Search

JP-2026075424-A - Information processing device, information processing method, and program

JP2026075424AJP 2026075424 AJP2026075424 AJP 2026075424AJP-2026075424-A

Abstract

[Problem] To reduce the burden of input operations on the user when scrutinizing OCR results. [Solution] The information processing device acquires a scanned image of a document containing the identification information corresponding to the document issuer from among the multiple identification information registered in the registrant information, extracts a string representing the identification information based on the OCR result of the scanned image, acquires similar strings similar to the extracted string from among the multiple identification information registered in the registrant information, and displays the acquired similar strings as candidates for correction of the extracted string. [Selection Diagram] Figure 3

Inventors

  • 日塔 雄一

Assignees

  • キヤノン株式会社

Dates

Publication Date
20260508
Application Date
20241022

Claims (18)

  1. Image acquisition means for acquiring a scanned image of a document containing the identification information corresponding to the document issuer, among the multiple identification information registered in the registrant information, An extraction means for extracting a string representing the identification information based on the OCR result for the scanned image, Similarity acquisition means for acquiring similar strings to the string extracted by the extraction means from the plurality of identification information registered in the registrant information, A display control means that displays the similar string obtained by the similarity acquisition means as a candidate for modification of the string extracted by the extraction means, An information processing device characterized by having the following:
  2. The information processing apparatus according to claim 1, characterized in that the similarity acquisition means acquires strings as similar strings whose degree of similarity to the string extracted by the extraction means is equal to or greater than a predetermined threshold.
  3. The information processing apparatus according to claim 1, characterized in that the display control means displays the string extracted by the extraction means.
  4. The information processing apparatus according to claim 1, characterized in that the display control means highlights and displays characters from the similar strings that are different from the string extracted by the extraction means.
  5. The information processing apparatus according to claim 1, characterized in that the display control means displays a scanned image of the form.
  6. The aforementioned registrant information is such that each of the registered identification pieces of information is associated with a registration period. The extraction means extracts a string indicating the issue date written on the document, The similarity acquisition means extracts the registration period associated with the similar string from the registrant information, The information processing apparatus according to claim 1, characterized in that the display control means displays information indicating the registration status of the document issuer, which is determined from the document issuance date and the registration period.
  7. The aforementioned registrant information is such that each of the multiple pieces of identification information registered is linked to a category. The similarity acquisition means extracts the category linked to the identification information indicated by the similar string from the registered user information, The information processing apparatus according to claim 1, characterized in that the display control means displays the classification of the document issuer.
  8. The information processing device according to claim 7, characterized in that the aforementioned classification is a tax law classification related to qualified invoice business registration.
  9. The information processing apparatus according to claim 7, characterized in that the display control means displays the reason for generating the classification.
  10. The information processing apparatus according to claim 1, characterized in that the display control means displays a button for reporting deficiencies in the form.
  11. The information processing apparatus according to claim 1, characterized in that the display control means displays buttons for the user to manually make corrections.
  12. The aforementioned registrant information is associated with the business name, The extraction means extracts a string of characters indicating the issuer of the document, The similarity acquisition means acquires similar strings to the issuer string extracted by the extraction means from the plurality of identification information registered in the registrant information, The information processing apparatus according to claim 1, characterized in that the display control means displays similar strings of the issuer obtained by the similarity acquisition means as correction candidates for the issuer extracted by the extraction means.
  13. The information processing apparatus according to claim 1, further comprising a receiving means for receiving user operations to confirm the OCR result.
  14. The system further includes a storage means for storing the OCR result determined by the user operation, The information processing apparatus according to claim 13, characterized in that, when the storage means stores the OCR results, the similarity acquisition means acquires the similar string from the OCR results stored by the storage means and the plurality of identification information registered in the registrant information.
  15. The extraction means extracts a string of characters indicating the expense item name written in the form, The information processing apparatus according to claim 14, wherein, if the storage means stores a string indicating the expense item name in association with the identification information included in the OCR results, the similarity acquisition means acquires a similar string that is similar to the string of identification information associated with the string of the expense item name extracted by the extraction means from the OCR results stored in the storage means.
  16. The information processing device according to claim 1, characterized in that the aforementioned registrant information is information indicating that the business operator indicated by the aforementioned identification information is registered as a qualified invoice issuer.
  17. An image acquisition step of acquiring a scanned image of a document containing the identification information corresponding to the document issuer, from among the multiple identification information registered in the registrant information, An extraction step of extracting a string representing the identification information based on the OCR result for the scanned image, A similarity acquisition step is performed to obtain similar strings to the string extracted in the extraction step from the plurality of identification information registered in the registrant information, A display control step that displays the similar string obtained in the similarity acquisition step as a candidate for modification of the string extracted in the extraction step, An information processing method characterized by including
  18. A program for causing a computer to execute the information processing method described in claim 17.

Description

This disclosure relates to a graphical user interface (GUI) for using electronic forms. In recent years, there are systems that extract information based on OCR results from scanned images of documents, verify the information, make corrections as needed, and then save the verified and corrected OCR results to a database for use in business processes. Regarding the technology for utilizing OCR results, Patent Document 1 discloses a technology for querying the registrant information for the identification number and issue date of a document extracted based on the OCR results of a scanned image of a document containing the identification number of the document issuer registered in the registrant information. Japanese Patent Publication No. 2024-55745 This is a diagram illustrating the overview of the information processing system.This figure shows an example of the hardware configuration of an information processing device.This figure shows an example of the functional configuration of an information processing device.This is a diagram showing the sequence of an information processing system.This table shows examples of data processed by an information processing system.This is a diagram showing an example of a UI screen. The following descriptions detail embodiments for carrying out the technology of this disclosure, with reference to the drawings. Note that the following embodiments do not limit the technology of this disclosure as defined in the claims. Not all combinations of features described in the embodiments are essential as solutions of the technology of this disclosure, and multiple features may be combined arbitrarily. Identical components are denoted by the same reference numerals. <<Embodiment 1>> (System configuration) Figure 1 is a diagram showing an overview of the information processing system according to this embodiment. The information processing system 1 of this embodiment includes a document recognition system 10, a core system 20, and a registered user management system 30, and each system 10, 20, and 30 is connected to each other via a network 40 so that data can be sent and received from each other. The document recognition system 10 includes an information processing device 101, an image forming device 102, and a terminal device 103, and each device 101, 102, and 103 is connected to each other via a network so that data can be sent and received from each other. The terminal device 103 is connected to the core system 20 via a network, for example, so that data can be sent and received from each other. In this embodiment, an invoice, a type of document, is used as an example. However, this technology is applicable to other documents such as receipts, delivery slips, and contracts, and exhibits similar effects on these documents as well. Furthermore, the document recognition system 10 is described as extracting information from a scanned image of the document obtained by scanning the invoice, including business information indicating the issuer of the invoice, invoice information indicating the invoiced amount, and detail information indicating the contents of the invoice details. In the document recognition system 10, the information processing device 101 uses the scanner function of the image forming apparatus 102 to scan the document and acquire image data showing the scanned image of the document. Alternatively, the information processing device 101 may receive image data showing the scanned image of the document from the terminal device 103. Upon acquiring the image data showing the scanned image of the document, the information processing device 101 extracts the items and their values contained in the scanned image and generates text data that associates the items with their values. Using Figure 6 (described later) as an example, text data is generated that associates the document title with "Invoice," the billing address with "CCC Corporation," the billing amount with "76800," the issue date with "2024/4/15," and the billing source with "AAA Corporation." Furthermore, text data is generated that associates the registration number, which is identification information for identifying the document issuer, with "T2023123456789," the details with the date, the expense item, and the amount. The core system 20 is, for example, a system that uses the results obtained by the document recognition system 10 to perform specific processing. If the document is an invoice, the core system 20 may be an accounting system that performs specific processing, such as transferring the invoice amount to a financial institution. The registrant management system 30 is a system composed of devices that manage registrant information. The registrant management system 30 may, for example, be a management system composed of a server managed by a government office that registers qualified invoice providers under the qualified invoice system. The qualified invoice system is a method of input tax credit that was