WO2023021636A1 - Data processing device, data processing method, and program - Google Patents

Data processing device, data processing method, and program Download PDF

Info

Publication number
WO2023021636A1
WO2023021636A1 PCT/JP2021/030274 JP2021030274W WO2023021636A1 WO 2023021636 A1 WO2023021636 A1 WO 2023021636A1 JP 2021030274 W JP2021030274 W JP 2021030274W WO 2023021636 A1 WO2023021636 A1 WO 2023021636A1
Authority
WO
WIPO (PCT)
Prior art keywords
logo
data
extracted
issuer
publisher
Prior art date
Application number
PCT/JP2021/030274
Other languages
French (fr)
Japanese (ja)
Inventor
鴻鵬 葛
顕 松田
智 小俣
啓太郎 森
貴亮 佐藤
将和 早川
Original Assignee
ファーストアカウンティング株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ファーストアカウンティング株式会社 filed Critical ファーストアカウンティング株式会社
Priority to PCT/JP2021/030274 priority Critical patent/WO2023021636A1/en
Priority to JP2021548658A priority patent/JP7037237B1/en
Priority to JP2022027702A priority patent/JP2023029196A/en
Publication of WO2023021636A1 publication Critical patent/WO2023021636A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/04—Billing or invoicing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/42—Document-oriented image-based pattern recognition based on the type of document

Definitions

  • the present invention relates to a data processing device, data processing method and program.
  • a technology is known that extracts information written on receipts and slips by optical character recognition and assigns appropriate expense items based on the extracted information.
  • Patent Document 1 describes a method of extracting a telephone number written on a receipt or the like by optical character recognition and specifying a store name based on the extracted telephone number in order to improve recognition accuracy.
  • the phone number is misrecognized, it is assumed that the wrong store name will be specified. There was a problem that it took time to confirm.
  • the present invention has been made in view of these points, and aims to reduce the time and effort required to confirm whether the evidence is correct or not.
  • the issuer name that is the name of the issuer that issues the voucher, the reference telephone number that is the telephone number of the issuer, and the logo indicating the issuer
  • a storage unit for storing one or more issuer data associated with a reference logo
  • an acquisition unit for acquiring voucher data indicating an issued voucher
  • a search unit for searching the first publisher data containing the extracted publisher name, which is the publisher name extracted by the extractor, from the one or more publisher data; the first publisher If the first reference phone number included in the data matches the extracted phone number, which is the phone number extracted by the extraction unit, or the first reference logo included in the first publisher data is extracted by the extraction unit a judgment unit for judging that there is no error in the acquired documented evidence data when the extracted logo matches the extracted logo.
  • the determination unit may determine that the first reference logo and the extracted logo match when the degree of similarity between the image data of the first reference logo and the image data of the extracted logo is equal to or greater than a threshold. good.
  • the extraction unit specifies a position where the extracted logo is arranged in the voucher data, and the determination unit determines that the similarity between the first reference logo and the extracted logo is equal to or greater than the threshold value, and the extracted It may be determined that the first reference logo and the extracted logo match when the logo is extracted from within a predetermined range from the reference position in the voucher data.
  • the storage unit associates and stores the reference logo with a reference position that differs for each issuer in the voucher data, and the determination unit stores the extracted logo at a reference position that differs for each issuer in the voucher data. It may be determined that the first reference logo and the extracted logo match when the logo is extracted from within a predetermined range from .
  • the extracted It may further include a display control unit that causes an operator terminal operated by an operator to display a screen for confirming whether to associate and store the issuer name and the extracted logo.
  • the search unit stores the first publisher data including the extracted telephone number when the first reference telephone number does not match the extracted telephone number and the first reference logo does not match the extracted logo.
  • second publisher data different from the second publisher data, and if the second reference logo, which is the reference logo included in the second publisher data, matches the extracted logo, the extracted publisher name is changed to the second publisher It may further have a replacement part for replacing with the publisher name included in the data.
  • a data processing method comprises a computer-executed step of acquiring voucher data indicating an issued voucher; a step of extracting a name, a telephone number, and a logo; an issuer name, a reference telephone number, which is the telephone number of the issuer, and a reference logo, which is a logo indicating the issuer, stored in a storage unit; a step of retrieving first publisher data including an extracted publisher name, which is the publisher name extracted by the extracting step, from one or more publisher data associated with If the first reference phone number matches the extracted phone number, which is the phone number extracted by the extracting step, or the first reference logo included in the first publisher data matches the logo extracted by the extracting step and determining that the acquired voucher data is error-free if it matches the extracted logo.
  • a program comprises a step of obtaining voucher data indicating an issued voucher, and an issuer name, which is the name of an issuer that issues the voucher included in the voucher data, to be executed by a computer.
  • first publisher data including an extracted publisher name, which is the publisher name extracted in the extracting step, from one or more publisher data; if the reference phone number matches the extracted phone number, which is the phone number extracted by the extracting step, or the first reference logo included in the first publisher data is the logo extracted by the extracting step; and determining that the acquired voucher data is error-free if it matches the extracted logo.
  • FIG. 3 is a diagram schematically showing the flow of processing in the data processing device 1;
  • FIG. 2 is a block diagram showing the configuration of the data processing device 1;
  • FIG. 4 is a diagram showing an example of the data structure of a publisher data table stored in a storage unit 12;
  • FIG. 4 is a diagram showing an example of voucher data acquired by an acquisition unit 131.
  • FIG. 4 is a flow chart showing the flow of processing in the data processing device 1;
  • FIG. 1 is a diagram schematically showing the flow of processing in the data processing device 1.
  • the data processing system S is a system for reading the contents described in a voucher such as an invoice and performing accounting processing such as sorting.
  • the data processing system S has a data processing device 1 , a reading device 2 and an accounting processing device 3 .
  • the data processing device 1 is a device for judging the correctness or incorrectness of the characters included in the voucher data.
  • the voucher data may be image data transmitted from an external device, or may be image data created by reading a paper voucher with the reading device 2 .
  • the reading device 2 inputs voucher data, which is image data obtained by reading a paper voucher, to the data processing device 1 .
  • the voucher data may be electronic data including text data created by the reader 2 recognizing characters by OCR (Optical Character Recognition).
  • the data processing device 1 extracts the issuer name, phone number, and logo included in the input voucher data.
  • the data processing device 1 extracts the issuer name and telephone number by executing character recognition processing. If the input voucher data contains text data, the data processing device 1 extracts the issuer name and telephone number based on the content of the text data.
  • the data processing device 1 refers to the publisher data table stored in advance, and acquires the publisher telephone number and reference logo corresponding to the extracted publisher name. The data processing device 1 determines whether the voucher data is correct or not by determining whether the extracted telephone number or logo matches the stored telephone number or reference logo of the issuer. A reference logo is image data of a logo indicating a publisher. When the data processing device 1 determines that the contents of the read voucher data are correct, the data processing device 1 inputs the voucher data to the accounting processing device 3 .
  • the accounting processing device 3 performs predetermined processing such as journalizing processing based on the entered voucher data.
  • the evidences handled by the data processing apparatus 1 are, for example, receipts, invoices, statements of delivery, order forms, receipts, and the like.
  • the data processing device 1, the reading device 2, and the accounting processing device 3 are described as separate devices, but the data processing device 1 may be configured as a part of the reading device 2, or the accounting processing device 3 may be configured.
  • FIG. 2 is a block diagram showing the configuration of the data processing device 1.
  • the data processing device 1 has a communication section 11 , a storage section 12 and a control section 13 .
  • the control unit 13 has an acquisition unit 131 , an extraction unit 132 , a search unit 133 , a determination unit 134 , a replacement unit 135 and a display control unit 136 .
  • the communication unit 11 is a communication interface for communicating with the reading device 2 and the accounting processing device 3 via a network.
  • the storage unit 12 is, for example, a storage medium such as ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drive), and hard disk.
  • the storage unit 12 stores one or more issuers associated with an issuer name, which is the name of an issuer that issues a voucher, a reference telephone number, which is the telephone number of the issuer, and a reference logo, which is a logo indicating the issuer. Store the original data.
  • FIG. 3 is a diagram showing an example of the data structure of the issuer data table stored in the storage unit 12.
  • the storage unit 12 stores an issuer data table in which issuer names, issuer telephone numbers, and reference logos are associated with each other.
  • the storage unit 12 may associate and store the reference logo and the reference position in the documented voucher data that differs for each issuer. That is, the storage unit 12 stores an issuer data table in which the reference logo and the reference position indicating the position where the reference logo is described in the voucher data are further associated with each other.
  • the reference position is data indicating a position in the voucher data, and is represented, for example, by two-dimensional coordinate data with a predetermined position (for example, the upper left corner position) in the voucher as the origin.
  • the control unit 13 is, for example, a CPU (Central Processing Unit).
  • the control unit 13 functions as an acquisition unit 131 , an extraction unit 132 , a search unit 133 , a determination unit 134 , a replacement unit 135 and a display control unit 136 by executing control programs stored in the storage unit 12 .
  • the acquisition unit 131 acquires voucher data indicating the issued voucher.
  • FIG. 4 is a diagram showing an example of voucher data acquired by the acquisition unit 131.
  • the voucher data includes, for example, destination business name, destination department name, destination business identification number, destination telephone number, issuer business name C1, logo C2, issuer telephone number C3, invoice number, invoice issue date , including the name of the product or service subject to the invoice, the amount invoiced, the tax amount, the bank account number, etc.
  • the voucher data is document data, image data or text data.
  • the extraction unit 132 extracts the issuer name, phone number, and logo included in the voucher data.
  • the extraction unit 132 performs character recognition on the voucher data, which is image data obtained by reading the voucher input from the reading device 2, so that the name of the issuer included in the voucher data (hereinafter sometimes referred to as the extracted issuer name) and the telephone Extracts text data indicating a number (hereinafter sometimes referred to as an extracted telephone number). Furthermore, the extracting unit 132 extracts image data representing a logo (hereinafter sometimes referred to as an extracted logo) by image recognition of the voucher data.
  • the extraction unit 132 may specify the position where the extracted logo is arranged in the voucher data.
  • the extraction unit 132 acquires voucher position data, which is the position at which the extracted logo is arranged in the voucher data, which is image data.
  • the voucher position data is, for example, two-dimensional coordinate data.
  • the voucher position data is, for example, the center of gravity of the logo extracted area or the coordinates of an arbitrary end point (upper left, etc.).
  • the search unit 133 searches for the first publisher data containing the extracted publisher name, which is the publisher name extracted by the extraction unit 132, from one or more publisher data.
  • the search unit 133 searches the publisher data table stored in the storage unit 12 for publisher data whose extracted publisher name matches the publisher name, and retrieves the telephone number (reference telephone number) associated with the extracted publisher data. (sometimes called a number) and a logo (sometimes called a reference logo).
  • the determination unit 134 determines whether the first reference telephone number included in the first issuer data matches the extracted telephone number, which is the telephone number extracted by the extraction unit 132, or the first reference telephone number included in the first issuer data. When the logo matches the extracted logo, which is the logo extracted by the extraction unit 132, it is determined that the acquired voucher data is correct. The determination unit 134 compares the character string that forms the first reference telephone number and the character string that forms the extracted telephone number. Furthermore, the determination unit 134 compares the first reference logo and the extracted logo. If either one of the telephone number comparison result and the logo comparison result matches, the determination unit 134 determines that there is no error in the acquired voucher data.
  • the determination unit 134 may determine that the first reference logo and the extracted logo match when the degree of similarity between the image data of the first reference logo and the image data of the extracted logo is equal to or greater than a threshold.
  • the determination unit 134 calculates the degree of similarity between the first reference logo, which is image data, and the extracted logo.
  • the determination unit 134 extracts the feature points of the first reference logo and the extracted logo, and calculates based on the distance of the extracted feature points.
  • the degree of similarity is represented by a real number between 0 and 1, for example.
  • the determining unit 134 determines that the first reference logo and the extracted logo match when the calculated degree of similarity is equal to or greater than the threshold.
  • the threshold is set to 0.8 as an example.
  • the determination unit 134 may determine whether or not the first reference logo and the extracted logo match based on a threshold that differs for each reference logo.
  • the storage unit 12 stores different threshold values for each reference logo in the issuer data table.
  • the determination unit 134 reads the reference logo stored in the storage unit 12 and the threshold associated with the reference logo, and calculates the similarity between the reference logo and the extracted logo.
  • the determining unit 134 determines that the reference logo and the extracted logo match when the calculated similarity is equal to or greater than the threshold value read from the storage unit 12 .
  • the threshold may be configured so that the user can set it by operating an operator terminal (not shown) communicatively connected to the data processing device 1 .
  • An operator terminal is a terminal used by an operator, such as an accountant who processes bills.
  • the determination unit 134 may extract the elements that make up the logo from the extracted logo, and calculate the degree of similarity between each element and the reference logo.
  • Elements constituting a logo are, for example, color, shape, size, and text included in the logo.
  • the determining unit 134 may calculate the sum or score of similarities of each element, and determine that the logos match when the calculated sum or score of similarities is equal to or greater than a threshold.
  • the determination unit 134 may determine that the logos match when the degree of similarity of each element is equal to or greater than a threshold.
  • the storage unit 12 stores a threshold value for each element, and the determination unit 134 may read the similarity for each element from the storage unit 12 and perform determination.
  • the determination unit 134 determines that the first reference logo and the extracted logo are separated. may be determined to match. That is, when the degree of similarity between the reference logo and the extracted logo is equal to or greater than the threshold, the determination unit 134 determines the reference position, which is coordinate data indicating the position where the logo is arranged in the voucher data, and the voucher position specified by the extraction unit 132. data, and if the difference between the two is within a threshold, it is determined that the reference logo and the extracted logo match.
  • a different reference position may be set for each issuer.
  • the determination unit 134 acquires the reference position associated with the extracted publisher name from the publisher data table stored in the storage unit 12 .
  • the determination unit 134 may determine that the first reference logo and the extracted logo match when the extracted logo is extracted from within a predetermined range from a reference position that differs for each issuer in the voucher data.
  • the determination unit 134 compares the obtained reference position with the voucher position data specified by the extraction unit 132, and determines that the reference logo and the extracted logo match when the difference between the two is within a threshold.
  • the determination unit 134 acquires the reference position corresponding to the reference logo of the publisher from the publisher data stored in the storage unit 12 .
  • the determination unit 134 compares the obtained reference position with the voucher position data specified by the extraction unit 132, and determines that the reference logo and the extracted logo match when the difference between the two is within a threshold.
  • the extracted publisher name may be corrected by the publisher data that matches elements other than the name, and it may be determined that there is no error in the read content. If the first reference phone number does not match the extracted phone number and the first reference logo does not match the extracted logo, the search unit 133 searches for a second publisher data that includes the extracted phone number and is different from the first publisher data. You may search for more data. Specifically, when the extracted phone number and extracted logo do not match the phone number and logo included in the first publisher data including the extracted publisher name, the search unit 133 retrieves the A plurality of issuer data tables are searched for issuer data (sometimes referred to as second issuer data) including the extracted telephone number.
  • issuer data sometimes referred to as second issuer data
  • the replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data when the second reference logo, which is the reference logo included in the second publisher data, matches the extracted logo.
  • the determination unit 134 calculates the degree of similarity between the reference logo and the extracted logo included in the second publisher data. If the calculated similarity is equal to or higher than a predetermined value, the replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data.
  • the issuer name can be replaced based on the specified information.
  • the operator can proceed with the processing of the voucher based on the information output from the data processing device 1 without referring to the voucher and confirming the issuer name.
  • the display control unit 136 causes an external terminal such as an operator terminal to display information based on the determination result of the determination unit 134 . If the issuer name and phone number match, but the logo does not match, it is assumed that the logo may have changed. Therefore, the display control unit 136 may cause the operator terminal to display a screen for asking the operator whether or not to register the logo in such a case.
  • the display control unit 136 determines that the first reference telephone number included in the first issuer data matches the extracted telephone number and the reference logo included in the first issuer data does not match the extracted logo.
  • the operator terminal operated by the operator displays a screen for confirming whether to store the extracted issuer name and the extracted logo in association with each other.
  • the display control unit 136 determines that the extracted logo is stored in the publisher data. is displayed on the screen of the operator terminal, and a screen is displayed asking the operator whether it is acceptable to register the extracted logo in the issuer data.
  • the display control unit 136 associates the publisher name with the extracted logo and stores them in the publisher data table stored in the storage unit 12 .
  • the data processing device 1 can judge whether the voucher data is correct or incorrect based on the new registered logo. As a result, it is possible to reduce the operator's labor required for confirming the voucher.
  • the display control unit 136 may be configured to display a screen on the operator terminal operated by the operator to confirm whether to associate and store the extracted publisher name and the extracted telephone number.
  • FIG. 5 is a flow chart showing the flow of processing in the data processing device 1. As shown in FIG. The flow chart in FIG. 5 starts from the timing when the data processing device 1 receives voucher data from the reading device 2 .
  • the acquiring unit 131 acquires voucher data (S101).
  • the extraction unit 132 extracts the issuer name, logo, and telephone number from the acquired voucher data (S102).
  • the search unit 133 searches the first publisher data containing the extracted publisher name from the publisher data table stored in the storage unit 12 (S103).
  • the determination unit 134 determines whether the extracted logo or telephone number extracted from the voucher data matches the logo or telephone number included in the issuer data acquired as the search result (S104).
  • the determination unit 134 determines whether both the logos and phone numbers match (S105). If either the logo or the phone number is different (NO in S105), the display control unit 136 displays a confirmation screen on the operator terminal operated by the operator (S106), and if the operator confirms the operation, the process to S110. If both the logo and the phone number match (YES in S105), determination unit 134 advances the process to S110.
  • the search unit 133 searches for the second publisher data containing the extracted phone number (S107).
  • the determination unit 134 determines whether the logo included in the second publisher data matches the extracted logo (S108). If the logo included in the second publisher data matches the extracted logo (YES in S108), the replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data (S109). .
  • the determination unit 134 determines that there is no error in the acquired voucher data (S110), inputs the voucher data to the accounting processing device 3, and terminates the process.
  • the issuer name which is the name of the issuer that issues the voucher
  • the reference telephone number which is the telephone number of the issuer
  • the reference logo which is the logo indicating the issuer.
  • the acquiring unit 131 acquires voucher data indicating the issued voucher
  • the extracting unit 132 extracts the issuer name, telephone number, and logo included in the voucher data.
  • the search unit 133 searches for first publisher data including the extracted publisher name, which is the publisher name extracted by the extraction unit 132, from the one or more publisher data
  • the determination unit 134 searches for the first publisher data.
  • the extraction unit 132 If the first reference telephone number included in the data matches the extracted telephone number that is the telephone number extracted by the extraction unit 132, or if the first reference logo included in the first issuer data is extracted by the extraction unit 132 If it matches the extracted logo, which is the logo, it is determined that the acquired voucher data is correct.
  • the data processing device 1 displays the judgment result on the operator terminal, and sends the evidenced data to the accounting processing device 3 on the condition that it is judged that there is no error in the evidenced data.
  • the person in charge of processing the voucher can automatically judge whether the voucher is correct or not without confirming the correctness of the voucher. The time required for confirmation can be reduced.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Databases & Information Systems (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Technology Law (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Image Analysis (AREA)
  • Telephonic Communication Services (AREA)

Abstract

A data processing device 1 determines whether the details of read documented evidence data are correct or not. The data processing device 1 comprises a storage unit 12 that stores one or more sets of issuer data associating an issuer name, which is the name of an issuer that issues documented evidence, a reference phone number that is the phone number of the issuer, and a reference logo that is a logo indicating the issuer with one another. An acquisition unit 131 acquires documented evidence data indicating issued documented evidence, and an extraction unit 132 extracts an issuer name, a phone number, and a logo included in the documented evidence data. Further, a retrieval unit 133 retrieves first issuer data including an extracted issuer name that is the issuer name extracted by the extraction unit from the one or more sets of issuer data, and a determination unit 134 determines that the acquired documented evidence data is correct when a first reference phone number included in the first issuer data matches an extracted phone number that is the phone number extracted by the extraction unit or when a first reference logo included in the first issuer data matches an extracted logo that is the logo extracted by the extraction unit.

Description

データ処理装置、データ処理方法及びプログラムData processing device, data processing method and program
　本発明は、データ処理装置、データ処理方法及びプログラムに関する。 The present invention relates to a data processing device, data processing method and program.
　レシートや伝票に記載された情報を光学的文字認識によって抽出し、抽出した情報に基いて適切な費目等を付与する技術が知られている。 A technology is known that extracts information written on receipts and slips by optical character recognition and assigns appropriate expense items based on the extracted information.
特開２０１７－１７４３０９号公報JP 2017-174309 A
　特許文献１においては、認識精度を向上させるためにレシート等に記載された電話番号を光学的文字認識によって抽出し、抽出した電話番号に基づいて店舗名を特定する方法が記載されている。しかし、特許文献１に記載された技術においては、電話番号が誤認識された場合に、誤った店舗名が特定されることが想定されるため、証憑の内容が適切であるかどうかをオペレータが確認するための手間がかかるという問題が生じていた。 Patent Document 1 describes a method of extracting a telephone number written on a receipt or the like by optical character recognition and specifying a store name based on the extracted telephone number in order to improve recognition accuracy. However, in the technology described in Patent Document 1, if the phone number is misrecognized, it is assumed that the wrong store name will be specified. There was a problem that it took time to confirm.
　そこで、本発明はこれらの点に鑑みてなされたものであり、証憑の正誤判定の確認にかかる手間を削減することを目的とする。 Therefore, the present invention has been made in view of these points, and aims to reduce the time and effort required to confirm whether the evidence is correct or not.
　本発明の第１の態様のデータ処理装置においては、証憑を発行する発行元の名称である発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた１以上の発行元データを記憶する記憶部と、発行された証憑を示す証憑データを取得する取得部と、前記証憑データに含まれる発行元名称と電話番号とロゴとを抽出する抽出部と、前記１以上の発行元データから、前記抽出部が抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索する検索部と、前記第１発行元データに含まれる第１基準電話番号が、前記抽出部が抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出部が抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定する判定部と、を有する。 In the data processing device according to the first aspect of the present invention, the issuer name that is the name of the issuer that issues the voucher, the reference telephone number that is the telephone number of the issuer, and the logo indicating the issuer a storage unit for storing one or more issuer data associated with a reference logo; an acquisition unit for acquiring voucher data indicating an issued voucher; and an issuer name, telephone number, and logo included in the voucher data. a search unit for searching the first publisher data containing the extracted publisher name, which is the publisher name extracted by the extractor, from the one or more publisher data; the first publisher If the first reference phone number included in the data matches the extracted phone number, which is the phone number extracted by the extraction unit, or the first reference logo included in the first publisher data is extracted by the extraction unit a judgment unit for judging that there is no error in the acquired documented evidence data when the extracted logo matches the extracted logo.
　前記判定部は、前記第１基準ロゴの画像データと、前記抽出ロゴの画像データと、の類似度が閾値以上の場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定してもよい。 The determination unit may determine that the first reference logo and the extracted logo match when the degree of similarity between the image data of the first reference logo and the image data of the extracted logo is equal to or greater than a threshold. good.
　前記抽出部は、前記抽出ロゴが前記証憑データにおいて配置された位置を特定し、前記判定部は、前記第１基準ロゴと前記抽出ロゴとの類似度が前記閾値以上であって、前記抽出したロゴが証憑データにおける基準位置から所定範囲以内から抽出された場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定してもよい。 The extraction unit specifies a position where the extracted logo is arranged in the voucher data, and the determination unit determines that the similarity between the first reference logo and the extracted logo is equal to or greater than the threshold value, and the extracted It may be determined that the first reference logo and the extracted logo match when the logo is extracted from within a predetermined range from the reference position in the voucher data.
　前記記憶部は、前記基準ロゴと、証憑データにおける前記発行元ごとに異なる基準位置と、を関連づけて記憶し、前記判定部は、前記抽出ロゴが、証憑データにおける前記発行元ごとに異なる基準位置から所定範囲以内から抽出された場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定してもよい。 The storage unit associates and stores the reference logo with a reference position that differs for each issuer in the voucher data, and the determination unit stores the extracted logo at a reference position that differs for each issuer in the voucher data. It may be determined that the first reference logo and the extracted logo match when the logo is extracted from within a predetermined range from .
　前記第１発行元データに含まれる前記第１基準電話番号が前記抽出電話番号と一致し、かつ、前記第１発行元データに含まれる前記基準ロゴが前記抽出ロゴと一致しない場合に、前記抽出発行元名称と、前記抽出ロゴと、を関連づけて記憶するかを確認する画面をオペレータが操作するオペレータ端末に表示させる表示制御部をさらに有していてもよい。 when the first reference telephone number included in the first issuer data matches the extracted telephone number and the reference logo included in the first issuer data does not match the extracted logo, the extracted It may further include a display control unit that causes an operator terminal operated by an operator to display a screen for confirming whether to associate and store the issuer name and the extracted logo.
　前記検索部は、前記第１基準電話番号が前記抽出電話番号と一致せず、かつ前記第１基準ロゴが前記抽出ロゴと一致しない場合に、前記抽出電話番号を含む、前記第１発行元データと異なる第２発行元データをさらに検索し、前記第２発行元データに含まれる基準ロゴである第２基準ロゴが前記抽出ロゴと一致する場合に、前記抽出発行元名称を前記第２発行元データに含まれる発行元名称に置換する置換部をさらに有してもよい。 The search unit stores the first publisher data including the extracted telephone number when the first reference telephone number does not match the extracted telephone number and the first reference logo does not match the extracted logo. second publisher data different from the second publisher data, and if the second reference logo, which is the reference logo included in the second publisher data, matches the extracted logo, the extracted publisher name is changed to the second publisher It may further have a replacement part for replacing with the publisher name included in the data.
　本発明の第２の態様のデータ処理方法は、コンピュータが実行する、発行された証憑を示す証憑データを取得するステップと、前記証憑データに含まれる証憑を発行する発行元の名称である発行元名称と電話番号とロゴとを抽出するステップと、記憶部に記憶された、発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた、１以上の発行元データから、前記抽出するステップが抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索するステップと、前記第１発行元データに含まれる第１基準電話番号が、前記抽出するステップが抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出するステップが抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定するステップと、を有する。 A data processing method according to a second aspect of the present invention comprises a computer-executed step of acquiring voucher data indicating an issued voucher; a step of extracting a name, a telephone number, and a logo; an issuer name, a reference telephone number, which is the telephone number of the issuer, and a reference logo, which is a logo indicating the issuer, stored in a storage unit; a step of retrieving first publisher data including an extracted publisher name, which is the publisher name extracted by the extracting step, from one or more publisher data associated with If the first reference phone number matches the extracted phone number, which is the phone number extracted by the extracting step, or the first reference logo included in the first publisher data matches the logo extracted by the extracting step and determining that the acquired voucher data is error-free if it matches the extracted logo.
　本発明の第３の態様のプログラムは、コンピュータに実行させる、発行された証憑を示す証憑データを取得するステップと、前記証憑データに含まれる証憑を発行する発行元の名称である発行元名称と電話番号とロゴとを抽出するステップと、記憶部に記憶された、発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた、１以上の発行元データから、前記抽出するステップが抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索するステップと、前記第１発行元データに含まれる第１基準電話番号が、前記抽出するステップが抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出するステップが抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定するステップと、を有する。 A program according to a third aspect of the present invention comprises a step of obtaining voucher data indicating an issued voucher, and an issuer name, which is the name of an issuer that issues the voucher included in the voucher data, to be executed by a computer. A step of extracting a telephone number and a logo, and associating an issuer name stored in a storage unit, a reference telephone number that is the telephone number of the issuer, and a reference logo that is the logo indicating the issuer. a step of retrieving first publisher data including an extracted publisher name, which is the publisher name extracted in the extracting step, from one or more publisher data; if the reference phone number matches the extracted phone number, which is the phone number extracted by the extracting step, or the first reference logo included in the first publisher data is the logo extracted by the extracting step; and determining that the acquired voucher data is error-free if it matches the extracted logo.
　本発明によれば、証憑の正誤判定の確認にかかる手間を削減するという効果を奏する。 According to the present invention, there is an effect of reducing the time and effort required to confirm whether the voucher is correct or incorrect.
データ処理装置１における処理の流れを模式的に示す図である。3 is a diagram schematically showing the flow of processing in the data processing device 1; FIG. データ処理装置１の構成を示すブロック図である。2 is a block diagram showing the configuration of the data processing device 1; FIG. 記憶部１２が記憶する発行元データテーブルのデータ構造の一例を示す図である。4 is a diagram showing an example of the data structure of a publisher data table stored in a storage unit 12; FIG. 取得部１３１が取得する証憑データの一例を示す図である。4 is a diagram showing an example of voucher data acquired by an acquisition unit 131. FIG. データ処理装置１における処理の流れを示すフローチャートである。4 is a flow chart showing the flow of processing in the data processing device 1;
［データ処理装置１の概要］
　図１は、データ処理装置１における処理の流れを模式的に示す図である。データ処理システムＳは、請求書等の証憑に記載された内容を読み取って仕分け等の会計処理を行うためのシステムである。データ処理システムＳは、データ処理装置１、読取装置２及び会計処理装置３を有する。 [Overview of Data Processing Device 1]
FIG. 1 is a diagram schematically showing the flow of processing in the data processing device 1. As shown in FIG. The data processing system S is a system for reading the contents described in a voucher such as an invoice and performing accounting processing such as sorting. The data processing system S has a data processing device 1 , a reading device 2 and an accounting processing device 3 .
　データ処理装置１は、証憑データに含まれる文字の正誤を判定する装置である。証憑データは、外部装置から送信された画像データであってもよく、読取装置２により紙の証憑を読み取ることにより作成された画像データであってもよい。一例として、読取装置２は、紙の証憑を読み取った画像データである証憑データをデータ処理装置１に入力する。証憑データは、読取装置２がＯＣＲ（Optical Character Recognition）により文字認識をすることにより作成されたテキストデータを含む電子データであってもよい。 The data processing device 1 is a device for judging the correctness or incorrectness of the characters included in the voucher data. The voucher data may be image data transmitted from an external device, or may be image data created by reading a paper voucher with the reading device 2 . As an example, the reading device 2 inputs voucher data, which is image data obtained by reading a paper voucher, to the data processing device 1 . The voucher data may be electronic data including text data created by the reader 2 recognizing characters by OCR (Optical Character Recognition).
　データ処理装置１は、入力された証憑データに含まれる発行元名称、電話番号、ロゴを抽出する。入力された証憑データが画像データである場合、データ処理装置１は文字認識処理を実行することにより、発行元名称及び電話番号を抽出する。入力された証憑データがテキストデータを含む場合、データ処理装置１はテキストデータの内容に基づいて発行元名称及び電話番号を抽出する。 The data processing device 1 extracts the issuer name, phone number, and logo included in the input voucher data. When the input voucher data is image data, the data processing device 1 extracts the issuer name and telephone number by executing character recognition processing. If the input voucher data contains text data, the data processing device 1 extracts the issuer name and telephone number based on the content of the text data.
　データ処理装置１は、予め記憶された発行元データテーブルを参照し、抽出した発行元名称に対応する発行元電話番号及び基準ロゴを取得する。データ処理装置１は、抽出した電話番号又はロゴと、記憶された発行元の電話番号又は基準ロゴと、が一致するかを判定することで証憑データの正誤を判定する。基準ロゴは、発行元を示すロゴの画像データである。データ処理装置１は、読み取った証憑データの内容が正しいと判定する場合、会計処理装置３に証憑データを入力する。 The data processing device 1 refers to the publisher data table stored in advance, and acquires the publisher telephone number and reference logo corresponding to the extracted publisher name. The data processing device 1 determines whether the voucher data is correct or not by determining whether the extracted telephone number or logo matches the stored telephone number or reference logo of the issuer. A reference logo is image data of a logo indicating a publisher. When the data processing device 1 determines that the contents of the read voucher data are correct, the data processing device 1 inputs the voucher data to the accounting processing device 3 .
　会計処理装置３は、入力された証憑データに基づいて仕訳処理等の所定の処理を行う。ここで、データ処理装置１が扱う証憑は、例えば領収書、請求書、納品書、注文書、レシート等である。図１においては、データ処理装置１、読取装置２、会計処理装置３を別々の装置として説明したが、データ処理装置１は、読取装置２の一部として構成されてもよいし、会計処理装置３の一部として構成されてもよい。 The accounting processing device 3 performs predetermined processing such as journalizing processing based on the entered voucher data. Here, the evidences handled by the data processing apparatus 1 are, for example, receipts, invoices, statements of delivery, order forms, receipts, and the like. In FIG. 1, the data processing device 1, the reading device 2, and the accounting processing device 3 are described as separate devices, but the data processing device 1 may be configured as a part of the reading device 2, or the accounting processing device 3 may be configured.
［データ処理装置１の構成］
　図２は、データ処理装置１の構成を示すブロック図である。データ処理装置１は、通信部１１、記憶部１２及び制御部１３を有する。制御部１３は、取得部１３１、抽出部１３２、検索部１３３、判定部１３４、置換部１３５及び表示制御部１３６を有する。通信部１１は、ネットワークを介して読取装置２及び会計処理装置３と通信するための通信インターフェースである。 [Configuration of data processor 1]
FIG. 2 is a block diagram showing the configuration of the data processing device 1. As shown in FIG. The data processing device 1 has a communication section 11 , a storage section 12 and a control section 13 . The control unit 13 has an acquisition unit 131 , an extraction unit 132 , a search unit 133 , a determination unit 134 , a replacement unit 135 and a display control unit 136 . The communication unit 11 is a communication interface for communicating with the reading device 2 and the accounting processing device 3 via a network.
　記憶部１２は、例えば、ＲＯＭ（Read Only Memory）、ＲＡＭ（Random Access Memory）、ＳＳＤ（Solid State Drive）、ハードディスク等の記憶媒体である。記憶部１２は、証憑を発行する発行元の名称である発行元名称と、発行元の電話番号である基準電話番号と、発行元を示すロゴである基準ロゴと、を関連付けた１以上の発行元データを記憶する。 The storage unit 12 is, for example, a storage medium such as ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drive), and hard disk. The storage unit 12 stores one or more issuers associated with an issuer name, which is the name of an issuer that issues a voucher, a reference telephone number, which is the telephone number of the issuer, and a reference logo, which is a logo indicating the issuer. Store the original data.
　図３は、記憶部１２が記憶する発行元データテーブルのデータ構造の一例を示す図である。記憶部１２は、発行元名称と発行元電話番号と基準ロゴとを関連付けた発行元データテーブルを記憶する。記憶部１２は、基準ロゴと、証憑データにおける発行元ごとに異なる基準位置と、を関連づけて記憶してもよい。すなわち、記憶部１２は、基準ロゴと基準ロゴが証憑データに記載される位置を示す基準位置とをさらに関連付けた発行元データテーブルを記憶する。基準位置は、証憑データにおける位置を示すデータであり、例えば証憑における所定の位置（例えば左上の角の位置）を原点とする二次元の座標データにより表される。 FIG. 3 is a diagram showing an example of the data structure of the issuer data table stored in the storage unit 12. As shown in FIG. The storage unit 12 stores an issuer data table in which issuer names, issuer telephone numbers, and reference logos are associated with each other. The storage unit 12 may associate and store the reference logo and the reference position in the documented voucher data that differs for each issuer. That is, the storage unit 12 stores an issuer data table in which the reference logo and the reference position indicating the position where the reference logo is described in the voucher data are further associated with each other. The reference position is data indicating a position in the voucher data, and is represented, for example, by two-dimensional coordinate data with a predetermined position (for example, the upper left corner position) in the voucher as the origin.
　制御部１３は、例えばＣＰＵ（Central Processing Unit）である。制御部１３は、記憶部１２に記憶されている制御プログラムを実行することにより、取得部１３１、抽出部１３２、検索部１３３、判定部１３４、置換部１３５及び表示制御部１３６として機能する。 The control unit 13 is, for example, a CPU (Central Processing Unit). The control unit 13 functions as an acquisition unit 131 , an extraction unit 132 , a search unit 133 , a determination unit 134 , a replacement unit 135 and a display control unit 136 by executing control programs stored in the storage unit 12 .
　取得部１３１は、発行された証憑を示す証憑データを取得する。図４は、取得部１３１が取得する証憑データの一例を示す図である。証憑データは、一例として、宛先事業者名、宛先部署名、宛先事業者識別番号、宛先電話番号、発行元事業者名Ｃ１、ロゴＣ２、発行元電話番号Ｃ３、請求書番号、請求書発行日、請求書対象となる商品名又はサービス名、請求額、税額、振込先口座番号等を含む。証憑データは文書データ、画像データ又はテキストデータである。 The acquisition unit 131 acquires voucher data indicating the issued voucher. FIG. 4 is a diagram showing an example of voucher data acquired by the acquisition unit 131. As shown in FIG. The voucher data includes, for example, destination business name, destination department name, destination business identification number, destination telephone number, issuer business name C1, logo C2, issuer telephone number C3, invoice number, invoice issue date , including the name of the product or service subject to the invoice, the amount invoiced, the tax amount, the bank account number, etc. The voucher data is document data, image data or text data.
　抽出部１３２は、証憑データに含まれる発行元名称と電話番号とロゴとを抽出する。抽出部１３２は、読取装置２から入力された証憑を読み取った画像データである証憑データを文字認識することで、証憑データに含まれる発行元名称（以下抽出発行元名称という場合がある）と電話番号（以下抽出電話番号という場合がある）とを示すテキストデータを抽出する。さらに、抽出部１３２は、証憑データを画像認識により、ロゴを示す画像データ（以下、抽出ロゴという場合がある）を抽出する。 The extraction unit 132 extracts the issuer name, phone number, and logo included in the voucher data. The extraction unit 132 performs character recognition on the voucher data, which is image data obtained by reading the voucher input from the reading device 2, so that the name of the issuer included in the voucher data (hereinafter sometimes referred to as the extracted issuer name) and the telephone Extracts text data indicating a number (hereinafter sometimes referred to as an extracted telephone number). Furthermore, the extracting unit 132 extracts image data representing a logo (hereinafter sometimes referred to as an extracted logo) by image recognition of the voucher data.
　抽出部１３２は、抽出ロゴが証憑データにおいて配置された位置を特定してもよい。抽出部１３２は、画像データである証憑データにおいて、抽出ロゴが証憑データに配置された位置である証憑位置データを取得する。証憑位置データは例えば二次元の座標データである。証憑位置データは例えば、ロゴを抽出した領域の重心又は任意の端点（左上等）の座標である。 The extraction unit 132 may specify the position where the extracted logo is arranged in the voucher data. The extraction unit 132 acquires voucher position data, which is the position at which the extracted logo is arranged in the voucher data, which is image data. The voucher position data is, for example, two-dimensional coordinate data. The voucher position data is, for example, the center of gravity of the logo extracted area or the coordinates of an arbitrary end point (upper left, etc.).
　検索部１３３は、１以上の発行元データから、抽出部１３２が抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索する。検索部１３３は、記憶部１２が記憶する発行元データテーブルから、抽出発行元名称と発行元名称が一致する発行元データを検索し、抽出された発行元データに関連付けられた電話番号（基準電話番号という場合がある）とロゴ（基準ロゴという場合がある）を取得する。 The search unit 133 searches for the first publisher data containing the extracted publisher name, which is the publisher name extracted by the extraction unit 132, from one or more publisher data. The search unit 133 searches the publisher data table stored in the storage unit 12 for publisher data whose extracted publisher name matches the publisher name, and retrieves the telephone number (reference telephone number) associated with the extracted publisher data. (sometimes called a number) and a logo (sometimes called a reference logo).
　判定部１３４は、第１発行元データに含まれる第１基準電話番号が、抽出部１３２が抽出した電話番号である抽出電話番号と一致する場合、又は第１発行元データに含まれる第１基準ロゴが、抽出部１３２が抽出したロゴである抽出ロゴと一致する場合に、取得された証憑データに誤りが無いと判定する。判定部１３４は、第１基準電話番号を構成する文字列と抽出電話番号を構成する文字列とを比較する。さらに判定部１３４は、第１基準ロゴと抽出ロゴとを比較する。そして、判定部１３４は、電話番号の比較結果とロゴの比較結果のうちいずれか一方が一致していれば取得した証憑データに誤りが無いと判定する。 The determination unit 134 determines whether the first reference telephone number included in the first issuer data matches the extracted telephone number, which is the telephone number extracted by the extraction unit 132, or the first reference telephone number included in the first issuer data. When the logo matches the extracted logo, which is the logo extracted by the extraction unit 132, it is determined that the acquired voucher data is correct. The determination unit 134 compares the character string that forms the first reference telephone number and the character string that forms the extracted telephone number. Furthermore, the determination unit 134 compares the first reference logo and the extracted logo. If either one of the telephone number comparison result and the logo comparison result matches, the determination unit 134 determines that there is no error in the acquired voucher data.
　判定部１３４は、第１基準ロゴの画像データと、抽出ロゴの画像データと、の類似度が閾値以上の場合に、第１基準ロゴと抽出ロゴとが一致すると判定してもよい。判定部１３４は、画像データである第１基準ロゴと抽出ロゴとの類似度を算出する。判定部１３４は、一例として、第１基準ロゴ及び抽出ロゴの特徴点を抽出し、抽出した特徴点の距離に基づいて算出する。類似度は例えば０から１の間の値を取る実数で表される。判定部１３４は、算出した類似度が閾値以上の場合に第１基準ロゴと抽出ロゴとが一致すると判定する。類似度が０から１で表される場合、閾値は一例として０．８と設定される。 The determination unit 134 may determine that the first reference logo and the extracted logo match when the degree of similarity between the image data of the first reference logo and the image data of the extracted logo is equal to or greater than a threshold. The determination unit 134 calculates the degree of similarity between the first reference logo, which is image data, and the extracted logo. As an example, the determination unit 134 extracts the feature points of the first reference logo and the extracted logo, and calculates based on the distance of the extracted feature points. The degree of similarity is represented by a real number between 0 and 1, for example. The determining unit 134 determines that the first reference logo and the extracted logo match when the calculated degree of similarity is equal to or greater than the threshold. When the degree of similarity is represented by 0 to 1, the threshold is set to 0.8 as an example.
　例えば、ロゴの形状や色彩によっては用紙やインク等の影響で表現されるロゴが一定せず、判定精度を安定させることが困難な場合も想定される。そこで、判定部１３４は、基準ロゴごとに異なる閾値に基づいて第１基準ロゴと抽出ロゴとが一致するか否かを判定してもよい。この場合、記憶部１２は、発行元データテーブルにおいて、基準ロゴごとに異なる閾値を記憶する。判定部１３４は、記憶部１２に記憶された基準ロゴと基準ロゴに関連付けられた閾値を読み出し、基準ロゴと抽出ロゴとの類似度を算出する。判定部１３４は、算出した類似度が記憶部１２から読みだした閾値以上であれば基準ロゴと抽出ロゴとが一致すると判定する。 For example, depending on the shape and color of the logo, it may be difficult to stabilize the judgment accuracy due to the inconsistency of the logo expressed due to the influence of paper, ink, etc. Therefore, the determination unit 134 may determine whether or not the first reference logo and the extracted logo match based on a threshold that differs for each reference logo. In this case, the storage unit 12 stores different threshold values for each reference logo in the issuer data table. The determination unit 134 reads the reference logo stored in the storage unit 12 and the threshold associated with the reference logo, and calculates the similarity between the reference logo and the extracted logo. The determining unit 134 determines that the reference logo and the extracted logo match when the calculated similarity is equal to or greater than the threshold value read from the storage unit 12 .
　なお、閾値は、ユーザがデータ処理装置１と通信可能に接続されたオペレータ端末（不図示）を操作することで設定できるように構成されてもよい。オペレータ端末は、例えば請求書の処理を行う経理担当者のようなオペレータが使用する端末である。データ処理装置１がこのように構成されることで、類似度の判断結果が安定しないロゴについても判定精度を向上させることができる。 Note that the threshold may be configured so that the user can set it by operating an operator terminal (not shown) communicatively connected to the data processing device 1 . An operator terminal is a terminal used by an operator, such as an accountant who processes bills. By configuring the data processing device 1 in this way, it is possible to improve the determination accuracy even for logos whose similarity determination results are not stable.
　判定部１３４は、抽出ロゴから、ロゴを構成する要素を抽出し、それぞれの要素ごとに基準ロゴとの類似度を算出してもよい。ロゴを構成する要素は、例えば色、形状、大きさ、ロゴに含まれるテキストである。この場合、判定部１３４は、各要素の類似度の和又は績を算出し、算出した類似度の和又は績が閾値以上である場合にロゴが一致すると判定してもよい。判定部１３４は、それぞれの要素の類似度が閾値以上である場合にロゴが一致すると判定してもよい。この場合、記憶部１２は、要素ごとの閾値を記憶しており、判定部１３４は要素ごとの類似度を記憶部１２から読みだして判定してもよい。 The determination unit 134 may extract the elements that make up the logo from the extracted logo, and calculate the degree of similarity between each element and the reference logo. Elements constituting a logo are, for example, color, shape, size, and text included in the logo. In this case, the determining unit 134 may calculate the sum or score of similarities of each element, and determine that the logos match when the calculated sum or score of similarities is equal to or greater than a threshold. The determination unit 134 may determine that the logos match when the degree of similarity of each element is equal to or greater than a threshold. In this case, the storage unit 12 stores a threshold value for each element, and the determination unit 134 may read the similarity for each element from the storage unit 12 and perform determination.
　判定部１３４は、第１基準ロゴと抽出ロゴとの類似度が閾値以上であって、抽出したロゴが証憑データにおける基準位置から所定範囲以内から抽出された場合に、第１基準ロゴと抽出ロゴとが一致すると判定してもよい。すなわち、基準ロゴと抽出ロゴとの類似度が閾値以上である場合、判定部１３４は、証憑データにおけるロゴが配置される位置を示す座標データである基準位置と、抽出部１３２が特定した証憑位置データとを比較し、両者の差分が閾値以内である場合に基準ロゴと抽出ロゴとが一致すると判定する。 If the degree of similarity between the first reference logo and the extracted logo is equal to or greater than a threshold and the extracted logo is extracted from within a predetermined range from the reference position in the voucher data, the determination unit 134 determines that the first reference logo and the extracted logo are separated. may be determined to match. That is, when the degree of similarity between the reference logo and the extracted logo is equal to or greater than the threshold, the determination unit 134 determines the reference position, which is coordinate data indicating the position where the logo is arranged in the voucher data, and the voucher position specified by the extraction unit 132. data, and if the difference between the two is within a threshold, it is determined that the reference logo and the extracted logo match.
　基準位置は、発行元ごとに異なる位置が設定されてもよい。判定部１３４は、記憶部１２が記憶する発行元データテーブルから抽出発行元名称に関連付けられた基準位置を取得する。判定部１３４は、抽出ロゴが、証憑データにおける発行元ごとに異なる基準位置から所定範囲以内から抽出された場合に、第１基準ロゴと抽出ロゴとが一致すると判定してもよい。判定部１３４は、取得した基準位置と抽出部１３２が特定した証憑位置データとを比較し、両者の差分が閾値以内である場合に基準ロゴと抽出ロゴとが一致すると判定する。判定部１３４は、記憶部１２が記憶する発行元データから発行元の基準ロゴに対応する基準位置を取得する。判定部１３４は、取得した基準位置と、抽出部１３２が特定した証憑位置データとを比較し、両者の差分が閾値以内である場合に基準ロゴと抽出ロゴとが一致すると判定する。 A different reference position may be set for each issuer. The determination unit 134 acquires the reference position associated with the extracted publisher name from the publisher data table stored in the storage unit 12 . The determination unit 134 may determine that the first reference logo and the extracted logo match when the extracted logo is extracted from within a predetermined range from a reference position that differs for each issuer in the voucher data. The determination unit 134 compares the obtained reference position with the voucher position data specified by the extraction unit 132, and determines that the reference logo and the extracted logo match when the difference between the two is within a threshold. The determination unit 134 acquires the reference position corresponding to the reference logo of the publisher from the publisher data stored in the storage unit 12 . The determination unit 134 compares the obtained reference position with the voucher position data specified by the extraction unit 132, and determines that the reference logo and the extracted logo match when the difference between the two is within a threshold.
　データ処理装置１がこのように構成されることで、証憑の発行元ごとに証憑のフォーマットが異なる場合であっても、証憑に記載された発行元を示すロゴを読み取ることができる。 By configuring the data processing device 1 in this way, even if the format of the voucher differs for each issuer of the voucher, it is possible to read the logo indicating the issuer written on the voucher.
　発行元名称の読取結果が異なる場合に、名称以外の要素が一致する発行元データにより抽出した発行元名称を補正し、読取内容に誤りが無いことを判定してもよい。検索部１３３は、第１基準電話番号が抽出電話番号と一致せず、かつ第１基準ロゴが抽出ロゴと一致しない場合に、抽出電話番号を含む、第１発行元データと異なる第２発行元データをさらに検索してもよい。具体的には、抽出電話番号及び抽出ロゴと、抽出した発行元名称を含む第１発行元データに含まれる電話番号及びロゴとが一致しない場合、検索部１３３は、記憶部１２に記憶された複数の発行元データテーブルから抽出電話番号を含む発行元データ（第２発行元データという場合がある）を検索する。 If the read result of the publisher name is different, the extracted publisher name may be corrected by the publisher data that matches elements other than the name, and it may be determined that there is no error in the read content. If the first reference phone number does not match the extracted phone number and the first reference logo does not match the extracted logo, the search unit 133 searches for a second publisher data that includes the extracted phone number and is different from the first publisher data. You may search for more data. Specifically, when the extracted phone number and extracted logo do not match the phone number and logo included in the first publisher data including the extracted publisher name, the search unit 133 retrieves the A plurality of issuer data tables are searched for issuer data (sometimes referred to as second issuer data) including the extracted telephone number.
　置換部１３５は、第２発行元データに含まれる基準ロゴである第２基準ロゴが抽出ロゴと一致する場合に、抽出発行元名称を第２発行元データに含まれる発行元名称に置換する。判定部１３４は、第２発行元データに含まれる基準ロゴと抽出ロゴとの類似度を算出する。置換部１３５は、算出した類似度が所定以上の場合、抽出発行元名称を第２発行元データに含まれる発行元名称に置換する。 The replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data when the second reference logo, which is the reference logo included in the second publisher data, matches the extracted logo. The determination unit 134 calculates the degree of similarity between the reference logo and the extracted logo included in the second publisher data. If the calculated similarity is equal to or higher than a predetermined value, the replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data.
　データ処理装置１がこのように構成されることで、抽出した電話番号及びロゴを用いて発行元を特定できる場合に、特定した情報に基づいて発行元名称を置換することができる。その結果、オペレータは証憑を参照して発行元名称を確認せずに、データ処理装置１から出力された情報に基づいて証憑の処理を進めることが可能となる。 By configuring the data processing device 1 in this way, when the issuer can be specified using the extracted phone number and logo, the issuer name can be replaced based on the specified information. As a result, the operator can proceed with the processing of the voucher based on the information output from the data processing device 1 without referring to the voucher and confirming the issuer name.
　表示制御部１３６は、オペレータ端末のような外部端末に、判定部１３４による判定結果に基づく情報を表示させる。発行元名称と電話番号が一致するが、ロゴが一致しない場合は、ロゴが変更になった可能性が想定される。そこで、表示制御部１３６は、このような場合にロゴの登録を行うかどうかをオペレータに確認する画面をオペレータ端末に表示させてもよい。 The display control unit 136 causes an external terminal such as an operator terminal to display information based on the determination result of the determination unit 134 . If the issuer name and phone number match, but the logo does not match, it is assumed that the logo may have changed. Therefore, the display control unit 136 may cause the operator terminal to display a screen for asking the operator whether or not to register the logo in such a case.
　具体的には、表示制御部１３６は、第１発行元データに含まれる第１基準電話番号が抽出電話番号と一致し、かつ、第１発行元データに含まれる基準ロゴが抽出ロゴと一致しない場合に、抽出発行元名称と、抽出ロゴと、を関連づけて記憶するかを確認する画面をオペレータが操作するオペレータ端末に表示させる。判定部１３４が第１基準電話番号と抽出電話番号とは一致するが、基準ロゴと抽出ロゴとが一致しないと判定する場合、表示制御部１３６は、抽出ロゴが発行元データに記憶された情報と異なることをオペレータ端末の画面上に表示し、オペレータに抽出ロゴを発行元データに登録してよいかを確認する画面を表示する。 Specifically, the display control unit 136 determines that the first reference telephone number included in the first issuer data matches the extracted telephone number and the reference logo included in the first issuer data does not match the extracted logo. In this case, the operator terminal operated by the operator displays a screen for confirming whether to store the extracted issuer name and the extracted logo in association with each other. When the determination unit 134 determines that the first reference telephone number and the extracted telephone number match but the reference logo and the extracted logo do not match, the display control unit 136 determines that the extracted logo is stored in the publisher data. is displayed on the screen of the operator terminal, and a screen is displayed asking the operator whether it is acceptable to register the extracted logo in the issuer data.
　オペレータが登録を許可する操作を行った場合、表示制御部１３６は、発行元名称と抽出されたロゴとを関連付けて記憶部１２が記憶する発行元データテーブルに記憶させる。データ処理装置１がこのように構成されることで、ロゴが変更になった場合において、読み取った証憑データに含まれるロゴを発行元データに登録することができる。そして、データ処理装置１は登録された新しいロゴに基づいて証憑データの正誤を判定できるようになる。その結果、証憑の確認に必要なオペレータの手間を削減することができる。 When the operator performs an operation to permit registration, the display control unit 136 associates the publisher name with the extracted logo and stores them in the publisher data table stored in the storage unit 12 . By configuring the data processing device 1 in this way, when the logo is changed, the logo included in the read voucher data can be registered in the issuer data. Then, the data processing device 1 can judge whether the voucher data is correct or incorrect based on the new registered logo. As a result, it is possible to reduce the operator's labor required for confirming the voucher.
　なお、表示制御部１３６は、第１発行元データに含まれる第１基準電話番号が抽出電話番号と一致せず、かつ、第１発行元データに含まれる基準ロゴが抽出ロゴと一致する場合に、抽出発行元名称と、抽出電話番号と、を関連づけて記憶するかを確認する画面をオペレータが操作するオペレータ端末に表示させるように構成されてもよい。 In addition, when the first reference telephone number included in the first issuer data does not match the extracted telephone number and the reference logo included in the first issuer data matches the extracted logo, the display control unit 136 , the extracted issuer name and the extracted telephone number may be configured to display a screen on the operator terminal operated by the operator to confirm whether to associate and store the extracted publisher name and the extracted telephone number.
［データ処理装置１における処理の流れ］
　図５は、データ処理装置１における処理の流れを示すフローチャートである。図５におけるフローチャートは、データ処理装置１が読取装置２から証憑データを受信するタイミングから開始している。取得部１３１は、証憑データを取得する（Ｓ１０１）。抽出部１３２は、取得した証憑データから発行元名称、ロゴ及び電話番号を抽出する（Ｓ１０２）。 [Flow of processing in data processor 1]
FIG. 5 is a flow chart showing the flow of processing in the data processing device 1. As shown in FIG. The flow chart in FIG. 5 starts from the timing when the data processing device 1 receives voucher data from the reading device 2 . The acquiring unit 131 acquires voucher data (S101). The extraction unit 132 extracts the issuer name, logo, and telephone number from the acquired voucher data (S102).
　検索部１３３は、記憶部１２が記憶する発行元データテーブルから、抽出した発行元名称を含む第１発行元データを検索する（Ｓ１０３）。判定部１３４は、証憑データから抽出した抽出ロゴ又は電話番号と、検索結果として取得された発行元データに含まれるロゴ又は電話番号が一致するかどうかを判定する（Ｓ１０４）。 The search unit 133 searches the first publisher data containing the extracted publisher name from the publisher data table stored in the storage unit 12 (S103). The determination unit 134 determines whether the extracted logo or telephone number extracted from the voucher data matches the logo or telephone number included in the issuer data acquired as the search result (S104).
　ロゴ又は電話番号が一致する場合（Ｓ１０４におけるＹＥＳ）、判定部１３４は、ロゴと電話番号いずれも一致しているかどうかを判定する（Ｓ１０５）。ロゴと電話番号のいずれか一方が異なる場合（Ｓ１０５におけるＮＯ）、表示制御部１３６は、オペレータが操作するオペレータ端末に確認画面を表示し（Ｓ１０６）、オペレータの確認操作が行われた場合、処理をＳ１１０に進める。ロゴと電話番号いずれも一致している場合（Ｓ１０５におけるＹＥＳ）、判定部１３４は、処理をＳ１１０に進める。 If the logos or phone numbers match (YES in S104), the determination unit 134 determines whether both the logos and phone numbers match (S105). If either the logo or the phone number is different (NO in S105), the display control unit 136 displays a confirmation screen on the operator terminal operated by the operator (S106), and if the operator confirms the operation, the process to S110. If both the logo and the phone number match (YES in S105), determination unit 134 advances the process to S110.
　ロゴ又は電話番号が一致しない場合（Ｓ１０４におけるＮＯ）、検索部１３３は、抽出した電話番号を含む第２発行元データを検索する（Ｓ１０７）。判定部１３４は、第２発行元データに含まれるロゴと抽出したロゴが一致するかどうかを判定する（Ｓ１０８）。第２発行元データに含まれるロゴと抽出したロゴが一致する場合（Ｓ１０８におけるＹＥＳ）、置換部１３５は、抽出発行元名称を第２発行元データに含まれる発行元名称に置換する（Ｓ１０９）。判定部１３４は、取得した証憑データに誤りがないと判定し（Ｓ１１０）、証憑データを会計処理装置３に入力し、処理を終了する。 If the logo or phone number do not match (NO in S104), the search unit 133 searches for the second publisher data containing the extracted phone number (S107). The determination unit 134 determines whether the logo included in the second publisher data matches the extracted logo (S108). If the logo included in the second publisher data matches the extracted logo (YES in S108), the replacement unit 135 replaces the extracted publisher name with the publisher name included in the second publisher data (S109). . The determination unit 134 determines that there is no error in the acquired voucher data (S110), inputs the voucher data to the accounting processing device 3, and terminates the process.
　第２発行元データに含まれるロゴと抽出したロゴが一致しない場合（Ｓ１０８におけるＮＯ）、取得した証憑データと一致する発行元データが無いことを示すエラー情報をオペレータ端末に出力するエラー処理を行い（Ｓ１１１）、データ処理装置１は処理を終了する。 If the logo included in the second issuer data and the extracted logo do not match (NO in S108), error processing is performed to output error information to the operator terminal indicating that there is no issuer data that matches the acquired voucher data. (S111), the data processing apparatus 1 terminates the process.
［データ処理装置１による効果］
　以上説明したように、データ処理装置１においては、証憑を発行する発行元の名称である発行元名称と、発行元の電話番号である基準電話番号と、発行元を示すロゴである基準ロゴと、を関連付けた１以上の発行元データを記憶する記憶部１２を有する。そして、取得部１３１が、発行された証憑を示す証憑データを取得し、抽出部１３２が、証憑データに含まれる発行元名称と電話番号とロゴとを抽出する。さらに、検索部１３３が、１以上の発行元データから、抽出部１３２が抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索し、判定部１３４が、第１発行元データに含まれる第１基準電話番号が、抽出部１３２が抽出した電話番号である抽出電話番号と一致する場合、又は第１発行元データに含まれる第１基準ロゴが、抽出部１３２が抽出したロゴである抽出ロゴと一致する場合に、取得された証憑データに誤りが無いと判定する。 [Effects of the data processing device 1]
As described above, in the data processing device 1, the issuer name, which is the name of the issuer that issues the voucher, the reference telephone number, which is the telephone number of the issuer, and the reference logo, which is the logo indicating the issuer. has a storage unit 12 for storing one or more issuer data associated with . Then, the acquiring unit 131 acquires voucher data indicating the issued voucher, and the extracting unit 132 extracts the issuer name, telephone number, and logo included in the voucher data. Further, the search unit 133 searches for first publisher data including the extracted publisher name, which is the publisher name extracted by the extraction unit 132, from the one or more publisher data, and the determination unit 134 searches for the first publisher data. If the first reference telephone number included in the data matches the extracted telephone number that is the telephone number extracted by the extraction unit 132, or if the first reference logo included in the first issuer data is extracted by the extraction unit 132 If it matches the extracted logo, which is the logo, it is determined that the acquired voucher data is correct.
　データ処理装置１は、判定した結果をオペレータ端末に表示させたり、証憑データに誤りがないと判定したことを条件として、証憑データを会計処理装置３に送信したりする。データ処理装置１がこのように構成されることで、証憑を処理する担当者が証憑の正誤を確認することなく自動的に証憑の正誤を判定することができるので、担当者が証憑の正誤の確認にかかる手間を削減することができる。 The data processing device 1 displays the judgment result on the operator terminal, and sends the evidenced data to the accounting processing device 3 on the condition that it is judged that there is no error in the evidenced data. By configuring the data processing device 1 in this way, the person in charge of processing the voucher can automatically judge whether the voucher is correct or not without confirming the correctness of the voucher. The time required for confirmation can be reduced.
　以上、実施の形態を用いて本発明を説明したが、本発明の技術的範囲は上記実施の形態に記載の範囲には限定されず、その要旨の範囲内で種々の変形及び変更が可能である。例えば、装置の全部又は一部は、任意の単位で機能的又は物理的に分散・統合して構成することができる。また、複数の実施の形態の任意の組み合わせによって生じる新たな実施の形態も、本発明の実施の形態に含まれる。組み合わせによって生じる新たな実施の形態の効果は、もとの実施の形態の効果を併せ持つ。 Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist thereof. be. For example, all or part of the device can be functionally or physically distributed and integrated in arbitrary units. In addition, new embodiments resulting from arbitrary combinations of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment caused by the combination has the effect of the original embodiment.
１　データ処理装置
２　読取装置
３　会計処理装置
１１　通信部
１２　記憶部
１３　制御部
１３１　取得部
１３２　抽出部
１３３　検索部
１３４　判定部
１３５　置換部
１３６　表示制御部 1 Data processing device 2 Reading device 3 Accounting device 11 Communication unit 12 Storage unit 13 Control unit 131 Acquisition unit 132 Extraction unit 133 Search unit 134 Judgment unit 135 Replacement unit 136 Display control unit

Claims (8)

  1. 　証憑を発行する発行元の名称である発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた１以上の発行元データを記憶する記憶部と、
    　発行された証憑を示す証憑データを取得する取得部と、
    　前記証憑データに含まれる発行元名称と電話番号とロゴとを抽出する抽出部と、
    　前記１以上の発行元データから、前記抽出部が抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索する検索部と、
    　前記第１発行元データに含まれる第１基準電話番号が、前記抽出部が抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出部が抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定する判定部と、
    　を有するデータ処理装置。     One or more issuer data that associates an issuer name that is the name of the issuer that issues the voucher, a reference telephone number that is the telephone number of the issuer, and a reference logo that is the logo that indicates the issuer. a storage unit that stores
    an acquisition unit that acquires voucher data indicating the issued voucher;
    an extraction unit for extracting the issuer name, telephone number, and logo included in the voucher data;
    a search unit that searches the one or more publisher data for first publisher data that includes an extracted publisher name that is the publisher name extracted by the extractor;
    If the first reference telephone number included in the first issuer data matches the extracted telephone number, which is the telephone number extracted by the extraction unit, or if the first reference logo included in the first issuer data is a judging unit that judges that the acquired documented evidence data has no error when it matches the extracted logo, which is the logo extracted by the extracting unit;
    A data processing device having
  2. 　前記判定部は、前記第１基準ロゴの画像データと、前記抽出ロゴの画像データと、の類似度が閾値以上の場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定する、
    　請求項１に記載するデータ処理装置。     The determination unit determines that the first reference logo and the extracted logo match when a degree of similarity between the image data of the first reference logo and the image data of the extracted logo is equal to or greater than a threshold.
    A data processing apparatus according to claim 1.
  3. 　前記抽出部は、前記抽出ロゴが前記証憑データにおいて配置された位置を特定し、
    　前記判定部は、前記第１基準ロゴと前記抽出ロゴとの類似度が前記閾値以上であって、前記抽出したロゴが証憑データにおける基準位置から所定範囲以内から抽出された場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定する、
    　請求項２に記載するデータ処理装置。     The extraction unit identifies a position where the extracted logo is arranged in the voucher data,
    If the similarity between the first reference logo and the extracted logo is equal to or greater than the threshold value and the extracted logo is extracted from within a predetermined range from a reference position in the evidenced document data, the determination unit determines the first determining that the reference logo and the extracted logo match;
    3. A data processing apparatus according to claim 2.
  4. 　前記記憶部は、前記基準ロゴと、証憑データにおける前記発行元ごとに異なる基準位置と、を関連づけて記憶し、
    　前記判定部は、前記抽出ロゴが、証憑データにおける前記発行元ごとに異なる基準位置から所定範囲以内から抽出された場合に、前記第１基準ロゴと前記抽出ロゴとが一致すると判定する、
    　請求項３に記載するデータ処理装置。     the storage unit associates and stores the reference logo with a reference position in the voucher data that differs for each issuer;
    The determining unit determines that the first reference logo and the extracted logo match when the extracted logo is extracted from within a predetermined range from a reference position that differs for each issuer in the voucher data.
    4. A data processing apparatus according to claim 3.
  5. 　前記第１発行元データに含まれる前記第１基準電話番号が前記抽出電話番号と一致し、かつ、前記第１発行元データに含まれる前記基準ロゴが前記抽出ロゴと一致しない場合に、前記抽出発行元名称と、前記抽出ロゴと、を関連づけて記憶するかを確認する画面をオペレータが操作するオペレータ端末に表示させる表示制御部をさらに有する、
    　請求項１から４のいずれか１項に記載するデータ処理装置。     when the first reference telephone number included in the first issuer data matches the extracted telephone number and the reference logo included in the first issuer data does not match the extracted logo, the extracted further comprising a display control unit that causes an operator terminal operated by an operator to display a screen for confirming whether to associate and store the publisher name and the extracted logo,
    A data processing apparatus according to any one of claims 1 to 4.
  6. 　前記検索部は、前記第１基準電話番号が前記抽出電話番号と一致せず、かつ前記第１基準ロゴが前記抽出ロゴと一致しない場合に、前記抽出電話番号を含む、前記第１発行元データと異なる第２発行元データをさらに検索し、
    　前記第２発行元データに含まれる基準ロゴである第２基準ロゴが前記抽出ロゴと一致する場合に、前記抽出発行元名称を前記第２発行元データに含まれる発行元名称に置換する置換部をさらに有する、
    　請求項１から５のいずれか１項に記載するデータ処理装置。     The search unit stores the first publisher data including the extracted telephone number when the first reference telephone number does not match the extracted telephone number and the first reference logo does not match the extracted logo. further search for second publisher data different from
    A replacement unit that replaces the extracted publisher name with the publisher name included in the second publisher data when the second reference logo, which is the reference logo included in the second publisher data, matches the extracted logo. further having
    A data processing apparatus according to any one of claims 1 to 5.
  7. 　コンピュータが実行する、
    　発行された証憑を示す証憑データを取得するステップと、
    　前記証憑データに含まれる証憑を発行する発行元の名称である発行元名称と電話番号とロゴとを抽出するステップと、
    　記憶部に記憶された、発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた、１以上の発行元データから、前記抽出するステップが抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索するステップと、
    　前記第１発行元データに含まれる第１基準電話番号が、前記抽出するステップが抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出するステップが抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定するステップと、
    　を有するデータ処理方法。     the computer runs
    obtaining voucher data indicative of issued vouchers;
    a step of extracting the issuer name, telephone number, and logo, which are the name of the issuer that issues the voucher, included in the voucher data;
    from one or more issuer data that associates an issuer name, a reference telephone number that is the telephone number of the issuer, and a reference logo that is the logo that indicates the issuer, stored in a storage unit; searching for first publisher data containing the extracted publisher name, which is the publisher name extracted by the extracting step;
    if the first reference phone number included in the first publisher data matches the extracted phone number, which is the phone number extracted in the extracting step, or if the first reference logo included in the first publisher data is a step of determining that there is no error in the acquired voucher data if the extracted logo matches the logo extracted in the step of extracting;
    A data processing method comprising:
  8. 　コンピュータに実行させる、
    　発行された証憑を示す証憑データを取得するステップと、
    　前記証憑データに含まれる証憑を発行する発行元の名称である発行元名称と電話番号とロゴとを抽出するステップと、
    　記憶部に記憶された、発行元名称と、前記発行元の電話番号である基準電話番号と、前記発行元を示すロゴである基準ロゴと、を関連付けた、１以上の発行元データから、前記抽出するステップが抽出した発行元名称である抽出発行元名称を含む第１発行元データを検索するステップと、
    　前記第１発行元データに含まれる第１基準電話番号が、前記抽出するステップが抽出した電話番号である抽出電話番号と一致する場合、又は前記第１発行元データに含まれる第１基準ロゴが、前記抽出するステップが抽出したロゴである抽出ロゴと一致する場合に、取得された前記証憑データに誤りが無いと判定するステップと、
    　を有するプログラム。     make the computer run
    obtaining voucher data indicative of issued vouchers;
    a step of extracting the issuer name, telephone number, and logo, which are the name of the issuer that issues the voucher, included in the voucher data;
    from one or more issuer data that associates an issuer name, a reference telephone number that is the telephone number of the issuer, and a reference logo that is the logo that indicates the issuer, stored in a storage unit; searching for first publisher data containing the extracted publisher name, which is the publisher name extracted by the extracting step;
    if the first reference phone number included in the first publisher data matches the extracted phone number, which is the phone number extracted in the extracting step, or if the first reference logo included in the first publisher data is a step of determining that there is no error in the acquired voucher data if the extracted logo matches the logo extracted in the step of extracting;
    A program with
PCT/JP2021/030274 2021-08-19 2021-08-19 Data processing device, data processing method, and program WO2023021636A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2021/030274 WO2023021636A1 (en) 2021-08-19 2021-08-19 Data processing device, data processing method, and program
JP2021548658A JP7037237B1 (en) 2021-08-19 2021-08-19 Data processing equipment, data processing methods and programs
JP2022027702A JP2023029196A (en) 2021-08-19 2022-02-25 Data processing device, data processing method and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/030274 WO2023021636A1 (en) 2021-08-19 2021-08-19 Data processing device, data processing method, and program

Publications (1)

Publication Number Publication Date
WO2023021636A1 true WO2023021636A1 (en) 2023-02-23

Family

ID=81213572

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/030274 WO2023021636A1 (en) 2021-08-19 2021-08-19 Data processing device, data processing method, and program

Country Status (2)

Country Link
JP (2) JP7037237B1 (en)
WO (1) WO2023021636A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140195416A1 (en) * 2013-01-10 2014-07-10 Bill.Com, Inc. Systems and methods for payment processing
JP2017174309A (en) * 2016-03-25 2017-09-28 大日本印刷株式会社 Portable information device, server device, data input supporting system, and program
JP2020144636A (en) * 2019-03-07 2020-09-10 セイコーエプソン株式会社 Information processing apparatus, learning device, and learned model
JP6794564B1 (en) * 2020-04-09 2020-12-02 ファーストアカウンティング株式会社 Invoice management device, invoice management method and program
JP2021072110A (en) * 2020-04-30 2021-05-06 株式会社日本デジタル研究所 Voucher determination device, accounting processing device, voucher determination program, voucher determination system, and voucher determination method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140195416A1 (en) * 2013-01-10 2014-07-10 Bill.Com, Inc. Systems and methods for payment processing
JP2017174309A (en) * 2016-03-25 2017-09-28 大日本印刷株式会社 Portable information device, server device, data input supporting system, and program
JP2020144636A (en) * 2019-03-07 2020-09-10 セイコーエプソン株式会社 Information processing apparatus, learning device, and learned model
JP6794564B1 (en) * 2020-04-09 2020-12-02 ファーストアカウンティング株式会社 Invoice management device, invoice management method and program
JP2021072110A (en) * 2020-04-30 2021-05-06 株式会社日本デジタル研究所 Voucher determination device, accounting processing device, voucher determination program, voucher determination system, and voucher determination method

Also Published As

Publication number Publication date
JP2023029196A (en) 2023-03-03
JP7037237B1 (en) 2022-03-16
JPWO2023021636A1 (en) 2023-02-23

Similar Documents

Publication Publication Date Title
US11348330B2 (en) Key value extraction from documents
JP4996940B2 (en) Form recognition device and program thereof
JP6702629B2 (en) Type OCR system
US9158833B2 (en) System and method for obtaining document information
US11328504B2 (en) Image-processing device for document image, image-processing method for document image, and storage medium on which program is stored
JP2004139484A (en) Form processing device, program for implementing it, and program for creating form format
US11321936B2 (en) Image processing device, image processing method, and storage medium storing program
WO2007049270A2 (en) Form data extraction without customization
JP2005173730A (en) Business form ocr program, method, and device
US20150310269A1 (en) System and Method of Using Dynamic Variance Networks
CN109726369A (en) A kind of intelligent template questions record Implementation Technology based on normative document
JP2016192223A (en) Accounting information reading system and program
WO2023021636A1 (en) Data processing device, data processing method, and program
JP4347675B2 (en) Form OCR program, method and apparatus
JP4356908B2 (en) Automatic financial statement input device
US20210303782A1 (en) Information processing apparatus and non-transitory computer readable medium
US11989693B2 (en) Image-processing device, image processing method, and storage medium on which program is stored
JP3159087B2 (en) Document collation device and method
JPH10207981A (en) Document recognition method
CN104680414A (en) Receipt data manage system, method and device
JP3000349B2 (en) Key input editing method and editing device
JP2004164376A (en) Identification-code-attached form, form reading program, and form creation program
JP6541936B2 (en) Information processing apparatus, form reading method, and program
JPH06333085A (en) Optical character reader
JP2014002662A (en) Form printing system

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021548658

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21954209

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21954209

Country of ref document: EP

Kind code of ref document: A1