Expense inspection device, expense inspection method and program

Abstract

To address such a problem that it is difficult to properly check input of expenses by conventional techniques.SOLUTION: An expense inspection device 1 includes: a receiving unit 12 for receiving input expense information of expenses input by a user and a receipt image corresponding to the expenses; a character string acquisition unit 131 for acquiring one or more OCR character strings as a result of OCR for the receipt image; a score acquisition unit 132 for comparing the input expense information with the one or more OCR character strings and acquiring a score relating to certainty of the input expense information; and a related information output unit 141 for outputting related information related to the score, thereby properly checking input of expenses.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an expense checking device that checks information about expenses entered by a user. [Background technology]

[0002] Conventionally, there have been accounting systems with an automatic journal entry creation function that can automatically create journal entries for inputted expense information (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 3823164 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, it was difficult to properly verify input expenses. [Means for solving the problem]

[0005] The expense checking device of the first invention is an expense checking device comprising: a reception unit that receives input expense information regarding expenses input by a user and a receipt image corresponding to the expenses; a string acquisition unit that acquires one or more OCR strings which are the results of OCR on the receipt image; a score acquisition unit that compares the input expense information with the one or more OCR strings and acquires a score regarding the accuracy of the input expense information; and a related information output unit that outputs related information regarding the score.

[0006] This configuration enables appropriate confirmation of input expense information.

[0007] In addition, in contrast to the first invention, the expense checking device of the second invention is an expense checking device in which two or more receipts are included in a receipt image.

[0008] With this configuration, it is possible to properly check input expense information using a receipt image that includes two or more receipts.

[0009] In addition, the expense verification device of the third invention is an expense verification device in which, compared to the second invention, the character string acquisition unit acquires one or more OCR character strings from each image of two or more receipts without determining the boundaries between the images of the two or more receipts.

[0010] With this configuration, even for input expense information using a receipt image that includes two or more receipts, proper confirmation can be performed through simple processing.

[0011] In addition, the expense checking device of the fourth invention is an expense checking device according to the second or third invention, in which the reception unit receives two or more input expense information and a receipt image including two or more receipts, the character string acquisition unit acquires one or more OCR character strings which are the results of OCR on the receipt image including two or more receipts, and the score acquisition unit compares each of the two or more input expense information with the one or more OCR character strings to acquire a score related to the accuracy of the input expense information.

[0012] With this configuration, even when two or more expense entries and receipt images containing two or more receipts are mixed, proper confirmation is possible.

[0013] In addition, the expense checking device of the fifth invention is an expense checking device in which, compared to any one of the first to fourth inventions, the score acquisition unit acquires two or more pieces of partial information that are parts that make up the input expense information, compares each of the two or more pieces of partial information with a string in one or more OCR strings, and acquires a score using the comparison result for each of the two or more pieces of partial information.

[0014] This configuration enables appropriate confirmation of input expense information.

[0015] In addition, the expense checking device of the sixth invention is an expense checking device in which, compared to the fifth invention, the score acquisition unit acquires partial information, which is an n-gram string of element information constituting the input expense information, detects a matching string, which is a string that matches the partial information, from one or more OCR strings, acquires a forward character count, which is the number of characters of a forward string located before the matching string in the element information, and a forward character count, which is the number of characters of a backward string located after the matching string in the element information, acquires a comparison string consisting of an OCR forward character count, which is a forward string the number of characters ahead of the matching string, and an OCR backward character count, which is a backward string the number of characters behind the matching string, from the OCR string containing the matching string, calculates a distance between the element information and the comparison string, and acquires a score using the distance.

[0016] This configuration enables appropriate confirmation of input expense information.

[0017] In addition, the expense checking device of the seventh invention is an expense checking device in which, compared to the sixth invention, the score acquisition unit uses element information that constitutes the input expense information to generate second element information, which is a different notation with the same meaning as the element information, acquires a comparison string for the second element information, calculates the distance between the second element information and the comparison string, and acquires a score using the distance.

[0018] This configuration enables appropriate confirmation of input expense information.

[0019] In addition, the expense checking device of the eighth invention is an expense checking device according to any one of the first to seventh inventions, in which the related information output unit notifies a user or administrator corresponding to the input expense information of related information regarding an error in the input expense information when the information indicates a probability that the score is low enough to satisfy a predetermined condition.

[0020] With this configuration, when expense information that is likely to be inappropriate is entered, appropriate notification can be given.

[0021] Further, an expense checking device according to a ninth aspect of the present invention is the expense checking device according to any one of the first to seventh aspects of the present invention, in which the related information output unit outputs related information on the score in association with the input expense information.

[0022] This configuration enables appropriate confirmation of input expense information.

[0023] In addition, the expense checking device of the tenth invention is an expense checking device according to any one of the first to ninth inventions, in which the input expense information includes two or more of the following information: date, amount, and payee, the score acquisition unit compares each of the two or more pieces of information with one or more OCR character strings, acquires a score for each of the two or more pieces of information, acquires a representative score which is a representative value of the two or more scores, and the related information output unit outputs related information related to the representative score.

[0024] This configuration enables appropriate confirmation of input expense information. Effect of the Invention

[0025] The expense verification device according to the present invention allows appropriate verification of expense input. [Brief description of the drawings]

[0026] [Figure 1] Conceptual diagram of information system A in embodiment 1. [Diagram 2] Block diagram of Information System A [Diagram 3] A flowchart for explaining an example of the operation of the expense inspection device 1. [Figure 4] A flowchart for explaining an example of the element score acquisition process [Diagram 5] A flowchart illustrating an example of the second element information generation process. [Figure 6] A flowchart for explaining an example of the partial score acquisition process [Figure 7] A flowchart illustrating an example of the related information acquisition process. [Figure 8] FIG. 13 is a diagram showing an example of the user information management table. [Figure 9] FIG. 13 shows an example of the expense information management table. [Figure 10] FIG. 13 is an example of the pattern management table. [Figure 11] FIG. 13 shows an example of the receipt image. [Figure 12] FIG. 13 shows an example of the character recognition result. [Figure 13] FIG. 13 is a diagram showing an example of a management table of pairs of partial information and comparison character strings in the score acquisition process. [Figure 14] FIG. 13 shows an example of the receipt image. [Figure 15] FIG. 13 shows an example of the character recognition result. [Figure 16] Overview of the computer system [Figure 17] Block diagram of the computer system DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] Hereinafter, an embodiment of the expense inspection device and the like will be described with reference to the drawings. Note that, in the embodiments, components with the same reference numerals perform similar operations, so that repeated description may be omitted.

[0028] (Embodiment 1) In this embodiment, an expense verification device is described that compares input expense information input by a user with an OCR result of a receipt image corresponding to the input expense information, obtains a score regarding the accuracy of the input expense information, and outputs related information regarding the score. Note that in this embodiment, the receipt image may include images of two or more receipts. Also, in this embodiment, for example, the score is obtained using the distance between a part of the input expense information and a part of the OCR result.

[0029] In addition, in this embodiment, we will describe an expense verification device that can obtain a score regarding the accuracy of input expense information and output related information regarding the score even when the input expense information includes two or more images of two or more receipts.

[0030] 1 is a conceptual diagram of an information system A according to the present embodiment. The information system A includes an expense verification device 1 and one or more terminal devices 2.

[0031] The expense checking device 1 is a device that checks input expense information. The expense checking device 1 is usually a so-called server, for example, a cloud server, an ASP server, etc. The type of the expense checking device 1 is not important.

[0032] The terminal device 2 is a terminal used by a user. The user is, for example, a user who applies for expenses. The user is, for example, an accountant, a manager, etc. The terminal device 2 is, for example, a so-called personal computer, a tablet terminal, a smartphone, etc., and the type does not matter.

[0033] FIG. 2 is a block diagram of an information system A in this embodiment.

[0034] The expense checking device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a user information storage unit 111, and an expense information storage unit 112. The processing unit 13 includes a character string acquisition unit 131, a score acquisition unit 132, and a related information acquisition unit 133. The output unit 14 includes a related information output unit 141.

[0035] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit .

[0036] Various types of information are stored in the storage unit 11 constituting the expense verification device 1. The various types of information are, for example, user information, expense information, an arithmetic expression for calculating a score, and patterns and normal conditions, which will be described later. It is preferable that each of the one or more patterns corresponds to a type identifier, which will be described later. The normal conditions are conditions for determining whether or not a score is normal. For example, the normal conditions are that the score is equal to or greater than a threshold value. The normal conditions may exist for each type identifier.

[0037] The user information storage unit 111 stores one or more pieces of user information. User information is information about a user. User information typically has a user identifier. User information typically has one or more user attribute values. A user identifier is information that identifies a user. The user identifier is, for example, a user ID, an employee number, an email address, a telephone number, etc. The one or more user attribute values ​​are, for example, a name, a company name, a department name, an email address, and a superior's email address.

[0038] The expense information storage unit 112 stores one or more pieces of expense information. The expense information is information that specifies the contents of the claimed expense. The expense information includes, for example, a date, an amount, and a payee. The expense information includes, for example, an item, a summary, etc. The payee is the name of the company or store to which the expense is paid. For example, a receipt image is associated with each of the one or more pieces of expense information. One receipt image may be associated with two or more pieces of expense information. Two or more receipt images may be associated with two or more pieces of expense information. A receipt image is an image that includes a receipt. For example, one receipt image includes only one image of a receipt. However, a receipt image may include two or more images of receipts. The receipt image is, for example, jpeg, gif, etc., but the data format is not important. The receipt image is, for example, a file, but may also be information in a DB. The receipt image is information that is the subject of character recognition processing.

[0039] The reception unit 12 receives various instructions and information. The various instructions and information are, for example, input expense information and a receipt image. The input expense information is information related to expenses input by a user. The input expense information has one or more element information. The element information is the input expense information or information constituting the expense information. The element information is, for example, a date, an amount, and a payee. It is preferable that the input expense information includes two or more element information of the date, the amount, and the payee. All or a part of the element information constituting the input expense information is information constituting the expense information. Note that there is no restriction on how each of the two or more element information in the input expense information is separated. For example, a tag is associated with each of the two or more element information in the input expense information. For example, each of the two or more element information in the input expense information is separated by a delimiter. The delimiter is, for example, ",", "|", a space, etc., but there is no restriction on the method.

[0040] The accepting unit 12 accepts the associated input expense information and receipt image. The accepting unit 12 may accept two or more pieces of input expense information and one receipt image in association with each other.

[0041] The accepting unit 12 may accept two or more pieces of input expense information and two or more receipt images including receipts in association with each other.

[0042] The reception unit 12 receives, for example, an output instruction. The output instruction is an instruction to output expense information, etc. The output instruction includes information indicating conditions for the expense information, etc. to be output.

[0043] Here, "acceptance" usually means reception from the terminal device 2. However, "acceptance" only means that information can be acquired. Also, the acceptance unit 12 does not need to accept the input expense information and the receipt image together. It is sufficient for the acceptance unit 12 to acquire the input expense information and the receipt image in a manner that allows them to be associated with each other.

[0044] The processing unit 13 performs various types of processing. The various types of processing are processing performed by a character string acquisition unit 131, a score acquisition unit 132, and a related information acquisition unit 133.

[0045] The character string acquisition unit 131 acquires one or more OCR character strings that are the results of OCR on the receipt image accepted by the acceptance unit 12. One OCR character string is, for example, a character string of one line. However, the OCR character string may be a character string of two or more lines.

[0046] The character string acquisition unit 131 can be realized by a known OCR technique (character recognition technique). The OCR character string is a character string that is a result of the OCR.

[0047] The character string acquisition unit 131 may receive one or more OCR character strings, which are the results of character recognition of the receipt image, from an external device (not shown). In this case, the character string acquisition unit 131 does not perform character recognition processing. In this case, the character string acquisition unit 131 transmits the receipt image to an external device that performs character recognition processing, and receives one or more OCR character strings from the external device, for example.

[0048] When one receipt image contains two or more receipt images, it is preferable for the character string acquisition unit 131 to acquire one or more OCR character strings that are the result of character recognition processing of the one receipt image without determining the boundaries of the two or more receipt images. In other words, the character string acquisition unit 131 acquires one or more OCR character strings that are the result of character recognition processing performed on the accepted receipt image file.

[0049] In addition, when one receipt image contains two or more receipt images, the character string acquisition unit 131 may acquire one or more OCR character strings in a situation where character strings acquired from each of the two or more receipt images are mixed.

[0050] The score acquisition unit 132 compares the input expense information with one or more OCR character strings and acquires a score. It can be said that the score is information regarding the accuracy of the input expense information. The score may be information indicating the degree of correctness of the input expense information. The score may be said to be probability information. Generally, the larger the score value, the greater the degree of correctness of the input expense information, but the score may be information indicating that the smaller the score value, the greater the degree of correctness of the input expense information. The score is information using the result of comparing the input expense information with one or more OCR character strings. For example, the more information in the input expense information is included in one or more OCR character strings, the greater the score.

[0051] It is preferable that the score acquisition unit 132 compares two or more pieces of element information constituting the input expense information with one or more OCR character strings to acquire a score. Note that there is no restriction on the method of acquiring the score. For example, the score is the ratio of characters constituting the input expense information that exist in one or more OCR character strings.

[0052] The score acquisition unit 132 may compare each of two or more pieces of input expense information with one or more OCR character strings, and acquire a score related to the accuracy of the input expense information.

[0053] The score acquisition unit 132, for example, compares one or more pieces of element information constituting the input expense information with a character string in one or more OCR character strings, and acquires a score using a comparison result with the one or more pieces of element information.

[0054] The score acquisition unit 132, for example, acquires two or more pieces of partial information that constitute the input expense information, compares each of the two or more pieces of partial information with a string in one or more OCR strings, and acquires a score using the comparison result for each of the two or more pieces of partial information.

[0055] The score acquisition unit 132, for example, acquires two or more pieces of partial information that are parts of the element information for each of one or more pieces of element information that constitute the input expense information, compares each of the two or more pieces of partial information with a character string in one or more OCR character strings, and acquires a score using the comparison result for each of the two or more pieces of partial information.

[0056] The score acquiring unit 132, for example, calculates the distance between the element information constituting the input expense information and one or more comparison character strings, and acquires a score using the distance. The score acquiring unit 132 acquires a higher score value as the distance becomes smaller. The score acquiring unit 132 acquires the score, for example, by a decreasing function using the distance as a parameter. The comparison character string will be described later.

[0057] The score acquiring unit 132, for example, calculates the distance between the element information constituting the input expense information and one or more comparison character strings, and acquires the score using the shortest distance. For example, the score acquiring unit 132 acquires a higher score value as the shortest distance is smaller. For example, the score acquiring unit 132 calculates the score using a decreasing function with the shortest distance as a parameter.

[0058] When there are two or more pieces of element information constituting the input expense information, the score acquiring unit 132 acquires, for example, a score for each of the two or more pieces of element information. Then, the score acquiring unit 132 acquires the score of the input expense information using the score of two or more. The score acquiring unit 132 acquires, for example, a representative value of the scores of two or more. The representative value of the score is, for example, the average value, median value, minimum value, or maximum value of the scores. The score acquiring unit 132 calculates the score of the input expense information, for example, by an increasing function using the scores of the two or more pieces of element information as parameters.

[0059] The distance may be any information regarding the difference between two character strings, such as edit distance, Levenshtein distance, or minimum edit distance.

[0060] The score acquiring unit 132 acquires a comparison character string, for example, as follows. That is, the score acquiring unit 132 detects a matching character string from one or more OCR character strings. Then, the score acquiring unit 132 acquires one or more other OCR characters from the OCR character string including the matching character string. Note that a matching character string is a character string that matches partial information.

[0061] Next, the score acquisition unit 132 acquires a comparison string consisting of, for example, an OCR forward string, a matching string, and an OCR backward string. The OCR forward string is a string in the OCR string that includes the matching string, is a string located immediately before the matching string, and is a string with the number of forward characters. The number of forward characters is the number of characters in the forward string that is a string located before the matching string in the element information. The OCR backward string is a string in the OCR string that includes the matching string, is a string located immediately after the matching string, and is a string with the number of backward characters. The number of backward characters is the number of characters in the forward string that is a string located after the matching string in the element information.

[0062] There may be cases where the OCR front character string does not exist. In such cases, the score acquisition unit 132 acquires, for example, a comparison character string consisting of a matching character string and an OCR rear character string. There may also be cases where the OCR rear character string does not exist. In such cases, the score acquisition unit 132 acquires, for example, a comparison character string consisting of an OCR front character string and a matching character string.

[0063] That is, the score acquisition unit 132 acquires partial information (for example, a character string of an n-gram) constituting element information constituting the input expense information, and detects a matching character string that is a character string that matches the partial information from one or more OCR character strings. Next, the score acquisition unit 132 acquires, for example, a forward character count that is the number of characters of a forward character string located before the matching character string in the element information, and a forward character count that is the number of characters of a backward character string located after the matching character string in the element information, and acquires a comparison character string consisting of an OCR forward character string, a matching character string, and an OCR backward character string from an OCR character string including a matching character string. Next, the score acquisition unit 132 calculates, for example, a distance between the element information and the comparison character string, and acquires a score for the element information using the distance. Also, the score acquisition unit 132 acquires a score for the input expense information using, for example, scores for two or more pieces of element information.

[0064] The score acquiring unit 132, for example, calculates the distance between the element information constituting the input expense information and each of two or more comparison character strings, and acquires the score using the minimum distance among the two or more distances. The score acquiring unit 132 acquires the score using, for example, a decreasing function with the minimum distance as a parameter.

[0065] The score acquisition unit 132 compares, for example, two or more pieces of element information among the date, amount, and payee contained in the input expense information with one or more OCR character strings, acquires a score for each of the two or more pieces of element information, and acquires a representative score that is a representative value of the two or more scores. Note that the representative score is, for example, the average, median, maximum, or minimum of the two or more scores.

[0066] The input expense information may include character strings written by the applicant after issuing a receipt, such as the number of participants, the applicant's signature, the name of the department using the expenses, etc. The score acquisition unit 132 may acquire a score using the likelihood of the character strings written by the applicant after issuing a receipt, such as the number of participants, the applicant's signature, the name of the department using the expenses, etc.

[0067] The element information is, for example, the date, amount, or payee in the input expense information. In addition, although it is preferable that the n-gram is a 3-gram, it may be a character string of other lengths such as a 2-gram or 4-gram. If the element information is the date "2021 / 3 / 11", the partial information of the 3-gram is, for example, "202", "021", "21 / ", "1 / 3 / ", " / 3 / ", "3 / 1", and " / 11".

[0068] It is preferable that the score acquisition unit 132 uses element information constituting the input expense information to acquire one or more second element information that is a different expression with the same meaning as the element information, acquires one or more comparison strings for each of the one or more second element information, calculates the distance between the second element information and each of the one or more comparison strings, and acquires a score using the distance. Note that the second element information may also be called element information. Also, the algorithm for acquiring the comparison string using the second element information is the same as the algorithm for acquiring the comparison string using the element information.

[0069] The score acquiring unit 132 acquires one or more pieces of second element information as follows, for example, by using element information constituting the input expense information. The score acquiring unit 132 acquires one or more pieces of second element information by using, for example, one or more patterns stored in the storage unit 11. In other words, the score acquiring unit 132 transforms the element information by using the pattern to acquire the second element information.

[0070] In the case where the type identifier of the element information is "date", the storage unit 11 contains information of the pattern "???? / ?? / ??", "???? year ?? month ?? day" (? is any number from 0 to 9), and the element information held by the input expense information is "2020 / 8 / 27", the score acquisition unit 132 refers to the pattern in the storage unit 11 and obtains the second element information "August 27, 2020". Note that the technology for generating the notation of another date from information of one date taking into account variations in the notation of dates is a publicly known technology, and therefore a detailed description is omitted. Note that the type identifier is information that identifies the type of element information, such as "date", "amount", or "payee".

[0071] The score acquiring unit 132 acquires one or more character strings from each of the one or more OCR character strings, which are, for example, one or more character strings having the same number of characters as the number of characters of each element information constituting the input expense information, and calculates a distance between each of the one or more character strings (which may be called a comparison character string) and each element information.The score acquiring unit 132 may then acquire a score using a distance of 1 or more.It is preferable that the score acquiring unit 132 acquires a score using the minimum distance of the distances of 1 or more.

[0072] The score acquiring unit 132, for example, acquires the number of characters of each element information constituting the input expense information, acquires one or more character strings of one or more OCR character strings having the same number of characters as the number of characters, shifting each OCR character string by one character from the beginning of each OCR character string, and calculates the distance between each of the one or more character strings (which may be called a comparison character string) and each element information.The score acquiring unit 132 may then acquire a score using the minimum distance.

[0073] The related information acquisition unit 133 acquires related information related to the score. The related information acquisition unit 133 acquires the related information by using the score acquired by the score acquisition unit 132.

[0074] The related information is, for example, a score, information regarding the test results of the input expense information, input expense information that has been determined to be correct, and input expense information that has been determined to be correct and a receipt image.

[0075] For example, if the score is smaller than a threshold value or equal to or less than the threshold value, the related information acquiring unit 133 acquires related information indicating that there is an error in the input expense information.

[0076] When the score acquisition unit 132 acquires a score for each element information, the related information acquisition unit 133 may determine whether the input expense information is correct, for example, using different thresholds (different criteria) for combinations of two or more different elements.

[0077] When the related information acquisition unit 133 judges whether the input expense information is correct using two scores of the element information "date" and the element information "amount", the related information acquisition unit 133 judges whether the input expense information is correct, for example, based on whether the sum of the two scores acquired by the score acquisition unit 132 (for example, the sum of two edit distances) is equal to or greater than a first threshold value (for example, 1.85). Note that such a case is, for example, when no payee is input.

[0078] On the other hand, when the related information acquisition unit 133 judges whether the input expense information is correct using the three scores of the element information "date", the element information "amount", and the element information "payee", the related information acquisition unit 133 judges whether the input expense information is correct, for example, based on whether the sum of the three scores acquired by the score acquisition unit 132 (for example, the sum of the three edit distances) is equal to or greater than a second threshold value (for example, 2.7). Note that such a case is, for example, when the payee is not input.

[0079] Also, for example, the score is calculated for each of two or more types of element information such as the element information "date," "amount," "payee," etc. And, the more types of element information to obtain the score, the more suitable it is for the related information obtaining unit 133 to increase the threshold value and determine whether the input expense information is correct.

[0080] When the score acquisition unit 132 acquires a score of 2 or more, the related information acquisition unit 133 acquires related information indicating that there is an error in the input expense information, for example, when one or more scores are smaller than or equal to a threshold value. Note that the score of 2 or more here is usually a score of 2 or more for each element information.

[0081] The output unit 14 outputs various types of information, such as related information, expense information, and receipt images.

[0082] The related information output unit 141 outputs the related information acquired by the related information acquisition unit 133 .

[0083] If the score is low enough to satisfy a predetermined condition, the related information output unit 141 notifies the user corresponding to the input expense information or the administrator of related information regarding an error in the input expense information.

[0084] The related information output unit 141 outputs, for example, input expense information and a receipt image in association with each other. The related information output unit 141 outputs, for example, a score and input expense information in association with each other. The output here usually means accumulation. However, the output may be a concept including display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, and delivery of processing results to other processing devices or other programs.

[0085] The related information output unit 141 outputs, for example, related information relating to the representative score.

[0086] Various types of information are stored in the terminal storage unit 21 constituting the terminal device 2. The various types of information are, for example, a user identifier, input expense information, and a receipt image.

[0087] The terminal reception unit 22 receives various instructions and information, such as input expense information, receipt images, and output instructions.

[0088] The device processing unit 23 performs various types of processing. For example, the various types of processing are processing for converting instructions and information accepted by the terminal accepting unit 22 into instructions and information with a data structure to be transmitted. For example, the various types of processing are processing for converting information received by the terminal receiving unit 25 into information with a data structure to be output.

[0089] For example, when the terminal receiving unit 22 receives input expense information and a receipt image, the terminal processing unit 23 obtains the user identifier from the terminal storage unit 21, and associates the user identifier with the input expense information and the receipt image to configure the information to be transmitted.

[0090] The terminal transmission unit 24 transmits various instructions and information, such as input expense information, receipt images, user identifiers, and output instructions.

[0091] The terminal receiving unit 25 receives various types of information, such as related information, expense information, and receipt images.

[0092] The terminal output unit 26 outputs various types of information, such as related information, expense information, and receipt images.

[0093] The storage unit 11, the user information storage unit 111, the expense information storage unit 112, and the terminal storage unit 21 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0094] There is no restriction on the process by which information is stored in the storage unit 11, etc. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information inputted via an input device may be stored in the storage unit 11, etc.

[0095] The reception unit 12 and the terminal receiving unit 25 are usually realized by wireless or wired communication means.

[0096] The processing unit 13, the character string acquisition unit 131, the score acquisition unit 132, the related information acquisition unit 133, and the device processing unit 23 can usually be realized by a processor, a memory, etc. The processing procedure of the processing unit 13, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit). The processor may be an MPU, a CPU, a GPU, etc., and the type is not important.

[0097] The output unit 14, the related information output unit 141, and the terminal transmission unit 24 are usually realized by wireless or wired communication means.

[0098] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0099] The terminal output unit 26 may or may not include an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or a combination of driver software for an output device and an output device, etc.

[0100] Next, a description will be given of an example of the operation of the information system A. First, a description will be given of an example of the operation of the expense verification device 1 with reference to the flowchart of FIG.

[0101] (Step S301) The reception unit 12 judges whether or not input expense information and a receipt image have been received from the terminal device 2. If input expense information, etc. have been received, the process proceeds to step S302, and if input expense information, etc. have not been received, the process proceeds to step S309.

[0102] (Step S302) The character string acquisition unit 131 performs character recognition processing on the receipt image received in step S301 to acquire one or more OCR character strings. The character recognition processing may be performed by an external device (not shown). Here, one OCR character string is, for example, a character string of one line or a character string in one text box.

[0103] (Step S303) The score acquiring unit 132 assigns 1 to a counter i.

[0104] (Step S304) The score acquisition unit 132 judges whether or not the i-th element information is present in the input expense information received in step S301. If the i-th element information is present, the process proceeds to step S305, and if the i-th element information is not present, the process proceeds to step S307.

[0105] (Step S305) The score obtaining unit 132 obtains the score of the i-th element information. An example of such processing, that is, element score obtaining processing, will be described with reference to the flowchart of FIG.

[0106] (Step S306) The score acquiring unit 132 increments the counter i by 1. The process returns to step S304.

[0107] (Step S307) The related information acquisition unit 133 acquires related information by using the score acquired in step S305. An example of such related information acquisition processing will be described with reference to the flowchart of FIG.

[0108] (Step S308) The related information output unit 141 outputs the related information acquired in step S307. The process returns to step S301.

[0109] (Step S309) The reception unit 12 judges whether or not an output instruction has been received from the terminal device 2. If an output instruction has been received, the process proceeds to step S310, and if an output instruction has not been received, the process returns to step S301.

[0110] (Step S310) The processing unit 13 acquires from the expense information storage unit 112 one or more pieces of expense information etc. corresponding to the output instruction received in step S309.

[0111] (Step S311) The output unit 14 transmits the one or more pieces of expense information etc. acquired in step S310 to the terminal device 2 that transmitted the output instruction. Return to step S301.

[0112] In the flowchart of FIG. 3, when two or more pieces of input expense information are received in step S301, it is preferable to perform the processes from steps S303 to S308 for each of the two or more pieces of input expense information.

[0113] In the flowchart of FIG. 3, the process ends when the power is turned off or an interrupt occurs to end the process.

[0114] Next, an example of the element score acquisition process in step S305 will be described with reference to the flowchart in FIG.

[0115] (Step S401) The score acquisition unit 132 performs a second element information generation process. An example of the second element information generation process will be described with reference to the flowchart of FIG. 5. The second element information generation process is a process for generating one or more pieces of second element information using element information. There may be cases where the second element information cannot be generated here. The second element information may also be called element information.

[0116] (Step S402) The score acquiring unit 132 assigns 1 to a counter i.

[0117] (Step S403) The score acquisition unit 132 determines whether or not the i-th element information exists among the i-th element information in step S304 and one or more pieces of second element information generated in step S401.

[0118] (Step S404) The score acquiring unit 132 assigns 1 to a counter j.

[0119] (Step S405) The score acquisition unit 132 judges whether or not the jth partial information exists in the ith element information. If the jth partial information exists, the process proceeds to step S406, and if the jth partial information does not exist, the process proceeds to step S409. The partial information is, for example, an n-gram in the element information.

[0120] (Step S406) The score obtaining unit 132 obtains the j-th partial information in the i-th element information.

[0121] (Step S407) The score obtaining unit 132 performs a partial score obtaining process. An example of the partial score obtaining process will be described with reference to the flowchart in Fig. 6. Note that the partial score obtaining process is a process for obtaining a score corresponding to the j-th partial information.

[0122] (Step S408) The score acquiring unit 132 increments the counter j by 1. The process returns to step S405.

[0123] (Step S409) The score obtaining unit 132 increments the counter i by 1. The process returns to step S403.

[0124] (Step S410) The score acquisition unit 132 acquires a score for the i-th element information using the score of 1 or more acquired in step S407, pairs the score with the i-th element information, and temporarily accumulates the score in a buffer (not shown). The process returns to the upper level process.

[0125] For example, the score acquiring unit 132 acquires the maximum value of the scores equal to or greater than 1 acquired in step S407 as the score of the i-th element information.

[0126] Next, an example of the second element information generation process in step S401 will be described with reference to the flowchart in FIG.

[0127] (Step S501) The score acquiring unit 132 acquires a type identifier that identifies the type of the i-th element information (element information of interest) of step S304.

[0128] (Step S502) The score acquiring unit 132 assigns 1 to a counter i.

[0129] (Step S503) The score acquisition unit 132 judges whether or not the i-th pattern corresponding to the type identifier acquired in step S501 exists. If the i-th pattern exists, the process proceeds to step S504, and if the i-th pattern does not exist, the process returns to the upper process.

[0130] (Step S504) The score acquiring unit 132 judges whether the element information of interest is a character string corresponding to the i-th pattern. If the element information of interest is a character string corresponding to the i-th pattern, the process proceeds to step S506. If the element information of interest is not a character string corresponding to the i-th pattern, the process proceeds to step S505.

[0131] (Step S505) The score acquiring unit 132 acquires a character string corresponding to the i-th pattern corresponding to the type identifier acquired in step S501, using the element information of interest. This character string is the second element information.

[0132] (Step S506) The score acquiring unit 132 increments the counter i by 1. The process returns to step S503.

[0133] Next, an example of the partial score acquisition process in step S407 will be described with reference to the flowchart in FIG.

[0134] (Step S601) The score acquiring unit 132 assigns 1 to a counter i.

[0135] (Step S602) The score acquisition unit 132 judges whether or not the i-th OCR character string is present among the OCR character strings acquired in step S302. If the i-th OCR character string is present, the process proceeds to step S603, and if the i-th OCR character string is not present, the process returns to the upper process.

[0136] (Step S603) The score acquiring unit 132 assigns 1 to a counter j.

[0137] (Step S604) The score acquisition unit 132 judges whether or not it is possible to acquire a character string starting from the jth character string in the i-th OCR character string and having the number of characters of the jth partial information in step S406. If such a character string is acquireable, the process proceeds to step S605, and if not, the process proceeds to step S612.

[0138] (Step S605) The score acquisition unit 132 judges whether the j-th partial information of step S406 matches the character string starting from the j-th character string in the i-th OCR character string. If they match, the process proceeds to step S606, and if they do not match, the process proceeds to step S611.

[0139] (Step S606) The score acquiring unit 132 acquires the number of characters ahead. That is, the score acquiring unit 132 acquires the number of characters ahead of the partial information, which is a character string obtained by removing the j-th partial information (which can be said to be a matching character string) of step S406 from the element information of interest. Note that the number of characters ahead may be "0" here.

[0140] (Step S607) The score acquisition unit 132 acquires the OCR forward character string. That is, the score acquisition unit 132 acquires the OCR forward character string, which is the character string immediately before the matching character string and has the number of characters equal to the number of forward characters acquired in step S606, from the i-th OCR character string. Here, there may be cases where the OCR forward character string cannot be acquired.

[0141] (Step S608) The score acquiring unit 132 acquires the number of backward characters. That is, the score acquiring unit 132 acquires the number of backward characters, which is the number of characters following the partial information, which is a character string obtained by removing the j-th partial information (which can be said to be a matching character string) of step S406 from the element information of interest. Note that the number of backward characters may be "0" here.

[0142] (Step S609) The score acquiring unit 132 acquires an OCR rear character string. That is, the score acquiring unit 132 acquires an OCR rear character string, which is the number of characters equal to the number of rear characters acquired in step S606 from the i-th OCR character string and is the character string immediately following the matching character string.

[0143] (Step S610) The score acquisition unit 132 sequentially concatenates the OCR front character string acquired in step S607, the matching character string, and the OCR rear character string acquired in step S609 to acquire a comparison character string, and temporarily stores the comparison character string in a buffer (not shown). Note that there may be cases where the OCR rear character string cannot be acquired.

[0144] (Step S611) The score obtaining unit 132 increments the counter j by 1. The process returns to step S604.

[0145] (Step S612) The score acquiring unit 132 assigns 1 to a counter k.

[0146] (Step S613) The score acquisition unit 132 judges whether or not the kth comparison character string exists in a buffer (not shown). If the kth comparison character string exists, the process proceeds to step S614. If the kth comparison character string does not exist, the process proceeds to step S616.

[0147] (Step S614) The score acquiring unit 132 calculates the distance between the i-th element information of step S403 and the k-th comparison character string, and temporarily accumulates the distance in a buffer (not shown) in a pair with the k-th comparison character string.

[0148] (Step S615) The score acquiring unit 132 increments the counter k by 1. The process returns to step S613.

[0149] (Step S616) The score obtaining unit 132 increments the counter i by 1. The process returns to step S602.

[0150] In step S610 in FIG. 6, it is preferable that the score acquiring unit 132 acquires the same comparison character string in the same location only once.

[0151] In step S614 in FIG. 6, it is preferable that the score obtaining unit 132 obtains the distance between the same comparison character string and element information at the same location only once.

[0152] Next, an example of the related information acquisition process in step S307 will be described with reference to the flowchart in FIG.

[0153] (Step S701) The related information acquisition unit 133 judges whether or not the score of each of the one or more pieces of element information accumulated in step S410 satisfies a normal condition. If the normal condition is satisfied, the process proceeds to step S702, and if the normal condition is not satisfied, the process proceeds to step S703.

[0154] (Step S702) The related information acquisition unit 133 constructs related information having the input expense information and the receipt image received in step S301. The process returns to the upper level process. It is preferable that the related information is associated with the user identifier.

[0155] (Step S703) The related information acquiring unit 133 acquires abnormal element information.

[0156] (Step S704) The related information acquisition unit 133 constructs related information including the abnormal element information acquired in step S703 or the type identifier of the element information. The related information is information indicating that the received input expense information is abnormal.

[0157] Next, an example of the operation of the terminal device 2 will be described. The terminal reception unit 22 of the terminal device 2 receives input expense information and a receipt image. Next, the terminal processing unit 23 configures information to be transmitted by associating the input expense information and the receipt image received by the terminal reception unit 22 with the user identifier of the terminal storage unit 21. The terminal transmission unit 24 transmits the information to the expense checking device 1.

[0158] Next, the terminal receiving unit 25 of the terminal device 2 receives related information indicating whether the input expense information is normal or not from the expense checking device 1. Then, the terminal output unit 26 outputs the related information.

[0159] Furthermore, the terminal reception unit 22 of the terminal device 2 receives an output instruction. Then, the terminal transmission unit 24 transmits the output instruction to the expense checking device 1. Next, the terminal reception unit 25 receives one or more pieces of expense information corresponding to the output instruction from the expense checking device 1. Then, the terminal output unit 26 outputs one or more pieces of expense information.

[0160] Also, for example, the terminal receiving unit 25 of the terminal device 2 of the administrator or the accounting staff receives related information indicating that abnormal expense information has been entered by another user. Then, the terminal output unit 26 outputs the related information.

[0161] A specific example of the operation of the information system A in this embodiment will be described below.

[0162] Currently, the user information storage unit 111 of the expense inspection device 1 stores a user information management table shown in FIG. 8. The user information management table is a table for managing user information. The user information management table manages one or more records having an "ID", "user identifier", and "user attribute value". The "user attribute value" here has an "email address", "name", and "supervisor's email address". "ID" is information for identifying a record. "Email address" is the email address of a user identified by the user identifier. "Supervisor's email address" is the email address of the superior of the user identified by the user identifier.

[0163] The expense information storage unit 112 also stores an expense information management table having the structure shown in FIG. 9. The expense information management table is a table for managing expense information. The expense information management table manages one or more records having an "ID", "user identifier", "expense information", "receipt image", and "score". "ID" is information for identifying a record. "Expense information" here has a "date", "amount", and "payee".

[0164] Furthermore, the storage unit 11 stores a pattern management table shown in FIG. 10. The pattern management table is a table that manages notation patterns (hereinafter referred to as "patterns" as appropriate) for each type of element information that makes up the expense information. The pattern management table manages one or more records that have a "type identifier," a "pattern identifier," and a "notation pattern." The "type identifier" is information that identifies the type of element information that makes up the expense information. The "pattern identifier" is information that identifies a notation pattern within the same type. The "notation pattern" is a regular expression here, but the definition method is not important.

[0165] A character string according to the notation pattern of pattern identifier "1" of type identifier "date" is, for example, "2020 / 8 / 27". A character string according to the notation pattern of pattern identifier "2" of type identifier "date" is, for example, "August 27, 2020". A character string according to the notation pattern of pattern identifier "3" of type identifier "date" is, for example, "August 27, Reiwa 2".

[0166] A character string according to the notation pattern of the pattern identifier "1" of the type identifier "amount" is, for example, "940 yen." Also, a character string according to the notation pattern of the pattern identifier "2" of the type identifier "amount" is, for example, "￥940."

[0167] An example of a character string that follows the notation pattern of pattern identifier "1" of the type identifier "payee" is "Tsubame Taxi." An example of a character string that follows the notation pattern of pattern identifier "2" of the type identifier "payee" is "Tsubame Taxi Co., Ltd." An example of a character string that follows the notation pattern of pattern identifier "3" of the type identifier "payee" is "Tsubame Taxi Co., Ltd." An example of a character string that follows the notation pattern of pattern identifier "4" of the type identifier "payee" is "Tsubame Taxi Co., Ltd." An example of a character string that follows the notation pattern of pattern identifier "3" of the type identifier "payee" is "Tsubame Taxi Co., Ltd."

[0168] In this situation, the following two specific examples will be described. Specific Example 1 is a case where one receipt image contains one receipt image. Specific Example 2 is a case where one receipt image contains two receipt images.

[0169] (Example 1) Assume that the user "Yamada A-san" inputs the input expense information "<Date> 2020 / 8 / 27 <Amount> 940 <Payee> Tsubame Taxi Co., Ltd." and the receipt image of Fig. 11 into his / her terminal device 2. Note that the input screen, input interface, etc. for such information are not important.

[0170] Then, the terminal reception unit 22 of the terminal device 2 receives the input expense information and the receipt image. Next, the terminal processing unit 23 configures information to be transmitted by associating the input expense information and the receipt image received by the terminal reception unit 22 with the user identifier "U001" of the terminal storage unit 21. Next, the terminal transmission unit 24 transmits the input expense information "<Date> 2020 / 8 / 27 <Amount> 940 <Payee> Tsubame Taxi Co., Ltd.", the receipt image of FIG. 11, and the user identifier "U001" to the expense inspection device 1.

[0171] Next, the reception unit 12 of the expense checking device 1 receives the input expense information "<Date> 2020 / 8 / 27 <Amount> 940 <Payee> Tsubame Taxi Co., Ltd.", the receipt image of FIG. 11, and the user identifier "U001."

[0172] In this specific example 1, it is assumed that the information 1101, 1102, and 1103 on the receipt image in FIG. 11 is compared with the input expense information.

[0173] Next, the character string obtaining unit 131 performs character recognition processing on the receipt image of Fig. 11. Then, the character string obtaining unit 131 obtains one or more OCR character strings shown in Fig. 12. Here, each OCR character string is a character string of each line.

[0174] Next, the score acquisition unit 132 acquires the scores for each of the three element information "<Date> 2020 / 8 / 27", "<Amount> 940", and "<Payee> Tsubame Taxi Co., Ltd." contained in the received input expense information, in the order as follows:

[0175] That is, the score acquisition unit 132 first acquires the score of the element information "2020 / 8 / 27" of the type identifier "date" as follows:

[0176] The score acquiring unit 132 performs a second element information generation process according to the notation pattern paired with the type identifier "date" (see FIG. 10), and acquires "August 27, 2020", "August 27, 2020", etc. Here, the score acquiring unit 132 acquires element information such as the received element information "August 27, 2020", the generated element information "August 27, 2020", "August 27, 2020", etc.

[0177] Next, the score acquiring unit 132 acquires one or more pieces of partial information for each piece of element information. Here, it is assumed that the partial information is a 3-gram character string included in the element information.

[0178] Then, the score acquisition unit 132 first obtains partial information of 2 or more characters while shifting one character at a time from the first element information "2020 / 8 / 27". That is, the score acquisition unit 132 sequentially obtains the partial information "202", "020", "20 / ", "0 / 8", " / 8 / ", "8 / 2", " / 27" for the element information "2020 / 8 / 27".

[0179] Then, the score acquisition unit 132 checks whether any of the above partial information is included in each of the one or more OCR character strings shown in FIG. 12. And the score acquisition unit 132 determines that none of the above partial information is included in each of the one or more OCR character strings shown in FIG. 12. That is, the score acquisition unit 132 cannot obtain a comparison character string for the element information "2020 / 8 / 27".

[0180] Next, the score acquisition unit 132 sequentially obtains the partial information "202", "020", "20 years", "0 years 0", "years 08", "0 years 0", "years 08", "08 months", "8 months 2", "months 27", "27 days" for the next element information "August 27, 2020".

[0181] Next, the score acquisition unit 132 sequentially checks whether any of the above partial information is included in each of the one or more OCR character strings shown in FIG. 12. And the score acquisition unit 132 detects that "years 08" is included in the OCR character string "Date 20 still? years 08 months 27 days" shown in FIG. 12.

[0182] Next, the score acquisition unit 132 obtains the number of characters in front of the character example "2020" in front of the partial information, which is the character string obtained by removing the partial information "years 08" from the element information "August 27, 2020" that is being focused on, and the number of characters in front is "4".

[0183] Next, the score acquisition unit 132 obtains the OCR front character string "20 still?" which is the character string of the obtained number of characters in front "4" from the OCR character string "Date 20 still? years 08 months 27 days".

[0184] Next, the score acquisition unit 132 obtains, from the element information "August 27, 2020" of interest, a character string obtained by removing the partial information "August" and also obtains the number of characters "4" after the characters "27th of the month" behind the partial information.

[0185] Next, the score acquisition unit 132 obtains the OCR trailing character string "27th of the month", which is the character string of the obtained number of trailing characters "4", from the OCR character string "Date 20?? year August 27th".

[0186] Next, the score acquisition unit 132 concatenates the OCR leading character "20??", the matching character string "year August", and the OCR trailing character string "27th of the month" to obtain a comparison character string "20?? year August 27th".

[0187] Next, the score acquisition unit 132 calculates the edit distance (d1) between the element information "August 27, 2020" and the comparison character string "20?? year August 27th", and associates and accumulates the edit distance (d1) with the element information ("2020 / 8 / 27" or "August 27, 2020").

[0188] The score acquisition unit 132 performs the above processing for other partial information as well. Also, the score acquisition unit 132 performs the above processing for other element information (such as "August 27, Reiwa 2"). Then, during the above processing, while obtaining a set of partial information and comparison character strings as shown in FIG. 13, the score acquisition unit 132 obtains and accumulates the edit distance (d1) for the element information "2020 / 8 / 27" with respect to the type identifier "Date".

[0189] The score acquiring unit 132 also performs the same process as above for the element information "940" for the type identifier "amount". That is, the score acquiring unit 132 generates second element information "940 yen", "￥940", etc. for the element information "940". Then, the score acquiring unit 132 calculates the edit distance for each piece of element information "940", "940 yen", "￥940", etc., using the above algorithm. That is, the score acquiring unit 132 acquires and accumulates the edit distance (d2=0) between the comparison character string "940" acquired from the OCR character string "Kibing?? about 940 yen" and the element information "940".

[0190] Furthermore, the score acquiring unit 132 performs the same process as above for the element information "Tsubame Taxi Co., Ltd." for the type identifier "Payee." Then, the score acquiring unit 132 acquires and accumulates the edit distance (d3) between the comparison character string "(f) Tsubame Takt" acquired from the OCR character string "(f) Tsubame Takt" and the element information "Tsubame Taxi Co., Ltd."

[0191] Through the above process, the score obtaining section 132 can obtain the edit distance for each of the three pieces of element information.

[0192] Next, it is assumed that the score acquiring unit 132 acquires a score of "0.90" using a decreasing function with the edit distance for each of the three pieces of element information as a parameter.

[0193] Next, the related information acquisition unit 133 determines that the score of the element information satisfies the normal condition because the score is equal to or greater than a threshold (for example, 0.8 or greater). Note that the normal condition here is that the score is equal to or greater than a threshold.

[0194] Next, the related information acquisition unit 133 configures related information having the related information 'Input expense information "<Date> 2020 / 8 / 27 <Amount> 940 <Payee> Tsubame Taxi Co., Ltd." and a receipt image (Figure 11)'.

[0195] Next, the related information output unit 141 associates the related information "Input expense information "<Date> 2020 / 8 / 27 <Amount> 940 <Payee> Tsubame Taxi Co., Ltd." and receipt image (Figure 11)" with the score "0.9" and stores it in the expense information management table (see Figure 9) in association with the user identifier "U001." An example of such a record is the record of "ID=268" in Figure 9. It is assumed that the receipt image (Figure 11) is stored as a file with the generated file name "f268 / jpg."

[0196] (Example 2) Assume that a user “Inoue B” inputs into her terminal device 2 the input expense information “<Date> 2020 / 9 / 2 <Amount> 660 <Payee> Aomori Prefectural Road Corporation”, the input expense information “<Date> 2020 / 9 / 2 <Amount> 160 <Payee> Aomori Prefectural Road Corporation”, and the receipt image of Figure 14.

[0197] Then, the terminal reception unit 22 of Inoue B's terminal device 2 receives the two pieces of input expense information and the receipt image. Next, the terminal processing unit 23 configures information to be transmitted by associating the input expense information and receipt image received by the terminal reception unit 22 with the user identifier "U002" in the terminal storage unit 21. Next, the terminal transmission unit 24 transmits the input expense information, the receipt image in FIG. 14, and the user identifier "U002" to the expense checking device 1.

[0198] Next, the reception unit 12 of the expense checking apparatus 1 receives the two pieces of input expense information, the receipt image of FIG. 14, and the user identifier "U002".

[0199] In this specific example 2, it is assumed that the information 1401, 1402, 1403, 1404, 1405, and 1406 of the receipt image in FIG. 14 is compared with each of the two pieces of input expense information.

[0200] Next, the character string obtaining unit 131 performs character recognition processing on the receipt image of Fig. 14. Then, the character string obtaining unit 131 obtains one or more OCR character strings shown in Fig. 15. Here, each OCR character string is a character string for each line. Also, the character string obtaining unit 131 does not distinguish between the two receipt images, but performs character recognition processing on the file of the image of Fig. 14.

[0201] Next, the score acquisition unit 132 first performs the processing described in specific example 1 on the first input expense information “<Date> 2020 / 9 / 2 <Amount> 660 <Payee> Aomori Prefectural Road Corporation” using one or more OCR character strings shown in FIG. 15, and acquires a score for the first input expense information.

[0202] Next, it is assumed that the related information acquiring unit 133 determines that the score of the first input expense information satisfies the normal condition.

[0203] Next, the related information acquisition unit 133 constructs related information having "<Date> 2020 / 9 / 2 <Amount> 660 <Payee> Aomori Prefectural Road Public Corporation" and a receipt image (Figure 14).

[0204] Next, the related information output unit 141 associates the related information and the score (here, "0.98") with the user identifier "U002" and accumulates them in the expense information management table (see FIG. 9). An example of such a record is the record of "ID=351" in FIG. 9.

[0205] In addition, the score acquisition unit 132 performs similar processing on the second input expense information "<Date> 2020 / 9 / 2 <Amount> 160 <Payee> Aomori Prefectural Road Corporation" and acquires a score for the second input expense information.

[0206] Next, it is assumed that the related information acquiring unit 133 determines that the score of the second input expense information satisfies the normal condition.

[0207] Next, the related information acquisition unit 133 constructs related information having "<Date> 2020 / 9 / 2 <Amount> 160 <Payee> Aomori Prefectural Road Public Corporation" and a receipt image (Figure 14).

[0208] Next, the related information output unit 141 associates the related information and the score (here, "0.95") with the user identifier "U002" and accumulates them in the expense information management table (see FIG. 9). An example of such a record is the record of "ID=352" in FIG. 9.

[0209] As described above, in this specific example, processing can be performed when multiple receipt images are included. Also, in this specific example, processing can be performed for multiple pieces of input expense information.

[0210] As described above, according to this embodiment, it is possible to appropriately check the input expense information.

[0211] Furthermore, according to this embodiment, it is possible to appropriately check input expense information using a receipt image including two or more receipts.

[0212] Furthermore, according to this embodiment, the character string acquisition unit 131 acquires one or more OCR character strings from each image of two or more receipts without determining the boundaries between the images of two or more receipts, thereby enabling appropriate confirmation through simple processing even for input expense information using a receipt image that includes two or more receipts.

[0213] Furthermore, according to this embodiment, even when two or more expense entries and receipt images including two or more receipts are mixed together, appropriate confirmation is possible.

[0214] Furthermore, according to this embodiment, when expense information that is likely to be inappropriate is entered, appropriate notification can be given.

[0215] In this embodiment, the terminal device 2 may perform part of the processing performed by the expense checking device 1. For example, the terminal device 2 may perform processing of one or more components among the character string acquiring unit 131, the score acquiring unit 132, and the related information acquiring unit 13. In other words, there is no restriction on the method of dividing the processing between the expense checking device 1 and the terminal device 2. The expense checking device 1 may be a device that operates as a standalone device.

[0216] The process in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software for realizing the expense inspection device 1 in this embodiment is a program as follows. That is, this program is a program for making a computer function as a reception unit that receives input expense information related to expenses input by a user and a receipt image corresponding to the expenses, a character string acquisition unit that acquires one or more OCR character strings that are the results of OCR on the receipt image, a score acquisition unit that compares the input expense information with the one or more OCR character strings and acquires a score related to the accuracy of the input expense information, and a related information output unit that outputs related information related to the score.

[0217] Also, Fig. 16 shows the appearance of a computer that executes the program described in this specification to realize the expense inspection device 1 and the like of the various embodiments described above. The above-mentioned embodiments can be realized by computer hardware and a computer program executed thereon. Fig. 16 is an overview of this computer system 300, and Fig. 17 is a block diagram of the system 300.

[0218] In FIG. 16, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0219] 17, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0220] A program for causing the computer system 300 to execute the functions of the expense inspection device 1 of the above-mentioned embodiment may be stored on a CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 when executed. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0221] The program does not necessarily include an operating system (OS) or a third party program that causes the computer 301 to execute the functions of the expense inspection device 1 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain a desired result. How the computer system 300 operates is well known, and a detailed description will be omitted.

[0222] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmitting step (processing that is performed only by hardware).

[0223] The program may be executed by a single computer or a plurality of computers. That is, the program may be executed by a centralized processing or a distributed processing.

[0224] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0225] In each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0226] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0227] As described above, the expense checking device 1 according to the present invention has the effect of enabling appropriate checking of input expenses, and is useful as a server or the like that checks expense information. [Explanation of symbols]

[0228] 1. Expense inspection device 2 Terminal Equipment 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal Processing Section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Section 111 User information storage section 112 Expense information storage section 131 String acquisition part 132 Score Acquisition Section 133 Related Information Acquisition Department 141 Related information output section

Claims

1. a reception unit that receives input expense information regarding expenses input by a user and a receipt image corresponding to the expenses; a character string acquisition unit that acquires one or more OCR character strings that are a result of OCR on the receipt image; a score acquisition unit that compares the input expense information with the one or more OCR character strings and acquires a score regarding the accuracy of the input expense information; a related information output unit that outputs related information regarding the score, The expense verification device, wherein the receipt image includes two or more receipts.

2. The character string acquisition unit The expense verification device of claim 1 , further comprising: obtaining one or more OCR character strings from each of the two or more receipt images without determining a boundary of the two or more receipt images.

3. The reception unit is Accepting two or more pieces of input expense information and a receipt image including two or more receipts; The character string acquisition unit Obtaining one or more OCR character strings that are the result of OCR on the receipt image including the two or more receipts; The score acquisition unit, 3. The expense checking device according to claim 1, further comprising: a processor for comparing each of the two or more pieces of input expense information with the one or more OCR character strings to obtain a score relating to the accuracy of the input expense information.

4. The score acquisition unit, The expense verification device according to any one of claims 1 to 3, further comprising: acquiring two or more pieces of partial information that constitute the input expense information; comparing each of the two or more pieces of partial information with a character string in the one or more OCR character strings; and acquiring a score using a comparison result for each of the two or more pieces of partial information.

5. The score acquisition unit, The expense verification device of claim 4, further comprising: acquiring two or more pieces of partial information, which are n-gram character strings that constitute the input expense information; detecting a character string that has the smallest distance from each of the two or more pieces of partial information from the one or more OCR character strings; and acquiring a score using the distance from each of the detected character strings that has the smallest distance.

6. The related information output unit An expense verification device as described in any one of claims 1 to 5, wherein if the score indicates a probability low enough to satisfy a predetermined condition, a user or administrator corresponding to the input expense information is notified of relevant information regarding errors in the input expense information.

7. The related information output unit The expense checking device according to claim 1 , further comprising: outputting related information on the score in association with the input expense information.

8. The input expense information includes two or more of the following information: date, amount, and payee; The score acquisition unit, comparing each of the two or more pieces of information with the one or more OCR character strings, obtaining a score for each of the two or more pieces of information, and obtaining a representative score that is a representative value of the two or more scores; The related information output unit 8. The expense checking device according to claim 1, further comprising: an output unit for outputting relevant information about said representative score.

9. A cost inspection method comprising all steps performed by the cost inspection device according to any one of claims 1 to 8.

10. Computer, A program for causing the expense inspection device according to any one of claims 1 to 9 to function as such.

Images