Accounting information processing system, accounting information processing method, and accounting information processing program
The system automates the calculation of prepaid expenses using OCR and a learning model to determine billing periods and apportion expenses, enhancing accounting efficiency and accuracy.
Patent Information
- Application Number
- JP2024194864
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2025-10-14
- Estimated Expiration
- 2044-11-07
AI Technical Summary
Calculating and inputting prepaid expenses from invoices is cumbersome and prone to errors in existing accounting systems.
An accounting information processing system that utilizes OCR and a learning model to extract voucher text information, determines prepaid expenses based on billing period and date, and calculates expense apportionment amounts for each accounting period.
Facilitates easy and accurate calculation of prepaid expenses, reducing user burden and improving accounting accuracy.
Smart Images

Figure 0007752837000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an accounting information processing system, an accounting information processing method, and an accounting information processing program. [Background technology]
[0002] When a company receives an invoice, an accountant or other person inputs the information listed on the invoice, such as the name of the invoice issuer, the invoice amount, the invoice date, the payment due date, and the account item, into an accounting information processing system. To reduce the labor required for inputting information, a technology has been proposed that applies OCR to invoice images to automatically input invoice information (Non-Patent Document 1). [Prior art documents] [Non-patent literature]
[0003] [Non-Patent Document 1] https: / / www.rakurakumeisai.jp / column / invoice / 2009151.php Summary of the Invention [Problem to be solved by the invention]
[0004] When an invoice lists expenses for future services, the accounting staff enters the expenses for future services under the account heading of "prepaid expenses." However, the task of calculating prepaid expenses from the invoice information is cumbersome and prone to errors.
[0005] An object of the present invention is to provide an accounting information processing system, an accounting information processing method, and an accounting information processing program that can easily and reliably perform input processing related to prepaid expenses. [Means for solving the problem]
[0006] In order to solve the above problems, the accounting information processing system according to an embodiment of the present invention includes a voucher text information storage unit that stores the voucher text information written on the voucher, and the voucher text information includes information regarding the billing period and the billing date. The accounting information processing system also includes a prepaid expense determination unit that determines whether the claim related to the voucher is a claim for prepaid expenses based on the information regarding the billing period and the information regarding the billing date, and an output unit that outputs the determination result of the prepaid expense determination unit.
[0007] Furthermore, the system may include a learning model that has been machine-trained to output the voucher text information recorded in the voucher image when the voucher image is input, and a voucher text information output unit that outputs the voucher text information recorded in the voucher when the voucher image of the voucher is input into the learning model, and the voucher text information storage unit may store the voucher text information output by the voucher text information output unit.
[0008] Furthermore, the system may include an accounting period memory unit that stores information regarding the accounting period of the organization to which the user belongs, the supporting document text information including information regarding the invoice amount, and an expense apportionment amount calculation unit that calculates the expense apportionment amount for each accounting period based on the information regarding the accounting period and the information regarding the invoice amount stored in the accounting period memory unit, and the output unit may output the expense apportionment amount for each accounting period calculated by the expense apportionment amount calculation unit.
[0009] An accounting information processing method according to an embodiment of the present invention includes a voucher text information storage step executed by a computer, which stores voucher text information including information regarding the billing period and billing date stated on the voucher; a prepaid expense determination step which determines whether the claim on the voucher is a claim for prepaid expenses based on the information regarding the billing period and the information regarding the billing date; and an output step which outputs the determination result of the prepaid expense determination unit.
[0010] An accounting information processing program according to an embodiment of the present invention is a program for causing a computer to execute a voucher text information storage step for storing information voucher text information including information regarding the billing period and billing date stated on the voucher, a prepaid expense determination step for determining whether the claim related to the voucher is a claim for prepaid expenses based on the information regarding the billing period and the information regarding the billing date, and an output step for outputting the determination result of the prepaid expense determination unit. [Effects of the Invention]
[0011] According to the present invention, it is possible to provide an accounting information processing system, an accounting information processing method, and an accounting information processing program that enable input work related to prepaid expenses to be performed easily and reliably. [Brief explanation of the drawings]
[0012] [Figure 1] 1 is a diagram showing the configuration of an accounting information processing system according to an embodiment of the present invention.
[0023] FIG. [Figure 2] FIG. 1 is a diagram showing the configuration of a computer used in this accounting information processing system. [Figure 3] FIG. 10 is a flowchart illustrating an example of information processing by the present transaction information processing system. [Figure 4] FIG. 10 is a diagram showing an invoice image according to the first embodiment. [Figure 5] FIG. 10 is a diagram showing text information recognized by AI-OCR in Example 1. [Figure 6] FIG. 10 is a diagram showing the results of journalization performed by the accounting information processing system in Example 1. [Figure 7] This is a diagram showing the accounting period of Company A. [Figure 8] FIG. 10 is a diagram showing the amount of expenses recorded for each accounting period. DETAILED DESCRIPTION OF THE INVENTION
[0013] The following describes an accounting information processing system according to an embodiment of the present invention. Figure 1 shows the configuration of this system.
[0014] This system includes a voucher text information acquisition unit 11 that acquires voucher text information by applying character recognition technology to the voucher image, and the voucher text information includes information regarding the billing period and the billing date, and includes a prepaid expense determination unit 12 that determines whether the claim related to the voucher image is a claim for prepaid expenses based on the information regarding the billing period and the information regarding the billing date, and an output unit 13 that outputs the determination result of the prepaid expense determination unit 12.
[0015] The system also includes an accounting period reception unit 14 that receives information regarding the accounting period of the organization to which the user belongs, the supporting document text information including information regarding the invoice amount, and an expense apportionment amount calculation unit 15 that calculates the expense apportionment amount for each accounting period based on the information regarding the accounting period and the information regarding the invoice amount received by the accounting period reception unit 14, and the output unit 13 outputs the expense apportionment amount for each accounting period calculated by the expense apportionment amount calculation unit 15.
[0016] In this specification, a voucher refers to a document or file that serves as evidence of a transaction, and specifically includes, but is not limited to, estimates, orders (including purchase orders), delivery notes, inspection slips, invoices, etc. Figure 4 shows an example of an invoice.
[0017] In this specification, text information refers to information made up of letters, numbers, symbols, etc., and includes text data and text files.
[0018] FIG. 2 shows the configuration of a computer 20 used for information processing in this system. The memory unit 21 is a device for storing information, and stores computer programs, data, etc., and is composed of a hard disk, SSD, semiconductor memory, etc. The calculation unit 22 is a device for performing calculations and executing programs, etc. The calculation unit 22 functions as the prepaid expense determination unit 12, the expense calculation unit 15, etc. It also functions as a control unit for controlling each device, such as the memory unit 21, the input unit 23, and the output unit 24. The input unit 23 is a device for a user to input information into the computer 20, and is composed of a mouse, keyboard, camera, microphone, etc. The output unit 24 is a device for outputting information read from the memory unit 21 in a format that can be recognized by the user, and is composed of a display (display unit), speakers, etc.
[0019] Figure 3 is a flowchart illustrating an example of information processing by this system. First, AI-OCR is applied to an image of a document, such as an invoice, to organize and extract text information recorded in the invoice image (ST1). AI-OCR (Optical Character Recognition / Reader) not only extracts text information recorded in an image, but also extracts text information corresponding to specified items such as the invoice amount, invoice date, invoice period (bill period), and invoice issuer name. Specifically, when an invoice image is input, the learning model is trained using machine learning of training data (also called teacher data) to output text information corresponding to specified items such as the invoice amount, invoice date, invoice period, and invoice issuer name, thereby extracting text information corresponding to the specified items. Figure 5 shows an example of text information extracted from an invoice image using AI-OCR.
[0020] Next, based on the relationship between the billing date and the billing period, expenses relating to the billing period up to the month before the billing date are determined to be expenses, and expenses relating to the billing period from the month in which the billing date falls are determined to be prepaid expenses (ST2). Then, based on the determination result, the account item for each billing period is calculated, and the account item for each billing period is displayed on the display and output to the user (ST5). Figure 6 is an example of the output screen.
[0021] The user also inputs the accounting period of the organization to which the user belongs into the system (ST3). Figure 7 shows the accounting periods of A Corporation (Company A). Company A's fiscal year ends in December, and the accounting periods are from the first quarter to the fourth quarter.
[0022] The billed amount is then divided proportionally among the accounting periods, and the expenses recorded for each accounting period are calculated (ST4) and displayed on the display (ST5). 81 in Figure 8 is an example of a display screen showing the expenses recorded for each accounting period. [Example]
[0023] The operation of the accounting information processing system according to the first embodiment of the present invention will now be described.
[0024] FIG. 4 is a diagram showing an invoice image 41 in PDF format issued by ABC System Co., Ltd. to Company A and sent as an email attachment. At Company A, the invoice image 41 is uploaded to an accounting information processing system and input into an LLM (Large Language Model). A language model is a learning model that has been machine-learned using training data so that, when an output instruction in natural language is input, it outputs an answer in accordance with the output instruction. A language model that has been machine-learned using a large amount of training data is called an LLM (Large Language Model). In this specification, a language model that has been machine-learned using 1 GB or more of training data is called an LLM. There are LLMs that can process image data and LLMs that cannot, but in this embodiment, an LLM that can process image data is used.
[0025] When an output instruction for a standard template such as "Output the billing amount, consumption tax amount, billing date, payment due date, billing period, bill issuer, and account item recorded in the attached invoice image" is input to an LLM (functioning in this case as a document text information acquisition unit) capable of processing image data, the text information corresponding to these items recorded in invoice image 41 in Figure 4 is output. For example, from the sentence "System A license fee (August 2023 to July 2025)" recorded in section 42 of invoice image 41, the LLM determines that the billing period is "August 1, 2024 to July 31, 2027." In this way, the text information corresponding to the specified items extracted from invoice image 41 is shown in Figure 5.
[0026] The LLM (Prepaid Expense Determination Unit) then compares the billing date with the billing period to determine whether the account item is an expense or a prepaid expense. In Figure 5, since the "billing date" is set to "April 2, 2024," expenses related to the billing period from April 2024 onward (April 1, 2024 to July 31, 2026), to which the billing date belongs, are determined to be prepaid expenses. Furthermore, expenses related to the billing period from the month before the month to which the billing date belongs (August 1, 2024 to July 31, 2025) are determined to be expenses, specifically communication expenses, rather than prepaid expenses.
[0027] Next, the proposed journal data output by the LLM is displayed on the display and shown to the user. Figure 6 shows a display screen 61 of the journal data output by the LLM.
[0028] The accounting period storage unit 14 receives and stores information about the accounting period of the organization to which the user belongs. FIG. 7 is a diagram showing the accounting periods of Company A. Company A's business year runs from January 1 to December 31, its fiscal year ends in December, and its accounting period is divided into four periods: the first quarter (January 1 to March 31), the second quarter (April 1 to June 30), the third quarter (July 1 to September 30), and the fourth quarter (October 1 to December 31). The fiscal year and the length of the unit accounting period vary depending on the organization. Note that "1Q" in FIG. 7 is an abbreviation of "1st quarter" and means "1st quarter."
[0029] The expense calculation unit of this system calculates the expense for each accounting period based on the information on the accounting period stored in the accounting period storage unit.
[0030] FIG. 8 is a diagram showing the display screen of the expense amounts for each accounting period calculated by the expense calculation unit. For each period from 2023 / 4Q to 2025 / 2Q, the billing amount for the three-month billing period, 1,500,000 yen, is recorded as an expense for that accounting period. For 2023 / 3Q, the billing period is the two months of August and September 2023, so the billing amount for two months, 1,000,000 yen, is recorded as an expense for 2023 / 3Q. For 2025 / 3Q, the billing period is the one month of July 2025, so the billing amount for one month, 500,000 yen, is recorded as an expense for 2025 / 3Q. In this way, the billing amount for each accounting period is calculated from the billing period of that period, and this amount is recorded as an expense for that accounting period. The display format can be changed by, for example, color-coding the background of the prepaid expense period and the expense period, so that the prepaid expense and expense periods can be intuitively identified, or words such as "prepaid expense" and "expense" can be displayed on the display screen.
[0031] According to this embodiment, expenses or prepaid expenses are calculated automatically, which reduces the burden on users of the previously complicated task of determining and calculating prepaid expenses, and enables accounting work to be carried out accurately.
[0032] In addition, the expense amount for each accounting period is automatically calculated based on the fiscal year and accounting period of the organization to which the user belongs, reducing the burden on users of calculating the expense amount for each accounting period, which was previously cumbersome, and allowing them to carry out accounting work accurately.
[0033] The embodiments of the present invention are not limited to the above-described embodiments and examples, and various modifications of the above embodiments and examples can be made within the scope of the claims. For example, in Example 1, a language model capable of processing image data is used to extract invoice text information such as the invoice amount, invoice date, and invoice issuer from an invoice image. However, it is also possible to extract invoice text information from an invoice image using a learning model that is not a language model trained by machine learning to output invoice text information when an invoice image is input. [Explanation of symbols]
[0034] 11. Voucher text information storage unit 12 Prepaid Expenses Determination Section 13 Output section 14 Accounting Period Memory Section 20 Computer 21 Memory section 22 Calculation unit (control unit) 23 Input section 24 Output section 25 Communications Department 41 Invoice 42 A System License Fee (August 2023 to July 2025) 61 Journal entry preview screen 81 Expense amount display screen
Claims
1. a voucher text information storage unit for storing voucher text information written on the voucher, The voucher text information includes information about the billing period and information about the billing date, a prepaid expense determination unit that determines whether the claim related to the voucher is a claim related to prepaid expenses based on the information related to the claim period and the information related to the claim date; an output unit that outputs the determination result of the prepaid expense determination unit.
2. a learning model that has been machine-learned to output the document text information recorded in the document image when the document image is input; a voucher text information output unit that outputs voucher text information described in the voucher by inputting a voucher image of the voucher into the learning model, the evidence text information storage unit stores the evidence text information output by the evidence text information output unit; 2. The accounting information processing system according to claim 1.
3. an accounting period storage unit for storing information about the accounting period of an organization to which a user belongs; The voucher text information includes information regarding the invoice amount, an expense calculation unit that calculates the expense amount for each accounting period based on the information about the accounting period and the information about the billing amount stored in the accounting period storage unit; The accounting information processing system according to claim 1 , wherein the output unit outputs the expense amounts for each accounting period calculated by the expense amount calculation unit.
4. computer-implemented, a voucher text information storage step for storing information voucher text information including information on the claim period and information on the claim date described in the voucher; a prepaid expense determination step for determining whether the claim related to the voucher is a claim related to prepaid expenses based on the information related to the claim period and the information related to the claim date; an output step of outputting a determination result of the prepaid expense determination step; An accounting information processing method having the above.
5. On the computer, a voucher text information storage step for storing information voucher text information including information on the claim period and information on the claim date described in the voucher; a prepaid expense determination step for determining whether the claim related to the voucher is a claim related to prepaid expenses based on the information related to the claim period and the information related to the claim date; an output step of outputting a determination result of the prepaid expense determination step; An accounting information processing program for executing the above.
Citation Information
Patent Citations
System for received money, method for received money, and program therefor
JP2003256750A
A system for analyzing electronic legal invoice data
JP2017520043A
Report information generation device, method, and program
JP2022013524A