Character Matching Device and Program

Abstract

To provide a character verification device and a program which, if character verification results indicate a mismatch, make a notification based on contents of the mismatch.SOLUTION: A character verification server 1 comprises: a comparison unit 15 which compares a first text for a prescribed item obtained from an application document with a second text obtained from a personal identification document and corresponding to the prescribed item; a determination unit 16 which, if results of the comparison by the comparison unit 15 indicate a mismatch, determines contents of the mismatch; and a notification processing unit 17 which makes a notification corresponding to the contents of the mismatch determined by the determination unit 16.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a character matching device and a program.

Background Art

[0002] Conventionally, an information processing device that identifies a character string representing a name, company name, store name, etc. from among character strings described in a specific medium has been disclosed (for example, Patent Document 1). When printed characters are read using an optical character recognition device (OCR), incorrect recognition may occur, resulting in incorrect text being output. Patent Document 1 presents a method of collating a name or the like using information such as an email address or a network address.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] For example, in the process of examination in various operations such as account opening operations, card issuance operations, and insurance contract operations, it is confirmed that the name etc. described in the application documents matches the description in the personal identification documents such as a driver's license. Conducting these confirmations by visual inspection by humans can increase the workload and ultimately be a factor causing mistakes. Therefore, in recent years, texts have been compared using a computer to determine whether they match or not. However, even when the comparison result is inconsistent, there are cases where it may be acceptable under some conditions, but such discrimination could not be made.

[0005] Therefore, an object of the present invention is to provide a character matching device and a program that issue a notification based on the content of a mismatch when the character matching result is inconsistent.

Means for Solving the Problems

[0006] The present invention solves the above problems by the following solutions. A first invention is a character matching device including: a comparison unit that compares a first text for a predetermined item obtained from a first document with a second text for the predetermined item obtained from a second document; a determination unit that determines a disagreement content when a result of comparison by the comparison unit is a disagreement; and a notification unit that gives a notification corresponding to the disagreement content determined by the determination unit. A second invention is the character matching device of the first invention, wherein when a pair of characters that are in disagreement are registered in a variant character dictionary storing variant characters, the determination unit determines that the disagreement content is a variant character, and the notification unit notifies that it is a variant character. A third invention is the character matching device of the first invention or the second invention, wherein the determination unit calculates a similarity between pairs of characters that are in disagreement, and when the calculated similarity is equal to or more than a threshold value, determines that the disagreement content is a variant character or a mis-conversion, and the notification unit notifies that it is a variant character or a mis-conversion. A fourth invention is the character matching device of the third invention, wherein the determination unit divides an image area indicating a pair of characters that are in disagreement into a plurality of small areas, compares the small areas at the same position, and calculates the similarity. A fifth invention is the character matching device according to any one of the first invention to the fourth invention, including a character number confirmation unit that confirms the number of characters of the first text and the second text, and when the comparison unit confirms the match of the number of characters by the character number confirmation unit, compares one character by one character in order. A sixth invention is the character matching device of the fifth invention, wherein when the character number confirmation unit confirms a disagreement in the number of characters, a similarity calculation unit that specifies each of the disagreeing characters and calculates a similarity between a combination of the specified plurality of characters and a paired character is provided, and when the similarity calculated by the similarity calculation unit is equal to or more than a threshold value, the notification unit notifies that it is a mis-conversion. The seventh invention is a character matching device according to any one of the first to sixth inventions, wherein the predetermined item includes at least one of a name and an address. The eighth invention is a character matching device according to any one of the first to seventh inventions, comprising: first data acquisition means for acquiring first data obtained by imaging the first document; second data acquisition means for acquiring second data obtained by imaging the second document; first text acquisition means for acquiring the predetermined item from the first data acquired by the first data acquisition means and acquiring the value corresponding to the acquired predetermined item as the first text; and second text acquisition means for acquiring the predetermined item from the second data acquired by the second data acquisition means and acquiring the value corresponding to the acquired predetermined item as the second text. The ninth invention is the character matching device according to the eighth invention, wherein the first data and / or the second data are imaging data of a document including handwritten characters, and the first text and / or the second text are texts obtained by performing character recognition processing on the imaging data. The tenth invention is a program for causing a computer to function as any one of the character matching devices according to the first to ninth inventions.

Advantages of the Invention

[0007] According to the present invention, there can be provided a character matching device and a program that give a notice based on the content of a mismatch when the character matching result is a mismatch.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. Note that this is merely an example, and the technical scope of the present invention is not limited thereto. (Embodiment) <Overall Configuration of Character Collation System 100> FIG. 1 is a diagram showing the overall configuration of the character collation system 100 and the functional blocks of the character collation server 1 according to this embodiment. FIG. 2 is a diagram showing an example of the variant character DB 4 according to this embodiment.

[0010] The character collation system 100 shown in FIG. 1 is, for example, a system that collates the contents related to the collation target items (predetermined items) among the application documents (first documents) and the identity confirmation documents (second documents) and outputs the collation result. The character collation system 100 compares the texts, which are the contents of the collation target items in both documents, and when they do not match, gives a notification according to the non-matching content. By doing so, the character collation system 100 can reduce the workload of visual inspection by the user who confirms the documents (hereinafter, the person who confirms the documents is also referred to as an operator). The character matching system 100 includes a character matching server 1 (a character matching device), a variant character DB (database) 4 (variant character dictionary), and a terminal 5. The character matching server 1, the variant character DB 4, and the terminal 5 are communicably connected via a communication network N.

[0011] <Character matching server 1> The character matching server 1 is a server that can be used for various review operations. The character matching server 1 collates, for example, application form data (first data) obtained by imaging application forms and personal identification data (second data) obtained by imaging personal identification documents used for reviewing the application forms. The character matching server 1 includes a control unit 10, a storage unit 20, and a communication interface unit 29. The control unit 10 is a CPU (central processing unit) that controls the entire character matching server 1. The control unit 10 appropriately reads and executes the OS (operating system) and various application programs stored in the storage unit 20, and cooperates with the above-described hardware to execute various functions.

[0012] The control unit 10 includes an application data acquisition unit 11 (first data acquisition means), a first text acquisition unit 12 (first text acquisition means), a personal identification data acquisition unit 13 (second data acquisition means), a second text acquisition unit 14 (second text acquisition means), a comparison unit 15 (character count confirmation means, comparison means), a determination unit 16 (determination means, similarity calculation means), and a notification processing unit 17 (notification means).

[0013] The application data acquisition unit 11 acquires application data obtained by imaging application documents. The application documents refer to, for example, application forms for opening a bank account, application forms for various insurance contracts such as life insurance, etc. The application documents may include handwritten characters in part thereof. And, for example, when there is a submission of documents via the Web from the requester, the application data acquisition unit 11 receives the application data from a requester terminal (not shown). Also, for example, when there is a submission of documents by mail from the requester, the application data acquisition unit 11 receives the application data after imaging the paper-based application documents. Then, the application data acquisition unit 11 stores the acquired application data in the document data storage unit 22.

[0014] The first text acquisition unit 12 performs a process (character recognition process) by OCR (Optical Character Recognition) on the application data to obtain text data. Then, the first text acquisition unit 12 acquires collation target items from the text data, and acquires the values corresponding to the acquired collation target items as the first text. Here, the collation target items refer to the items to be collated in the examination work, for example, name (surname and given name), address, etc. And, the first text acquisition unit 12 stores the acquired items and their values (the first text) in the comparison data storage unit 23. In addition, in the case of submission of documents via the Web, etc., when the application data acquired by the application data acquisition unit 11 includes text data, the process of obtaining the text data by the first text acquisition unit 12 is unnecessary.

[0015] The personal identification data acquisition unit 13 acquires personal identification data obtained by imaging personal identification documents. The personal identification documents are for identifying the applicant, and examples include a driver's license, insurance certificate, passport, etc. The personal identification documents may include handwritten characters in part thereof. And, for example, when there is a submission of documents by the requester via the Web, the personal identification data acquisition unit 13 receives the personal identification data from a requester terminal (not shown). Also, for example, when there is a submission of documents by the requester by mail, the personal identification data acquisition unit 13 receives the personal identification data after imaging a copy of the mailed personal identification documents. Then, the personal identification data acquisition unit 13 stores the acquired personal identification data in the document data storage unit 22 in association with the application data received together for collation.

[0016] The second text acquisition unit 14 performs OCR processing on the personal identification data to obtain text data. Then, the second text acquisition unit 14 acquires collation target items from the text data, and acquires the values corresponding to the acquired collation target items as the second text. Then, the second text acquisition unit 14 stores the acquired values (second text) in the comparison data storage unit 23 in association with the items and values (first text) obtained from the application data to be collated. In addition, in the case of submission of documents via the Web or the like, when the personal identification data acquired by the personal identification data acquisition unit 13 includes text data, the process of obtaining text data by the second text acquisition unit 14 is unnecessary.

[0017] The comparison unit 15 checks the number of characters of the first text and the second text for the collation target items stored in the comparison data storage unit 23. Also, when the comparison unit 15 checks that the number of characters matches, the comparison unit 15 compares the first text and the second text one character at a time in order.

[0018] When the comparison unit 15 checks that the number of characters does not match, the determination unit 16 identifies the non-matching characters, and calculates the similarity between the identified combination of a plurality of characters and the paired characters. Further, when the result of the character comparison by the comparison unit 15 is inconsistent, the determination unit 16 determines the content of the inconsistency. More specifically, the determination unit 16 determines whether both of the pair of inconsistent characters are registered in the variant character DB4. And when both of the pair of inconsistent characters are registered in the variant character DB4, the determination unit 16 determines that the content of the inconsistency is a variant character. Further, the determination unit 16 may calculate the similarity between the pair of inconsistent characters. And when the calculated similarity is equal to or greater than a threshold value, the determination unit 16 determines that the content of the inconsistency is a variant character or a mis-conversion. Here, the determination unit 16 calculates the similarity, for example, by dividing the image area indicating the pair of inconsistent characters into a plurality of small areas and comparing the small areas at the same position.

[0019] When the determination unit 16 determines the content of the inconsistency, the notification processing unit 17 gives a notification corresponding to the content of the inconsistency. More specifically, when the determination unit 16 determines that the content of the inconsistency is a variant character, the notification processing unit 17 notifies that it is a variant character. Also, when the determination unit 16 determines that the content of the inconsistency is a variant character or a mis-conversion, the notification processing unit 17 notifies that it is a variant character or a mis-conversion. Further, when the similarity between the combination of a plurality of characters that are the inconsistent characters calculated by the determination unit 16 and the paired characters is equal to or greater than the threshold value, the notification processing unit 17 notifies that it is a mis-conversion.

[0020] The storage unit 20 is a storage device such as a hard disk or a semiconductor memory element for storing programs, data, etc. necessary for the operation of the character matching server 1. The storage unit 20 includes a program storage unit 21, a document data storage unit 22, and a comparison data storage unit 23. The program storage unit 21 is a storage area for storing programs. The program storage unit 21 stores a character matching program 21a (program). The character matching program 21a is a program for executing each function of the control unit 10.

[0021] The document data storage unit 22 is a storage area that stores the application data and the personal identification data for verifying the application data in association with each other. The comparison data storage unit 23 stores, in association with each other, the items to be verified obtained from the application data and their values (first text), and the values corresponding to the items obtained from the personal identification data (second text). Note that the document data storage unit 22 and the comparison data storage unit 23 may be temporarily used when performing the character comparison process. The communication interface unit 29 is an interface unit for communicating with the variant character DB 4 and the terminal 5 via the communication network N.

[0022] Note that a computer refers to an information processing device equipped with a control unit, a storage device, etc. The character comparison server 1 is an information processing device equipped with a control unit 10, a storage unit 20, etc., and is included in the concept of a computer. In addition, there is no limit to the number of hardware components that make up the character comparison server 1. It may be configured by one or more as needed. Also, the hardware of the character comparison server 1 may include various servers such as a web server, a DB (database) server, and an application server as needed, and may be configured by one server, or by separate servers respectively. Furthermore, the character comparison server 1 may be, for example, a cloud.

[0023] <variant character DB 4> The variant character DB 4 is a database that stores variant characters. As shown in FIG. 2, the variant character DB 4 stores the characters and the variant characters in association with each other. The characters are the characters in the standard font. The variant characters are Chinese characters that are different from the standard font but have the same meaning and pronunciation and are interchangeable. The variant character DB 4 may store a plurality of variant characters for one character. The variant character DB 4 is created and registered in advance. Also, the variant character DB 4 may be sequentially added and updated manually. Although not shown in the figure, the variant character DB4 includes a control unit, a storage unit, and a communication interface unit. Note that the variant character DB4 may not have a control unit, and the control unit 10 of the character collation server 1 may control the variant character DB4.

[0024] <Terminal 5> Terminal 5 is a terminal used by an operator related to the examination work. Terminal 5 can be configured by, for example, a personal computer (PC), a tablet terminal, etc. Terminal 5 may be a dedicated terminal for business use or a terminal shared with other business operations. Although not shown in the figure, Terminal 5 includes a control unit, a storage unit, an input unit, a display unit, a communication interface unit, etc.

[0025] <Explanation of processing> Next, the processing performed by the character collation server 1 will be described. FIG. 3 is a flowchart showing the character discrimination processing of the character collation server 1 according to the present embodiment. FIG. 4 is a flowchart showing the collation target acquisition processing of the character collation server 1 according to the present embodiment.

[0026] In step S (hereinafter, "step S" will be simply referred to as "S") 11 in FIG. 3, the control unit 10 of the character collation server 1 performs collation target acquisition processing. Here, the collation target acquisition processing will be described with reference to FIG. 4. In S21 of FIG. 4, the control unit 10 (application data acquisition unit 11) acquires application data obtained by imaging application documents. Then, the control unit 10 stores the acquired application data in the document data storage unit 22. In S22, the control unit 10 (first text acquisition unit 12) performs OCR processing on the application data, and acquires a collation target item and a value (first text) corresponding to the item from the character string (text data). Here, the collation target items may be a plurality of items, and in that case, the control unit 10 acquires each value corresponding to each collation target item.

[0027] In S23, the control unit 10 (the personal identification data acquisition unit 13) acquires personal identification data obtained by imaging personal identification documents to be compared with the application documents. Then, the control unit 10 stores the acquired personal identification data in the document data storage unit 22 in association with the application data to be compared. In S24, the control unit 10 (the second text acquisition unit 14) performs OCR processing on the personal identification data to acquire a comparison target item and a value (second text) corresponding to the item from the character string (text data). In S25, the control unit 10 associates the comparison target item with the first text and the second text corresponding to the item and stores them in the comparison data storage unit 23. Then, the control unit 10 moves the process to S12 in FIG. 3.

[0028] In S12 of FIG. 3, the control unit 10 (the comparison unit 15) acquires each text corresponding to the comparison target item from the comparison data storage unit 23 and compares the texts with each other. In S13, the control unit 10 (the comparison unit 15) determines whether the number of characters matches. If the number of characters matches (S13: YES), the control unit 10 moves the process to S14. On the other hand, if the number of characters does not match (S13: NO), the control unit 10 moves the process to S16. Note that the case where the number of characters does not match includes the case where there may be incorrect conversion when converting from image data to text.

[0029] In S14, the control unit 10 (the comparison unit 15) determines whether the characters exactly match. Here, the case where the characters exactly match means that the text of the comparison target item described in the application documents matches the text of the same item described in the personal identification documents without any difference in even one character. If the characters exactly match (S14: YES), the control unit 10 moves the process to S17. On the other hand, if the characters do not exactly match (S14: NO), the control unit 10 moves the process to S15.

[0030] In S15, the control unit 10 performs a discrimination process for variant characters and the like described in FIG. 5 below. Then, the control unit 10 moves the process to S17. In S16, the control unit 10 performs an incorrect conversion determination process described with reference to FIG. 7 which will be described later. After that, the control unit 10 transfers the process to S17.

[0031] In S17, the control unit 10 determines whether processing has been performed for all the collation targets. If processing has been performed for all the data stored in the comparison data storage unit 23, the control unit 10 can determine that processing has been performed for all the collation targets. If processing has been performed for all the collation targets (S17: YES), the control unit 10 transfers the process to S18. On the other hand, if processing has not been performed for all the collation targets (S17: NO), the control unit 10 transfers the process to S12 and performs processing for the remaining collation targets stored in the comparison data storage unit 23.

[0032] In S18, the control unit 10 (notification processing unit 17) performs result output processing. Specifically, if a message has been generated in the previous processing, the control unit 10 outputs the message to the terminal 5. If no message has been generated in the previous processing, the control unit 10 outputs a message indicating that there is no problem with the collation result to the terminal 5. Note that if the text of the collation target completely matches, no message has been generated when the process reaches S18. After that, the control unit 10 ends this process.

[0033] Next, the discrimination process for variant characters and the like will be described. FIG. 5 is a flowchart showing the discrimination process for variant characters and the like of the character collation server 1 according to the present embodiment. FIG. 6 is a diagram showing an example of a method for calculating similarity in the discrimination process for variant characters and the like according to the present embodiment.

[0034] In S31 of FIG. 5, the control unit 10 (determination unit 16) searches the variant character DB4 for pairs of characters that do not match. In S32, the control unit 10 (determination unit 16) determines whether the mismatched pair of characters is registered in the character variant DB 4. If both of the mismatched pair of characters are registered as characters or character variants in the same record in the character variant DB 4, the control unit 10 determines that the characters are registered in the character variant DB 4. For example, in the case of " _ ... If the mismatched pair of characters is registered in the character variant DB4 (S32: YES), the control unit 10 proceeds to S33. On the other hand, if the mismatched pair of characters is not registered in the character variant DB4 (S32: NO), the control unit 10 proceeds to S34.

[0035] In S33, the control unit 10 (determination unit 16) generates a notification message indicating that the character is a variant character, and the process proceeds to S17 in FIG. In S34, the control unit 10 (determination unit 16) calculates the similarity between the mismatched characters. As an example of a method for calculating the similarity between characters, the control unit 10 divides an image area showing characters into a plurality of small areas. Then, the control unit 10 calculates the similarity between characters by comparing the small areas at the same position.

[0036] Here, a method for calculating the similarity between characters will be described with reference to FIG. 6(A) shows a calculation of the similarity between characters shown in an image area 61 and characters shown in an image area 62. The control unit 10 divides the image area 61 into n×n small areas. The control unit 10 then vectorizes the image area 61 and represents each small area with a value of 0 or 1. Similarly, the control unit 10 vectorizes the image area 62. Then, the control unit 10 calculates the Sum of Square Difference (SSD) using the vectorized values. The SSD calculates the degree of difference between the image region 61 and the image region 62. When the value obtained by vectorizing the image area 61 as x is represented by x(a, b) and the value obtained by vectorizing the image area 62 as y is represented by y(a, b), the SSD can be calculated by the following formula.

[0037]

Equation

[0038] According to this (Equation 1), the number of small areas with different values among the small areas at the same position can be calculated. Next, the control unit 10 calculates Sim, which indicates the similarity between the image area 61 and the image area 62, using the SSD by the following formula.

[0039]

Equation

[0040] Here, a more understandable Figure 6(B) will be used as an example for explanation. When calculating the similarity between the image area 63 and the image area 64, the control unit 10 applies the value 63a obtained by vectorizing the image area 63 and the value 64a obtained by vectorizing the image area 64 to (Equation 1) to calculate the SSD.

[0041]

Equation

[0042] Next, the control unit 10 applies the calculated SSD to (Equation 2) to calculate Sim, and sets the value of the calculated Sim as the similarity between the image area 63 and the image area 64.

[0043]

Equation

[0044] 5, the control unit 10 (determination unit 16) determines whether the calculated similarity is equal to or greater than a threshold. If the similarity is equal to or greater than the threshold (S35: YES), the control unit 10 proceeds to S36. On the other hand, if the similarity is not equal to or greater than the threshold (S35: NO), the control unit 10 proceeds to S37. For example, if the threshold value is 0.8, in the case of FIG. 6(B), the control unit 10 determines that the similarity is equal to or greater than the threshold value.

[0045] In S36, the control unit 10 (determination unit 16) generates a notification message indicating that the character is a variant or a mistranslation, and proceeds to S17 in Fig. 3. For example, in the case of Fig. 6(A), if the calculated similarity is equal to or greater than the threshold, the process proceeds to S36, but in this example, the character is a variant. In actual processing, the character shown in Fig. 6(A) is registered in the variant DB4, so the result of S32 becomes YES. Therefore, when this process is reached and the character is a variant, it corresponds to a case where the character is a variant that is not registered in the variant DB4. Examples of incorrect conversions include "tsuki" and "me", "iri" and "hito", and "ga" and "ke". In S37, the control unit 10 (determination unit 16) generates a warning message indicating a mismatch, and the process proceeds to S17 in FIG.

[0046] Next, the erroneous conversion determination process will be described. FIG. 7 is a flowchart showing the erroneous conversion determination process of the character matching server 1 according to this embodiment. In S41 of FIG. 7, the control unit 10 (determination unit 16) identifies the mismatched characters. In S42, the control unit 10 (determination unit 16) calculates the similarity between the identified combination of multiple characters and the paired character. The calculation of the similarity here can be performed using the same process as the calculation of the similarity between characters described in FIG. 6. However, the character region of the combination of multiple characters is twice as large in the horizontal direction as the paired character region. Therefore, for example, when dividing the character region of the combination of multiple characters into small regions, the control unit 10 doubles the horizontal size of the characters to make the width of one region. By doing so, it is possible to generate the same number of small regions as the paired characters, so that the processes from vectorization onwards can be performed in the same way.

[0047] In S43, the control unit 10 (determination unit 16) determines whether the similarity is equal to or greater than a threshold. If the similarity is equal to or greater than the threshold (S43: YES), the control unit 10 proceeds to S44. On the other hand, if the similarity is not equal to or greater than the threshold (S43: NO), the control unit 10 proceeds to S45. In S44, the control unit 10 (determination unit 16) generates a notification message to the effect that the conversion is incorrect, and moves the process to S17 in Fig. 3. Examples of cases that proceed to the process of S44 include when a single character "好" (good) is erroneously converted into two characters "女" (woman) and "子" (child), when a single character "明" (light) is erroneously converted into two characters "日" (sun) and "月" (month), or when a single character "飯" (meal) is erroneously converted into two characters "食" (food) and "反" (anti-food). In S45, the control unit 10 (determination unit 16) generates a warning message indicating a mismatch, and the process proceeds to S17 in FIG.

[0048] Next, a series of processing steps will be described with a specific example. FIG. 8 is a diagram showing a specific example of character discrimination in the character matching system 100 according to this embodiment. First, application data obtained by imaging an application document 7 and personal identification data obtained by imaging an identification document 8 are input to the character verification server 1. In the character matching server 1, the control unit 10 extracts the items and values to be matched from the application data and stores them in the comparison data storage unit 23. Further, the control unit 10 extracts the items and values from the identity verification data and stores them in the comparison data storage unit 23. Next, in the character matching server 1, the control unit 10 extracts the value of the name as the item to be matched from the comparison data storage unit 23 and performs a comparison. If there is a mismatch as a result of the comparison and it is determined that the characters are variant characters, the control unit 10 of the character matching server 1 generates a message indicating that the characters are variant characters and outputs it to the terminal 5 as a pop-up message 51.

[0049] As described above, according to this embodiment, the character matching server 1 has the following effects. (1) Compare the first text, which is the value for the item to be matched obtained from the application documents, with the second text, which is the value for the item obtained from the identity verification documents. When the result of the comparison is a mismatch, determine the content of the mismatch and issue a notification corresponding to the determined content of the mismatch. Therefore, when the result of comparing the two texts is a mismatch, a notification corresponding to the content of the mismatch can be issued. As a result, an easy-to-understand notification can be output to the operator who checks the matching content.

[0050] (2) Refer to the variant character DB 4. When the pair of characters that do not match is registered in the variant character DB 4, determine that the content of the mismatch is a variant character and notify that it is a variant character. Therefore, by determining whether it is a variant character based on the variant character DB 4 and notifying that it is a variant character when it applies, the operator can be prompted to pay attention.

[0051] (3) Calculate the similarity between the pair of characters that do not match. When the calculated similarity is equal to or greater than the threshold value, determine that the content of the mismatch is a variant character or a mis-conversion, and notify to that effect. Therefore, even if there are variant characters not registered in the variant character DB4, the operator can be alerted by the notification. Also, in the case of similar characters, there is a possibility of incorrect conversion, so the operator can be alerted by the notification. (4) Since the image area showing the pair of characters that do not match is divided into a plurality of small areas, and the small areas at the same position are compared to calculate the similarity, the similarity can be calculated by a simple process.

[0052] (5) When the number of characters in the first text and the second text is confirmed and the equality of the number of characters is confirmed, they are compared one by one in order. Therefore, by excluding the case where the number of characters does not match first, the process can be performed efficiently. (6) When the number of characters does not match, the characters that do not match are specified, the similarity between the specified combinations of a plurality of characters and the corresponding characters is calculated, and if the calculated similarity is equal to or greater than the threshold value, it is determined that there is an incorrect conversion. Therefore, the operator can be alerted even about incorrect conversions such as when one character is converted into two characters.

[0053] (7) Since the predetermined item includes at least one of the name and the address, it can be used for items that are likely to include variant characters as values for the item. (8) The collation target item and value are acquired from the application data obtained by imaging the application documents, and the value corresponding to the same collation target item is acquired from the personal confirmation data obtained by imaging the personal confirmation documents and compared. Therefore, based on the imaged data, character collation for the collation target item can be automatically performed.

[0054] The embodiments of the present invention have been described above, but the present invention is not limited to the above-described embodiments. Also, the effects described in the embodiments merely list the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments. Note that the above-described embodiments and the deformation modes described later can be used in appropriate combinations, but detailed descriptions thereof are omitted.

[0055] (Modification mode) (1) In this embodiment, it has been described that the variant character DB is communicably connected to the character collation server, but it is not limited to this. The variant character DB may be included in the character collation server. (2) In this embodiment, an example has been described in which both the use of the variant character DB and the calculation of the similarity between pairs of characters that do not match are used in combination, but it is not limited to this. Only one of the methods may be used. However, using both methods enables more reliable collation.

[0056] (3) In this embodiment, an example has been described in which the character collation server determines whether a character is a variant character or a mis-converted character, but it is not limited to this. The processing performed by the character collation server may be incorporated into the apparatus that performs the application process, and the function may be used as part of various processes for the application.

[0057] (4) In this embodiment, the variant character DB has been described as storing the variant characters themselves, but it is not limited to this. For example, a variant character string storage unit (not shown) that stores character strings including variant characters commonly used in personal names and place names may be used. In that case, the character collation server determines the collation character string based on whether the characters before and after the variant character are stored in the variant character string storage unit. Then, the character collation server determines whether the character is a variant character by determining whether the character string including the paired character string is stored in the variant character string storage unit. By performing such processing, the reliability of the collation is further improved.

Explanation of Reference Numerals

[0058] 1 Character Collation Server 4 Variant Character DB 5 Terminal 7 Application Documents 8 Identity Verification Documents 10 Control Unit 11 Application Data Acquisition Unit 12 First Text Acquisition Unit 13 Identity Verification Data Acquisition Unit 14 Second Text Acquisition Unit 15 Comparison Unit 16 Determination Unit 17 Notification Processing Unit 20 Memory Unit 21a Character Matching Program 23 Comparison Data Memory Unit 51 Pop-up Message 100 Character Matching System N Communication Network

Claims

1. comparison means for comparing a first text for a predetermined item obtained from a first document with a second text for the predetermined item obtained from a second document; determination means for determining inconsistent content including variant characters and incorrect conversions when the result of comparison by the comparison means is inconsistent; notification means for notifying the inconsistent content determined by the determination means; A character collation device comprising:

2. In the character collation device according to claim 1, when the pair of characters that are inconsistent are registered in a variant character dictionary storing variant characters, the determination means determines that the inconsistent content is a variant character; the notification means notifies that it is a variant character. A character collation device.

3. In the character collation device according to claim 1 or claim 2, the determination means calculates the similarity between the pair of inconsistent characters, and when the calculated similarity is equal to or greater than a threshold value, determines that the inconsistent content is a variant character or an incorrect conversion; the notification means notifies that it is a variant character or an incorrect conversion. A character collation device.

4. In the character collation device according to claim 3, the determination means divides an image area indicating a pair of inconsistent characters into a plurality of small areas, compares the small areas at the same position, and calculates the similarity. A character collation device.

5. In the character collation device according to any one of claims 1 to 4, it includes character count confirmation means for confirming the number of characters in the first text and the second text; when the comparison means confirms the equality of the number of characters by the character count confirmation means, the comparison means compares one character at a time in order. A character collation device.

6. In the character collation device according to claim 5, when the character count confirmation means confirms a difference in the number of characters, a plurality of combinations of the characters that are inconsistent characters as a result of the comparison between the first text and the second text by the comparison means, and the paired characters are specified, and an image area indicating the plurality of specified character combinations and an image area indicating the paired specified characters are each divided into the same number of small areas and compared to calculate a similarity calculation means for calculating the similarity; when the similarity calculated by the similarity calculation means is equal to or greater than a threshold value, the notification means notifies that it is an incorrect conversion. A character collation device.

7. In the character collation device according to any one of claims 1 to 6, the predetermined item includes at least one of a name and an address. A character collation device.

8. In the character matching device according to any one of claims 1 to 7, first data acquisition means for acquiring first data obtained by imaging the first document; second data acquisition means for acquiring second data obtained by imaging the second document; first text acquisition means for acquiring the predetermined item from the first data acquired by the first data acquisition means and acquiring, as the first text, a value corresponding to the acquired predetermined item; second text acquisition means for acquiring the predetermined item from the second data acquired by the second data acquisition means and acquiring, as the second text, a value corresponding to the acquired predetermined item; A character matching device comprising:

9. In the character matching device according to claim 8, the first data and / or the second data is imaging data of a document including handwritten characters, the character matching device, wherein the first text and / or the second text is text obtained by performing character recognition processing on the imaging data.

10. A program for causing a computer to function as the character matching device according to any one of claims 1 to 9.

Images