Production planning device and computer-readable recording medium

Abstract

A production planning device according to the present disclosure comprises: a manufacturing order reception unit that receives a manufacturing order including an instruction to produce a workpiece using an industrial machine; a data collection unit that collects data from a control device for controlling the industrial machine; a constraint condition estimation pattern storage unit that stores a constraint condition estimation pattern pertaining to production of the workpiece; a constraint condition estimation unit that, on the basis of the data collected by the data collection unit and the constraint condition estimation pattern, estimates a constraint condition necessary for creating a production plan pertaining to the manufacturing order; a constraint condition determination interaction unit that displays the estimated constraint condition and the basis thereof, receives a correction instruction including natural language that corresponds to the display, and exchanges the received correction instruction with an interactive response device, thereby correcting the estimation pattern corresponding to the constraint condition; and a production plan creation unit that creates a production plan for the workpiece on the basis of an estimated value of the estimated constraint condition. The constraint condition determination interaction unit commands the constraint condition estimation unit to estimate the constraint condition using the corrected constraint condition estimation pattern.

Description

Production planning device and computer-readable recording medium

[0001] The present disclosure relates to a production planning device and a computer-readable recording medium.

[0002] In order to operate production facilities efficiently, it is necessary to create a production plan for the production process for producing products. The production plan determines the time required for each process, the types and numbers of various pieces of equipment that the production facility has, etc. (For example, see Patent Document 1). When creating a production plan, constraints on the work in the production process are determined in advance. Then, a production process that satisfies those constraints is created.

[0003] Japanese Patent Application Laid-Open No. 2006-309577

[0004] The number of constraints increases as the scale of production equipment and the number of workpieces to be machined increase. Manually inputting all of the constraints places a heavy burden on operators. Therefore, there is a need for technology that reduces the effort required to input constraints when creating a production plan.

[0005] The production planning device disclosed herein solves the above-mentioned problems by extracting constraints necessary for creating a production plan from data collected from a numerical control device. The constraints necessary for creating a production plan (such as machining processes, the time required for the processes, setup time, executable machining programs for the equipment, the number of workers who can simultaneously perform setup, and warm-up time) are inferred from the collected data, and the inferred constraints are modified interactively with the user using a large-scale language model (LLM). The system then presents the basis for the inferred constraints and modifies them as necessary, enabling automatic and accurate extraction.

[0006] One aspect of the present disclosure is a production system including a production order receiving unit that receives a production order including an instruction to produce workpieces with at least one industrial machine; a data collecting unit that collects data from a control device that controls the industrial machine; a constraint condition estimation pattern storage unit that stores at least one constraint condition estimation pattern that associates predetermined constraint conditions related to the production of workpieces with estimation patterns used to estimate the constraint conditions; and a constraint estimation unit that estimates constraint conditions necessary to create a production plan related to the production order based on the data collected by the data collecting unit and the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit. The production planning device comprises a condition estimation unit, a constraint condition determination dialogue unit that displays the constraint conditions estimated by the constraint condition estimation unit and their grounds, accepts correction instructions including natural language corresponding to the display, and modifies the constraint condition estimation pattern by exchanging the accepted correction instructions with an interactive response device, and a production plan creation unit that creates a production plan for the work based on the estimated values ​​of the constraint conditions estimated by the constraint condition estimation unit, wherein when the constraint condition determination dialogue unit accepts a correction instruction and modifies the constraint condition estimation pattern, it instructs the constraint condition estimation unit to estimate constraint conditions using the modified estimation pattern.

[0007] FIG. 1 is a schematic hardware configuration diagram of a production planning device according to an embodiment of the present disclosure. FIG. 2 is a block diagram showing schematic functions of a production planning device according to a first embodiment. FIG. 3 is a table showing an example of a manufacturing order. FIG. 4 is a table showing an example of a constraint condition estimation pattern. FIG. 5 is a screen diagram showing an example of displaying estimated values ​​of constraint conditions. FIG. 6 is a screen diagram showing an example of displaying a response to a modification instruction. FIG. 7 is a table showing an example of a constraint condition estimation pattern modified by a constraint condition determination dialogue unit. FIG. 8 is a screen diagram showing an example of displaying estimated values ​​of constraint conditions estimated based on the modified constraint condition estimation pattern. FIG. 9 is a block diagram showing schematic functions of a production planning device according to a second embodiment.

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following description, components having the same or similar functions will be denoted by the same reference numerals. Duplicate descriptions of those components may be omitted.

[0009] In this application, "based on XX" means "based on at least XX," and includes cases where it is based on other elements in addition to XX. Furthermore, "based on XX" is not limited to cases where XX is used directly, but also includes cases where it is based on XX that has been calculated or processed. "XX" is any element (for example, any information).

[0010] 1 is a schematic hardware configuration diagram showing the main parts of a production planning device according to a first embodiment of the present disclosure. The production planning device 1 according to this embodiment can be implemented on a computer such as a personal computer attached to a control device, a personal computer connected to the control device via a wired or wireless network, a cell computer, a fog computer 6, or a cloud server 7. This embodiment shows an example in which the production planning device 1 is implemented on a computer connected via a network to a control device that controls industrial machinery.

[0011] The CPU 11 provided in the production planning device 1 according to this embodiment is a processor that controls the entire production planning device 1. The CPU 11 reads a system program stored in the ROM 12 via the bus 22 and controls the entire production planning device 1 in accordance with the system program. The RAM 13 temporarily stores temporary calculation data, display data, various data acquired from outside, and the like.

[0012] The nonvolatile memory 14 is configured, for example, by a memory backed up by a battery (not shown) or an SSD (Solid State Drive), and maintains its stored state even when the power to the production planning device 1 is turned off. The nonvolatile memory 14 stores programs and data read from an external device 72 via the interface 15, programs and data input via the input device 71, programs and data acquired from the industrial machine 4 or other devices via the network 5, and the like. The programs and data stored in the nonvolatile memory 14 may be expanded into the RAM 13 when executed / used. In addition, various system programs such as known analysis programs are written in the ROM 12 in advance.

[0013] The interface 15 is an interface for connecting the CPU 11 of the production planning device 1 to an external device 72 such as a USB device. For example, system programs, setting data, etc. are read from the external device 72. In addition, programs and setting data created and edited within the production planning device 1 can be stored in external storage means via the external device 72.

[0014] The interface 20 is an interface for connecting the CPU 11 of the production planning device 1 to a wired or wireless network 5. The network 5 may be one that communicates using technologies such as serial communication such as RS-485, Ethernet (registered trademark), optical communication, wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. At least one industrial machine 4 to be controlled, at least one other industrial machine 4, an interactive response device 2 that responds to inquiries from users, a fog computer 6, a cloud server 7, etc. are connected to the network 5, and data is exchanged between the network 5 and the production planning device 1.

[0015] The display device 70 displays various data read into the memory, data obtained as a result of executing programs, etc., output via the interface 17. An input device 71, which is comprised of a keyboard, pointing device, etc., passes instructions, data, etc. based on operations by an operator to the CPU 11 via the interface 18.

[0016] The interactive response device 2 is configured as a device that returns a response sentence in response to a predetermined sentence. The interactive response device 2 includes a large-scale language model (LLM) that has learned a response sentence for the predetermined sentence. This model can be a known model, such as a Transformer model. The large-scale language model learns, for each text, the probability that the given sentence will be a response to the given sentence when the given sentence is input. It also learns the probability that each of the given texts will be followed by other texts. By repeating this learning process, the large-scale language model, when input, comes to output a text string with a high probability as a response to the given sentence. Depending on how the learning process learns documents that will be responses to the given sentence, the interactive response device 2 can be used for purposes such as dialogue, question and answer session, text summarization, text editing, text translation, text conversion, text modification, text optimization, text interpretation / detection, recognition, prediction, judgment, code generation, image generation, and comprehensive judgment.

[0017] The production planning device 1 according to the present disclosure is assumed to be connected to an interactive response device 2 via a network 5. This interactive response device 2 may be one that has learned various documents, including reports on past production plan creation and revisions by skilled workers. In this case, the interactive response device 2 may learn from, for example, reports recording problems that occurred in previously created production plans, the causes of those problems, and solutions to those problems, books describing how to create production plans, etc. Narrowing down the information used for learning makes it possible to prepare an interactive response device 2 that returns responses to inquiries with a certain degree of accuracy.

[0018] 2 is a schematic block diagram showing functions of the production planning device 1 according to the first embodiment of the present disclosure. Each function of the production planning device 1 according to this embodiment is realized by the CPU 11 of the production planning device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the production planning device 1.

[0019] The production planning device 1 of this embodiment includes a manufacturing order receiving unit 100, a data collecting unit 110, a constraint condition estimating unit 120, a constraint condition determining dialogue unit 130, a production plan creating unit 140, and an output unit 150. The RAM 13 to the nonvolatile memory 14 of the production planning device 1 also include a constraint condition estimation pattern storage unit 200, which is an area for storing estimation patterns of constraint conditions in advance.

[0020] The manufacturing order receiving unit 100 receives manufacturing orders for creating a production plan. FIG. 3 is a table showing an example of a manufacturing order. The manufacturing order includes, for example, the type, quantity, and manufacturing deadline of the product (work) to be manufactured. The manufacturing order may also include information related to the processes required to manufacture the product. The manufacturing order may also include information on resources used for processing, such as identification information for identifying the processing program executed in each process. The manufacturing order receiving unit 100 outputs the received manufacturing order to the constraint condition estimation unit 120 and the production plan creation unit 140.

[0021] [Correction based on Rule 91 13.11.2025] The data collection unit 110 collects predetermined data from the control device of the industrial machine 4. The predetermined data may be, for example, the required operation time for each workpiece, each process, and each resource (equipment), the start time of each process, the end time of each process, the number of workpieces produced, the executed machining programs, the number of times each machining program was executed, and any alerts that occurred. The data collection unit 110 outputs the collected data to the constraint condition estimation unit 120.

[0022] The constraint condition estimation unit 120 estimates constraint conditions required for creating a production plan based on the data collected by the data collection unit 110 and the estimation patterns stored in the constraint condition estimation pattern storage unit 200. Examples of constraint conditions include the processes required for product production, the resources (equipment) used in each process, the time required for each process, and the setup time for each process. The constraint condition estimation unit 120 outputs the estimated constraint conditions to the constraint condition determination dialogue unit 130.

[0023] FIG. 4 is a table showing examples of constraint inference patterns stored in the constraint inference pattern storage unit 200. As illustrated in FIG. 4 , the constraint inference pattern associates a predetermined constraint with an inference pattern used to infer the constraint. The inference pattern may be a calculation formula or rule for inferring the constraint based on data collected by the data collection unit 110. The inference pattern may include items such as a method for calculating the constraint, specification of target data to be used in the calculation, the range of data, extraction conditions for the data to be used in the calculation, and other supplementary information. The supplementary information is information that serves as a reference when the user considers the validity of the estimated value of the constraint. For example, FIG. 4 defines an inference pattern that infers the constraint "production process of work A" by selecting the most frequent combination of processes performed in the production of work A in the past. The target data used in the calculation is a combination of processes performed in the production of work A in the past, data related to production performed within the past three months is used, there are no extraction conditions for the data to be used in the calculation, and there is no supplementary information. When such a constraint condition estimation pattern is defined, if work A was most often produced through two processes (process A, process B) over the past three months, the constraint condition estimation unit 120 will estimate that the two processes (process A, process B) should be performed to produce work A.

[0024] In the example of FIG. 4 , an estimation pattern is defined that estimates the constraint "resources for process A" by selecting the top two most frequently used resources (equipment) among those used when carrying out process A in the past. The data to be used for calculation are resources used when carrying out process A in the past, and data related to production carried out within the past three months is used. There are no extraction conditions for the data to be used for calculation, and no supplementary information is provided. When such a constraint estimation pattern is defined, assume that the most frequently used resource for carrying out process A over the past three months was facility X, followed by facility Y. In this case, the constraint estimation unit 120 estimates that the resource that can be used when carrying out process A is either facility X or facility Y.

[0025] In another example, FIG. 4 defines an estimation pattern for estimating the constraint "standard time for process A" by calculating the average value of the time required to perform process A in the past. The data used for the calculation is the time required for process A in the past, the range for calculating the average value is the entire period, there are no conditions for extracting data used for the calculation, and the auxiliary information is maximum and minimum values. When such a constraint estimation pattern is defined, it is assumed that process A, in which processing program X is executed on equipment X, and process B, in which processing program Y is executed on equipment Y after process A, have already been estimated as constraints as processes required to machine workpiece A. In this case, the constraint estimation unit 120 extracts the time required for machining the workpiece when processing program X is executed on equipment X from the data collected by the data collection unit 110. Then, the average value of the time required for process A is calculated.

[0026] In the example of FIG. 4 , an estimation pattern is defined that estimates the constraint "setup time for process B" by calculating the average value of the time required for setup for process B in the past. The data used for the calculation is the time required for setup for process B in the past, the range for calculating the average value is the entire period, there are no data extraction conditions for the calculation, and the auxiliary information is the maximum and minimum values. When such a constraint estimation pattern is defined, it is assumed that process A, in which machining program X is executed on equipment X, and process B, in which machining program Y is executed on equipment Y after process A, have already been estimated as constraints as processes required for machining the workpiece. In this case, the constraint estimation unit 120 extracts the time required from the end of process A on equipment X to the start of process B on equipment Y, i.e., the setup time for process B, from the data collected by the data collection unit 110. Then, the average value of the time required for setup for process B is calculated.

[0027] The constraint condition determination dialogue unit 130 displays the constraint conditions estimated by the constraint condition estimation unit 120 and the grounds for determining the constraint conditions on the display device 70 and presents them to the operator. Then, the estimation pattern and estimated values ​​of the constraint conditions are corrected through dialogue with the operator.

[0028] 5 is a diagram showing an example of a screen displaying estimated values ​​of constraint conditions. In the example of FIG. 5, a plurality of constraint conditions, their estimated values, and the grounds for the estimated values ​​are displayed on the screen. The constraint condition determination dialogue unit 130 displays the estimated values ​​for the constraint conditions estimated by the constraint condition estimation unit 120. The constraint condition determination dialogue unit 130 also displays the grounds for the estimated values ​​based on an estimation pattern included in the constraint condition estimation pattern.

[0029] The constraint condition determination dialogue unit 130 receives inquiries from the operator regarding correction of each estimated value. A dialogue window for the operator and the constraint condition determination dialogue unit 130 is displayed at the bottom of the screen in FIG. 5 . The constraint condition determination dialogue unit 130 receives instructions for correcting the inferred pattern of the constraint condition from the operator in natural language. This input may be input by the operator via the input device 71. Alternatively, the instruction for correction may be received via voice input from the operator via a voice input device such as a microphone (not shown). The constraint condition determination dialogue unit 130 transmits the received instruction for correction to the interactive response device 2. At this time, the constraint condition determination dialogue unit 130 may also transmit to the interactive response device 2 the results of the constraint condition estimation, the constraint condition inferred pattern used by the constraint condition estimation unit 120 to infer the constraint condition, and the data used by the constraint condition estimation unit 120 to infer the constraint condition, together.

[0030] The interactive response device 2, which has received the instruction for correction from the constraint condition determination dialogue unit 130, creates a response in natural language to the instruction for correction and a correction to the inferred pattern, and then transmits the created response in natural language and the correction to the inferred pattern as a response to the constraint condition determination dialogue unit 130.

[0031] Upon receiving a response from the interactive response device 2, the constraint condition determination dialogue unit 130 displays the response in the natural language contained in the response in the dialogue window. Furthermore, the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit 200 is modified based on the modification to the estimation pattern contained in the response. When the response from the interactive response device 2 includes a specific modification to the constraint condition estimation pattern, the constraint condition determination dialogue unit 130 adds the modification to the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit 200. When the response from the interactive response device 2 includes a modification to the constraint condition estimation pattern in natural language, the constraint condition determination dialogue unit 130 analyzes the natural language to create a modification and adds the created modification to the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit 200. Figure 6 is a screen diagram showing an example of displaying a response to a modification instruction. In the example of Figure 6, the worker inputs a modification instruction to set a standard time except when a problem occurs in process A and the time is extended. In response to this, assume that the interactive response system 2 responds by stating that it will calculate an estimated value for the standard time of process A except when a problem occurs (when a specified alert occurs) or when the time taken significantly deviates from the average time. In such cases, the constraint condition determination dialogue unit 130 displays the natural language response in the dialogue window and modifies the estimated pattern. FIG. 7 is a table showing an example of an estimated pattern modified by the constraint condition determination dialogue unit 130. In the example of FIG. 7, based on the response from the interactive response system 2, the data extraction conditions used to calculate the estimated pattern of the constraint condition related to the standard time of process A are modified to include the following: "When an alert occurs during the process, or when an outlier is found in a 5% significance level test, exclude it from the calculation of the average time." After making such modifications, the constraint condition determination dialogue unit 130 instructs the constraint condition estimation unit 120 to re-estimate the constraint conditions. Then, the constraint condition estimation unit 120 estimates the constraint conditions required to create a production plan based on the data collected by the data collection unit 110 and the modified estimation pattern stored in the constraint condition estimation pattern storage unit 200.

[0032] FIG. 8 is a screen diagram showing an example of displaying estimated values ​​of constraint conditions estimated based on a modified constraint condition estimation pattern. After modifying the constraint condition estimation pattern, as shown in FIG. 8, the constraint condition determination dialogue unit 130 displays the re-estimated estimated values ​​of the constraint conditions on the screen. The re-estimated estimated values ​​of the constraint conditions may be displayed so as to be distinguishable from others, for example, by highlighting, changing the text color or background color, or blinking. The constraint condition determination dialogue unit 130 may continuously accept instructions to modify the constraint condition estimation pattern. The constraint condition determination dialogue unit 130 may accept instructions to modify the estimated values ​​of each constraint condition from the worker until the worker is satisfied. When the constraint condition determination dialogue unit 130 receives an input from the worker indicating that the instructions to modify the constraint conditions have been terminated, the constraint condition determination dialogue unit 130 outputs the finally determined values ​​of the constraint conditions to the production plan creation unit 140.

[0033] When the constraint condition values ​​are input from the constraint condition determination dialogue unit 130, the production plan creation unit 140 creates a production plan based on the determined constraint condition values ​​and the production order accepted by the production order acceptance unit 100. The creation of a production plan can be treated as a constraint satisfaction problem, in which workpiece processing is assigned to each industrial machine 4 in order to manufacture the product specified in the production order within the deadline while satisfying the constraint conditions. The production plan creation unit 140 uses a known algorithm, such as linear programming, to create a production plan that maximizes an evaluation function (such as a delivery date compliance rate) based on, for example, information on the constraint conditions and the production order (such as product, delivery date, and quantity). FIG. 9 is a table showing an example of a production plan created by the production plan creation unit 140.

[0034] The output unit 150 outputs the production plan created by the production plan creation unit 140. The output unit 150 may be configured to display and output the created production plan on the display device 70. Furthermore, the output unit 150 may be configured to transmit and output the created production plan to a higher-level computer such as the cloud server 7 or a fog computer, or to each industrial machine 4.

[0035] The production planning system 1 according to this embodiment, which is configured as described above, automatically estimates the values ​​of constraints required for creating a production plan. Furthermore, these values ​​can be easily revised through dialogue with the operator. When there are a large number of pieces of equipment and a large number of workpieces to be machined, the number of constraints becomes enormous, but even in such cases, it is expected that the labor of the operator can be reduced.

[0036] Second Embodiment A production planning device according to a second embodiment of the present disclosure will be described below. The production planning device 1 according to this embodiment has the same hardware configuration as the production planning device 1 according to the first embodiment.

[0037] 10 is a schematic block diagram showing functions of the production planning device 1 according to the second embodiment of the present disclosure. Each function of the production planning device 1 according to this embodiment is realized by the CPU 11 of the production planning device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the production planning device 1.

[0038] The production planning device 1 according to this embodiment includes a manufacturing order receiving unit 100, a data collecting unit 110, a constraint condition estimating unit 120, a constraint condition determining dialogue unit 130, a production plan creating unit 140, and an output unit 150, as well as a machining program process analyzing unit 160. The RAM 13 to the nonvolatile memory 14 of the production planning device 1 are provided with a constraint condition estimation pattern storage unit 200, which is an area for storing estimation patterns of constraint conditions in advance.

[0039] The production order receiving unit 100, data collecting unit 110, production plan creating unit 140, and output unit 150 provided in the production planning device 1 according to this embodiment have the same functions as those in the first embodiment.

[0040] The machining program step analysis unit 160 according to this embodiment infers the procedure for a process related to machining a workpiece from the contents of the machining program. The machining program step analysis unit 160 receives from the data collection unit 110 the machining program used to machine the workpiece specified in the manufacturing order input from the manufacturing order receiving unit 100. The received machining program is then analyzed. The machining program step analysis unit 160 compares the number of executions of each of the multiple machining programs X1, X2, ... executed in a specific process, for example. If the number of executions matches the number of workpieces produced in that process, the machining program step analysis unit 160 may infer that these machining programs are executed in sequence to machine one workpiece. The machining program step analysis unit 160 also analyzes the shape of the workpiece machined by the multiple machining programs X1, X2, ... executed to machine one workpiece. The machining program step analysis unit 160 may then infer that the machining programs are executed in order of the size of the workpiece shape after machining. The machining program step analysis unit 160 outputs the inferred results to the constraint condition estimation unit 120.

[0041] The constraint condition estimation unit 120 according to this embodiment estimates constraint conditions required for creating a production plan based on the data collected by the data collection unit 110, the estimation patterns stored in the constraint condition estimation pattern storage unit 200, and the procedure of the machining processes estimated by the machining program process analysis unit 160. Examples of constraint conditions include the processes required for producing the product, the time required for each process, the setup time for each process, and the execution sequence of the machining program for each process. The constraint condition estimation unit 120 outputs the estimated constraint conditions to the constraint condition determination dialogue unit 130.

[0042] The constraint condition determination dialogue unit 130 according to this embodiment displays the constraint conditions estimated by the constraint condition estimation unit 120 and the basis for the constraint conditions on the display device 70, and presents them to the operator. The constraint conditions displayed by the constraint condition determination dialogue unit 130 include the execution order of the machining programs in each process. The operator can modify the execution order of the machining programs in each process by interacting with the constraint condition determination dialogue unit 130.

[0043] The production planning device 1 according to the present embodiment, which is configured as described above, can automatically grasp the machining procedure for each process based on the contents of the machining program being executed in each process. Furthermore, it is possible to correct the execution order of the machining program with a simple instruction from the worker, which is expected to reduce the worker's workload.

[0044] Although the embodiments of the present disclosure have been described in detail above, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible in these embodiments without departing from the gist of the invention or the idea and intent of the present disclosure derived from the content described in the claims and their equivalents. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical expressions are used in the description of the above-described embodiments.

[0045] The following are supplementary notes relating to embodiments of the present disclosure. (Supplementary Note 1) A production planning device (1) according to one aspect of the present disclosure includes a manufacturing order receiving unit (100) that receives a manufacturing order including an instruction to produce workpieces with at least one industrial machine (4), a data collection unit (110) that collects data from a control device that controls the industrial machine (4), a constraint condition estimation pattern storage unit (200) that stores at least one constraint condition estimation pattern that associates predetermined constraint conditions related to the production of workpieces with estimation patterns used to estimate the constraint conditions, and a constraint condition estimation pattern storage unit (200) that estimates constraint conditions necessary for creating a production plan related to the manufacturing order based on the data collected by the data collection unit (110) and the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit (200). a constraint condition determination dialogue unit (130) that displays the constraint conditions and their grounds inferred by the constraint condition estimation unit (120), accepts a correction instruction including a natural language corresponding to the display, and corrects the constraint condition estimation pattern by exchanging the accepted correction instruction with an interactive response device (2), and a production plan creation unit (140) that creates a production plan for the workpiece based on the estimated values ​​of the constraint conditions inferred by the constraint condition estimation unit (120), and when the constraint condition determination dialogue unit (130) accepts a correction instruction and corrects the constraint condition estimation pattern, instructs the constraint condition estimation unit (120) to infer constraint conditions using the corrected estimation pattern. (Supplementary Note 2) A production planning device (1) according to another aspect of the present disclosure includes a machining program process analysis unit (160) that infers processes from the contents of an executed machining program.

[0046] (Supplementary Note 3) A computer-readable recording medium according to one aspect of the present disclosure includes a manufacturing order receiving unit (100) that receives a manufacturing order including an instruction to produce workpieces with at least one industrial machine (4), a data collection unit (110) that collects data from a control device that controls the industrial machine (4), a constraint condition estimation pattern storage unit (200) that stores at least one constraint condition estimation pattern that associates predetermined constraint conditions related to the production of workpieces with estimation patterns used to estimate the constraint conditions, and a constraint condition estimation pattern storage unit (200) that estimates constraint conditions necessary to create a production plan related to the manufacturing order based on the data collected by the data collection unit (110) and the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit (200). The program recorded is one that causes the computer to function as a constraint estimation unit (120), a constraint determination dialogue unit (130) that displays the constraints estimated by the constraint estimation unit (120) and their grounds, accepts correction instructions including natural language corresponding to the display, and modifies the constraint estimation pattern by exchanging the accepted correction instructions with an interactive response device, and a production plan creation unit (140) that creates a production plan for the work based on the estimated values ​​of the constraints estimated by the constraint estimation unit (120), and when the constraint determination dialogue unit (130) accepts a correction instruction and modifies the constraint estimation pattern, it instructs the constraint estimation unit (120) to infer constraints using the modified estimation pattern.

[0047] REFERENCE SIGNS LIST 1 Production planning device 2 Interactive response device 4 Industrial machine 5 Network 6 Fog computer 7 Cloud server 11 CPU 12 ROM 13 RAM 14 Non-volatile memory 15, 17, 18, 20 Interface 22 Bus 70 Display device 71 Input device 72 External device 100 Manufacturing order receiving unit 110 Data collection unit 120 Constraint condition estimation unit 130 Constraint condition determination dialogue unit 140 Production plan creation unit 150 Output unit 160 Machining program process analysis unit 200 Constraint condition estimation pattern storage unit

Claims

1. A system comprising: a manufacturing order receiving unit that receives a manufacturing order including an instruction to produce workpieces using at least one industrial machine; a data collecting unit that collects data from a control device that controls the industrial machine; a constraint condition estimation pattern storage unit that stores at least one constraint condition estimation pattern that associates predetermined constraint conditions related to the production of workpieces with an estimation pattern used to estimate the constraint conditions; a constraint condition estimation unit that estimates constraint conditions necessary to create a production plan for the manufacturing order based on the data collected by the data collecting unit and the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit; a constraint condition determination dialogue unit that displays the constraint conditions estimated by the constraint condition estimation unit and their grounds, receives correction instructions including natural language corresponding to the display, and exchanges the received correction instructions with an interactive response device to modify the constraint condition estimation pattern; and a production plan creation unit that creates a production plan for the workpieces based on the estimated values ​​of the constraint conditions estimated by the constraint condition estimation unit, the constraint condition determination dialogue unit, when receiving a modification instruction and modifying the constraint condition estimation pattern, instructs the constraint condition estimation unit to estimate constraint conditions using the modified estimation pattern.

2. The production planning device according to claim 1, further comprising a machining program process analysis unit that infers processes from the contents of an executed machining program.

3. A program that causes a computer to function as: a manufacturing order receiving unit that receives a manufacturing order including an instruction to produce workpieces with at least one industrial machine; a data collection unit that collects data from a control device that controls the industrial machine; a constraint condition estimation pattern storage unit that stores at least one constraint condition estimation pattern that associates predetermined constraint conditions related to workpiece production with an estimation pattern used to estimate the constraint conditions; a constraint condition estimation unit that estimates constraint conditions necessary to create a production plan for the manufacturing order based on the data collected by the data collection unit and the constraint condition estimation pattern stored in the constraint condition estimation pattern storage unit; a constraint condition determination dialogue unit that displays the constraint conditions estimated by the constraint condition estimation unit and their grounds, receives correction instructions including natural language corresponding to the display, and exchanges the received correction instructions with an interactive response device, thereby correcting the constraint condition estimation pattern; and a production plan creation unit that creates a production plan for the workpieces based on estimated values ​​of the constraint conditions estimated by the constraint condition estimation unit, a computer-readable recording medium having a program recorded thereon, wherein the constraint condition determination dialogue unit instructs the constraint condition estimation unit to estimate constraint conditions using the modified estimation pattern when receiving a modification instruction and modifying the constraint condition estimation pattern.

Images