each component part based on the production quantity of each product in the production quantity information 126 calculated. The reason why the order quantity of the target part is input as 0 (zero) in this manner is when the target part is used only in the target product. For example, when the target part is also used in products other than the target product, the order quantity obtained by subtracting (reducing) the required quantity of the target part in the target product from the required quantity used in the other products is input in the procurement feature.

[0098] Next, the production plan generating unit 113 identifies the in-house production switching timing, work allocation, and work sequence at that time that satisfy the production quantity, maximize the production efficiency, and minimize the procurement risk (step S46). Specifically, the production plan generating unit 113 identifies the in-house production switching timing and work allocation combination that satisfy the production quantity registered in the production quantity information 126 and result in production efficiency and procurement risk that exceed the thresholds set in step S43.

[0099] In addition, the production plan generation unit 113 identifies, from among the identified combinations of internal production switchover timing and work allocation, a combination that maximizes production efficiency and minimizes procurement risk.

[0100] In addition, the in-house production switching plan generation unit 112 registers the identified in-house production switching time in a corresponding record of the in-house production switching plan information 129.

[0101] Next, the production plan generating unit 113 creates a production plan (step S47). Specifically, the production plan generating unit 113 creates a production plan that reflects the internal production switching time, the work allocation, and the work sequence identified in step S46, and outputs this to a display via the output unit 150. Note that information such as the created production plan may be displayed on the external device 200 via the communication unit 160.

[0102] FIG. 16 is a diagram showing an example of an output screen including an in-house production switchover plan and a production plan. As shown in the figure, the output screen displays the product number, part number, and in-house production switchover time of the in-house production switchover plan, which is the in-house production switchover plan. The output screen also displays a production plan in which production efficiency and procurement risk are optimized. Note that the example shown in the figure shows a production plan that achieves higher production efficiency while ensuring the proficiency for in-house production against procurement risk by switching part number "A04" to in-house production from October 2023.

[0103] The screen information displayed on the display is not limited to the production plan, and may also display, for example, the results of prediction of procurement risk and proficiency level in response to a user instruction.

[0104] 17 is a diagram showing an example of screen information showing the results of prediction of procurement risk and proficiency. As shown in the figure, the screen shows the results of prediction of procurement risk and proficiency when in-house production is not performed and the results of prediction of procurement risk and proficiency when in-house production is performed at an appropriate time, in a comparative manner.

[0105] The production plan generation process has been described above in detail.

[0106] According to such a production planning device 100, it is possible to create an in-house production switching plan and a production plan that ensures the proficiency of workers for in-house production in accordance with the procurement risk of parts.

[0107] In particular, the production planning device can set as the target parts for in-house production switchover those parts that have a period where the procurement risk increases and the worker's proficiency decreases overlap, and can create a production plan in which the in-house production switchover time is set between the present and the overlapping period, taking into account the work time required for improving the worker's proficiency. Furthermore, the production planning device can calculate the in-house production switchover time that maximizes production efficiency and minimizes procurement risk. As a result, the production planning device can create an in-house production switchover plan and a production plan that can improve the worker's proficiency while maintaining production efficiency to the maximum.

[0108] Second Embodiment In the second embodiment, a production planning device 100 that can be applied to an operation mode in which materials and child parts required for manufacturing outsourced parts are supplied to a supplier, and parts manufactured using the supplied materials are procured will be described.

[0109] Figure 18 is a diagram showing an example of the procurement and supply of materials used for outsourced parts. There are two ways to procure outsourced parts: one is to present specification information to a supplier, and the supplier (supplier A) itself procures the materials and sub-parts required for manufacturing parts that meet the specifications, and the other is to supply the supplier (supplier B) with the specification information as well as the materials and sub-parts required for manufacturing.

[0110] In the former case, the production planning device 100 according to the first embodiment can devise an in-house production switching plan and a production plan that ensures the proficiency of workers for in-house production in accordance with the procurement risk of parts.

[0111] On the other hand, in the latter case, the procurement risk of outsourced parts is affected by both the procurement risk of materials and sub-parts procured by the company and the procurement risk related to the manufacturing of supplier B. Note that, although the past procurement performance information 121 with supplier B includes the influence of the procurement risk related to the manufacturing of supplier B, the information does not include the influence of the procurement risk of materials and sub-parts.

[0112] Therefore, the production planning device 100 of this embodiment considers the impact of procurement risks of materials and sub-parts and develops an in-house production switching plan and production plan that ensures the proficiency of workers for in-house production.

[0113] In the following, the configuration and processing different from the first embodiment will be mainly described, and the same configurations and the like as those in the first embodiment will be denoted by the same reference numerals and detailed description will be omitted.

[0114] Fig. 19 is a diagram showing an example of procurement record information 121 according to this embodiment. As shown in the figure, the work record information 121 has items of procurement number 121aa and supply item 121jj in addition to each item of procurement record information 121 shown in Fig. 2. These items are provided because both arrangements with a business partner who will undertake manufacturing and arrangements for procuring materials and parts are required at the time of procurement, and they are provided as information that associates the two.

[0115] The procurement number 121aa is identification information of the procurement record of the part. Furthermore, the supply item 121jj is used to specify the procurement number 121aa of a material or a sub-part when a corresponding part is procured. The method of linking a part and its supply item is not limited to this, and for example, inventory information (not shown) may be used.

[0116] Next, a production plan generating process executed by the production planning device 100 according to this embodiment will be described.

[0117] In step S10 of the production plan generation process, the prediction model generation unit 111 of the production planning device 100 extracts, in addition to records related to each outsourced part, records of procurement numbers registered in the supply items 121jj, i.e., records related to the supply items, from the procurement record information 121 and the trading market information 122. In addition, the prediction model generation unit 111 generates a procurement risk prediction model 124 related to each of the outsourced parts and the supply items.

[0118] In addition, in step S30, the in-house production switching plan generating unit 112 generates an in-house production switching plan for supplied items linked to outsourced parts, in addition to outsourced parts whose procurement type in the product information 127 is "outsourced." Specifically, the in-house production switching plan generating unit 112 identifies supplied items whose production dates are the same as the production dates when the time series prediction value of the procurement risk is equal to or greater than a predetermined threshold and the production dates when the time series prediction value of the proficiency is less than a predetermined threshold, and registers the specified supplied items in the in-house production switching plan as target supplied items.

[0119] Also, in the same manner as in the first embodiment, in step S40, the production plan generating unit 113 creates a production plan for the parts registered in the in-house production switchover plan information 129, i.e., the outsourced parts identified in step S30, and the supplied items linked thereto. Specifically, the production plan generating unit 113 identifies a combination of in-house production switchover timing, work allocation, and work sequence for each target part and each supplied item registered in the in-house production switchover plan, which satisfies the production quantity registered in the production quantity information 126 and exceeds the threshold value set in step S43 in terms of production efficiency and procurement risk.

[0120] In addition, the production plan generating unit 113 identifies the combination of work allocation that maximizes production efficiency and minimizes procurement risk among the identified combinations, and creates a production plan that reflects the in-house production switching timing, work allocation, and work sequence at that time. This process is the same as step S40 in the first embodiment.

[0121] The production planning device 100 according to the second embodiment has been described above.

[0122] According to such a production planning device 100, even if the outsourcing company for manufacturing and the supplier of the supplied goods are different, it is possible to devise an in-house production switching plan and production plan that ensures the proficiency of workers for in-house production in accordance with the procurement risk of the supplied goods.

[0123] <Hardware configuration of the production planning device 100>

[0124] 20 is a diagram showing an example of a 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 connects these devices to each other.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] An example of the hardware configuration of the production planning device 100 has been described above.

[0130] 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.

[0131] Moreover, the input unit 140 is realized by an input device 310. Moreover, the output unit 150 is realized by an output device 320. Moreover, the storage unit 120 is realized by a main storage device 340 or an auxiliary storage device 350, or a combination of these. Moreover, the communication unit 160 is realized by a communication device 360.

[0132] In addition, the above-mentioned configurations, functions, processing unit 110, processing means, etc. of the production planning device 100 may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. In addition, the above-mentioned configurations and functions may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as the program, table, file, etc. that realizes each function can be stored in a storage device such as a memory, a hard disk, or an SSD, or in a recording medium such as an IC card, an SD card, or a DVD.

[0133] Furthermore, the present invention is not limited to the above-mentioned embodiment and modified examples, and various modified examples are included within the scope of the same technical idea. For example, the above-mentioned embodiment has been described in detail to explain the present invention in an easy-to-understand manner, and is not necessarily limited to those having all of the configurations described. Furthermore, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0134] In addition, in the above explanation, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0135] 100 production planning device, 110 processing unit, 111 prediction model generation unit, 112 in-house production switching plan generation unit, 113 production plan generation unit, 120 storage unit, 121 procurement performance information, 122 trading market information, 123 work performance information, 124 procurement risk prediction model, 125 skill prediction model, 126 production quantity information, 127 product information information, 128... worker information, 129... in-house production switching plan information, 130... production plan information, 140... input section, 150... output section, 160... 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 prediction model generation unit that generates a procurement risk prediction model that predicts a time-series change in the procurement risk of the part based on the procurement record of the part and a trading market state, and a proficiency prediction model that predicts a time-series change in the proficiency of a worker based on the work record of the worker; an internal production changeover plan generation unit that uses the procurement risk prediction model and the proficiency prediction model to identify an overlapping period in which the procurement risk increases and the proficiency decreases, and generates an internal production changeover plan in which the parts having the overlapping period are registered; A production plan generation unit that uses the procurement risk prediction model and the proficiency prediction model to calculate a production efficiency according to the proficiency of the worker and an internal production switching time at which the procurement risk is optimized, and a combination of work assignments to the worker, and creates a production plan based on the internal production switching time and the work assignments. A production planning device comprising:

2. The production planning device according to claim 1, The procurement risks include: There are indicators related to delivery time, price, part acceptance rate, lead time, number of potential buyers and supply quantity. The in-house production switching plan generation unit identifies a time when the procurement risk will increase using at least one or more of the indicators. A production planning device comprising:

3. The production planning device according to claim 1, The proficiency includes: There are indicators for work time and work success rate. The in-house production switching plan generation unit identifies a time when the proficiency level will decrease by using at least one or more of the indicators. A production planning device comprising:

4. The production planning device according to claim 1, The production plan generation unit Set the in-house production switching time between now and the overlap period so that the production efficiency and the procurement risk are optimized. A production planning device comprising:

5. The production planning device according to claim 1, An output unit that outputs screen information including the in-house production switching plan including the calculated in-house production switching time and a production plan generated based on the in-house production switching plan. A production planning device comprising:

6. The production planning device according to claim 1, An output unit that outputs screen information including a time-series prediction result of the procurement risk and the proficiency of the worker when the part is not switched to in-house production, and a time-series prediction result of the procurement risk and the proficiency of the worker when the part is switched to in-house production at the calculated in-house production switching time. A production planning device comprising:

7. The production planning device according to claim 1, The prediction model generation unit generates the procurement risk prediction model of a supply item to be supplied to a manufacturer of the part, The production plan generation unit uses the procurement risk prediction model and the proficiency prediction model for the parts and the supplies to calculate the production efficiency according to the proficiency of the workers and the in-house production switchover timing and the combination of work allocation to the workers that optimizes the procurement risk, and creates a production plan based on the in-house production switchover timing and the work allocation. A production planning device comprising:

8. A production planning method performed by a production planning device, The production planning device includes: a prediction model generation step of generating a procurement risk prediction model for predicting a time-series change in the procurement risk of the part based on the procurement record of the part and a trading market state, and a proficiency prediction model for predicting a time-series change in the proficiency of a worker based on the work record of the worker; an in-house production changeover plan generation step of identifying an overlapping period in which the period in which the procurement risk increases and the period in which the proficiency decreases overlap by using the procurement risk prediction model and the proficiency prediction model, and generating an in-house production changeover plan in which the parts having the overlapping period are registered; A production plan generation step of calculating a production efficiency according to the proficiency of the worker and an internal production switching time that optimizes the procurement risk and a combination of work assignments to the worker using the procurement risk prediction model and the proficiency prediction model, and formulating a production plan based on the internal production switching time and the work assignment. A production planning method comprising:

9. 9. The production planning method according to claim 8, The production planning device includes: By executing the production plan generation step, Set the in-house production switching time between now and the overlap period so that the production efficiency and the procurement risk are optimized. A production planning method comprising:

10. A program for causing a computer to function as a production planning device, The computer, a prediction model generation unit that generates a procurement risk prediction model that predicts a time-series change in the procurement risk of the part based on the procurement record of the part and a trading market state, and a proficiency prediction model that predicts a time-series change in the proficiency of a worker based on the work record of the worker; an internal production changeover plan generation unit that uses the procurement risk prediction model and the proficiency prediction model to identify an overlapping period in which the procurement risk increases and the proficiency decreases, and generates an internal production changeover plan in which the parts having the overlapping period are registered; Using the procurement risk prediction model and the proficiency prediction model, a production plan generation unit calculates a production efficiency according to the proficiency of the worker and an internal production switching time at which the procurement risk is optimized, and a combination of work allocation to the worker, and functions as a production plan generation unit that formulates a production plan based on the internal production switching time and the work allocation. A program characterized by:

11. The program according to claim 10, The production plan generation unit, The internal production switching time is set between the present time and the overlap time so that the production efficiency and the procurement risk are optimized. A program characterized by:

Images