Program product, information processing apparatus, and energy information estimation method

Abstract

The present application relates to a program, an information processing apparatus, an energy information estimation method, and a learned model, and provides a technology capable of estimating energy information such as an amount of discharge of a greenhouse gas and an amount of energy consumption at a design stage of a product. The program causes a computer to realize: an acquisition function that acquires product information including a design value related to a specification of a product, which is settable at the design stage of the product; and an estimation function that estimates energy information generated in the production of a predetermined production product by inputting product information of the predetermined production product to a learned model learned using a data set including a combination of the energy information and the product information, the energy information being at least any one of an amount of energy consumption and an amount of discharge of a greenhouse gas generated by the production of the product.

Description

Technical Field

[0001] This disclosure relates to procedures, information processing devices, energy information estimation methods, and learning-complete models. Background Technology

[0002] A known carbon dioxide emission calculation device (e.g., Patent Document 1) uses information about the production process and equipment during the production of a product to calculate the carbon dioxide emission in order to calculate the carbon dioxide emission generated during the production of the product with high accuracy based on the equipment.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2012-108691 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] In order to design products that take into account energy information such as greenhouse gas emissions and energy consumption, it is desirable to obtain energy information during the product design phase.

[0008] Technical solutions for solving the problem

[0009] This disclosure can be implemented in the following ways.

[0010] (1) According to one aspect of the present disclosure, a program is provided. The program enables a computer to perform the following functions: an acquisition function, which acquires product information containing design values ​​related to the specifications of the product that can be set during the product design phase; and an estimation function, which estimates energy information generated in the production of the predetermined product by inputting the product information of the predetermined product into a learning model that has been learned using a dataset, the dataset containing a combination of the energy information and the product information, the energy information including at least one of energy consumption generated by the production of the product and greenhouse gas emissions.

[0011] According to this procedure, energy information can be estimated during the design phase of the planned production product, and product design of the planned production product can be carried out with energy information in mind.

[0012] (2) In the above-described procedure, the acquisition function may further include the function of acquiring the energy information. The procedure may also enable the computer to implement a learning function, which uses a dataset containing a combination of the energy information acquired by the acquisition function and the product information to enable the learning model to learn.

[0013] According to this procedure, whenever a dataset of pre-prepared production products is used to estimate energy information, the learning model learns and can improve the estimation accuracy of energy information.

[0014] (3) In the above-described procedure, the learning model can be trained using a dataset containing a combination of the energy information generated for each product produced and the product information.

[0015] According to this method, the estimation accuracy of energy information can be improved compared to obtaining the total amount of energy information generated in a predetermined period.

[0016] (4) In the above-described procedure, the acquisition function may further include the function of acquiring production line information, which can be set during the design phase of the product and includes the production conditions set in the production line for producing the product. The estimation function may include the following function: by inputting the product information of the predetermined product and the production line information for producing the predetermined product into the learning model learned using a dataset containing a combination of the production line information, the product information and the energy information, the energy information generated in the production of the predetermined product is estimated.

[0017] According to this procedure, the accuracy of energy information estimation can be improved by increasing the amount of data used for energy information estimation.

[0018] (5) In the above-described procedure, the production line information may also include at least one of the following: job type, location of the production line, number of equipment in the production line, processing time of the product by the production line, mold information related to the mold used in the processing of the product, and design information. The job type indicates whether the processing of the product by the production line includes manual operations, and the design information includes the design values ​​of the product before it is processed by the production line.

[0019] According to this method, by setting statistically significant factors for energy information in the production line information, the estimation accuracy of energy information using the production line information can be improved.

[0020] (6) In the above procedure, the product information may also include at least one of the following: material information, the size of the product, the weight of the product, and the allowable tolerance of the size and weight of the product. The material information includes the material name and material of the product.

[0021] According to this procedure, by setting statistically significant factors for energy information in the product information, the estimation accuracy of energy information using the product information can be improved.

[0022] (7) According to other aspects of this disclosure, a learning model is provided. This learning model uses a dataset to learn the relationship between product information and energy information, the dataset containing a combination of the product information and the energy information, the product information being set during the product design phase and including design values ​​related to the product specifications, and the energy information including at least one of energy consumption generated from the production of the product and greenhouse gas emissions. By inputting product information of a predetermined product to be produced, an estimated value of the energy information generated in the production of the predetermined product is output.

[0023] Based on the learned model, energy information can be estimated during the design phase of the planned production product, and product design of the planned production product can be carried out with energy information in mind.

[0024] This disclosure can also be implemented in various ways other than programs and information processing devices. For example, it can be implemented by energy information estimation methods, learning methods of learning models, control methods of information processing devices, computer programs that implement the control methods, and non-temporary recording media that record the computer programs. Attached Figure Description

[0025] Figure 1 This is an explanatory diagram schematically illustrating the structure of the information processing apparatus according to the first embodiment of this disclosure.

[0026] Figure 2 It is a block diagram representing the internal functional structure of an information processing device.

[0027] Figure 3 This is a flowchart illustrating the method for estimating energy information.

[0028] Figure 4 This is a flowchart showing the details of the learning process.

[0029] Figure 5 This is an illustrative diagram representing a database used for machine learning datasets.

[0030] Figure 6 This is a flowchart showing the details of the estimated process.

[0031] Figure 7 This is an explanatory diagram showing how to set up each item in product information and production line information.

[0032] Figure 8 This is an explanatory diagram illustrating an example of the calculated results of an estimated value for carbon dioxide emissions. Detailed Implementation

[0033] A. First implementation method: Figure 1 This is an explanatory diagram schematically illustrating the structure of the information processing apparatus 60 according to the first embodiment of this disclosure. The information processing apparatus 60 utilizes machine learning to estimate the energy information generated during the design phase of product WK through production line Ln. The "energy information" includes information related to the consumption of various forms of energy generated during product production, such as electricity, gas, and liquid fuels including kerosene and heavy oil, and information related to the emission of greenhouse gases such as carbon dioxide (CO2) and methane (CH4) generated through this energy consumption. The information processing apparatus 60 estimates the energy information generated during the production of the intended product by inputting information from the design phase of the intended product to be produced using the production line into a learned learning model (hereinafter also referred to as the "learned model"). In this embodiment, the information processing apparatus 60 estimates the carbon dioxide emission as energy information.

[0034] The information processing device 60 performs machine learning using energy information generated in processes PR1 and PR2 of production line Ln during the production of product WK, and product information D1 and production line information D2 of product WK stored in a database DB on an external device. "Product information" refers to information related to product design, which can be set during the design phase before production begins. "Production line information" refers to information related to the production conditions set in production line Ln for product production, which can also be set during the design phase before production begins. The energy information used as learning data is obtained from sensors 70 installed in processes PR1 and PR2 of production line Ln.

[0035] The sensor 70 includes a detection unit 72 and a communication unit 74. The detection unit 72 detects energy information generated during processing in steps PR1 and PR2. For example, a power meter or a gas meter can be used as the detection unit 72. In this embodiment, the detection unit 72 is a power meter, detecting the amount of power consumed in steps PR1 and PR2 as energy information. The power consumption detected by the detection unit 72 is output to the communication unit 74. The communication unit 74 transmits the power consumption to the information processing device 60 wirelessly according to any communication protocol. Furthermore, the sensor 70 is not limited to being separate from the information processing device 60; it can also be integrated with the information processing device 60. The communication unit 74 may also receive execution commands from the information processing device 60.

[0036] The product information D1 and production line information D2 may include multiple items used by the information processing device 60 for learning and estimation data. In this embodiment, factors that are statistically significant for carbon dioxide emissions are extracted in advance through experiments in the product information D1 and production line information D2. Specifically, as factors that are statistically significant for carbon dioxide emissions, the product information D1 includes design values ​​related to the product specifications. The product information D1 may also include at least one of the following: the product's material name and material information, the product's dimensions, the product's weight, and the allowable tolerances for the product's dimensions and weight. The production line information D2 includes the production conditions set in the production line Ln for producing the product. The production line information D2 may also include at least one of the following: the location of the production line, the number of machines included in the production line, the production line's processing time for the product, the type of operation indicating whether the processing of product WK in production line Ln includes manual operations, mold information related to the molds used in the product processing, and design information including the design values ​​of the product before it is processed by the production line. "Mold information" refers to design information describing the mold's properties, such as the volume of its internal space and the shape of its internal space (cavity). "Design values ​​of the product before production line processing" refers to, for example, the inner angles of the corners of the product before chamfering, in the case of chamfering the corners of the product through machining; it refers to design information indicating the changes in the product's properties before production line processing. Production line information is not limited to these examples; for example, it may also include the scheduled production season, date and time, and operator shifts.

[0037] Figure 2 This is a block diagram showing the internal functional structure 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 and a touch panel, an input unit 67, and a communication unit 68. The CPU 62, storage device 64, display unit 66, input unit 67, and communication unit 68 are interconnected via a bus 61, enabling bidirectional communication. The input unit 67 is, for example, a keyboard or mouse, used for inputting product information and production line information.

[0038] The communication unit 68 is an interface for communication control of receiving datasets for machine learning and estimation data via a network. The communication unit 68 functions as an acquisition unit for obtaining product information D1 and production line information D2 from an external device storing the design phase database DB. In this embodiment, the communication unit 68 also acquires energy information via sensor 70.

[0039] The storage device 64 is, for example, RAM, ROM, or a hard disk drive (HDD). Various programs for implementing the functions provided in this embodiment are stored in the HDD or ROM. The various programs read from the HDD or ROM are expanded in RAM and executed by the CPU 62. The storage device 64 includes the following in its readable and writable areas: 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. Furthermore, various calculation results generated by the CO2 emission estimation unit are temporarily stored in the storage device 64. The storage device 64 may also use an optical disc, an SSD (Solid State Drive), flash memory, etc.

[0040] Energy information acquired during past production is recorded in the energy information storage unit 640. In this embodiment, carbon dioxide emissions are recorded in the energy information storage unit 640 as part of a database corresponding to product information, production line information, and product identification information. Product identification information refers to, for example, a serial number assigned to each product. Energy information such as electricity consumption may also be recorded in the energy information storage unit 640 along with or instead of carbon dioxide emissions. Acquired product information D1 is recorded in the product information storage unit 642, and acquired production line information D2 is recorded in the production line information storage unit 644.

[0041] The CO2 emission coefficient storage unit 646 stores CO2 emission coefficients used to derive CO2 emission amounts. The "CO2 emission coefficient" is the amount of carbon dioxide emitted per unit of activity, referring to the amount of carbon dioxide emitted relative to a predetermined amount of energy consumed per unit. In this embodiment, the CO2 emission coefficient is equivalent to the amount of carbon dioxide emitted to generate 1 kWh of electricity, and its unit is, for example, g / kWh. In this embodiment, the emission coefficient is based on laws related to the promotion of global warming countermeasures (the Climate Control Law), and uses emission coefficients published by the Ministry of the Environment and the Ministry of Economy, Trade and Industry for each electricity operator, and is pre-stored in the CO2 emission coefficient storage unit 646. However, the CO2 emission coefficient is not limited to being preset to a fixed value; it can also be updated sequentially via a wide area network such as the Internet. With this configuration, the CO2 emission amount can be derived using the latest CO2 emission coefficient.

[0042] CPU 62 functions as a learning model generation unit 622 and a CO2 emission estimation unit 624 by executing a program stored in storage device 64. This program enables the computer to perform the following functions: acquisition function, acquiring product information and production line information; and estimation function, estimating the energy information generated when producing a predetermined product. Learning model generation unit 622 uses a dataset for machine learning to generate a learned model. The machine learning dataset consists of energy information generated in production line Ln obtained from sensor 70, and product information D1 and production line information D2 stored in database DB. CO2 emission estimation unit 624 uses the learned model to estimate the amount of carbon dioxide emitted when producing a predetermined product.

[0043] Figure 3 This is a flowchart illustrating the energy information estimation method executed by the information processing device 60. In step S10, the learning model generation unit 622 acquires a dataset for machine learning and performs machine learning using the acquired dataset to generate a learned model. In step S20, the learned model is used to estimate the amount of carbon dioxide emissions as energy information generated in the production of any predetermined product.

[0044] Figure 4 This is a flowchart showing the details of the learning process. In step S100, a dataset for machine learning is obtained. Specifically, in step S102, the learning model generation unit 622 obtains product information D1 from the database DB of an external device via the communication unit 68. In step S104, the learning model generation unit 622 obtains production line information D2 from the database DB of an external device via the communication unit 68.

[0045] In step S106, the learning model generation unit 622 obtains the CO2 emission amount. In this embodiment, the learning model generation unit 622 obtains the power consumption of each production line Ln via the communication unit 68 through wireless communication with the sensor 70. The learning model generation unit 622 calculates the CO2 emission amount by multiplying the obtained power consumption amount by the CO2 emission coefficient stored in the CO2 emission coefficient storage unit 646. Alternatively, the CO2 emission amount can also be calculated by the sensor 70 that obtains the power consumption amount. In this case, the information processing device 60 obtains the CO2 emission amount from the sensor 70 via the communication unit 68.

[0046] In this embodiment, the learning model generation unit 622 obtains the power consumption generated per product produced from the sensor 70 and calculates the CO2 emissions generated per product produced. However, it is not limited to this; it may also obtain the total CO2 emissions generated by producing multiple products in a predetermined period, or calculate the CO2 emissions generated per product by dividing the total by the number of products produced. The learning model generation unit 622 generates a database of machine learning datasets that associates the obtained product information D1, production line information D2, CO2 emissions, and product serial numbers.

[0047] Figure 5 This is an illustrative diagram representing the database MD used for machine learning datasets. For example... Figure 5 As shown, in the database MD, the items of the obtained product information D1, the items of the production line information D2, as well as the CO2 emission and the product serial number are recorded in a corresponding manner.

[0048] return Figure 4 In step S110, the learning model generation unit 622 performs machine learning using the dataset for machine learning stored in the storage device 64, generating a learned learning model. In this embodiment, the learning model generation unit 622 performs supervised learning of a regression problem using product information and production line information recorded in the database MD as explanatory variables and carbon dioxide emissions as a response variable. Furthermore, explanatory variables are also referred to as input variables, independent variables, etc., and the response variable is also referred to as a dependent variable, etc. The learning model generation unit 622 may also perform machine learning using linear regression, such as the least squares method. The learning model generation unit 622 may also perform machine learning using recurrent neural networks (RNNs), general regression neural networks, or random forests, etc.

[0049] Figure 6This is a flowchart showing the details of the estimated process. Step S202 is the process of obtaining product information and production line information of the product to be produced. The CO2 emission estimation unit 624 obtains the product information D1 and production line information D2 of the product to be produced from the database DB of an external device. The product information D1 and production line information D2 of the product to be produced can also be input by the user through operation of the input unit 67. In this embodiment, multiple levels that can be selected 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.

[0050] Figure 7 This is an explanatory diagram showing how to set the items for product information D1 and production line information D2 for products scheduled for production. Figure 7 Table TB1 shown is a setting screen for calculating estimated carbon dioxide emissions, for example, displayed on display unit 66. The user can input or select items 82 and 84 as product information D1 (for products scheduled for production) and items 85 and 86 as production line information D2 (for products scheduled for production) through operation of input unit 67. Figure 7 In the example, item 84 represents the name of the material used in the planned production product. In this embodiment, materials M1 and M2 are set as candidates for the design stage of the planned production product. Similarly, item 86 represents the production conditions of process PR1 of the planned production product, and set as setting values ​​C1 and C2 as multiple levels. When all items are entered and the execution button 88 is operated, the estimated value of carbon dioxide emissions based on the learned model begins to be calculated according to the combination of the levels set for each item.

[0051] return Figure 6 In step S204, the CO2 emission estimation unit 624 inputs the product information D1 and production line information D2 of the planned production product into the learned model stored in the learning model storage unit 648. If multiple levels are set in the items of product information D1 and production line information D2, the CO2 emission estimation unit 624 inputs all combinations of the multiple levels set in each item of product information D1 and production line information D2 into the learned model.

[0052] In step S206, the CO2 emission estimation unit 624 outputs the estimated CO2 emission value obtained from the learned model to the display unit 66. In step S208, the user determines the product information D1 and the production line information D2. More specifically, if the product information D1 and the production line information D2 contain multiple levels, the user selects one level by referring to the estimated CO2 emission value obtained from the learned model.

[0053] Figure 8 This is an explanatory diagram illustrating an example of the calculated results of an estimated value for carbon dioxide emissions. Figure 8 The table TB2 shown is an example of the operation. Figure 7 The execution button 88 shown is then displayed on the display unit 66. In Table TB2, the estimated carbon dioxide emissions are represented by a combination of multiple levels set in each item of the product information D1 and production line information D2. Figure 8 In the example, Figure 7 For each of the four combinations of materials M1 and M2 in item 84 and setting values ​​C1 and C2 in item 86, an estimated value for carbon dioxide emissions is shown. With this configuration, when a user is designing a product and has multiple levels as candidates in the various items of product information D1 and production line information D2, they can refer to the estimated value of CO2 emissions for each combination. Therefore, the user can set the various items of product information D1 and production line information D2 for the product to be manufactured based on the estimated CO2 emissions.

[0054] As explained above, the program stored in the information processing apparatus 60 of this embodiment enables the computer to perform the following functions: an acquisition function, which acquires product information D1 that can be set during the design phase of product WK; and an estimation function, which estimates the amount of carbon dioxide emissions generated when producing the predetermined product by inputting the product information D1 of the predetermined product into the learned model. According to the program of this embodiment, the amount of carbon dioxide emissions can be estimated using the product information D1 of the predetermined product. Therefore, the amount of carbon dioxide emissions can be estimated during the design phase of the predetermined product, and product design that takes carbon dioxide emissions into account is possible.

[0055] The program stored in the information processing apparatus 60 of this embodiment includes a function to acquire carbon dioxide emissions as energy information, enabling the computer to perform a learning function. This learning function uses a dataset containing a combination of the acquired product information D1 and the carbon dioxide emissions to train the learning model. According to the program of this embodiment, the learning model can be trained using the dataset acquired when estimating carbon dioxide emissions. Therefore, whenever the carbon dioxide emissions are estimated using a dataset of predetermined production products, training the learning model can improve the accuracy of carbon dioxide emission estimation.

[0056] According to the program stored in the information processing device 60 of this embodiment, the model is trained using the carbon dioxide emissions generated for each product produced. According to the program of this embodiment, the accuracy of carbon dioxide emission estimation can be improved compared to obtaining the total amount of carbon dioxide emissions generated in a predetermined period.

[0057] As an acquisition function, the program stored in the information processing device 60 of this embodiment also enables the computer to acquire production line information D2. Production line information D2 can be set during the design stage of product WK and includes the production conditions set in production line Ln for producing product WK. According to the program of this embodiment, by increasing the number of data points used in estimating carbon dioxide emissions, the accuracy of carbon dioxide emission estimation can be improved.

[0058] The program stored in the information processing device 60 of this embodiment includes production conditions, job type, location of production line Ln, number of machines in production line Ln, processing time of product WK by production line Ln, mold information related to the mold used in processing product WK, and design information including the design value of product WK before processing by production line Ln in the production line information D2. According to the program of this embodiment, by setting statistically significant factors for carbon dioxide emissions in the items of production line information D2, the estimation accuracy of carbon dioxide emissions using production line information D2 can be improved.

[0059] The program stored in the information processing device 60 of this embodiment includes material information such as the material name and material of product WK, the dimensions of product WK, the weight of product WK, and the allowable tolerances for the dimensions and weight of product WK in product information D1. According to the program of this embodiment, by setting statistically significant factors for carbon dioxide emissions in the items of product information D1, the accuracy of estimating carbon dioxide emissions using product information D1 can be improved.

[0060] B. Other implementation methods: (B1) In the first embodiment described above, an example is shown where multiple levels that can be selected by the user are set in each item of product information D1 and production line information D2. In contrast, a single level can also be set in each item of product information D1 and production line information D2. Even in this way, an estimated value of carbon dioxide emissions can be output using a single level set in each item of product information D1 and production line information D2.

[0061] (B2) In the first embodiment described above, an example is shown where the user selects a single level when multiple levels are included in the items of product information D1 and production line information D2. In contrast, the level for each item in product information D1 and production line information D2 can also be selected, for example, as a combination of levels for each item in product information D1 and production line information D2 with the lowest carbon dioxide emissions, and the information processing device 60 determines this according to preset conditions. In this case, the [missing information] can be omitted. Figure 8 The generation of Table TB2 is shown.

[0062] (B3) In the first embodiment described above, an example is shown of using information from both product information D1 and production line information D2 to calculate an estimated value of carbon dioxide emissions. In contrast, for example, if sufficient accuracy in estimating carbon dioxide emissions can be obtained using only product information D1, the learning model generation unit 622 and the CO2 emission estimation unit 624 may not need to obtain production line information D2.

[0063] (B4) In the first embodiment described above, an example of the information processing device 60 estimating carbon dioxide emissions as energy information is shown. In contrast, the information processing device 60 can also estimate the emissions of greenhouse gases other than carbon dioxide, such as methane (CH4). Furthermore, the information processing device 60 can also estimate energy consumption, such as electricity consumption, instead of carbon dioxide emissions or together with them. For example, the information processing device 60 can learn the relationship between product information D1 and production line information D2 and energy consumption, and use the product information D1 and production line information D2 of a predetermined product to estimate energy consumption. Alternatively, the estimated value of carbon dioxide emissions can be obtained by multiplying the obtained estimated value of energy consumption by a CO2 emission coefficient. Furthermore, the information processing device 60 can estimate both energy consumption and greenhouse gas emissions.

[0064] (B5) In the first embodiment described above, an example of an energy information estimation method having a learning step is shown. In contrast, if 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 performed.

[0065] The control unit and methods described in this disclosure can also be implemented by a dedicated computer, which is provided by comprising a processor and memory programmed to perform one or more functions implemented by a computer program. Alternatively, the control unit and methods described in this disclosure can also be implemented by a dedicated computer, which is provided by comprising a processor composed of one or more dedicated hardware logic circuits. Alternatively, the control unit and methods described in this disclosure can also be implemented by one or more dedicated computers, which are composed of a combination of a processor and memory programmed to perform one or more functions and a processor composed of one or more hardware logic circuits. Furthermore, the computer program can also be stored as instructions executable by the computer on a computer-readable non-transitional tangible recording medium.

[0066] This disclosure is not limited to the embodiments described above, and can be implemented through various configurations without departing from its spirit. For example, the technical features in the embodiments corresponding to the technical features described in the Summary of the Invention section can be appropriately replaced or combined to solve some or all of the above problems or to achieve some or all of the above effects. In addition, if a technical feature is not required to be described in this specification, it can be appropriately deleted.

[0067] Label Explanation

[0068] 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…Execute 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 product, wherein, The program product enables the computer to perform the following functions: The function retrieves product information containing design values ​​related to the product's specifications that can be set during the product design phase; and The estimation function estimates energy information generated in the production of a predetermined product by inputting product information of that product into a learning model trained on a dataset. The dataset contains a combination of the energy information and the product information, wherein the energy information includes at least one of energy consumption from the production of the product and greenhouse gas emissions. The acquisition function also includes the ability to acquire production line information, which can be set during the product design phase and includes production conditions set in the production line for producing the product. The estimation function includes the following function: by inputting product information of the predetermined product and production line information for producing the predetermined product into the learning model learned using a dataset containing a combination of the production line information, the product information, and the energy information, the estimation function estimates the energy information generated in the production of the predetermined product. The design values ​​included in the product information and the production conditions included in the production line information each include multiple levels that can be selected by the user. The estimation function estimates the energy information according to each of the multiple levels, and displays the estimated energy information on the display unit according to each of the multiple levels.

2. The program product according to claim 1, wherein, The acquisition function also includes the function of acquiring the energy information. The program product enables the computer to perform a learning function, which uses a dataset containing a combination of the energy information and the product information obtained by the acquisition function to enable the learning model to learn.

3. The program product according to claim 1, wherein, The learning model is trained using a dataset containing a combination of energy information generated for each product produced and product information.

4. The program product according to claim 1, wherein, The production line information also includes at least one of the following: job type, location of the production line, number of equipment in the production line, processing time of the product by the production line, mold information related to the mold used in the processing of the product, and design information. The job type indicates whether the processing of the product by the production line includes manual operations, and the design information includes the design values ​​of the product before it is processed by the production line.

5. The program product according to claim 1, wherein, The product information includes at least one of the following: material information, product dimensions, product weight, and allowable tolerances for the product dimensions and weight. The material information includes the material name and material composition of the product.

6. The program product according to claim 1, wherein, The program product also enables the computer to select the combination of levels from the plurality of levels that have the lowest estimated energy information.

7. An information processing apparatus, wherein, The information processing device includes: The acquisition department acquires product information that can be set during the product design phase, including design values ​​related to the product's specifications; and The estimation unit estimates energy information generated during the production of the predetermined product by inputting product information of the predetermined product into a learning model that has been trained using a dataset. The dataset contains a combination of the energy information and the product information, wherein the energy information includes at least one of energy consumption and greenhouse gas emissions generated by the production of the product. The acquiring unit also acquires production line information, which can be set during the product design phase and includes production conditions set in the production line for producing the product. The estimation unit estimates the energy information generated during the production of the predetermined product by inputting the product information of the predetermined product and the production line information for producing the predetermined product into the learning model, which is learned using a dataset containing a combination of the production line information, the product information, and the energy information. The design values ​​included in the product information and the production conditions included in the production line information each include multiple levels that can be selected by the user. The estimation unit estimates the energy information according to each combination of the plurality of levels, and displays the estimated energy information on the display unit according to each combination of the plurality of levels.

8. A method for estimating energy information, wherein, The energy information estimation method includes the following steps: The acquisition process involves acquiring product information that can be set during the product design phase, including design values ​​related to the product's specifications; and The estimation process involves inputting product information of a predetermined product to a learning model that has been trained using a dataset to estimate the energy information generated during the production of the predetermined product. The dataset contains a combination of the energy information and the product information, wherein the energy information includes at least one of energy consumption and greenhouse gas emissions from the production of the product. In the acquisition process, production line information is also acquired. This production line information can be set during the product design phase and includes the production conditions set in the production line for producing the product. In the estimation process, the energy information generated during the production of the predetermined product is estimated by inputting the product information of the predetermined product and the production line information for producing the predetermined product into the learning model, which is learned using a dataset containing a combination of the production line information, the product information, and the energy information. The design values ​​included in the product information and the production conditions included in the production line information each include multiple levels that can be selected by the user. In the estimation process, the energy information is estimated according to each combination of the plurality of levels, and the estimated energy information is displayed on the display unit according to each combination of the plurality of levels.

Images