Information processing device and information processing method

Abstract

To accurately calculate a greenhouse gas emission coefficient and an emission amount without causing trouble to a user. [Solution] The information processing device comprises a classification unit that classifies each of multiple accounting data into classification items including at least one of major classification, medium classification, or summary, a data conversion unit that converts the classified classification items into input data for a machine learning model, an inference unit that inputs the input data to a trained machine learning model and acquires greenhouse gas emission-related information inferred by the machine learning model, a master selection unit that selects master data corresponding to the emission-related information acquired by the inference unit from multiple master data each including greenhouse gas emission coefficients in the global supply chain, a search unit that searches for an emission coefficient corresponding to the emission-related information acquired by the inference unit from the master data selected by the master selection unit, and a calculation unit that calculates the greenhouse gas emission amount based on the searched emission coefficient.

Description

[Technical field]

[0001] The present disclosure relates to an information processing device and an information processing method. [Background technology]

[0002] As efforts to reduce greenhouse gases (GHG) such as carbon dioxide accelerate, many businesses are being asked to operate in an environmentally conscious manner. In order to manage a business's activities as a whole, it is important to account for greenhouse gas emissions associated with activities in the business's supply chain, not just products. To calculate greenhouse gas emissions, it is necessary to understand the emission coefficient for each individual activity. The emission coefficient is also called the emission unit.

[0003] A technology has been disclosed that derives greenhouse gas emissions for each of multiple scopes and categories based on activity information indicating the activity content and the activity amount of the activity content, and ratio identification information for identifying the ratio of multiple scopes and categories within which greenhouse gas emissions are calculated (see Patent Document 1).

[0004] In addition, a technology has been disclosed that selects the optimal emission unit format for new activity data from among existing emission unit formats, taking into consideration the user's industry and the type of application from which the activity data was created (see Patent Document 2). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7369984 [Patent Document 2] Patent No. 7132580 Summary of the Invention [Problem to be solved by the invention]

[0006] In the case of Patent Document 1, the task of specifying the ratios for allocating activity details and amounts of activity to multiple scopes and categories is time-consuming, and since there is no guarantee that the specified ratios are correct, there is a risk that greenhouse gas emissions cannot be predicted with high accuracy. In addition, in the case of Patent Document 2, the user must create an existing emission intensity unit format by himself / herself, which requires a lot of work for the user. Also, there is a risk that an inappropriate emission intensity unit format will be created due to a user's input error, etc., and there is no guarantee that the emission coefficient (emission intensity) can be calculated correctly.

[0007] Therefore, the present disclosure provides an information processing device and an information processing method that can accurately calculate the emission coefficient and emission amount of greenhouse gases without causing any trouble to the user. [Means for solving the problem]

[0008] In order to solve the above problems, according to the present disclosure, a classification unit classifies each of a plurality of accounting data into classification items including at least one of a major classification, a medium classification, or a summary; a data conversion unit that converts the classification items classified by the classification unit into input data for a machine learning model; an inference unit that inputs the input data into the trained machine learning model and acquires greenhouse gas emission-related information inferred by the machine learning model; a master selection unit that selects master data corresponding to the emission-related information acquired by the inference unit from among a plurality of master data each including an emission coefficient of greenhouse gas in a global supply chain; a search unit that searches the master data selected by the master selection unit for an emission coefficient corresponding to the emission-related information acquired by the inference unit; There is provided an information processing device including: a calculation unit that calculates the greenhouse gas emission amount based on the emission coefficient searched for by the search unit. [Brief description of the drawings]

[0009] [Figure 1]FIG. 1 is a block diagram showing a schematic configuration of an information processing apparatus according to an embodiment. [Diagram 2] A diagram explaining greenhouse gas emissions in the supply chain. [Diagram 3] FIG. 4 is a diagram showing a data configuration of first master data. [Figure 4] FIG. 13 is a diagram showing a data configuration of second master data. [Diagram 5] FIG. 13 is a diagram showing a data configuration of third master data. [Figure 6] FIG. 13 is a diagram showing a data configuration of fourth master data. [Figure 7] FIG. 13 is a diagram showing the data configuration of fifth master data. [Figure 8] FIG. 13 is a diagram showing the data configuration of sixth master data. [Figure 9] FIG. 13 is a diagram showing the data configuration of the seventh master data. [Figure 10] 1 is a flowchart showing a processing operation of an information processing device according to an embodiment. [Figure 11] FIG. 13 is a diagram showing an example of a list. [Figure 12] FIG. 13 is a diagram showing an example of part-of-speech analysis. [Figure 13] FIG. 13 is a diagram showing an example of a stop word. [Figure 14] 11 is a flowchart showing details of the processing operations in steps S6 and S7 of FIG. 10. [Figure 15] FIG. 11 is a diagram showing an example of additional emission coefficient data generated in step S11 of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of an information processing device and an information processing method will be described with reference to the drawings. The following description will focus on the main components of the information processing device, but the information processing device may include components and functions that are not shown or described. The following description does not exclude components and functions that are not shown or described.

[0011] FIG. 1 is a block diagram showing a schematic configuration of an information processing device 1 according to an embodiment. The processing of the information processing device 1 according to an embodiment is executed by, for example, a computer. In this case, the block diagram shown in FIG. 1 is a functional block diagram of the processing executed by the computer. Alternatively, the information processing device 1 according to an embodiment can be configured by a semiconductor chip or a discrete circuit. In this case, each block shown in FIG. 1 is configured by a hardware circuit built into the semiconductor chip or discrete circuit.

[0012] As shown in FIG. 1, an information processing device 1 according to an embodiment includes a classification unit 2, a data conversion unit 3, an inference unit 4, a master selection unit 5, a search unit 6, and a calculation unit .

[0013] The classification unit 2 classifies each of the multiple accounting data into classification items including at least one of major classification, medium classification, or summary. Classification items are items that represent the characteristics of accounting data. Accounting data is data related to the flow of money resulting from the activities of a business operator. Accounting data includes information such as the fiscal year, date, business name, aggregation unit, activity content, activity amount, and unit. Activity amount includes, for example, monetary amount or physical quantity. The unit is the unit of activity amount.

[0014] The process in which the classification unit 2 classifies accounting data into classification items may be a process performed manually by an operator, or may be an automated process using a computer or the like. The abstracts included in the classification items are accounting items that more specifically represent the accounting items of the medium classification. The medium classifications are accounting items that more specifically represent the accounting items of the large classification. In other words, the accounting items of the abstracts are included in the accounting items of the medium classification, and the accounting items of the medium classifications are included in the accounting items of the large classification.

[0015] There are cases where accounting data is classified into classification items that include the three components of major divisions, major divisions, and summaries, and cases where accounting data is classified into classification items that do not include any one or more of major divisions, major divisions, or summaries. Also, depending on the accounting data, there are cases where it is classified into classification items other than major divisions, major divisions, and summaries.

[0016] The data conversion unit 3 converts the classification items classified by the classification unit 2 into input data for a machine learning model. The machine learning model is, for example, a deep learning model derived from the BERT (Bidirectional Encoder Representations from Transformers) model, and is a model specialized for natural language processing of Japanese. The detailed processing operation of the data conversion unit 3 will be described later.

[0017] The inference unit 4 inputs the input data converted by the data conversion unit 3 into the trained machine learning model, performs inference in the machine learning model, and obtains greenhouse gas emission-related information that is the inference result output from the machine learning model. In this specification, the emission-related information may be referred to as linking content. As described later, the linking content is linked to the emission coefficient in the master data.

[0018] The master selection unit 5 selects master data corresponding to the emission-related information (linking content) acquired by the inference unit 4 from among a plurality of master data each including an emission coefficient of greenhouse gas in a global supply chain. Each master data is data including a correspondence between the emission-related information (linking content) and an emission coefficient. The plurality of master data are generated based on various databases including emission coefficients provided by, for example, the National Institute for Environmental Studies, the Ministry of the Environment, the Tokyo Metropolitan Government Bureau of Environment, or the National Institute of Advanced Industrial Science and Technology. Specific contents of the master data will be described later.

[0019] The search unit 6 searches the master data selected by the master selection unit 5 for an emission coefficient that corresponds to the emission-related information (linking details) acquired by the inference unit 4.

[0020] The calculation unit 7 calculates the greenhouse gas emission amount based on the emission coefficient searched by the search unit 6. More specifically, the calculation unit 7 calculates the emission amount by multiplying the emission coefficient searched by the search unit 6 by the corresponding activity amount for each of the multiple accounting data.

[0021] 1, an information processing device 1 according to an embodiment may include an additional information generating unit 8. The additional information generating unit 8 generates, for each of a plurality of accounting data, emission coefficient additional data including a classification item, information on the master data selected by the master selecting unit 5, and an emission coefficient searched by the searching unit 6. Specific examples of the emission coefficient additional data will be described later.

[0022] Figure 2 explains greenhouse gas emissions in a supply chain. A supply chain refers to a series of activities carried out by a business operator, such as raw material procurement, manufacturing, logistics, sales, and disposal. In this specification, greenhouse gas emissions generated in the supply chain are referred to as supply chain emissions.

[0023] Supply chain emissions are classified into Scope 1, Scope 2, and Scope 3. Greenhouse gas emissions from upstream and downstream supply chains are Scope 3, while greenhouse gas emissions by businesses themselves are Scope 1 and Scope 2.

[0024] Scope 1 is the direct greenhouse gas emissions by the business itself. Scope 2 is the indirect greenhouse gas emissions associated with the use of electricity, heat, and steam supplied by other companies. Scope 3 is the indirect greenhouse gas emissions other than Scope 1 and Scope 2, and is the greenhouse gas emissions by other businesses related to the business's activities.

[0025] Scope 3 is divided into 15 categories and any number of other categories. The other categories are unique to the basic guidelines of the Ministry of the Environment and the Ministry of Economy, Trade and Industry. The 15 categories are consistent with the Scope 3 standards of the GHG Protocol. The greenhouse gases covered are carbon dioxide (CO2), methane (CH4), nitrous oxide (N2O), hydrofluorocarbons (HFCs), perfluorocarbons (PFCs), sulfur hexafluoride (SF6), and nitrogen trifluoride (NF3). In this specification, the CO2 equivalent amount of these greenhouse gases is referred to as "CO2", and "emissions after CO2 conversion" is referred to as "emissions".

[0026] Scope 3, which is upstream of the supply chain, includes categories 1 to 8. Category 1 is emissions associated with activities up to the manufacturing of raw materials, parts, containers, and packaging. Category 2 is emissions associated with the construction or manufacturing of capital goods by the business (the company). Category 3 is emissions associated with the upstream process (excavation or refining, etc.) of procured fuel and emissions associated with the upstream process (excavation or refining of fuel used for power generation, etc.) of procured electricity. Category 4 is (1) emissions associated with logistics (transportation, loading and unloading, storage) from suppliers of products and services purchased in the reporting fiscal year to the business (the company), and (2) emissions associated with logistics services (transportation, loading and unloading, storage) other than (1) purchased in the reporting fiscal year (emissions associated with logistics at the expense of the business). Category 5 is emissions associated with the transportation and processing of waste generated by the business (the company). Category 6 is emissions associated with employee business trips. Category 7 is emissions associated with employees' travel when commuting to work. Category 8 is emissions associated with the operation of leased assets rented by a business operator (its own company) (excluding cases where these are calculated under Scope 1 and Scope 2).

[0027] Scope 3 downstream of the supply chain includes categories 9 to 15. Category 9 is emissions associated with the logistics (transportation, loading and unloading, storage, sales) of products sold by a business operator (your company) to the end consumer (limited to emissions for which the business does not bear the cost). Category 10 is emissions associated with the processing of intermediate products by business operators. Category 11 is emissions associated with the use of products by users (consumers, businesses). Category 12 is emissions associated with the disposal of products by users (consumers, businesses). Category 13 is emissions associated with the application of lease assets that a business operator (your company) owns as a rental business operator and rents to others. Category 14 is emissions from franchisees. Category 15 is emissions associated with the management of investments.

[0028] Supply chain emissions categorized into Scope 1, Scope 2, and Scope 3 are registered in a plurality of master data. The plurality of master data is data generated based on a database compiling emission intensity units (emission coefficients) published by countries or organizations. The plurality of master data includes, for example, seven master data. In this specification, the seven master data are referred to as first to seventh master data. FIGS. 3 to 9 are diagrams showing the data configurations of the first to seventh master data.

[0029] The first master data shown in FIG. 3 is an emission intensity database estimated using the GLIO (Global Link Input-Output) model provided by the National Institute for Environmental Studies. FIG. 3 is an excerpt of the first master data. The first master data has items of row ID, row code, department name, unit, and GLIO1 to GLIO5. The department name indicates, for example, the specific product name or service name purchased by the business. The department name corresponds to the emission-related information (linking content). GLIO1 is the price of the purchased product or service including shipping fee, and is the producer's selling price without wholesale and retail. GLIO2 is the price including shipping fee, and is the purchase price of the purchaser with wholesale and retail. GLIO3 is the producer's selling price without shipping fee and without wholesale. GLIO4 is the purchase price of the purchaser with wholesale and retail without shipping fee conforming to the DB[5] of the Ministry of the Environment. GLIO5 is the producer's selling price conforming to the DB[5] of the Ministry of the Environment. In this embodiment, the emission coefficients are determined in the order of priority: GLIO2→GLIO4→GLIO5.

[0030] The second master data shown in Figure 4 is data extracted from the emission factor database provided by the Ministry of the Environment for Scope 3 categories 4, 6, and 7 emission factors. Figure 4 is an excerpt of the second master data. As shown in Figure 4, the second master data has the fields of linking details, emission factor_unit, and emission factor. The second master data is generated by extracting parts of multiple other master data, as described in the source column.

[0031] The third master data shown in Fig. 5 is data including emission coefficients for each electric power supplier provided by the Ministry of the Environment. As shown in Fig. 5, the third master data has items such as a fiscal year, an emission coefficient, a unit, and a source.

[0032] The fourth master data shown in Fig. 6 is data including emission factors of the calculation, reporting, and publication system (SHK system) provided by the Ministry of the Environment. Fig. 6 is an excerpt of the fourth master data. As shown in Fig. 6, the fourth master data has the items of fiscal year, database version, sheet, linking content 2, linking content, emission factor, unit, and source.

[0033] The fifth master data shown in Fig. 7 is a list of coefficients in the Global Warming Prevention Reporting System provided by the Tokyo Metropolitan Government Bureau of Environment. As shown in Fig. 7, the fifth master data has the following items: fiscal year, linking details, emission coefficient, unit, and source.

[0034] The sixth master data shown in Fig. 8 is data including the unit calorific value of each energy type issued by the Agency for Natural Resources and Energy based on the coefficients of the inventory database IDEAv3.1 provided by the National Institute of Advanced Industrial Science and Technology, and the emission coefficient per unit price calculated based on the unit price of each energy type. The sixth master data is data on fuel emission coefficients. As shown in Fig. 8, the sixth master data has the following items: fiscal year, fuel name, IDEA product code, combustion energy_emission coefficient, combustion energy_unit, unit calorific value_high, unit calorific value_unit, fuel_average unit price, fuel_unit, emission coefficient for amount used, unit for amount used, emission coefficient for amount_t-co2eq / million yen, and data source_emission coefficient. Of these, the fuel name corresponds to the linking content.

[0035] The seventh master data shown in Figure 9 is an excerpt from the inventory database IDEAv3.1 mentioned above. As shown in Figure 9, the seventh master data includes emission factors for various items related to waterworks, cement, and general lumber. Waterworks, cement, and general lumber are linked contents.

[0036] As described above, the first to seventh master data each include the emission-related information (linking details) and the emission coefficient. Note that the multiple master data in this embodiment does not necessarily have to include all of the first to seventh master data described above, and data other than the first to seventh master data may be used as master data, but it is necessary to include the emission-related information (linking details) and the emission coefficient.

[0037] The master selection unit 5 selects master data including the emission-related information (linking contents) acquired by the inference unit 4. For example, if the linking contents are "advertising," "office supplies," "goods rental business (excluding rental automobiles)," "mobile telecommunications," "bolts, nuts, and springs," "petroleum products," "piping work accessories, powder metallurgy products, and tools," or "construction metal products," the master selection unit 5 selects the first master data (GLIO). Also, if the linking contents are, for example, "category 4_road freight transport (excluding private transport)," "category 5_waste disposal (public) ★★," "category 5_sewerage ★★," "category 6_passenger railroad," or "category 7_passenger railroad," the master selection unit 5 selects the second master data (category 4 to 6, etc.). Also, if the linking contents are, for example, "Scope 2_electricity," the master selection unit 5 selects the third master data (by electric utility). Also, if the linking contents are, for example, "Scope 2_chilled water," the master selection unit 5 selects the fourth master data (SHK system). In addition, the master selection unit 5 selects the sixth master data (fuel emission coefficient) if the linked content is, for example, "Scope1_LPG." In addition, the master selection unit 5 selects the seventh master data (IDEAv3.1) if the linked content is, for example, "tap water supply (unit m3)," "cement, 4 digits," or "general lumber, 4 digits."

[0038] 10 is a flowchart showing the processing operation of the information processing device 1 according to an embodiment. First, accounting data of a business is input (step S1). A file including multiple accounting data may be input, or each piece of accounting data may be input individually.

[0039] Next, the classification unit 2 classifies the input accounting data into classification items including at least one of major classifications, medium classifications, and summaries (step S2). For example, major classifications include utility expenses, miscellaneous expenses, commuting expenses, business trip transportation expenses, office supplies expenses, miscellaneous expenses, communication and transportation expenses, XX factory, etc. Medium classifications include utility expenses, commuting expenses, business trip expenses, XX department XX section, etc. Summary includes, for example, "XX business establishment gas bill," "xXX business establishment electricity bill," "XX business establishment water bill," etc.

[0040] Next, the data conversion unit 3 lists the classification items classified by the classification unit 2 (step S3). FIG. 11 is a diagram showing an example of listing. In listing, each text information of the major classification, the medium classification, and the summary is linked to generate one piece of text information. In the example of FIG. 11, the major classification is "Utility bills", the medium classification is "Utility bills", and the summary is "XX business establishment gas bill". In this case, by listing, one piece of text information "Utility bills, Utility bills, XX business establishment gas bill" is generated. As shown in FIG. 11, in listing, each piece of text information is separated by a comma, and one piece of text information is generated by linking multiple pieces of text information.

[0041] Next, the data conversion unit 3 performs a part-of-speech analysis of one piece of text information that has been listed (step S4 in FIG. 10). FIG. 12 is a diagram showing an example of part-of-speech analysis. In part-of-speech analysis, after morphological analysis of the text information, parts of speech are decomposed. In the example of FIG. 12, morphological analysis is performed on the text information "Water, light, electricity, electricity, electricity, XX business, gas, electricity" to generate the text information "Water, light, electricity, electricity, electricity, XX, business, gas, electricity." The text information divided by morphological analysis is called a subword.

[0042] Next, the parts of speech are broken down into text information including the parts of speech "Water / noun, Light / noun, Cost / noun, XX / noun, Business / noun, Gas / noun, Substitute / noun." In the example of Fig. 12, all the parts of speech are nouns, but depending on the text information, they may be broken down into parts of speech such as "Verb," ​​"Particle," "Auxiliary verb," ​​and "Symbol."

[0043] Next, the data conversion unit 3 removes stop words (step S5 in FIG. 10). FIG. 13 is a diagram showing an example of a stop word. A character or character string separated by a comma is a stop word. A stop word is a character or character string that is not necessary for natural language processing. Stop words included in the text information that has been subjected to part-of-speech analysis in step S4 are removed.

[0044] Next, the data conversion unit 3 tokenizes the text information (step S6 in FIG. 10). In step S6, the words that have been subjected to the morphological analysis are divided into tokens, and a token ID is assigned to each token. The token ID is identification information that identifies each token.

[0045] Next, vectorization is performed by the data conversion unit 3 (step S7 in FIG. 10). In step S7, a vector is generated in which the ID of each token is an element. By the vectorization, input data to be input to the deep learning model is generated.

[0046] Next, in the inference unit 4, the input data generated in step S7 is input into the trained deep learning model to perform inference, and the linking content, which is the discharge-related information output from the deep learning model, is obtained (step S8 in Figure 10).

[0047] Next, the master selection unit 5 selects the master data corresponding to the linking details acquired in step S8 from the first to seventh master data (step S9 in FIG. 10).

[0048] Next, the search unit 6 searches the master data selected by the master selection unit 5 for an emission coefficient that corresponds to the linked content (step S10 in FIG. 10).

[0049] Next, the additional information generating unit 8 generates emission coefficient additional data including the classification items, information on the master data selected by the master selecting unit 5, and the emission coefficients searched by the searching unit 6 (step S11 in FIG. 10).

[0050] Next, the calculation unit 7 converts the units (step S12 in FIG. 10). Here, for example, the units are set to tCO2 / million yen.

[0051] Next, the input value included in the emission coefficient additional data is multiplied by the emission coefficient to calculate the CO2 emission amount (Step S13 in FIG. 10). The input value represents the amount of activity that represents the monetary amount or physical amount of the corresponding classification item.

[0052] Fig. 14 is a flow chart showing the details of the processing operations in steps S6 and S7 in Fig. 10. First, the input data divided into words by morphological analysis is divided into subwords, which are units smaller than words (step S21). For example, WordPiece is used for the processing in step S21. Each subword is called a token.

[0053] Next, special tokens are inserted at the beginning and end of the token (step S22). The special tokens inserted at the beginning and end of the token are called CLS and SEP, respectively.

[0054] Next, each of the multiple tokens is converted into an ID (hereinafter referred to as a token ID), and padding is generated to unify the length of the batch processing for processing multiple tokens together (step S23). A vector is generated by the multiple token IDs and padding.

[0055] Next, an attention mask is generated to distinguish between multiple token IDs and padding included in the vector (step S24). The vectorized input data including the multiple token IDs and the attention mask is input to the machine learning model (step S25).

[0056] Figure 15 is a diagram showing an example of emission coefficient-added data generated in step S11 of Figure 10. The emission coefficient-added data of Figure 15 includes items such as fiscal year, company name, aggregation unit, major category, medium category, summary, input value, unit, linking content, emission coefficient, and emission coefficient unit. The fiscal year, company name, aggregation unit, input value, and unit included in the emission coefficient-added data of Figure 15 are accounting data entered in step S1 of Figure 10. The major category, medium category, and summary of Figure 15 are classification items into which the accounting data is classified in step S2 of Figure 10.

[0057] Each line of the emission factor added data is a different accounting data. The amount of CO2 emissions can be calculated by multiplying the input value of each line by the emission factor.

[0058] In this manner, in this embodiment, accounting data is classified into classification items consisting of major classifications, medium classifications, and summaries, master data that matches the classification items is selected, linking details and emission coefficients corresponding to the classification items are selected from the selected master data, and greenhouse gas emissions are calculated from the selected emission coefficients. Also, emission coefficient-added data is generated that includes the accounting data, classification items, and the selected linking details and emission coefficients. This allows greenhouse gas emissions corresponding to the accounting data to be calculated easily and accurately.

[0059] At least a part of the information processing device described in the above embodiment may be configured with hardware or software. When configured with software, a program that realizes at least a part of the functions of the information processing device may be stored in a recording medium such as a flexible disk or an optical disk, and may be read and executed by a computer. The recording medium is not limited to a removable one such as a magnetic disk or an optical disk, but may be a fixed recording medium such as a hard disk device or a memory.

[0060] In addition, a program that realizes at least a part of the functions of an information processing device may be distributed via a communication line (including wireless communication) such as the Internet. Furthermore, the program may be encrypted, modulated, or compressed and distributed via a wired line or wireless line such as the Internet, or stored on a recording medium.

[0061] The aspects of the present invention are not limited to the above-mentioned individual embodiments, but include various modifications that may be conceived by a person skilled in the art, and the effects of the present invention are not limited to the above-mentioned contents. In other words, various additions, modifications, and partial deletions are possible within the scope of the conceptual idea and intent of the present invention derived from the contents defined in the claims and their equivalents.

[0062] [Note] [Item 1] A classification unit that classifies each of the plurality of accounting data into classification items including at least one of a major classification, a medium classification, or a summary; a data conversion unit that converts the classification items classified by the classification unit into input data for a machine learning model; an inference unit that inputs the input data into the trained machine learning model and acquires greenhouse gas emission-related information inferred by the machine learning model; a master selection unit that selects master data corresponding to the emission-related information acquired by the inference unit from among a plurality of master data each including an emission coefficient of greenhouse gas in a global supply chain; a search unit that searches the master data selected by the master selection unit for an emission coefficient corresponding to the emission-related information acquired by the inference unit; A calculation unit that calculates the greenhouse gas emission amount based on the emission coefficient searched by the search unit. Information processing device. [Item 2] The plurality of master data are generated based on a database including the emission coefficients provided by at least one of the National Institute for Environmental Studies, the Ministry of the Environment, the Tokyo Metropolitan Government Bureau of Environment, and the National Institute of Advanced Industrial Science and Technology. Item 1. An information processing device according to item 1. [Item 3] and an additional information generating unit configured to generate, for each of the plurality of accounting data, emission coefficient additional data including the classification item, information on the master data selected by the master selection unit, and the emission coefficient searched for by the search unit. 3. The information processing device according to item 1 or 2. [Item 4] The summary included in the classification item is an accounting subject that more specifically represents the accounting subject of the medium classification, The medium classifications included in the classification items are accounting subjects that more specifically represent the large classifications. 4. The information processing device according to any one of items 1 to 3. [Item 5] the data conversion unit sequentially performs a listing and a part-of-speech analysis of text information included in each classification item classified by the classification unit, converts the text information into a plurality of tokens, and generates the input data based on a vector having identification information of each of the plurality of tokens as an element. 5. An information processing device according to any one of items 1 to 4. [Item 6] When performing the part-of-speech analysis, the data conversion unit performs a morphological analysis on the listed text information and then performs part-of-speech analysis. Item 5. An information processing device according to item 5. [Item 7] the data conversion unit, after performing the part-of-speech analysis, removes words that are unnecessary for conversion into the tokens from the text information; Item 7. The information processing device according to item 5 or 6. [Item 8] Each of the plurality of accounting data includes an activity amount that indicates an amount or a quantity of the corresponding classification item, The calculation unit calculates the emission amount by multiplying the emission coefficient searched for by the search unit by the corresponding activity amount for each of the plurality of accounting data. 8. An information processing device according to any one of items 1 to 7. [Item 9] The machine learning model is a deep learning model derived from the BERT (Bidirectional Encoder Representations from Transformers) model. 9. An information processing device according to any one of items 1 to 8. [Item 10] The plurality of master data includes emission factors in Scope 1, Scope 2, and Scope 3 in the supply chain, 10. An information processing device according to any one of items 1 to 9. [Item 11] The computer A step of classifying each of the plurality of accounting data into classification items including at least one of a major classification, a medium classification, or a summary; converting the classified items into input data for a machine learning model; inputting the input data into the trained machine learning model to obtain greenhouse gas emission-related information inferred by the machine learning model; selecting master data corresponding to the acquired emission-related information from among a plurality of master data each including an emission factor of greenhouse gas in a global supply chain; searching for an emission coefficient corresponding to the acquired emission-related information from the selected master data; and calculating the amount of greenhouse gas emissions based on the retrieved emission coefficient. Information processing methods.

[0063] The aspects of the present disclosure are not limited to the above-mentioned individual embodiments, but include various modifications that may be conceived by a person skilled in the art, and the effects of the present disclosure are not limited to the above-mentioned contents. In other words, various additions, modifications, and partial deletions are possible within the scope of the conceptual idea and intent of the present disclosure derived from the contents defined in the claims and their equivalents. [Explanation of symbols]

[0064] Reference Signs List 1 Information processing device, 2 Classification unit, 3 Data conversion unit, 4 Inference unit, 5 Master selection unit, 6 Search unit, 7 Calculation unit, 8 Additional information generation unit

Claims

1. A classification unit that classifies each of the plurality of accounting data into classification items including at least one of a major classification, a medium classification, or a summary; a data conversion unit that converts the classification items classified by the classification unit into input data for a machine learning model; an inference unit that inputs the input data into the trained machine learning model and acquires emission-related information linked to the greenhouse gas emission coefficient inferred by the machine learning model; a master selection unit that selects master data including the emission-related information acquired by the inference unit from a plurality of master data each including a correspondence relationship between an emission coefficient of greenhouse gas in a global supply chain and the emission-related information; a search unit that searches the master data selected by the master selection unit for an emission coefficient corresponding to the emission-related information acquired by the inference unit; A calculation unit that calculates the greenhouse gas emission amount based on the emission coefficient searched by the search unit. Information processing device.

2. The plurality of master data are generated based on a database including the emission coefficients provided by at least one of the National Institute for Environmental Studies, the Ministry of the Environment, the Tokyo Metropolitan Government Bureau of Environment, and the National Institute of Advanced Industrial Science and Technology. The information processing device according to claim 1 .

3. and an additional information generating unit configured to generate, for each of the plurality of accounting data, emission coefficient additional data including the classification item, information on the master data selected by the master selection unit, and the emission coefficient searched for by the search unit. The information processing device according to claim 1 .

4. The summary included in the classification item is an accounting subject that more specifically represents the accounting subject of the medium classification, The medium classifications included in the classification items are accounting subjects that more specifically represent the large classifications. The information processing device according to claim 1 .

5. the data conversion unit sequentially performs a listing and a part-of-speech analysis of text information included in each classification item classified by the classification unit, converts the text information into a plurality of tokens, and generates the input data based on a vector having identification information of each of the plurality of tokens as an element. The information processing device according to claim 1 .

6. When performing the part-of-speech analysis, the data conversion unit performs a morphological analysis on the listed text information and then performs part-of-speech analysis. The information processing device according to claim 5 .

7. the data conversion unit, after performing the part-of-speech analysis, removes words that are unnecessary for conversion into the tokens from the text information; The information processing device according to claim 5 .

8. Each of the plurality of accounting data includes an activity amount that indicates an amount or a quantity of the corresponding classification item, The calculation unit calculates the emission amount by multiplying the emission coefficient searched by the search unit by the corresponding activity amount for each of the plurality of accounting data. The information processing device according to claim 1 .

9. The machine learning model is a deep learning model derived from the Bidirectional Encoder Representations from Transformers (BERT) model. The information processing device according to claim 1 .

10. The plurality of master data includes emission factors in Scope 1, Scope 2, and Scope 3 in the supply chain, The information processing device according to claim 1 .

11. The computer A step of classifying each of the plurality of accounting data into classification items including at least one of a major classification, a medium classification, or a summary; converting the classified items into input data for a machine learning model; inputting the input data into the trained machine learning model to obtain emission-related information associated with the greenhouse gas emission coefficient inferred by the machine learning model; selecting master data including the acquired emission-related information from among a plurality of master data each including a correspondence relationship between an emission coefficient of greenhouse gas in a global supply chain and the emission-related information; searching for an emission coefficient corresponding to the acquired emission-related information from the selected master data; and calculating the amount of greenhouse gas emissions based on the retrieved emission coefficient. Information processing methods.

Images