Financial due diligence document preparation support device, financial due diligence document preparation support method, and financial due diligence document preparation support program

Abstract

The objective is to provide a financial due diligence document preparation support device for efficiently creating financial due diligence documents. [Solution] The financial due diligence document creation support system acquires financial report information containing information on the target company's financial statements for each of multiple fiscal years, extracts text from each of the multiple financial reports, extracts item information indicating items including multiple accounts and total items, and amount information indicating the amount corresponding to each item, and generates financial statements that include information on the trend of amounts in each account and total item based on the item information and amount information. The financial due diligence document creation support system acquires response information indicating interviews with the target company's management or answers to questions, and generates a summary of the answers using a pre-trained model that has been trained by machine learning to summarize and output the input text.

Description

Technical Field

[0001] The present invention relates to a financial due diligence document creation support device, a financial due diligence document creation support method, and a financial due diligence document creation support program.

Background Art

[0002] In recent years, even in Japan, mergers and acquisitions between companies have become widely known as M&A (Merger and Acquisitions).

[0003] In order to succeed in M&A, it is necessary to conduct a detailed investigation, analysis, etc. in advance on the target company, but such investigations and analyses require a great deal of effort. In particular, in financial due diligence for investigating and analyzing a company's financial situation, it is necessary to organize a huge amount of settlement documents and the content of interviews with managers, etc., and summarize them as financial due diligence documents for relevant parties to judge whether to implement M&A.

[0004] In relation to this, for example, in order to extract information from documents, various OCR (Optical Character Recognition) technologies for analyzing an image obtained by reading a paper document with a scanner and automatically recognizing characters and numbers are known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] [[ID=?]] However, simply extracting information from paper documents using the OCR technology described above is not enough to organize the information necessary to determine whether or not to proceed with an M&A and to create financial due diligence documents.

[0007] The present invention has been made in view of the above circumstances, and aims to provide a financial due diligence document creation support device, a financial due diligence document creation support method, and a financial due diligence document creation support program for efficiently creating financial due diligence documents. [Means for solving the problem]

[0008] The above objectives will be achieved by the following means.

[0009] The financial due diligence document creation support system comprises a financial information acquisition unit, a text acquisition unit, an extraction unit, a financial statement generation unit, a response information acquisition unit, a summary generation unit, and an output unit. The financial information acquisition unit acquires financial report information, which includes information showing the financial reports of the target company for each of several fiscal years. The text acquisition unit acquires text from each of the multiple financial reports shown by the financial report information acquired by the financial information acquisition unit. The extraction unit extracts item information, which includes items containing multiple accounts and total items, and amount information, which shows the amount corresponding to each item, from the text acquired by the text acquisition unit. The financial statement generation unit generates financial statements, which include information on the trends in amounts for each account and total item, based on the item information and amount information extracted by the extraction unit. The response information acquisition unit acquires response information, which shows interviews with the management of the target company or answers to questions. The summary generation unit inputs the response information acquired by the response information acquisition unit into a trained model that has been trained to summarize and output the input text, and generates a summary. The output unit outputs the financial statements generated by the financial statement generation unit and the summary text generated by the summary generation unit together.

[0010] The financial due diligence document preparation support method is a computer-based method for preparing financial due diligence documents, and includes a financial information acquisition unit, a text acquisition unit, an extraction unit, a financial statement generation unit, a response information acquisition unit, a summary generation unit, and an output unit. The financial information acquisition step acquires financial report information that includes information showing the financial reports of the target company for each of several fiscal years. The text acquisition step acquires text from each of the multiple financial reports shown by the financial report information acquired in the financial information acquisition step. The extraction step extracts item information showing items including multiple accounts and total items, and amount information showing the amounts corresponding to each item, from the text acquired in the text acquisition step. The financial statement generation step generates financial statements that include information on the trends of amounts in each account and total item, based on the item information and amount information extracted in the extraction step. The response information acquisition step acquires response information showing interviews with the management of the target company or answers to questions. The summary generation step inputs the response information acquired in the response information acquisition step into a trained model that has been trained to machine learn and output the input text, and generates a summary text. The output step outputs the financial statements generated in the financial statement generation step and the summary generated in the summary generation step together.

[0011] The financial due diligence document preparation support program is configured to make a computer function as the financial due diligence document preparation support device described above. [Effects of the Invention]

[0012] According to the financial due diligence document creation support device of the present invention, financial report information containing information showing the financial reports of a target company for each of several fiscal years is acquired, and text is acquired from each of the multiple financial reports shown by the acquired financial report information. The financial due diligence document creation support device extracts item information showing items including multiple accounts and total items, and amount information showing the amount corresponding to each item, from the acquired text. Based on the extracted item information and amount information, the financial due diligence document creation support device generates financial statements that include information on the trend of amounts in each account and total item. The financial due diligence document creation support device acquires response information showing interviews with the management of the target company or answers to questions. The financial due diligence document creation support device inputs the acquired response information into a trained model that has been trained to summarize and output the input text, and generates a summary sentence. The financial due diligence document creation support device outputs the generated financial statements and the generated summary sentence together as financial due diligence documents. This makes it possible to efficiently create financial due diligence documents. [Brief explanation of the drawing]

[0013] [Figure 1] This figure shows a schematic configuration of a system according to one embodiment of the present invention. [Figure 2] This is a block diagram showing the general configuration of the user terminal. [Figure 3] This is a diagram showing the schematic configuration of the support device. [Figure 4] This is a diagram showing the functional configuration of the support device. [Figure 5] This flowchart shows the procedure for processing performed by the support device. [Figure 6] Figure 5 is a flowchart of the subroutine showing the procedure for the financial statement generation process, as indicated in step S104. [Figure 7] This is a conceptual diagram illustrating the processing flow performed in the support device. [Figure 8] This is a diagram for explaining the position determination process of total items executed in the support device. [Figure 9] This is a diagram for explaining the major item determination process of bad debt provisions executed in the support device. [Figure 10] This is a diagram for explaining the major item determination process of bad debt provisions executed in the support device. [Figure 11] This is a diagram for explaining the major item determination process of bad debt provisions executed in the support device. [Figure 12] This is a diagram for explaining the major item determination process of bad debt provisions executed in the support device. [Figure 13A] This is a diagram for explaining the general ledger processing of accounting items executed in the support device. [Figure 13B] This is a diagram for explaining the general ledger processing of accounting items executed in the support device. [Figure 14] This is a diagram for explaining the notation fluctuation correction process executed in the support device. [Figure 15] This is a diagram for explaining the increase / decrease output process executed in the support device. [Figure 16] This is a diagram for explaining the verification process executed in the support device. [Figure 17] This is a diagram showing an example of the financial due diligence document output by the support device. [Figure 18] This is a diagram showing an example of the financial due diligence document output by the support device.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present invention will be described with reference to the attached drawings. In the description of the drawings, the same reference numerals are assigned to the same elements, and duplicate descriptions are omitted. Also, the dimensional ratios in the drawings are exaggerated for the convenience of explanation and may be different from the actual ratios.

[0015] <System Configuration> Figure 1 is a diagram showing the schematic configuration of a system according to one embodiment of the present invention.

[0016] As shown in Figure 1, the system consists of a user terminal 100 and a support device 200, and each component is configured to communicate with each other via a network.

[0017] User terminal 100 is an information terminal such as a notebook PC, desktop PC, smartphone, or tablet PC used by the client.

[0018] The support device 200 is a server provided by the business operator that manages and operates the financial due diligence document preparation support service. The support device 200 constitutes the financial due diligence document preparation support system.

[0019] The following provides a detailed explanation of each component.

[0020] <User terminal 100> Figure 2 is a block diagram showing the schematic configuration of a user terminal.

[0021] As shown in Figure 2, the user terminal 100 includes a CPU (Central Processing Unit) 110, ROM (Read Only Memory) 120, RAM (Random Access Memory) 130, storage 140, a communication interface 150, an operation unit 160, and a display unit 170. Each component is connected to the others via a bus 180 so that they can communicate with each other.

[0022] The CPU 110 controls each of the above configurations and performs various calculations according to the programs recorded in the ROM 120 and storage 140.

[0023] ROM120 stores various programs and data.

[0024] RAM130 is used as a working area to temporarily store programs and data.

[0025] Storage 140 stores various programs, including the operating system, as well as various data.

[0026] The communication interface 150 is an interface for communicating with external devices such as the support device 200, and for example, standards such as 3G, 4G, and 5G for mobile phone communication, or Wi-Fi (registered trademark) can be used.

[0027] The operating unit 160 includes a pointing device such as a mouse and a keyboard, and is used for various types of input.

[0028] The display unit 170 is, for example, a liquid crystal display and displays various information. The display unit 170 may also function as an operation unit 160 by being configured as a touch panel display.

[0029] <Support device 200> Figure 3 is a block diagram showing the schematic configuration of the support device.

[0030] As shown in Figure 3, the support device 200 includes a CPU 210, ROM 220, RAM 230, storage 240, communication interface 250, operation unit 260, and display unit 270. Each component is connected to the others via a bus 280 so as to be able to communicate with each other. Note that the components of the CPU 210, ROM 220, RAM 230, storage 240, communication interface 250, operation unit 260, and display unit 270 have the same functions as the CPU 110, ROM 120, RAM 130, storage 140, communication interface 150, operation unit 160, and display unit 170 of the user terminal 100, so redundant explanations are omitted.

[0031] Storage 140 stores programs that enable the CPU 210 to function as a financial information acquisition unit, text acquisition unit, extraction unit, financial statement generation unit, response information acquisition unit, summary generation unit, output unit, judgment unit, identification unit, classification setting reception unit, aggregation setting unit, aggregation calculation unit, table registration unit, conversion unit, calculation unit, increase / decrease output unit, editing unit, verification unit, notification unit, and comment generation unit. Storage 140 also stores various information necessary for executing the processing performed by each of the above units.

[0032] <Functions of support device 200> Figure 4 is a block diagram showing the functional configuration of the support device.

[0033] As shown in Figure 4, the support device 200 functions as a financial information acquisition unit 2101, a text acquisition unit 2102, an extraction unit 2103, a financial statement generation unit 2104, a response information acquisition unit 2105, a summary generation unit 2106, an output unit 2107, a determination unit 2108, a specific unit 2109, a classification setting reception unit 2110, a summation setting unit 2111, a summation calculation unit 2112, a table registration unit 2113, a conversion unit 2114, a calculation unit 2115, an increase / decrease output unit 2116, an editing unit 2117, a verification unit 2118, a notification unit 2119, and a comment generation unit 2120, by having the CPU 210 read a program stored in the storage 240 and execute processing.

[0034] The financial information acquisition unit 2101 acquires financial report information that includes information showing the financial reports of the target company for each of multiple fiscal years.

[0035] The text acquisition unit 2102 acquires text from each of the multiple financial statements indicated by the financial statement information acquired by the financial information acquisition unit 2101.

[0036] The extraction unit 2103 extracts item information indicating items containing multiple account titles and total items, and amount information indicating the corresponding amounts for each item, from the text acquired by the text acquisition unit 2102. The extraction unit 2103 also extracts location information regarding the position where each item is listed in the financial statements.

[0037] The financial statement generation unit 2104 generates financial statements that include information on the trends in amounts for each account and total item, based on the item information and amount information extracted by the extraction unit 2103.

[0038] The response information acquisition unit 2105 acquires response information that shows the answers to the interview or questions given to the management of the target company. The response information acquisition unit 2105 may also acquire response information that shows the answers to the interview or questions for each account item.

[0039] The summary generation unit 2106 inputs the response information acquired by the response information acquisition unit 2105 into a trained model that has been trained to summarize and output the input text, thereby generating a summary sentence. The trained model is, for example, a large-scale language model. The summary generation unit 2106 may also generate a summary sentence for each account by inputting the response information for each account, information on the amount corresponding to the account, and pre-set instructions and rules for creating the summary sentence into the trained model.

[0040] The output unit 2107 outputs the financial statements generated by the financial statement generation unit 2104 and the summary generated by the summary generation unit 2106 together. The output unit 2107 may also output the summary generated for each account in association with each account in the financial statements.

[0041] Based on the item information and location information extracted by the extraction unit 2103, the determination unit 2108 compares the location of the accounts receivable or accounts payable account titles with the location of the total items for current assets or current liabilities to determine whether the total items are listed above or below each account title included in the total items.

[0042] The identification unit 2109 determines whether the allowance for doubtful accounts account is recorded as a current asset or a fixed asset, based on the determination result from the determination unit 2108 and the location of the account title and total item for the allowance for doubtful accounts extracted by the extraction unit 2103.

[0043] The classification setting reception unit 2110 accepts the setting of classification information indicating the classification for each account.

[0044] The aggregation setting unit 2111 sets the target account as an aggregation target if the amount of the target account is less than a predetermined percentage of the total amount of all accounts belonging to the classification set for that account.

[0045] The summing calculation unit 2112 calculates the total amount of the accounts set as targets for summation by the summing setting unit 2111, integrates each account as an "other item", and outputs it in association with the calculated total amount of the targets for summation.

[0046] The table registration unit 2113 accepts registration of mapping table information for converting the names of multiple accounts corresponding to the same account into a single unified name.

[0047] The conversion unit 2114 converts the names of each account title extracted by the extraction unit 2103 into a unified name using the mapping table information registered by the table registration unit 2113.

[0048] The calculation unit 2115 calculates the year-to-year increase or decrease in the amounts corresponding to each account and total item for each of the multiple fiscal years, based on the item information and amount information extracted by the extraction unit 2103.

[0049] The increase / decrease output unit 2116 outputs the increase / decrease value of the amount between fiscal years calculated by the calculation unit 2115.

[0050] The editing unit 2117 edits the financial statements generated by the financial statement generation unit 2104 and the summary generated by the summary generation unit 2106 so that they can be output in a predetermined format. The output unit 2107 outputs the financial statements and the summary in the predetermined format.

[0051] The verification unit 2118 determines whether the sum of the amounts corresponding to multiple account titles extracted by the extraction unit 2103 matches the amount corresponding to the total item.

[0052] The notification unit 2119 notifies the user if the verification unit 2118 determines that they do not match.

[0053] The comment generation unit 2120 generates summary comments regarding the amounts and trends in amounts for each account and total item, based on the financial statements generated by the financial statement generation unit 2104. The output unit 2107 outputs the summary comments generated by the comment generation unit 2120 along with the financial statements and summary text.

[0054] Furthermore, the user terminal 100 and the support device 200 may include components other than those described above, or may not include some of the components described above.

[0055] <Processing Overview> Figure 5 is a flowchart illustrating the procedure of processing performed in the support device. Figure 6 is a flowchart of a subroutine showing the procedure of the financial statement generation process shown in step S104 of Figure 5. Figure 7 is a conceptual diagram illustrating the flow of processing performed in the support device. Figure 8 is a diagram illustrating the position determination process of total items performed in the support device. Figures 9-12 are diagrams illustrating the major item determination process for allowance for doubtful accounts performed in the support device. Figures 13A and 13B are diagrams illustrating the account consolidation process performed in the support device. Figure 14 is a diagram illustrating the notation variation correction process performed in the support device. Figure 15 is a diagram illustrating the increase / decrease output process performed in the support device. Figure 16 is a diagram illustrating the verification process performed in the support device. Figure 17 is a diagram illustrating an example of financial due diligence materials output by the support device. Figure 18 is a diagram illustrating an example of financial due diligence materials output by the support device. The processes shown in the flowcharts of Figures 5 and 6 are stored as programs in the storage 240 of the support device 200 and are executed by the CPU 210 controlling each part.

[0056] As shown in Figure 5, the support device 200 acquires financial report information that includes information showing the financial reports of the target company for each of several fiscal years (step S101). For example, the user terminal 100 transmits PDF files or the like showing the financial reports of a certain company for each of several fiscal years to the support device 200 via the network as financial report information. Financial reports are documents created, for example, when a company performs financial closing and files tax returns with the tax office, and include the company's income statement (PL or P / L) and balance sheet (BS or B / S) for the fiscal year to be reported. As shown in Figure 7, the support device 200 acquires information showing the financial reports for multiple fiscal years. The financial report information includes text such as characters, numbers, and symbols as image data (image information). The financial report information may also include the above-mentioned text as text data (text information) instead of image data.

[0057] The support device 200 acquires text from each of the multiple financial statements indicated by the financial statement information acquired in step S101 (step S102). For example, the support device 200 can acquire various texts contained in the financial statements by performing text recognition processing on the image data contained in the financial statement information using a known method. The text recognition processing may be performed by the support device 200, or it may be performed on an external device such as a cloud server, and the support device 200 may acquire the execution result. Alternatively, if various texts are already included as text data in the financial statement information, the support device 200 can acquire various texts from the text data.

[0058] In step S102, the support device 200 extracts item information indicating items containing multiple account titles and total items, and amount information indicating the amount corresponding to each item, from the text acquired in step S102 (step S103). Specifically, the support device 200 extracts item information indicating account titles and total items, and amount information indicating the amount corresponding to each account title and each total item, from the income statement and balance sheet included in the financial report. The process of extracting the sections corresponding to the income statement and balance sheet from the financial report may be performed by the support device 200 using known text matching techniques, pattern matching techniques, etc., or may be performed by receiving instructions for the relevant sections from the user. Furthermore, the process of extracting account titles and total items, and the amounts corresponding to each account title and each total item, from the income statement and balance sheet may be performed by the support device 200 using known text matching techniques, pattern matching techniques, etc., or may be performed by receiving instructions from the user.

[0059] The support device 200 generates financial statements (step S104) that include information on the trends in amounts for each account and total item, based on the item information and amount information extracted in step S103. Details of the process for generating financial statements will be described later.

[0060] The support device 200 obtains response information indicating interviews with the management of the target company or answers to questions (step S105). Interviews include, for example, management interviews and financial and tax interviews. Management interviews are interviews conducted with the management of the target company regarding general management. Management interviews include all aspects of the target company's management, such as the status of the business, personnel situation, performance, market situation, competitor situation, risk factors in business operations, competitive strategies with competitors, business challenges, and future management plans. Financial and tax interviews are interviews conducted with the financial and tax managers of the target company regarding finance and tax. Financial and tax interviews include all aspects of the target company's finance and tax, such as sales situation, cost situation, personnel expenses, rent, advertising expenses and other selling and administrative expenses, other revenue and expense situations, various tax situations, asset situation, liability situation, net asset situation, etc. Response information indicating answers to interviews can be obtained, for example, as text data (files) created by transcribing the questions and answers from an oral interview. Alternatively, if the interview is conducted on a text basis via online text chat or email, the records of the exchanged text data can be obtained as response information to the interview. Answers to questions are in the form of Q&A, for example, questions regarding the P&L or BS included in the financial statements, and the answers from the management of the target company, etc., are recorded as a Q&A sheet in table format or bulleted list format. In the Q&A sheet, the P&L and BS accounts to which each question pertains are clearly indicated, making it easy to recognize which account each question and answer pertains to. Response information indicating answers to questions can be obtained, for example, as table data (files) showing the Q&A sheet.

[0061] The support device 200 inputs the response information obtained in step S105 into a pre-trained model that has been trained to summarize and output the input text, thereby generating a summary. The pre-trained model is, for example, a well-known Large Language Model (LLM). A Large Language Model is a machine learning model capable of handling various natural language processing tasks. As a Large Language Model, for example, ChatGPT® (Chat Generative Pre-trained Transformer) may be used. As shown in Figure 7, the support device 200 inputs the response information into the pre-trained model to generate a summary of the response information for each account included in the P&L and BS of the financial statements. Details of the summary generation process will be described later.

[0062] As shown in Figure 7, the support device 200 outputs the financial statements generated in step S104 and the summary generated in step S106 together as a single document or image (step S107). Details of the output process will be described later.

[0063] <Details of the financial statement generation process in Step S104> As shown in Figure 6, the support device 200 executes the processes in steps S1041 to S1046, which are included in the financial statement generation process in step S104.

[0064] <Location detection and major category detection processing> The support device 200 determines the location of each item described in the financial statements (PL and BS) and determines which major category a given item belongs to (step S1041).

[0065] Specifically, the support device 200 extracts location information regarding the position where each item is listed in the financial report. The location information is extracted, for example, as coordinate information based on a certain position on the image of the financial report. The location information may also be relative information indicating the positional relationship between the extracted items. As shown in Figure 8, the support device 200 compares the position of the accounts receivable or accounts payable account with the position of the total items for current assets or current liabilities based on the item information and location information extracted from the financial report. The support device 200 determines whether the total item is listed above or below each account included in that total item. As shown as (1) in Figure 8, if the position of the total items for current assets or current liabilities is above the position of the accounts receivable or accounts payable account, the support device 200 determines that the total item is listed above each account included in that total item. On the other hand, as shown in Figure 8 (2), if the position of the total item for current assets or current liabilities is lower than the position of the account for accounts receivable or accounts payable, the support device 200 determines that the format is such that the total item is written below each account included in that total item.

[0066] The support device 200 determines whether the allowance for doubtful accounts account is listed as a current asset or a fixed asset, based on the determination result regarding the location of the total items described above, and the location of the extracted allowance for doubtful accounts account and the location of the total items. For example, as in the example in Figure 9, when the total items are listed above each account, if the allowance for doubtful accounts account is located between the total items for current assets and the total items for fixed assets, it is determined that the allowance for doubtful accounts is listed as a current asset. Also, as in the example in Figure 10, when the total items are listed above each account, if the allowance for doubtful accounts account is located below both the total items for current assets and the total items for fixed assets, it is determined that the allowance for doubtful accounts is listed as a fixed asset. Furthermore, as in the example in Figure 11, when the total items are listed below each account, if the allowance for doubtful accounts is located above both the total items for current assets and the total items for fixed assets, it is determined that the allowance for doubtful accounts is listed as a current asset. Furthermore, as shown in the example in Figure 12, when the total items are listed below each individual account, if the account for allowance for doubtful accounts is located between the total items for current assets and the total items for fixed assets, then the allowance for doubtful accounts is identified as being listed as a fixed asset.

[0067] <Account consolidation processing> The support device 200 performs an account consolidation process (step S1042) in which accounts belonging to the same classification with small amounts are grouped together as "other items" and aggregated.

[0068] Specifically, the support device 200 pre-accepts and registers classification information for each account. The classification information registered may have multiple levels, such as major categories, medium categories, and minor categories, as shown in Figure 13A. The classification information set for each account, as well as the relationship between each account and each total item (such as which accounts each total item includes), as shown in Figure 13A, are pre-registered as account master information and stored in the storage 240.

[0069] The support device 200 sets the target account to be included in the aggregation if the amount of the target account is less than a predetermined percentage of the total amount of all accounts belonging to the classification set for that account. The support device 200 calculates the total amount of the aggregation target by summing the amounts of each account set to be included in the aggregation target, integrates each account as an "other item", and outputs it in association with the calculated total amount of the aggregation target. The above process will be explained using the example where the predetermined percentage is set to 5%. For example, as shown in Figure 13B, there are five accounts 1 to 5 belonging to the same major category, and the sum of the amounts of accounts 1 to 2 accounts accounts accounts 95% of the total amount of that major category, then the amounts of accounts 3 to 5 accounts will each be 5% or less of the total amount of that major category. In this case, the support device 200 sets accounts 3 to 5 accounts to be included in the aggregation target. The support device 200 then integrates account codes 3 to 5 as "other items," and the sum of the amounts for account codes 3 to 5 is output as the total amount to be aggregated, associated with the "other items."

[0070] <Integration of variations in spelling> The support device 200 converts the names of each account into unified names based on pre-registered mapping table information (step S1043).

[0071] Specifically, the support device 200 accepts registration of mapping table information for converting the names of multiple accounts corresponding to the same account into a single unified name. For example, the support device 200 accepts registration of mapping table information as shown in Figure 14. Figure 14 shows an example of mapping table information for converting the names (names) of various account titles such as cash and deposits, cash deposits, cash, ordinary deposits, deposits, and petty cash into a unified name, cash and deposits. The support device 200 converts the names of each account title extracted from the financial statements into a unified name using the mapping table information described above.

[0072] <Increase / Decrease Calculation Process> Based on the item information and amount information extracted in step S103, the support device 200 calculates and outputs the year-to-year increase or decrease in the amounts corresponding to each account and total item for each of the multiple fiscal years (step S1044). Specifically, as shown in Figure 15, the support device 200 outputs the year-to-year increase or decrease in the amounts of each account and total item based on the amounts for the multiple fiscal years. In the example in Figure 15, the increase or decrease in amounts from 2020 to 2021 and from 2021 to 2022 are calculated based on the amounts of each account and total item for 2020, 2021, and 2022. The calculated increase or decrease values ​​are output in association with each account and total item. The support device 200 generates a table as a financial statement, which includes information on the amounts and trends of amounts for each account and total item over multiple fiscal years, as shown in Figure 15.

[0073] <Verification process> The support device 200 verifies whether the extracted amounts are correct by determining whether the sum of the amounts corresponding to the multiple accounts extracted in step S103 matches the amount corresponding to the total item of the classification set for those multiple accounts (step S1045). Specifically, as shown in Figure 16, the support device 200 determines whether the sum of the amounts read for each account (amounts read and extracted from the financial statements) matches the amount read for the total item of the classification set for that account (amounts read and extracted from the financial statements). If it is determined that the amounts do not match, the support device 200 notifies the user that a discrepancy has occurred.

[0074] For example, both the accounts "Capital Reserve" and "Other Capital Surplus" have "Capital Surplus" set as the sub-item 1 classification. The account "Capital Surplus" has "Sub-item 1" set in the total range column, and "Capital Surplus" is set in the sub-item 1 column. This indicates that the account "Capital Surplus" is the sum of accounts that have "Capital Surplus" set as sub-item 1, i.e., "Capital Reserve" and "Other Capital Surplus". Here, the sum of the read amounts for "Capital Reserve" and "Other Capital Surplus" is 110,000 yen. However, the read amount for "Capital Surplus", which is the sum of "Capital Reserve" and "Other Capital Surplus", is 300,000 yen. In this case, since the sum of the amounts read for each account does not match the sum of the total items in the classification set for that account, the support device 200 notifies the user that a discrepancy has occurred through screen display, message transmission, audio alert, etc.

[0075] <Process for generating summary comments for the trend table> The support device 200 generates summary comments regarding the amounts and trends of each account and total item based on the financial statements generated as shown in Figure 15 (step S1046). The summary comments are created, for example, based on predetermined generation rules. For example, a generation rule might be, "For the three largest accounts in the most recent fiscal year, summarize their breakdown and trends." For example, for the account "Cash and Deposits," the following summary comment may be generated. The breakdown of "Cash and Deposits," such as A to C (for example, names of financial institutions), A1 to A3 (for example, account information for financial institution A), and information indicating the corresponding amounts, is obtained in advance by the support device 200 by reading and extracting the financial statements and is stored in the storage 240.

[0076] <Example of summary comments for a trend table> Cash and deposits The amount for fiscal year YY was XXX million yen, broken down as follows: A = XXX million yen, B = XXX million yen, and C = XXX million yen. The breakdown of A is as follows: A1 is XXX million yen, A2 is XXX million yen, and A3 is XXX million yen. The breakdown of B is as follows: B1 is XXX million yen, B2 is XXX million yen, and B3 is XXX million yen. The breakdown of C is as follows: C1 is XXX million yen, C2 is XXX million yen, and C3 is XXX million yen. From fiscal year YY to fiscal year ZZ, the decrease was XXX million yen, with the largest decreases occurring in A (XXX million yen), B (XXX million yen), and C (XXX million yen). The largest decreases in category B are B1 (XXX million yen), B2 (XXX million yen), and B3 (XXX million yen).

[0077] The summary comments described above are output together with the financial statements and summary text.

[0078] Once the processing in step S1046 is complete, the support device 200 finishes processing in step S104 and then executes the processing from step S105 onwards, as shown in Figure 5.

[0079] <Details of the generation process of the summary text of S106> The support device 200 can create a summary text of the response information for each accounting item, for example, by giving the following prompt to the large language model based on an instruction from the user or the like.

[0080] <Example of prompt> # Work instruction · You are a professional in M&A. · The given data is related to the financial and tax situation of a company. · Please summarize the content described for each accounting item. · The output should be the summary content (up to 3 sentences in Japanese), in JSON format (the key is the accounting item, and the value is a list of strings split by sentence). # Accounting item · Cash and deposits · Accounts receivable · Inventories # Rules · For accounting items not described in the data, output "Not described in the data". · Describe the cited data No. in parentheses at the end of the string. · Do not include facts without description. · Output in "is adjusted". · The length of the list of strings may vary depending on the accounting item.

[0081] The support device 200 can, by means of the above prompt, while requesting a summary as an expert, instruct the generation of a summary text for each accounting item. Also, the support device 200 can, by means of the above prompt, generate a summary text for each accounting item by citing the summary comment generated by the process of step S1046 in FIG. 6.

[0082] The support device 200 can combine (integrate) the summary text generated as described above and the summary comment generated by the process of step S1046 in FIG. 6 based on the following rules, and output it as a summary text for each account item.

[0083] <Example of rules for combining> · Summarize the summary text for each account item. · The order of description shall be the summary comment of the transition table, the summary text of Q&A, the summary text of the financial and tax interview, and the summary text of the management interview. · If there is no description of the corresponding account item in Q&A or the interview, write "Not described in the data".

[0084] The support device 200 can generate the following summary text for the account item "accounts receivable" by the above process.

[0085] "For the fiscal year ending December 2022, it is XXX million yen, with A being XXX million yen, B being 22 million yen, and C being 13 million yen. From the fiscal year ending December 2020 to the fiscal year ending December 2022, it has decreased by XXX million yen. The largest decreases are 571 million yen for A, 61 million yen for C, and 47 million yen for D. The balance of accounts receivable has decreased to XXX million yen in the fiscal year ending December 2021, XXX million yen in the fiscal year ending December 2022, and XXX million yen in August 2023. The reason for the decrease in accounts receivable is due to the decrease in sales, especially affected by the decline in sales due to COVID-19. The proportion of accounts receivable for individual installment payments is large, and approximately XXX billion yen is due to installment payments (arrears). Data for the past two years must be considered, and there is an accumulation of uncollectible arrears not recognized in court (arrears). For arrears with a delay of more than 3 months, a provision of 50% is made, and for those with a delay of more than 6 months, a provision of 100% is made (arrears). Not described in the data." <Details of the output process of S107> The support device 200 edits the financial statements generated by the processing in step S104 and the summary text generated by the processing in step S106 so that they can be output in a predetermined format specified in advance, and outputs them as financial due diligence materials. Specifically, as shown in Figures 17 and 18, the support device 200 displays the financial statements and summary texts side by side for easy viewing and output as financial due diligence materials. Figure 17 is a financial due diligence document showing an overview of the balance sheet (BS), and Figure 18 is a financial due diligence document showing an overview of the profit and loss statement (PL). As shown in Figures 17 and 18, the left side of the document displays the progress tables of the BS and PL, and the right side displays the summary texts generated for each account in the BS and PL, associated with each account. The support device 200 can output the financial due diligence materials on a web page so that they can be easily converted to the final output format (file format) and downloaded, while facilitating content verification and modification.

[0086] As described above, the support device 200 according to this embodiment acquires financial report information that includes information showing the financial reports of the target company for each of several fiscal years, and acquires text from each of the multiple financial reports shown by the acquired financial report information. The support device 200 extracts item information that shows items including multiple account titles and total items, and amount information that shows the amount corresponding to each item, from the acquired text. Based on the extracted item information and amount information, the support device 200 generates financial statements that include information on the trend of amounts in each account title and total item. The support device 200 acquires response information that shows interviews with the management of the target company or answers to questions. The support device 200 inputs the acquired response information into a trained model that has been trained to summarize and output the input text, and generates a summary. The support device 200 outputs the generated financial statements and the generated summary together as financial due diligence materials. This makes it possible to efficiently create financial due diligence materials. Traditionally, creating financial due diligence materials required a tremendous amount of work: reviewing each and every paper document, such as annual financial statements, to collect and organize the necessary figures, and then compiling them into financial statements. Furthermore, simply creating financial statements and organizing the figures only allowed for the understanding of facts and results such as increases and decreases in figures; it did not allow for the understanding of the factors that caused those increases and decreases. Therefore, it was necessary to conduct interviews and Q&A sessions with management and others, extract summaries from the vast amount of recorded results, and organize them together with the financial statements. With the support device 200 of this embodiment, financial due diligence materials can be created simply by inputting the financial statements for each of the multiple years and the interview or question answers, thus enabling the efficient creation of financial due diligence materials.

[0087] Furthermore, the support device 200 extracts location information regarding the position where each item is listed in the financial statements. Based on the extracted item information and location information, the support device 200 compares the position of the accounts receivable or accounts payable account with the position of the total items for current assets or current liabilities. The support device 200 determines whether the total item is listed above or below each account included in that total item. This makes it possible to reliably and easily determine whether the total items in the balance sheet (BS) and profit and loss statement (PL) are listed above or below. In financial statements, depending on the preferences of the preparer and the specifications of the accounting system, both formats exist where total items are listed above and where they are listed below. For example, the account "allowance for doubtful accounts" may belong to the total item "current assets" or to the total item "fixed assets." In this case, if it is not possible to know whether the position of the total items for each account is above or below, it becomes difficult to properly determine which total item the allowance for doubtful accounts belongs to. According to the support device 200 of this embodiment, it is possible to reliably and easily determine and understand whether the total items are listed in an upper or lower format, thereby appropriately understanding the total items to which each account belongs.

[0088] Furthermore, the support device 200 identifies whether the allowance for doubtful accounts account is recorded as a current asset or a fixed asset, based on the determination result regarding the recording location of the total items, the recording location of the allowance for doubtful accounts account, and the recording location of the total items. This ensures reliable identification of whether the allowance for doubtful accounts account is recorded as a current asset or a fixed asset, allowing for the easy creation of appropriate financial statements without requiring manual verification or instructions from the user.

[0089] Furthermore, the support device 200 accepts the setting of classification information indicating the classification for each account. If the amount of a target account is less than a predetermined percentage of the total amount of all accounts belonging to the classification set for that account, the support device 200 sets the target account as an account to be aggregated. This makes it possible to group together accounts with relatively small amounts that belong to the same classification and set them as accounts to be aggregated.

[0090] Furthermore, the support device 200 calculates the total amount of each account set as the target of aggregation by summing the amounts of each account, integrates each account as an "other item," and outputs it in association with the calculated total amount of the target of aggregation. This makes it possible to integrate accounts with relatively small amounts set as targets of aggregation as "other items" and output the total amount of the "other items." Therefore, accounts with relatively small amounts can be integrated and output as "other items," while accounts with relatively large and important amounts can be output individually, thus enabling the generation of effective financial statements that allow for easy visualization and understanding of the contents of important accounts.

[0091] Furthermore, the support device 200 accepts registration of mapping table information for converting the names of multiple accounts corresponding to the same account into a single unified name. The support device 200 converts the extracted names of each account into a unified name using the mapping table information. Often, different names are used for the same account from company to company. Moreover, even within the same company, different names may be used from year to year if the person who prepares the financial statements, the preparation method, or the preparation system changes. According to the support device 200 of this embodiment, it is possible to generate financial due diligence materials after converting accounts with the same content that are written with different names into a unified name. Therefore, financial due diligence materials can be easily generated from financial statements of multiple years for various different companies.

[0092] Furthermore, the support device 200 calculates the inter-year increase or decrease in the amounts corresponding to each account and total item for each of the multiple fiscal years based on the extracted item information and amount information, and outputs the calculated inter-year increase or decrease in amounts. This makes it possible to calculate and output inter-year increase or decrease values ​​even if only the P&L and BS for a given fiscal year are included in the financial report. This makes it easy to grasp the trends in the P&L and BS, and to easily generate financial due diligence materials that allow for a more accurate understanding of the management status of the target company.

[0093] Furthermore, the support device 200 edits the generated financial statements and the generated summary so that they can be output in a predetermined format, and outputs the financial statements and the summary in the predetermined format. For example, the support device 200 can output financial due diligence materials to a web page so that they can be easily converted to the final output format (file format) and downloaded, while making it easy to check and correct the content. Conventionally, it was necessary to create a progress table using a spreadsheet application, copy the created progress table, paste it into a page of a presentation application file to be used as financial due diligence material, and adjust the layout on the page. According to this embodiment, since the generated financial statements and the generated summary can be edited and output so that they can be output in a predetermined format, financial due diligence materials can be created efficiently.

[0094] Furthermore, the support device 200 determines whether the sum of the amounts corresponding to the extracted multiple accounts matches the amount corresponding to the total item. If it determines that they do not match, the support device 200 notifies the user. This allows for verification of the accuracy of the information extracted from the financial statements, and if the information is incorrect, the user is notified and allowed to confirm, thus enabling the creation of appropriate financial due diligence materials.

[0095] Furthermore, the support device 200 generates summary comments regarding the amounts and trends in amounts for each account and total item based on the generated financial statements, and outputs the summary comments together with the financial statements and summary text. This makes it possible to create and output comments that summarize the contents of the financial statements as text, thus enabling the creation of financial due diligence materials that are easy to understand.

[0096] Furthermore, the support device 200 acquires response information for each account, indicating the answers to the interview or questions. The support device 200 generates a summary sentence for each account by inputting the response information for each account, information on the amount corresponding to the account, and pre-set instructions and rules for creating the summary sentence into a trained model. The support device 200 outputs the summary sentence generated for each account, associated with each account in the financial statements. As a result, a summary sentence of the answers to the interview or questions can be output for each account, and a summary sentence corresponding to each account in the financial statements can be associated and output. Therefore, appropriate financial due diligence materials can be easily created.

[0097] Furthermore, the present invention is not limited to the embodiments described above, and can be modified in various ways within the scope of the claims.

[0098] For example, the user terminal 100 and the support device 200 may each be composed of multiple devices or a single device.

[0099] Furthermore, the functions of each configuration may be realized by other configurations. For example, some of the functions of the support device 200 may be realized by the user terminal 100. Some of the functions of the support device 200 may be realized by an external configuration such as a cloud server that can be connected via a network.

[0100] Furthermore, the processing units in the flowcharts of the above embodiments are divided according to the main processing content in order to facilitate understanding of each process. The present invention is not limited by the way the processing steps are classified. Each process can be further divided into more processing steps. Also, one processing step may perform even more processes.

[0101] The means and methods for performing various processing tasks in the system according to the above embodiment can be implemented by either a dedicated hardware circuit or a programmed computer. The program may be provided, for example, on a computer-readable recording medium such as a flexible disk or CD-ROM, or it may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is usually transferred to and stored in a storage unit such as a hard disk. Furthermore, the program may be provided as a standalone application software, or it may be incorporated into the software of the device as a function of the system. [Explanation of symbols]

[0102] 100 user terminals, 110 CPU, 120 ROM, 130 RAM, 140 storage, 150 communication interfaces, 160 Operation section, 170 display section, 180 bus, 200 Support equipment; 210 CPU, 2101 Financial information acquisition department; 2102 Text acquisition unit, 2103 Extraction part, 2104 Financial Statement Generation Department, 2105 Answer information acquisition department; 2106 Summary generator, 2107 Output section, 2108 Judgment Department, 2109 Specific Department; 2110 Classification Setting Reception Department, 2111 Combined setting section, 2112 Combined power output unit, 2113 Table Registration Section, 2114 Conversion unit, 2115 Calculation Unit, 2116 Increase / decrease output section, 2117 Editorial Department, 2118 Verification Department, 2119 Notification Department; 2120 Comment generation unit, 220 ROM, 230 RAM, 240 storage, 250 communication interfaces, 260 operation section, 270 display section, 280 buses.

Claims

1. A financial information acquisition unit that acquires financial report information containing information showing the financial reports of target companies for each of multiple fiscal years, A text acquisition unit that acquires text from each of the multiple financial reports indicated by the financial report information acquired by the financial information acquisition unit, From the text acquired by the text acquisition unit, an extraction unit extracts item information indicating items that include multiple account titles and total items, and amount information indicating the amount corresponding to each item. A financial statement generation unit generates financial statements that include information on the trends in amounts for each account and total item, based on the item information and amount information extracted by the extraction unit. A response information acquisition unit that acquires response information showing interviews with the management of the aforementioned target company or answers to questions, A summary generation unit inputs the response information obtained by the response information acquisition unit into a trained model that has been trained to perform machine learning to summarize and output the input text, and generates a summary text. An output unit that outputs the financial statements generated by the financial statement generation unit and the summary statement generated by the summary generation unit together, A financial due diligence document preparation support device.

2. The extraction unit further extracts location information relating to the location where each item is described in the financial report, The financial due diligence document creation support device according to claim 1, further comprising a determination unit that, based on the item information and position information extracted by the extraction unit, compares the position of the account title for accounts receivable or accounts payable with the position of the total item for current assets or current liabilities, and determines whether the total item is listed above or below each account title included in the total item.

3. The financial due diligence document preparation support device according to claim 2, further comprising a specification unit that identifies whether the allowance for doubtful accounts account is recorded as a current asset or as a fixed asset, based on the determination result by the determination unit and the recording location of the allowance for doubtful accounts account and the recording location of the total item extracted by the extraction unit.

4. A classification setting reception unit that accepts the setting of classification information indicating the classification for each of the aforementioned account titles, If the amount of the account in question is less than a predetermined percentage of the total amount of all accounts belonging to the classification set for that account, the aggregation setting unit sets the account in question as an aggregation target, A financial due diligence document preparation support device according to any one of claims 1 to 3, further comprising the above.

5. The financial due diligence document creation support device according to claim 4, further comprising a summing calculation unit that calculates a total sum of the amounts of each account set as the summing target by the summing setting unit, integrates each account as other items, and outputs it in association with the calculated total sum of the summing target.

6. The aforementioned classification is a financial due diligence document preparation support device according to claim 4, having multiple stages.

7. A table registration unit accepts registration of mapping table information for converting the names of multiple account titles corresponding to the same account title into a single unified name, A conversion unit converts the names of each account title extracted by the extraction unit into the unified names using the correspondence table information, A financial due diligence document preparation support device according to any one of claims 1 to 3, further comprising the above.

8. A calculation unit calculates the year-to-year increase or decrease in the amount corresponding to each account and total item for each of the multiple fiscal years, based on the item information and amount information extracted by the extraction unit. An increase / decrease output unit outputs the increase / decrease value of the amount for the year calculated by the calculation unit, A financial due diligence document preparation support device according to any one of claims 1 to 3, further comprising the above.

9. The system further includes an editing unit that edits the financial statements generated by the financial statement generation unit and the summary text generated by the summary generation unit so that they can be output in a predetermined format. The financial due diligence document creation support device according to any one of claims 1 to 3, wherein the output unit outputs the financial statements and the summary in the predetermined format.

10. A verification unit that determines whether the sum of the amounts corresponding to the multiple account titles extracted by the extraction unit matches the amount corresponding to the total item, A notification unit that notifies the user if the verification unit determines that they do not match, A financial due diligence document preparation support device according to any one of claims 1 to 3, further comprising the above.

11. The system further includes a comment generation unit that generates summary comments regarding the amounts and trends in the amounts for each account and total item based on the financial statements generated by the financial statement generation unit, The financial due diligence document creation support device according to any one of claims 1 to 3, wherein the output unit outputs the summary comments together with the financial statements and the summary text.

12. The response information acquisition unit acquires response information for each account item, indicating the answer to the interview or the question. The summary generation unit generates the summary for each account by inputting the response information for each account, information regarding the amount corresponding to the account, and pre-set instructions and rules for creating the summary into the trained model. The financial due diligence document creation support device according to any one of claims 1 to 3, wherein the output unit outputs the summary text generated for each account in association with each account of the financial statements.

13. The financial due diligence document creation support device according to any one of claims 1 to 3, wherein the pre-trained model is a large-scale language model.

14. A method for assisting in the preparation of financial due diligence documents, performed by a computer, A financial information acquisition step that obtains financial report information that includes information showing the financial reports of the target company for each of multiple fiscal years, A text acquisition step which acquires text from each of the multiple financial reports indicated by the financial report information acquired in the financial information acquisition step, An extraction step is performed to extract item information indicating items that include multiple account titles and total items, and amount information indicating the amount corresponding to each item, from the text recognized in the text acquisition step. A financial statement generation step generates financial statements that include information on the trends in amounts for each account and total item, based on the item information and amount information extracted in the extraction step. A step to obtain response information, which involves interviewing the management of the aforementioned target company or obtaining response information showing their answers to questions, A summary generation step is performed to generate a summary sentence using a pre-trained model that has been trained to summarize and output the input text, based on the response information obtained in the response information acquisition step. An output step that outputs the financial statements generated in the financial statement generation step and the summary statement generated in the summary generation step together, A method for supporting the preparation of financial due diligence documents, including [specific details omitted].

15. A financial due diligence document preparation support program for causing a computer to function as a financial due diligence document preparation support device according to any one of claims 1 to 3.

Images