JP7170366B1 - Data processing device, data processing method and program - Google Patents

Abstract

The data processing device 1 includes a storage unit 22 for storing a plurality of determination data indicating at least one of the characteristics of predetermined characters or images included in the regular voucher data in association with a plurality of issuers of the voucher, and the voucher data. an acquiring unit 231 that acquires the acquired voucher data, a specifying unit 232 that specifies the issuer of the voucher data based on at least one of characters or images included in the acquired voucher data acquired by the acquiring unit 231, and the specifying unit 232 specifies At least one of the characteristics of predetermined characters or images included in the determination data stored in the storage unit 22 in association with the issuer and at least one of the characteristics of the predetermined characters or images included in the obtained voucher data It comprises a determination unit 233 that determines whether or not the obtained voucher data is authentic data by comparison, and an output unit 234 that outputs the determination result of the determination unit 233 .

Description

The present invention relates to a data processing device, data processing method and program for processing billing data.

2. Description of the Related Art Conventionally, the authenticity of an issuer of document data such as voucher data is determined (see Patent Document 1, for example). Patent Document 1 describes verifying the authenticity of form data by verifying an electronic signature embedded in the form data.

JP 2007-206964 A

The technique described in Patent Literature 1 has a problem that if the electronic signature is not embedded in the voucher data, it cannot be determined whether or not the voucher data is genuine.

Accordingly, the present invention has been made in view of these points, and it is an object of the present invention to provide an information output device, an information output method, and a program capable of determining whether documented evidence data is genuine. do.

A data processing apparatus according to a first aspect of the present invention stores a plurality of determination data indicating at least one of predetermined characters or images included in regular voucher data in association with a plurality of issuers of vouchers. a storage unit that acquires evidence data, an identification unit that identifies an issuer of the evidence data based on at least one of characters or images included in the acquired evidence data acquired by the acquisition unit; At least one of the characteristics of the predetermined character or image included in the determination data stored in the storage unit in association with the issuer identified by the identification unit, and the predetermined character included in the obtained voucher data a determination unit that determines whether or not the obtained voucher data is authentic data by comparing at least one characteristic of characters or images; and an output unit that outputs the determination result of the determination unit. Prepare.

The determination unit determines the position of the predetermined character or image included in the determination data stored in the storage unit in association with the issuer identified by the identification unit, and the predetermined character or image included in the obtained voucher data. It may be determined whether or not the obtained voucher data is authentic data by comparing the positions of the characters or images of the above. The acquisition unit acquires an electronic invoice including a markup language for designating a data structure as the voucher data, and the determination unit stores it in the storage unit in association with the issuer identified by the identification unit. determining whether or not the obtained voucher data is authentic data by comparing the predetermined characters included in the obtained judgment data with the predetermined characters included in the obtained voucher data. good too.

The judging unit determines whether the predetermined character included in the judgment data stored in the storage unit in association with the issuer identified by the identifying unit and the predetermined character included in the obtained voucher data. A degree of matching may be specified, and based on the specified degree of matching, it may be determined whether or not the obtained voucher data is genuine data. The judging unit uses the voucher data and information indicating an issuer of the voucher data as input data, and outputs information indicating whether or not the voucher data is issued by the issuer and is genuine. The acquired voucher data acquired by the acquisition unit and the information indicating the issuer identified by the identification unit are input to the learned machine learning model, and the voucher data output by the machine learning model is the issuer It may be determined whether or not the obtained voucher data is authentic based on information issued by the source indicating whether or not the data is authentic.

The data processing device stores learning data including the evidenced data associated with a label indicating that it has been obtained from an authentic issuer and the evidenced data associated with a label that indicates that it has been obtained from a false issuer. It may further include a generation unit that generates the machine learning model by performing machine learning. The data processing apparatus further includes a receiving unit that receives a user input as to whether or not the determination result is correct, and the generating unit receives a user input indicating that the determination result that the acquired voucher data is authentic is correct. When an input is received, the machine learning model performs machine learning using new learning data obtained by adding the corresponding evidenced data to the learning data in association with a label indicating that the corresponding evidenced data is authentic. may be generated.

A data processing apparatus according to a second aspect of the present invention stores a plurality of determination data indicating at least one of predetermined characters or images included in regular voucher data in association with a plurality of issuers of vouchers. a storage unit that acquires documentary evidence data; a feature of at least one of the predetermined characters or images included in each of the plurality of determination data stored in the storage unit; an identification unit that identifies the determination data indicating characteristics most similar to the acquired evidenced data by comparing the characteristics of at least one of the predetermined characters or images included in the acquired evidenced evidenced data; a determination unit that determines whether or not the issuer specified based on at least one of characters or images included in the voucher data matches the issuer corresponding to the determination data specified by the specification unit; and an output unit for outputting the determination result of the determination unit.

A data processing method according to a third aspect of the present invention is a computer-executed step of acquiring voucher data; a step of identifying an issuer; and referring to a storage unit that stores a plurality of judgment data indicating characteristics of at least one of predetermined characters or images included in the normalized voucher data in association with a plurality of issuers of the voucher. and at least one of the predetermined character or image included in the determination data stored in the storage unit in association with the specified issuer, and the predetermined character or image included in the obtained voucher data. determining whether or not the acquired documented voucher data is authentic data by comparing with at least one feature of the image; and outputting the determination result.

A data processing method according to a fourth aspect of the present invention is a computer-executed step of acquiring voucher data; At least one of the characteristics of the predetermined character or image included in each of the plurality of determination data stored in the storage unit with reference to a storage unit that stores a plurality of determination data indicating any of the characteristics and the characteristics of at least one of the predetermined characters or images included in the acquired voucher data to identify the judgment data most similar to the acquired voucher data; determining whether or not a publisher identified based on at least one of characters or images included in the data matches the publisher corresponding to the identified determination data; and outputting a determination result. a step;

A program according to a fifth aspect of the present invention provides a computer with a step of acquiring voucher data; and referring to a storage unit that stores a plurality of judgment data indicating at least one of the characteristics of predetermined characters or images included in the normal voucher data in association with a plurality of issuers of the voucher, At least one of the predetermined character or image included in the determination data stored in the storage unit in association with the issuer, and at least one of the predetermined character or image included in the obtained voucher data A step of determining whether or not the acquired documented voucher data is authentic data by comparing with the characteristic, and a step of outputting the determination result are executed.

A program according to a sixth aspect of the present invention is provided in a computer with a step of obtaining voucher data, and at least one characteristic of a predetermined character or image included in regular voucher data in association with a plurality of issuers of voucher data. with reference to a storage unit that stores a plurality of determination data indicating the acquired a step of identifying the judgment data most similar to the judgment data by comparing the characteristics of at least one of the predetermined characters or images contained in the acquired voucher data; determining whether or not a publisher identified based on at least one of characters or images matches the publisher corresponding to the identified determination data; and outputting a determination result. let it run.

According to the present invention, there is an effect that it is determined whether or not evidenced document data is authentic.

1 is a diagram for explaining an overview of a data processing system according to a first embodiment; FIG. 1 shows the configuration of a data processing device; An example of a determination data table is shown. An example of feature extraction of acquired voucher data is shown. Another example of determination data is shown. Another example of feature extraction of voucher data is shown. 10 is a flow chart showing a processing procedure for authenticity determination of an issuer of voucher data by a data processing device; 10 is a flow chart showing a processing procedure for authenticity determination of documented voucher data by the data processing device 2 of the modified example. child 1 shows the configuration of a data processing device according to a second embodiment; 10 is a flow chart showing a processing procedure for authenticity determination of an issuer of voucher data by a data processing device;

[Overview of data processing system S]
FIG. 1 is a diagram for explaining an outline of a data processing system S according to the first embodiment. A data processing system S includes an external device 1 , a data processing device 2 and a staff terminal 3 . The data processing system S may include a plurality of person-in-charge terminals 3 .

The external device 1 is, for example, a computer installed at a facility of a business partner such as a business partner, a computer of an employee of the business operator who uses the data processing device 2, or an access point of a network through which electronic invoices are transmitted and received. . The external device 1 communicates with the data processing device 2 via a network. The external device 1 transmits voucher data such as invoice data to the data processing device 2 . The voucher data is bill data and receipt data, for example. The voucher data may be an electronic invoice or electronic data such as PDF (Portable Document Format) data. The voucher data may be obtained by reading a paper bill with OCR (Optical Character Recognition). The person in charge terminal 3 may function as the external device 1 .

The person in charge terminal 3 is, for example, a computer used by a person in charge of an accounting department who uses the data processing device 2 . The person in charge terminal 3 communicates with the data processing device 2 via the network. Note that the person in charge terminal 3 may transmit and receive data to and from the external device 1 via a network.

The data processing device 2 communicates with the external device 1 and the person in charge terminal 3 via the network N. FIG. The data processing device 2 is, for example, a server connected to a local network of an operator, but may be a cloud server. The data processing device 2 acquires voucher data (hereinafter also referred to as “obtained voucher data”) from the external device 1 ((1) in FIG. 1). When the person in charge terminal 3 receives the evidence data from the external device 1 , the data processing device 2 may acquire the evidence data from the person in charge terminal 3 .

The data processing device 2 identifies the issuer of the acquired voucher data based on characters or images (hereinafter referred to as "characters, etc.") indicating the company included in the acquired voucher data ((2 in FIG. 1). )). The data processing device 2 stores a determination data table containing a plurality of determination data indicating characteristics such as predetermined characters included in the regular voucher data in association with multiple issuers of the voucher. The data processing device 2 refers to the stored judgment data table and identifies the judgment data stored in association with the identified issuer.

The data processing device 2 compares the characteristics such as predetermined characters included in the specified determination data with the corresponding characteristics such as predetermined characters included in the acquired voucher data, thereby confirming the authenticity of the issuer of the acquired voucher data. ((3) in FIG. 1). The data processing device 2 outputs the determination result as to whether or not the obtained voucher data is authentic to the person in charge terminal 3 ((4) in FIG. 1).

In this way, the data processing device 2 outputs the judgment result as to whether or not the billing data is authentic based on at least one of the characters or images included in the acquired voucher data. To prevent a user from being a victim of fraud when falsified documented evidence data is received.

[Configuration of data processor 2]
FIG. 2 shows the configuration of the data processing device 2. As shown in FIG. The data processing device 2 includes a communication section 21 , a storage section 22 and a control section 23 . The control unit 23 includes an acquisition unit 231 , an identification unit 232 , a determination unit 233 and an output unit 234 .

The communication unit 21 is an interface for communicating with the person in charge terminal 3 . The storage unit 22 has a storage medium such as a ROM (Read Only Memory), a RAM (Random Access Memory), and a hard disk. The storage unit 22 stores programs executed by the control unit 23 . The storage unit 22 stores issuer information that associates the issuer of the evidenced data with an image such as a logo indicating the issuer of the evidenced data.

The storage unit 22 stores a data table for determination in which information indicating a plurality of issuers of vouchers is associated with a plurality of data for determination indicating at least one characteristic of predetermined characters or images included in the normal voucher data. is stored. Authentic evidence data is evidence data that is known in advance to have been issued by a legitimate issuer. The determination data indicates, for example, the position of a character string indicating the issuer as a feature of a predetermined character or image included in the authorized voucher data. For example, the position of the character string indicating the publisher includes the distance from the left edge of the page to the position of the character string indicating the publisher, and the distance from the top edge of the page to the position of the character string indicating the publisher. Expressed in units.

FIG. 3 shows an example of the determination data table. FIG. 4 shows an example of feature extraction of acquired voucher data. In the judgment data table shown in FIG. 3, the issuer of the authorized voucher data, the first judgment data indicating the distance from the left edge of the paper surface of the name of the issuer included in the authorized voucher data, and the first judgment data included in the authorized voucher data It is associated with second determination data indicating the distance from the upper edge of the paper surface to the position of the publisher name.

The distance from the left edge of the page to the position of the publisher name is D1 shown in FIG. 4, for example. In the example shown in FIG. 4, the left end of the character string indicating the publisher name is the position of the publisher name, but the position of the publisher name may be the right end of the character string indicating the publisher name. may be in the center of Similarly, the distance from the upper edge of the page to the position of the publisher name is D2 shown in FIG. 4, for example. In the example shown in FIG. 4, the upper end of the character string indicating the publisher name is the position of the publisher name, but the position of the publisher name may be the lower end of the character string indicating the publisher name. may be in the center of

In the example in the first row from the top of FIG. 3, the distance from the left edge of the paper surface of the character string indicating the name of the issuer in the authentic voucher data issued by the issuer "AB Trading" is 201 mm, indicating the name of the issuer. The distance from the upper edge of the paper surface to the position of the character string is 60 millimeters. In the example on the second row from the top of FIG. It indicates that the distance from the top edge of the paper surface to the position of the character string indicating the name is 30 millimeters.

FIG. 4 shows an example of extracting features of voucher data. In FIG. 4, the company name "AB Trading" of the issuer name is indicated by a dashed frame line. In the example of FIG. 4, the distance D1 from the left edge of the page to the position of the character string "AB Trading" indicating the company name of the issuer included in the acquired voucher data is extracted as a feature by the determination unit 233, which will be described later. The determination unit 233 extracts the distance D2 from the upper end of the page to the position of the character string “AB Trading” indicating the issuer included in the acquired voucher data as a feature.

FIG. 5 shows another example of determination data. FIG. 6 shows another example of feature extraction of voucher data. The data for determination shown in FIG. It is associated with the second determination data indicating the distance from the top edge of the page to the position of the included logo image indicating the publisher.

The distance from the left edge of the page to the position of the logo image indicating the publisher is D1' shown in FIG. 6, for example. In the example shown in FIG. 6, the left end of the logo image indicating the publisher is the position of the logo image, but the position of the logo image indicating the publisher may be the right end of the logo image indicating the publisher. It can be central. Similarly, the distance of the position of the logo image from the upper edge of the paper surface is, for example, D2' shown in FIG. In the example shown in FIG. 6, the position of the logo image is the upper end of the logo image indicating the issuer, but the position of the logo image may be the lower end of the logo image indicating the issuer, or the center of the logo image. may

In the example in the first row from the top of FIG. 5, the distance from the left edge of the page to the position of the logo image indicating the issuer in the regular document data issued by the issuer "AB Trading" is 20 mm, indicating the issuer. It shows that the distance from the top edge of the paper surface of the logo image is 16 millimeters. In the example on the second row from the top of FIG. 5, the distance from the left edge of the page to the position of the logo image indicating the issuing name in the official document data issued by the issuing source “CD Manufacturing” is 17 mm. The logo image shown is 30 millimeters from the top edge of the paper surface.

FIG. 6 shows another example of extraction of features of acquired voucher data. As shown in the example of FIG. 6, the distance D1' from the left edge of the page to the position of the logo image of the issuer "AB Trading" in the form of "AB" included in the acquired voucher data is determined as a feature by the determination unit 233, which will be described later. extracted. The determination unit 233 extracts the distance D2' from the top edge of the paper surface to the position of the logo image shaped like "AB" of the issuer "AB Trading" included in the acquired voucher data as a feature.

The control unit 23 in FIG. 2 is, for example, a CPU (Central Processing Unit). The control unit 23 functions as an acquisition unit 231 , an identification unit 232 , a determination unit 233 and an output unit 234 by executing programs stored in the storage unit 22 .

The acquisition unit 231 communicates with the external device 1 or the person in charge terminal 3 via the communication unit 21 . Acquisition unit 231 acquires voucher data via external device 1 . The acquisition unit 231 may acquire an electronic invoice including a markup language for designating the data structure as the voucher data. For example, the acquisition unit 231 may acquire an electronic invoice written in XML format as voucher data. The obtaining unit 231 may obtain the voucher data from the terminal 3 of the person in charge when the terminal 3 of the person in charge receives the voucher data from the external device 1 . The acquisition unit 231 outputs the acquired voucher data to the identification unit 232 .

[Identify publisher]
The identifying unit 232 identifies the issuer of the voucher data based on at least one of the characters or images included in the acquired voucher data acquired by the acquiring unit 231 . For example, the identifying unit 232 identifies, as the issuer of the voucher data, a company name that does not have a keyword such as "your" indicating the destination among the company names included in the acquired voucher data. When the documented evidence data is an electronic invoice, the identification unit 232 identifies a character string with a tag indicating the issuer as the issuer name.

The identification unit 232 may identify the issuer of the evidenced data based on the logo image indicating the issuer of the evidenced data. First, the identifying unit 232 reads from the storage unit 22 the issuer information that associates the issuer of the evidenced data with the logo image indicating the issuer of the evidenced data. The specifying unit 232 refers to the read issuer information, and specifies the issuer stored in association with the logo image whose similarity to the logo image included in the acquired voucher data is equal to or greater than a threshold in the issuer information. good too. The threshold is, for example, a value determined as a value required to identify the issuer of the voucher data with the same accuracy as when identifying the issuer of the voucher data based on the company name included in the acquired voucher data. The identification unit 232 outputs information indicating the identified publisher to the determination unit 233 .

[Verification of the authenticity of the issuer of the acquired voucher data]
The determination unit 233 determines whether or not the obtained voucher data is authentic. First, the determination unit 233 extracts the characteristics of at least one of predetermined characters or images included in the obtained voucher data. For example, the determination unit 233 extracts the position, size, typeface, or the like of predetermined characters or images included in the obtained voucher data as features.

The determination unit 233 refers to the determination data table stored in the storage unit 22 and identifies determination data stored in association with the issuer identified by the identification unit 232 . This determination data includes characteristics such as the position, size, or typeface of predetermined characters or images extracted from the regular voucher data. The judging unit 233 determines the authenticity of the acquired voucher data by comparing the characteristics such as the position, size, or typeface of a predetermined character or image extracted from the acquired voucher data with the corresponding characteristics included in the specified determination data. It is determined whether or not the data is valid.

In the example of FIG. 4, the determination unit 233 extracts, as described above, the distance D1 from the left edge of the page to the position of the character string "AB Trading" indicating the company name of the issuer included in the acquired voucher data as a feature. The determination unit 233 extracts the distance D2 from the upper edge of the page to the position of the character string “AB Trading” indicating the issuer contained in the acquired voucher data as a feature.

The determination unit 233 refers to the determination data table (see FIG. 3) stored in the storage unit 22, and refers to the first determination data table stored in association with the issuer “AB Trading” identified by the identification unit 232. It is specified that the distance from the left edge of the page to the position of the issuer name included in the regular voucher data indicated by the data is 201 millimeters.

The judging unit 233 refers to the judging data table stored in the storage unit 22, and confirms the authentic document indicated by the second judging data stored in association with the issuer "AB Trading" identified by the identifying unit 232. Specify that the distance from the top edge of the page to the position of the publisher name included in the data is 160 millimeters. The determination unit 233 determines whether the difference between the extracted distance D1 and the distance (201 mm) indicated by the specified first determination data is equal to or less than a threshold. The determination unit 233 determines whether the difference between the extracted distance D2 and the distance (160 mm) indicated by the specified second determination data is equal to or less than a threshold.

The determination unit 233 determines that the difference between the extracted distance D1 and the distance indicated by the specified first determination data is equal to or less than a threshold, and the difference between the extracted distance D2 and the specified distance indicated by the second determination data is determined. If the difference is equal to or less than the threshold value, it is determined that the acquired voucher data is genuine voucher data issued by the issuer "AB Trading". On the other hand, if the difference between the extracted distance D1 and the distance indicated by the specified first determination data exceeds a threshold, or if the difference between the extracted distance D2 and the specified second determination data exceeds a threshold value, it is determined that the obtained voucher data is not genuine voucher data issued by the issuer "AB Trading".

As shown in the example of FIG. 6, the determination unit 233 determines the distance D1′ from the left edge of the page to the position of the logo image of the issuer “AB Trading” in the shape of “AB” included in the acquired voucher data, as described above. You may extract it as a feature. The determination unit 233 may extract the distance D2' from the upper edge of the page to the position of the logo image shaped like "AB" of the issuer "AB Trading" included in the acquired voucher data as a feature. Regarding the method of determining the authenticity of the issuer of the acquired voucher data using the distance D1′ and the distance D2′ from the left edge and the upper edge of the position of the logo image extracted by the determination unit 233, Since it is the same as the method of judging the authenticity of the issuer of the obtained voucher data using the distance D1 and the distance D2 from the left edge and the upper edge of the paper, the explanation is omitted.

Further, the determination unit 233 is not limited to determining the authenticity of the issuer based on the position of the character string indicating the issuer included in the acquired voucher data. The determination unit 233 may determine the authenticity of the issuer based on the position of the character string that corresponds one-to-one with the issuer, such as the character string indicating the bank account name.

[E-invoice issuer authenticity determination]
When the voucher data acquired by the acquisition unit 231 is an electronic invoice, the determination unit 233 determines the predetermined characters included in the determination data stored in the storage unit 22 in association with the issuer specified by the specification unit 232. and predetermined characters included in the acquired voucher data, it is determined whether or not the acquired voucher data is authentic data.

First, the determination unit 233 extracts the XML text indicating the tag information or layout information corresponding to the character string indicating the issuer or the logo image in the obtained voucher data. The determination unit 233 may extract tag information or XML text indicating layout information corresponding to the character string indicating the bank account in the acquired voucher data.

The determination unit 233 refers to the determination data table stored in the storage unit 22 and identifies determination data stored in association with the issuer identified by the identification unit 232 . This determination data includes a character string indicating the publisher, tag information corresponding to the logo image, or XML text indicating layout information as predetermined character features. The determination unit 233 compares the XML text indicating the tag information or layout information included in the specified determination data with the XML text indicating the extracted tag information or layout information, thereby confirming the authenticity of the issuer of the acquired voucher data. It is determined whether or not.

More specifically, the determining unit 233 determines that the issuer of the acquired voucher data is authentic when the XML text indicating the tag information and the like included in the specified determination data matches the XML text indicating the extracted tag information and the like. It is determined that If the XML text indicating the tag information, etc. included in the specified determination data does not match the extracted XML text indicating the corresponding tag information, etc., the determination unit 233 determines that the issuer of the obtained voucher data is not authentic. I judge.

The judgment unit 233 identifies the degree of matching between the predetermined characters included in the determination data stored in the storage unit 22 in association with the issuer identified by the identification unit 232 and the predetermined characters included in the obtained voucher data. . The determination unit 233 may determine whether or not the acquired voucher data is authentic voucher data based on the specified degree of matching.

For example, when the determination unit 233 extracts, as predetermined characters, a plurality of tag information corresponding to a character string indicating an issuer in the acquired voucher data or a character string indicating layout information, the determination unit 233 extracts a plurality of characters extracted from the acquired voucher data. Among the character strings indicating the tag information or the layout information, the ratio of the character strings indicating the plurality of tag information or the character strings indicating the layout information included in the identified determination data is specified as the degree of matching. The determination unit 233 may determine that the acquired voucher data is authentic voucher data when the specified degree of matching is equal to or greater than a threshold. The determining unit 233 may determine that the acquired voucher data is not authentic voucher data when the specified degree of matching is less than a threshold. The threshold is specified by the user, for example.

[Output judgment result]
The output unit 234 communicates with the person in charge terminal 3 via the communication unit 21 . The output unit 234 outputs the determination result of the determination unit 233 as to whether or not the issuer of the obtained voucher data is genuine. For example, the output unit 234 displays the issuer identified by the identification unit 232 and the determination result of the determination unit 233 on the display of the person in charge terminal 3 .

[Processing procedure for authenticity determination of voucher data by data processing device 2]
FIG. 7 is a flow chart showing the processing procedure of authenticity determination of the issuer of the voucher data by the data processing device 2 . This processing procedure is started, for example, when the acquisition unit 231 acquires the voucher data from the external device 1 . First, the acquisition unit 231 determines whether or not the acquired voucher data is an electronic invoice (S101). When the acquiring unit 231 determines that the acquired voucher data is not an electronic invoice (NO in S101), the specifying unit 232 determines the acquired voucher data based on the characters included in the acquired voucher data acquired by the acquiring unit 231. is specified (S102).

The determination unit 233 extracts the positions of predetermined characters included in the obtained voucher data as features. The determination unit 233 refers to the determination data table stored in the storage unit 22 and identifies determination data stored in association with the issuer identified by the identification unit 232 . The determination unit 233 determines whether or not the deviation between the position of the predetermined character extracted from the obtained voucher data and the position of the predetermined character included in the specified determination data is equal to or less than a threshold value (S103).

If the deviation between the position of the predetermined character extracted from the acquired voucher data and the position of the predetermined character included in the specified determination data is equal to or less than the threshold (YES in S103), the determination unit 233 determines the acquired voucher data. is determined to be authentic (S104). The output unit 234 outputs the determination result of the determination unit 233 to the person in charge terminal 3 (S105), and ends the process.

When the acquisition unit 231 determines that the acquired voucher data is an electronic invoice in the determination of S101 (YES in S101), it acquires the XML text included in the acquired voucher data (S106). The identification unit 232 identifies the issuer of the obtained voucher data based on the obtained XML text (S107). The determination unit 233 extracts tag information corresponding to the character string indicating the issuer in the acquired voucher data or XML text indicating layout information as a feature of predetermined characters.

The determination unit 233 refers to the determination data table stored in the storage unit 22 and identifies determination data stored in association with the issuer identified by the identification unit 232 . The determination unit 233 determines whether or not the character string indicating the tag information or layout information included in the specified determination data matches the extracted character string indicating the tag information or layout information (S108). If the character string indicating the tag information or layout information included in the specified determination data does not match the character string indicating the extracted tag information or layout information (NO in S108), the determination unit 233 determines the obtained voucher data. is not authentic (S109), and the process proceeds to S105.

If the position of the predetermined character extracted from the acquired voucher data in the determination of S103 and the position of the predetermined character included in the specified determination data is greater than a threshold value (NO in S103), the determining unit 233 It is determined that the issuer of the obtained voucher data is not authentic (S109), and the process proceeds to S105. In the determination of S108, if the tag information included in the specified determination data matches the extracted tag information (YES in S108), the determination unit 233 determines that the issuer of the obtained voucher data is genuine. (S110), and the process proceeds to S105.

[Effects of the data processing device 2 of the first embodiment]
In the data processing device 2 of the first embodiment, the output unit 234 determines whether or not the issuer of the billing data is genuine, based on at least one of the characteristics of characters or images included in the acquired voucher data. Output the result. Therefore, the output unit 234 can prevent the business operator who received the evidenced data from being a victim of fraud when the acquiring unit 231 acquires the evidenced data whose issuer is false.

<Modification>
In the first embodiment, an example has been described in which the determining unit 233 determines whether or not the specified issuer of the evidenced data is authentic after the specifying unit 232 specifies the issuer of the evidenced data. The invention is not limited to this. For example, the specifying unit 232 may specify regular voucher data having features most similar to the features extracted from the acquired voucher data, and specify the issuer of the specified regular voucher data as the issuer of the acquired voucher data.

As in the first embodiment, the identifying unit 232 of this modified example extracts the characteristics of at least one of predetermined characters or images included in the acquired voucher data acquired by the acquiring unit 231 . The identification unit 232 refers to the determination data table stored in the storage unit 22, and identifies at least predetermined characters or images included in each of the plurality of determination data stored in the determination data table of the storage unit 22. By comparing any of the features with the features extracted from the acquired voucher data, determination data indicating the features most similar to the acquired voucher data are specified.

The specifying unit 232 refers to the determination data table stored in the storage unit 22 to specify the first issuer corresponding to the determination data including the characteristics most similar to the acquired voucher data. As in the first embodiment, the identification unit 232 identifies the second issuer of the acquired voucher data based on at least one of a character string such as an issuer name or an image included in the acquired voucher data.

The determination unit 233 determines whether or not the first issuer identified by the identification unit 232 matches the second issuer. The determination unit 233 determines that the issuer of the obtained voucher data is authentic when the first issuer and the second issuer match. If the first issuer and the second issuer do not match, the determination unit 233 determines that the issuer of the obtained voucher data is not authentic.

FIG. 8 is a flow chart showing a processing procedure for determining authenticity of documented voucher data by the data processing device 2 of the present modification. This processing procedure is started, for example, when the obtaining unit 231 obtains the obtained voucher data from the external device 1 . First, the acquisition unit 231 determines whether or not the acquired voucher data is an electronic invoice (S201). When the acquiring unit 231 determines that the acquired voucher data is not an electronic invoice (NO in S201), the identifying unit 232 uses the position of a predetermined character included in the acquired voucher data acquired by the acquiring unit 231 as a feature. Extract.

The identification unit 232 compares the position of a predetermined character included in each of the plurality of judgment data stored in the storage unit 22 with the position of a predetermined character extracted from the acquired voucher data, thereby identifying the acquired voucher data. Determination data indicating the position of the most similar predetermined character is specified (S202). The specifying unit 232 refers to the determination data table stored in the storage unit 22 and specifies the first issuer stored in association with the determination data including the characteristics most similar to the acquired voucher data.

As in the first embodiment, the identification unit 232 identifies the second issuer of the acquired voucher data based on at least one of characters or images included in the acquired voucher data. The determination unit 233 determines whether or not the second issuer identified by the identification unit 232 matches the first issuer stored in association with the determination data (S203). If the second issuer identified by the identification unit 232 matches the first issuer (YES in S203), the determination unit 233 determines that the issuer of the obtained voucher data is authentic (S204). The output unit 234 outputs the determination result of the determination unit 233 to the person in charge terminal 3 (S205), and ends the process.

If the obtaining unit 231 determines that the obtained voucher data is an electronic invoice in the determination of S201 (YES in S201), the obtaining unit 231 obtains the XML text included in the obtained voucher data (S206). The identification unit 232 extracts a plurality of pieces of tag information corresponding to the character string indicating the issuer in the acquired voucher data or XML text indicating layout information as predetermined character features. The identification unit 232 determines, among a plurality of pieces of determination data stored in the determination data table of the storage unit 22, the tag information or the like having the highest degree of matching with the tag information or layout information specified by the identification unit 232. data is specified (S207).

The specifying unit 232 refers to the determination data table stored in the storage unit 22 to specify the first issuer stored in association with the determination data indicating the tag information with the highest degree of matching. As in the first embodiment, the identification unit 232 identifies the second issuer of the acquired voucher data based on the XML text acquired from the acquired voucher data, and proceeds to the determination of S203.

If the second issuer specified by the specifying unit 232 does not match the first issuer in the determination of S203 (NO in S203), the determination unit 233 determines that the issuer of the acquired voucher data is not authentic (S208 ), the process proceeds to S205.

<Second embodiment>
In the second embodiment, an example of determining the authenticity of the acquired voucher data using a machine learning model that has already been learned will be described. FIG. 9 shows the configuration of a data processing device 300 according to the second embodiment. A data processing apparatus 300 according to the second embodiment is the same as that shown in FIG. Functional blocks similar to those in FIG. 4 are given the same reference numerals as those in FIG. 4, and descriptions thereof are omitted.

The judging unit 301 has learned that the voucher data and the information indicating the issuer of the voucher data are input data, and the information indicating whether or not the voucher data is issued by the issuer is genuine as the output data. machine learning model to determine whether the acquired voucher data is genuine. The voucher data may be electronic invoices. First, the determination unit 301 reads this learned machine learning model from the storage unit 22 . The determination unit 301 inputs the acquired voucher data acquired by the acquisition unit 231 and the information indicating the issuer identified by the identification unit 232 to the read machine learning model, and the acquired voucher data is authenticated as issued by this issuer. Acquire the information output by the machine learning model that indicates whether or not the Based on the information output by the machine learning model, the determination unit 301 determines whether or not the acquired voucher data is authentic data.

[Processing procedure for machine learning model learning]
Hereinafter, the processing during learning of the machine learning model stored in the storage unit 22 will be described. The generation unit 302 performs machine learning using the evidenced data and information indicating the issuer of the evidenced data as input data and outputting information indicating whether the evidenced data is authentic and issued by the issuer. Generate a model. The generation unit 302 machine-learns learning data including evidenced data associated with a label indicating that it has been obtained from an authentic issuer and evidenced data associated with a label that indicates that it has been obtained from a fake issuer. to generate a machine learning model.

Voucher data associated with a label obtained from a fake issuer includes, for example, the issuer name, the logo image indicating the issuer, or the position of the transfer account name included in the voucher data. A plurality of voucher data are used that are shifted by a threshold value or more from the position of the issuer name, etc. of the voucher data associated with the label indicating that. The threshold is determined by an expert in the field according to, for example, the accuracy required for authenticity determination of the issuer of documented document data by a machine learning model that has already been trained.

The evidence data associated with a label obtained from a fake publisher is the evidence data associated with a label that indicates that the size or typeface of the publisher name, etc. included in this evidence data has been obtained from a genuine publisher. A plurality of voucher data different from the size or typeface of the issuer name may be used. The voucher data may be electronic invoices.

Further, in the data processing apparatus of the second embodiment, after the determination unit 301 determines whether or not the acquired voucher data is authentic data, the determination unit 301 determines whether or not the issuer of the acquired voucher data is authentic. A reception unit 303 may be provided to receive user input as to whether the determination result indicating whether or not is correct. When the receiving unit 303 receives a user's input indicating that the information indicating whether the issuer is authentic by the determining unit 301 is correct, the generating unit 302 generates new data corresponding to the determination result by the determining unit 301 . Create training data.

When the reception unit 303 receives a user input indicating that the determination result by the determination unit 301 that the voucher data is authentic is correct, the generation unit 302 determines that the target acquired voucher data determined by the determination unit 301 is authentic. The obtained voucher data is added to the learning data in association with a label indicating that there is. When the reception unit 303 receives a user input indicating that the determination result by the determination unit 301 that the voucher data is not authentic is correct, the generation unit 302 determines that the acquired voucher data determined by the determination unit 301 is not authentic. is added to the learning data in association with the label indicating the acquired voucher data.

When the generation unit 302 receives user input indicating that the determination result of the determination unit 301 that the voucher data is authentic is not correct, the generation unit 302 indicates that the target acquired voucher data determined by the determination unit 301 is not authentic. Add the obtained voucher data to the learning data in association with the label. When the reception unit 303 receives a user's input indicating that the determination result by the determination unit 301 that the voucher data is not authentic is incorrect, the generation unit 302 determines that the target acquired voucher data determined by the determination unit 301 is authentic. The obtained voucher data is added to the learning data in association with a label indicating that there is.

The generation unit 302 may generate a machine learning model by performing machine learning on new learning data after addition of documented evidence data whose authenticity has been determined by the user in this way. In this way, the generation unit 302 can further improve the accuracy of authenticity determination of the issuer of the documented evidence data by the learned machine learning model. The generating unit 302 causes the storage unit 22 to store the generated learned machine learning model.

[Processing procedure for authenticity determination of voucher data by data processing device 300]
FIG. 10 is a flow chart showing the processing procedure of authenticity determination of the issuer of the voucher data by the data processing device 300 . This processing procedure starts, for example, while the data processing device 300 is communicating with the external device 1 . First, the acquiring unit 231 acquires voucher data from the external device 1 (S301). The identification unit 232 identifies the issuer of the obtained voucher data (S302). When the acquired voucher data is an electronic invoice, the specifying unit 232 specifies the issuer of the acquired voucher data based on the XML text included in the acquired voucher data.

The judging unit 233 has learned that the voucher data and information indicating the issuer of the voucher data are input data, and the information indicating whether or not the voucher data is issued by the issuer is genuine as output data. is read out from the storage unit 22. The determining unit 233 inputs the obtained voucher data obtained by the obtaining unit 231 and the information indicating the issuer identified by the identifying unit 232 to the read machine learning model (S303), and the obtained voucher data is issued by this issuer. Obtain the information output by the machine learning model that indicates whether the product is authentic or not. Based on the information output by the machine learning model, the determination unit 301 determines whether or not the acquired voucher data is authentic data (S304). The output unit 234 outputs the determination result of the determination unit 233 as to whether or not the obtained voucher data is authentic data to the person in charge terminal 3 (S305), and ends the process.

[Effects of the data processing device 2 of the second embodiment]
In the data processing device 2 of the second embodiment, the output unit 234 improves the accuracy of determining the authenticity of the issuer of the acquired voucher data by using a learned machine learning model. It is possible to prevent the user from becoming a victim of fraud.

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. 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 External device 2 Data processing device 3 Person in charge terminal 21 Communication unit 22 Storage unit 23 Control unit 231 Acquisition unit 232 Identification unit 233 Judgment unit 234 Output unit 300 Data processing unit 301 Judgment unit 302 Generation unit 303 Acceptance unit

Claims (11)

a storage unit that stores a plurality of determination data indicating the positions of predetermined characters or images included in regular voucher data in association with a plurality of issuers of vouchers;
an acquisition unit that acquires voucher data;
an identification unit that identifies an issuer of the evidenced data acquired by the acquisition unit based on a character string or a tag indicating an issuer included in the acquired evidenced data;
The position of the predetermined character or image included in the determination data stored in the storage unit in association with the issuer identified by the identification unit, and the predetermined character or image included in the obtained voucher data a determination unit that determines whether or not the acquired voucher data is authentic data by comparing the positions of
an output unit that outputs the determination result of the determination unit;
A data processing device comprising: The acquisition unit acquires an electronic invoice including a markup language for designating a data structure as the voucher data,
The determination unit determines the predetermined character included in the determination data stored in the storage unit in association with the issuer identified by the identification unit, and the predetermined character included in the obtained voucher data. determining whether the obtained voucher data is authentic data by comparison;
2. A data processing apparatus according to claim 1 . The judging unit determines whether the predetermined character included in the judgment data stored in the storage unit in association with the issuer identified by the identifying unit and the predetermined character included in the obtained voucher data. identifying the degree of matching, and determining whether or not the obtained voucher data is genuine data based on the identified degree of matching;
3. A data processing apparatus according to claim 2 . The judging unit uses the voucher data and information indicating an issuer of the voucher data as input data, and outputs information indicating whether or not the voucher data is issued by the issuer and is genuine. The acquired voucher data acquired by the acquisition unit and the information indicating the issuer identified by the identification unit are input to the learned machine learning model, and the voucher data output by the machine learning model is the issuer Determining whether or not the obtained voucher data is authentic based on information issued by the source indicating whether or not it is authentic;
2. A data processing apparatus according to claim 1. By machine learning learning data including the evidence data associated with a label indicating that it was obtained from a genuine issuer and the evidence data associated with a label indicating that it was obtained from a fake issuer, Further comprising a generation unit that generates the machine learning model,
5. A data processing apparatus according to claim 4 . further comprising a reception unit that receives a user's input as to whether the determination result is correct,
When receiving user input indicating that the determination result that the obtained evidenced data is authentic is correct, the generation unit associates the corresponding evidenced evidenced data with a label indicating that the corresponding evidenced evidence data is authentic. is added to the learning data, and machine learning is performed using new learning data to generate the machine learning model.
6. A data processing apparatus according to claim 5 . a storage unit that stores a plurality of determination data indicating the positions of predetermined characters or images included in regular voucher data in association with a plurality of issuers of vouchers;
an acquisition unit that acquires voucher data;
the position of the predetermined character or image included in each of the plurality of determination data stored in the storage unit and the position of the predetermined character or image included in the acquired voucher data acquired by the acquisition unit; a specifying unit that specifies the data for determination that exhibits characteristics most similar to the obtained documented document data by comparison;
It is determined whether or not the issuer specified based on the character string or tag indicating the issuer included in the obtained voucher data matches the issuer corresponding to the determination data specified by the specifying unit. a determination unit;
an output unit that outputs the determination result of the determination unit;
A data processing device comprising: the computer runs
obtaining voucher data;
a step of identifying an issuer of the acquired voucher data based on a character string or a tag indicating an issuer included in the obtained acquired voucher data;
Referring to a storage unit for storing a plurality of data for determination indicating positions of predetermined characters or images included in normal voucher data in association with a plurality of issuers of the voucher, and storing the data in association with the specified issuer. By comparing the position of the predetermined character or image included in the determination data stored in the unit and the position of the predetermined character or image included in the acquired voucher data, the obtained voucher data is determined as a step of determining whether the data is authentic;
a step of outputting a judgment result;
A data processing method comprising: the computer runs
obtaining voucher data;
By referring to a storage unit that stores a plurality of determination data indicating the positions of predetermined characters or images included in the normalized voucher data in association with a plurality of issuers of the voucher, By comparing the position of the predetermined character or image included in each judgment data with the position of the predetermined character or image included in the acquired voucher data, the most similar to the acquired voucher data is determined. identifying decision data;
a step of determining whether or not the issuer specified based on the character string or tag indicating the issuer included in the acquired voucher data matches the issuer corresponding to the specified determination data;
a step of outputting a judgment result;
A data processing method comprising: to the computer,
obtaining voucher data;
a step of identifying an issuer of the acquired voucher data based on a character string or a tag indicating an issuer included in the obtained acquired voucher data;
Referring to a storage unit for storing a plurality of data for determination indicating positions of predetermined characters or images included in normal voucher data in association with a plurality of issuers of the voucher, and storing the data in association with the specified issuer. By comparing the position of the predetermined character or image included in the determination data stored in the unit and the position of the predetermined character or image included in the acquired voucher data, the obtained voucher data is determined as a step of determining whether the data is authentic;
a step of outputting a judgment result;
The program that causes the to run. to the computer,
obtaining voucher data;
By referring to a storage unit that stores a plurality of determination data indicating the positions of predetermined characters or images included in the normalized voucher data in association with a plurality of issuers of the voucher, By comparing the position of the predetermined character or image included in each of the data for determination with the position of the predetermined character or image included in the acquired documented document data, the position of the predetermined character or image that is most similar to the data for determination is determined. identifying decision data;
a step of determining whether or not the issuer specified based on the character string or tag indicating the issuer included in the acquired voucher data matches the issuer corresponding to the specified determination data;
a step of outputting a judgment result;
The program that causes the to run.

Images