PROGRAM, INFORMATION PROCESSING APPARATUS, AND ENERGY INFORMATION ESTIMATION METHOD

Abstract

To provide a technique capable of estimating energy information such as greenhouse gas emissions and energy consumption at a product design stage.SOLUTION: A program causes a computer to realize: an acquisition function for acquiring product information including design values related to product specifications that can be set at a product design stage; and an estimation function for estimating energy information that is generated when a production planned product is produced by inputting the product information of the production planned product planned to be produced into a learning model that has been trained using a data set including a combination of the product information and the energy information that includes at least one of energy consumption and greenhouse gas emissions generated by product production.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a program, an information processing device, an energy information estimation method, and a trained model. [Background technology]

[0002] In order to accurately calculate the amount of carbon dioxide emissions generated during the production of a product in accordance with the equipment, a carbon dioxide emission calculation device is known that calculates the amount of carbon dioxide emissions using information about the production process and equipment during the production of the product (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-108691 A Summary of the Invention [Problem to be solved by the invention]

[0004] 2. Description of the Related Art In order to design products taking into consideration energy information such as greenhouse gas emissions and energy consumption, there is a demand for grasping energy information at the product design stage. [Means for solving the problem]

[0005] The present disclosure can be realized in the following forms. A first aspect of the present disclosure is a program, which causes a computer to realize an acquisition function of acquiring product information including design values ​​related to product specifications that can be set at a design stage of the product, and an estimation function of estimating the energy information generated when the planned production product is produced by inputting product information of a planned production product to a learning model that has been trained using a dataset including a combination of energy information including at least one of energy consumption and greenhouse gas emissions generated by the production of the product, and the product information, and the acquisition function further includes a function of acquiring production line information including production conditions that can be set at the design stage of the product and are set on a production line to produce the product, The estimation function includes a function of estimating the energy information that will be generated when the product to be produced is produced by inputting product information of the product to be produced and production line information for producing the product to be produced into the learning model, which has been trained using a dataset including a combination of the production line information, the product information, and the energy information, wherein the design values ​​included in the product information and the production conditions included in the production line information each include a plurality of levels that can be selected by a user, and the estimation function is a program that estimates the energy information for each combination of the plurality of levels and displays the estimated energy information on a display unit for each combination of the plurality of levels.

[0006] (1) According to one aspect of the present disclosure, there is provided a program that causes a computer to realize an acquisition function of acquiring product information including design values ​​related to product specifications that can be set at a product design stage, and an estimation function of estimating the energy information that will be generated when the product to be produced is produced by inputting product information of a product to be produced into a learning model that has been trained using a dataset including a combination of energy information including at least one of energy consumption and greenhouse gas emissions generated in the production of the product, and the product information. According to the program of this form, it is possible to estimate energy information at the design stage of a product to be produced, and to carry out product design of the product to be produced taking the energy information into consideration. (2) In the program of the above aspect, the acquisition function may further include a function of acquiring the energy information. The program may be configured to cause the computer to realize a learning function of training the learning model using a data set including a combination of the energy information acquired by the acquisition function and the product information. According to the program of this form, the learning model is trained each time energy information is estimated using a data set of a product to be produced, thereby improving the estimation accuracy of the energy information. (3) In the program of the above aspect, the learning model may have been trained using a dataset including a combination of the energy information generated each time one of the products is produced and the product information. According to the program of this aspect, it is possible to improve the accuracy of estimating the energy information, compared to the case where the total amount of energy information generated during a predetermined period is obtained. (4) In the program of the above aspect, the acquisition function may further include a function of acquiring production line information including production conditions that can be set at a design stage of the product and that are set on a production line to produce the product. The estimation function may include a function of estimating the energy information generated when the planned product is produced by inputting product information of the planned product and production line information for producing the planned product to the learning model trained using a data set including a combination of the production line information, the product information, and the energy information. According to the program of this aspect, the number of pieces of data used for estimating the energy information is increased, thereby making it possible to improve the accuracy of estimating the energy information. (5) In the program of the above form, the production line information may further include at least one of the following: a work type indicating whether or not manual work is included in the processing of the product by the production line; an installation location of the production line; the number of pieces of equipment included in the production line; processing time of the product by the production line; mold information regarding a mold used to process the product; and design information including design values ​​of a product immediately before being processed by the production line. According to the program of this aspect, by setting factors that are statistically significant with respect to the energy information in the production line information, it is possible to improve the estimation accuracy of the energy information using the production line information. (6) In the program of the above form, the product information may include at least one of material information including the name and quality of the material of the product, dimensions of the product, weight of the product, and set tolerances allowed for the dimensions and weight of the product. According to the program of this aspect, by setting a factor that is statistically significant with respect to the energy information in the product information, it is possible to improve the estimation accuracy of the energy information using the product information. (7) According to another aspect of the present disclosure, a trained model is provided. The trained model trains a relationship between product information and energy information using a data set including a combination of product information including design values ​​related to product specifications that can be set at the product design stage and energy information including at least one of energy consumption and greenhouse gas emissions generated by the production of the product. By inputting product information of a product to be produced, an estimate of the energy information generated when the product to be produced is output. According to this type of trained model, energy information can be estimated at the design stage of a product to be produced, and product design of the product to be produced can be carried out taking the energy information into account. The present disclosure may be realized in various forms other than a program and an information processing device, for example, in the form of an energy information estimation method, a learning method for a learning model, a control method for an information processing device, a computer program for realizing the control method, a non-transitory recording medium on which the computer program is recorded, etc. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is an explanatory diagram illustrating a schematic configuration of an information processing device according to a first embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram showing the internal functional configuration of the information processing device. [Diagram 3] 1 is a flow chart illustrating an energy information estimation method. [Figure 4] 11 is a flowchart showing details of a learning process. [Diagram 5] FIG. 1 is an explanatory diagram illustrating a database of machine learning datasets. [Figure 6] 11 is a flowchart showing details of an estimation process. [Figure 7] FIG. 4 is an explanatory diagram showing a method for setting each item of product information and production line information. [Figure 8] FIG. 11 is an explanatory diagram showing an example of a calculation result of an estimated value of carbon dioxide emission amount. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] A. First embodiment: FIG. 1 is an explanatory diagram showing a schematic configuration of an information processing device 60 according to a first embodiment of the present disclosure. The information processing device 60 estimates energy information generated by the production of a product WK by a production line Ln at the design stage of the product WK using machine learning. The "energy information" includes information on the consumption of various energies such as electricity, gas, and liquid fuels including kerosene and heavy oil generated by the production of the product, and information on the emission of greenhouse gases such as carbon dioxide (CO2) and methane (CH4) generated by the consumption of the energy. The information processing device 60 estimates energy information generated when the product to be produced is produced by inputting information on the design stage of a product to be produced using the production line to a trained learning model (hereinafter also referred to as a "trained model"). In this embodiment, the information processing device 60 estimates carbon dioxide emission as energy information.

[0009] The information processing device 60 performs machine learning using energy information generated in processes PR1 and PR2 of the production line Ln during the production of the product WK and product information D1 and production line information D2 of the product WK stored in a database DB of an external device. "Product information" refers to information related to product design, and can be set at a design stage before the production of the product starts. "Production line information" refers to information related to production conditions set on the production line Ln to produce the product, and can be set at a design stage before the production of the product starts. The energy information as learning data is acquired from sensors 70 installed in each of the processes PR1 and PR2 included in the production line Ln.

[0010] The sensor 70 includes a detection unit 72 and a communication unit 74. The detection unit 72 detects energy information generated during processing in the steps PR1 and PR2. For example, a watt-hour meter, a gas meter, or the like can be used as the detection unit 72. In this embodiment, the detection unit 72 is a watt-hour meter, and detects the amount of power consumption generated in the steps PR1 and PR2 as energy information. The amount of power consumption detected by the detection unit 72 is output to the communication unit 74. The communication unit 74 transmits the amount of power consumption to the information processing device 60 by wireless communication according to an arbitrary communication protocol. Note that the sensor 70 is not limited to being separate from the information processing device 60, and may be integrated with the information processing device 60. The communication unit 74 may further receive an execution command from the information processing device 60.

[0011] The product information D1 and the production line information D2 may include a plurality of items that the information processing device 60 uses as learning data and estimation data. In this embodiment, factors that are statistically significant for carbon dioxide emissions are experimentally extracted in advance from the product information D1 and the production line information D2. Specifically, the product information D1 includes design values ​​related to product specifications as factors that are statistically significant for carbon dioxide emissions. The product information D1 may further include at least one of material information including the material name and quality of the product, product dimensions, product weight, and set tolerances allowed for the product dimensions and weight. The production line information D2 includes production conditions set in the production line Ln to produce the product. The production line information D2 may further include at least one of the installation location of the production line, the number of pieces of equipment included in the production line, the processing time of the product by the production line, the type of work indicating whether or not manual work is included in the processing of the product WK by the production line Ln, mold information regarding the mold used to process the product, and design information including the design values ​​of the product immediately before being processed by the production line. "Mold information" refers to design information that indicates the properties of a mold, such as the volume of the internal space of the mold and the shape of the internal space (cavity), and "design values ​​of a product immediately before being processed by a production line" refers to, for example, the inner angle of a corner of a product immediately before chamfering in the case where the corners of the product are chamfered by machining, and refers to design information that indicates the properties of the product immediately before it is processed by the production line. Production line information is not limited to these examples, and may further include, for example, the season and date for which production is scheduled, the work shifts of workers, etc.

[0012] 2 is a block diagram showing the internal functional configuration of the information processing device 60. The information processing device 60 includes a CPU 62 as a central processing unit, a storage device 64, a display unit 66 such as a liquid crystal display or a touch panel, an input unit 67, and a communication unit 68. The CPU 62, the storage device 64, the display unit 66, the input unit 67, and the communication unit 68 are connected to one another via a bus 61 and are capable of bidirectional communication. The input unit 67 is, for example, a keyboard or a mouse, and is used to input product information and production line information.

[0013] The communication unit 68 is an interface that performs communication control to receive a machine learning dataset and estimation data via a network. The communication unit 68 functions as an acquisition unit that acquires product information D1 and production line information D2 from an external device that stores a design stage database DB. In this embodiment, the communication unit 68 further acquires energy information via a sensor 70.

[0014] The storage device 64 is, for example, a RAM, a ROM, or a hard disk drive (HDD). The HDD or ROM stores various programs for implementing the functions provided in this embodiment. The various programs read from the HDD or ROM are expanded on the RAM and executed by the CPU 62. The readable and writable area of ​​the storage device 64 includes an energy information storage unit 640 for storing acquired energy information, a product information storage unit 642 for storing acquired product information D1, a production line information storage unit 644 for storing acquired production line information D2, a CO2 emission coefficient storage unit 646, and a learning model storage unit 648 for storing a machine learning model. The storage device 64 temporarily stores various calculation results generated by the CO2 emission amount estimation unit. The storage device 64 may be an optical disk, an SSD (Solid State Drive), a flash memory, or the like.

[0015] The energy information storage unit 640 records energy information acquired during past production. In this embodiment, the energy information storage unit 640 records carbon dioxide emission amounts as a database associated with product information, production line information, and product identification information. The product identification information is, for example, a serial number assigned to each product. The energy information storage unit 640 may record energy information such as power consumption amounts together with or instead of the carbon dioxide emission amounts. The product information storage unit 642 records acquired product information D1, and the production line information storage unit 644 records acquired production line information D2.

[0016] The CO2 emission coefficient storage unit 646 stores a CO2 emission coefficient for deriving the CO2 emission amount. The "CO2 emission coefficient" is the amount of carbon dioxide emission per activity amount, and means the amount of carbon dioxide emission per unit amount of energy consumption determined in advance. In this embodiment, the CO2 emission coefficient corresponds to the amount of carbon dioxide emission emitted to generate 1 kWh of electricity, and the unit is, for example, g / kWh. In this embodiment, the emission coefficient is stored in advance in the CO2 emission coefficient storage unit 646 using the emission coefficient by electric utility published by the Ministry of the Environment and the Ministry of Economy, Trade and Industry based on the Law Concerning Promotion of Global Warming Countermeasures (Global Warming Countermeasures Law). However, the CO2 emission coefficient is not limited to being set in advance as a fixed value, and may be updated successively via a wide area network such as the Internet. By configuring in this way, the CO2 emission amount can be derived using the latest CO2 emission coefficient.

[0017] The CPU 62 executes a program stored in the storage device 64 to function as a learning model generation unit 622 and a CO2 emission amount estimation unit 624. This program causes the computer to realize an acquisition function for acquiring product information and production line information, and an estimation function for estimating energy information generated when the planned production product is produced. The learning model generation unit 622 generates a learned model using a machine learning dataset. The machine learning dataset is energy information generated on the production line Ln acquired from the sensor 70, and product information D1 and production line information D2 stored in the database DB. The CO2 emission amount estimation unit 624 estimates the carbon dioxide emission amount generated when the planned production product is produced using the learned model.

[0018] 3 is a flowchart showing an energy information estimation method executed by the information processing device 60. In step S10, the learning model generation unit 622 acquires a data set for machine learning, and generates a trained model by performing machine learning using the acquired data set for machine learning. In step S20, the trained model is used to estimate the amount of carbon dioxide emissions, as energy information, that will occur when any product to be produced is produced.

[0019] 4 is a flowchart showing the details of the learning process. In step S100, a data set for machine learning is acquired. Specifically, in step S102, the learning model generation unit 622 acquires product information D1 from the database DB of the external device via the communication unit 68. In step S104, the learning model generation unit 622 acquires production line information D2 from the database DB of the external device via the communication unit 68.

[0020] In step S106, the learning model generation unit 622 acquires the amount of CO2 emissions. In this embodiment, the learning model generation unit 622 acquires the amount of power consumption for each production line Ln by wireless communication with the sensor 70 via the communication unit 68. The learning model generation unit 622 calculates the amount of CO2 emissions by multiplying the acquired amount of power consumption by the CO2 emission coefficient stored in the CO2 emission coefficient storage unit 646. Note that the amount of CO2 emissions may be calculated by the sensor 70 that acquired the amount of power consumption, and in this case, the information processing device 60 acquires the amount of CO2 emissions from the sensor 70 via the communication unit 68.

[0021] In this embodiment, the learning model generation unit 622 obtains the amount of power consumption generated for each production of a product from the sensor 70, and calculates the amount of CO2 emissions generated for each production of a product. However, this is not limited to this, and the total amount of CO2 emissions generated by producing multiple products during a predetermined period may be obtained, and the total amount may be divided by the number of products produced to calculate the CO2 emissions generated per product. The learning model generation unit 622 generates a database of a data set for machine learning that associates the obtained product information D1, production line information D2, and CO2 emissions with the serial numbers of the products.

[0022] Fig. 5 is an explanatory diagram that shows a model of a database MD of a machine learning dataset. As shown in Fig. 5, in the database MD, each item of the acquired product information D1, each item of the production line information D2, the amount of CO2 emissions, and the serial number of the product are recorded in association with each other.

[0023] Returning to FIG. 4, in step S110, the learning model generation unit 622 performs machine learning using a machine learning dataset stored in the storage device 64, and generates a trained learning model. In this embodiment, the learning model generation unit 622 performs supervised learning of a regression problem with product information and production line information recorded in the database MD as explanatory variables and carbon dioxide emissions as a response variable. The explanatory variables are also called input variables, independent variables, etc., and the response variables are also called response variables, dependent variables, etc. The learning model generation unit 622 may perform machine learning using linear regression such as the least squares method. The learning model generation unit 622 may perform machine learning using, for example, a recurrent neural network (RNN), a general regression neural network, a random forest, or the like.

[0024] 6 is a flowchart showing details of the estimation step. Step S202 is an acquisition step for acquiring product information and production line information of a product to be produced, and the CO2 emission estimation unit 624 acquires product information D1 and production line information D2 of the product to be produced from a database DB of an external device. The product information D1 and production line information D2 of the product to be produced may be input by, for example, a user operating the input unit 67. In this embodiment, a plurality of levels selectable by the user can be set for each item of the product information D1 and production line information D2 of the product to be produced.

[0025] FIG. 7 is an explanatory diagram showing a method of setting each item of the product information D1 and the production line information D2 of the product to be produced. The table TB1 shown in FIG. 7 is a setting screen for calculating an estimated value of carbon dioxide emission, and is displayed on the display unit 66, for example. The user can input or select items 82 and 84 as the product information D1 of the product to be produced and items 85 and 86 as the production line information D2 of the product to be produced by operating the input unit 67. In the example of FIG. 7, the item 84 indicates the name of the material used in the product to be produced. In this embodiment, materials M1 and M2 are set as multiple levels as candidates for the design stage of the product to be produced. Similarly, the item 86 indicates the production conditions of the process PR1 of the product to be produced, and set values ​​C1 and C2 are set as multiple levels. When the input of all items is completed and the execute button 88 is operated, the estimated value of carbon dioxide emission by the trained model starts to calculate the estimated value of carbon dioxide emission for each combination of levels set in each item.

[0026] 6, in step S204, the CO2 emission amount estimation unit 624 inputs the product information D1 and production line information D2 of the product to be produced into the trained model stored in the trained model storage unit 648. When multiple levels are set for the items of the product information D1 and the production line information D2, the CO2 emission amount estimation unit 624 inputs all combinations of the multiple levels set for each item of the product information D1 and the production line information D2 into the trained model.

[0027] In step S206, the CO2 emission estimation unit 624 outputs the estimated value of the CO2 emission obtained from the trained model to the display unit 66. In step S208, the user determines the product information D1 and the production line information D2. More specifically, when the items of the product information D1 and the production line information D2 include multiple levels, the user refers to the estimated value of the CO2 emission obtained from the trained model and selects one of the levels.

[0028] FIG. 8 is an explanatory diagram showing an example of the calculation result of the estimated value of the carbon dioxide emission. Table TB2 shown in FIG. 8 is displayed on the display unit 66 after, for example, the execute button 88 shown in FIG. 7 is operated. In table TB2, the estimated value of the carbon dioxide emission is shown for each combination of multiple levels set for each item of the product information D1 and the production line information D2. In the example of FIG. 8, the estimated value of the carbon dioxide emission is shown for each of four combinations of the materials M1 and M2 of the item 84 shown in FIG. 7 and the set values ​​C1 and C2 of the item 86. By configuring in this way, when multiple levels are listed as candidates for each item of the product information D1 and the production line information D2 in the design stage of the product to be produced, the user can refer to the estimated value of the CO2 emission for each combination. Therefore, the user can set each item of the product information D1 and the production line information D2 of the product to be produced based on the estimated value of the CO2 emission.

[0029] As described above, the program stored in the information processing device 60 of this embodiment realizes in the computer an acquisition function for acquiring product information D1 that can be set at the design stage of the product WK, and an estimation function for estimating the amount of carbon dioxide emissions that will occur when the product to be produced is produced by inputting the product information D1 of the product to be produced into a trained learning model. According to the program of this embodiment, the amount of carbon dioxide emissions can be estimated using the product information D1 of the product to be produced. Therefore, the amount of carbon dioxide emissions can be estimated at the design stage of the product to be produced, and product design can be performed taking the amount of carbon dioxide emissions into consideration.

[0030] The program stored in the information processing device 60 of this embodiment has an acquisition function that further includes a function for acquiring carbon dioxide emission amount as energy information, and causes the computer to realize a learning function for training a learning model using a data set including a combination of the acquired product information D1 and the carbon dioxide emission amount. According to the program of this embodiment, the learning model can be trained using a data set acquired when estimating the carbon dioxide emission amount. Therefore, the learning model is trained every time the carbon dioxide emission amount is estimated using the data set of a product to be produced, and the estimation accuracy of the carbon dioxide emission amount can be improved.

[0031] According to the program stored in the information processing device 60 of this embodiment, the trained model is trained using the amount of carbon dioxide emission generated for each production of a product. According to the program of this embodiment, the accuracy of estimating the amount of carbon dioxide emission can be improved compared to the case where the total amount of carbon dioxide emission generated during a predetermined period is obtained.

[0032] The program stored in the information processing device 60 of this embodiment further realizes, as an acquisition function, a function of acquiring production line information D2 that can be set at the design stage of the product WK and includes production conditions that are set on the production line Ln to produce the product WK. According to the program of this embodiment, the accuracy of estimating the amount of carbon dioxide emissions can be improved by increasing the number of data used to estimate the amount of carbon dioxide emissions.

[0033] In the program stored in the information processing device 60 of this embodiment, the production line information D2 contains design information including production conditions, work types, the installation location of the production line Ln, the number of pieces of equipment included in the production line Ln, processing time of the product WK by the production line Ln, mold information related to the molds used to process the product WK, and design values ​​of the product WK immediately before being processed by the production line Ln. According to the program of this embodiment, factors that are statistically significant for the amount of carbon dioxide emissions are set as items in the production line information D2, thereby making it possible to improve the accuracy of estimating the amount of carbon dioxide emissions using the production line information D2.

[0034] In the program stored in the information processing device 60 of this embodiment, the product information D1 includes material information including the name and quality of the material of the product WK, the dimensions of the product WK, the weight of the product WK, and set tolerances allowed for the dimensions and weight of the product WK. According to the program of this embodiment, by setting factors that are statistically significant for the amount of carbon dioxide emissions in the items of the product information D1, it is possible to improve the accuracy of estimating the amount of carbon dioxide emissions using the product information D1.

[0035] B. Other embodiments: (B1) In the above first embodiment, an example was shown in which multiple levels selectable by the user are set for each item of the product information D1 and the production line information D2. In contrast, a single level may be set for each item of the product information D1 and the production line information D2. Even in this form, an estimated value of carbon dioxide emissions can be output using the single level set for each item of the product information D1 and the production line information D2.

[0036] (B2) In the above first embodiment, when multiple levels are included in the items of the product information D1 and the production line information D2, an example was shown in which the user selects one level. In contrast, the levels of each item of the product information D1 and the production line information D2 may be determined by the information processing device 60 according to a preset condition, for example, by selecting a combination of levels of each item of the product information D1 and the production line information D2 that minimizes carbon dioxide emissions. In this case, the generation of table TB2 shown in FIG. 8 may be omitted.

[0037] (B3) In the above first embodiment, an example was shown in which an estimated value of carbon dioxide emission was calculated using both the product information D1 and the production line information D2. In contrast, for example, in cases where sufficient accuracy in estimating the carbon dioxide emission can be obtained by using only the product information D1, the learning model generation unit 622 and the CO2 emission estimation unit 624 do not need to acquire the production line information D2.

[0038] (B4) In the above-described first embodiment, an example was shown in which the information processing device 60 estimates the amount of carbon dioxide emission as energy information. In contrast, the information processing device 60 may estimate the amount of emission of greenhouse gases other than carbon dioxide, such as methane (CH4). The information processing device 60 may estimate the amount of energy consumption, such as the amount of power consumption, instead of or in addition to the amount of carbon dioxide emission. For example, the information processing device 60 may learn the relationship between the product information D1 and the production line information D2 and the amount of energy consumption, and estimate the amount of energy consumption using the product information D1 and the production line information D2 of a product to be produced. An estimated value of the amount of carbon dioxide emission may be obtained by further multiplying the obtained estimated value of the energy consumption by a CO2 emission coefficient. The information processing device 60 may estimate both the amount of energy consumption and the amount of greenhouse gas emission.

[0039] (B5) In the above-described first embodiment, an example was shown in which the energy information estimation method includes a learning step. In contrast, in cases where the learning model stored in the learning model storage unit 648 has been sufficiently learned, the learning step of step S10 may be omitted and only the estimation step of step S20 may be executed.

[0040] The control unit and the method described in the present disclosure may be realized by a special-purpose computer provided by configuring a processor and a memory programmed to execute one or more functions embodied in a computer program. Alternatively, the control unit and the method described in the present disclosure may be realized by a special-purpose computer provided by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, the control unit and the method described in the present disclosure may be realized by one or more special-purpose computers configured by a combination of a processor and a memory programmed to execute one or more functions and a processor configured with one or more hardware logic circuits. In addition, the computer program may be stored in a computer-readable non-transitory tangible recording medium as instructions executed by a computer.

[0041] The present disclosure is not limited to the above-mentioned embodiment, and can be realized in various configurations without departing from the spirit of the present disclosure. For example, the technical features in the embodiments corresponding to the technical features in each aspect described in the Summary of the Invention column can be appropriately replaced or combined to solve some or all of the above-mentioned problems or to achieve some or all of the above-mentioned effects. Furthermore, if the technical feature is not described as essential in this specification, it can be appropriately deleted. [Explanation of symbols]

[0042] 60...information processing device, 61...bus, 62...CPU, 64...storage device, 66...display unit, 67...input unit, 68...communication unit, 70...sensor, 72...detection unit, 74...communication unit, 82-86...item, 88...execution button, 622...learning model generation unit, 624...CO2 emission estimation unit, 640...energy information storage unit, 642...product information storage unit, 644...production line information storage unit, 646...CO2 emission coefficient storage unit, 648...learning model storage unit, D1...product information, D2...production line information, DB...database, Ln...production line, MD...database, PR1,PR2...process, TB1,TB2...table, WK...product

Claims

1. A program, An acquisition function for acquiring product information including design values ​​related to the product specifications that can be set at the design stage of the product; an estimation function for estimating the energy information generated when the planned production product is produced by inputting product information of a planned production product to a learning model that has been trained using a dataset including a combination of energy information including at least one of an amount of energy consumption and an amount of greenhouse gas emission generated by the production of the product, and the product information; The acquisition function further includes a function of acquiring production line information including production conditions that can be set at a design stage of the product and are set on a production line for producing the product; the estimation function includes a function of estimating the energy information generated when the planned production product is produced by inputting product information of the planned production product and production line information for producing the planned production product into the learning model trained using a data set including a combination of the production line information, the product information, and the energy information; the design value included in the product information and the production condition included in the production line information each include a plurality of levels selectable by a user; the estimation function estimates the energy information for each combination of the plurality of levels, and displays the estimated energy information on a display unit for each combination of the plurality of levels. program.

2. The program according to claim 1, The acquisition function further includes a function of acquiring the energy information, A learning function for training the learning model using a data set including a combination of the energy information and the product information acquired by the acquisition function is implemented in a computer. program.

3. The program according to claim 1, The learning model has been trained using a dataset including a combination of the energy information generated each time the product is produced and the product information. program.

4. The program according to claim 1, The production line information further includes at least one of the following: a type of work indicating whether or not manual work is included in the processing of the product by the production line, an installation location of the production line, the number of pieces of equipment included in the production line, processing time of the product by the production line, mold information regarding a mold used in processing the product, and design information including design values ​​of a product immediately before being processed by the production line. program.

5. The program according to claim 1, The product information includes at least one of material information including a material name and a quality of the product, a dimension of the product, a weight of the product, and a set tolerance allowed for the dimension and weight of the product; program.

6. The program according to claim 1, Furthermore, the computer is caused to realize a function of selecting, from among the plurality of levels, a combination of levels that minimizes the estimated energy information. program.

7. An information processing device, An acquisition unit that acquires product information including design values ​​related to product specifications that can be set at a product design stage; an estimation unit that estimates the energy information generated when the planned production product is produced by inputting product information of a planned production product to a learning model that has been trained using a dataset including a combination of energy information including at least one of an energy consumption amount and a greenhouse gas emission amount generated by the production of the product, and the product information; The acquisition unit further acquires production line information including production conditions that can be set at a design stage of the product and that are set on a production line for producing the product; the estimation unit estimates the energy information generated when the planned production product is produced by inputting product information of the planned production product and production line information for producing the planned production product into the learning model trained using a data set including a combination of the production line information, the product information, and the energy information; the design value included in the product information and the production condition included in the production line information each include a plurality of levels selectable by a user; the estimation unit estimates the energy information for each combination of the plurality of levels, and displays the estimated energy information on a display unit for each combination of the plurality of levels. Information processing device.

8. 1. A method for estimating energy information, comprising: An acquisition step in which an information processing device acquires product information including design values ​​related to product specifications that can be set at a design stage of the product; an estimation step in which the information processing device estimates the energy information generated when the planned production product is produced by inputting product information of a planned production product to a learning model that has been trained using a data set including a combination of energy information including at least one of an amount of energy consumption and an amount of greenhouse gas emission generated by the production of the product, and the product information; In the acquiring step, the information processing device further acquires production line information including production conditions that can be set at a design stage of the product and that are set on a production line for producing the product; In the estimation step, the information processing device estimates the energy information generated when the planned production product is produced by inputting product information of the planned production product and production line information for producing the planned production product into the learning model trained using a data set including a combination of the production line information, the product information, and the energy information; the design value included in the product information and the production condition included in the production line information each include a plurality of levels selectable by a user; In the estimation step, the information processing device estimates the energy information for each combination of the plurality of levels, and displays the estimated energy information on a display unit for each combination of the plurality of levels. Energy information estimation method.

Images