Expense inspection device, expense inspection method, and program

Abstract

To properly perform an inspection of an improper expense application, in contrast to the prior art.SOLUTION: An expense inspection device 1 is provided with: an expense receiving unit 121 that receives expense information specifying contents of an expense application; an inspection unit 131 that acquires an inspection result by performing an inspection concerning fraud in the expense information received by the expense receiving unit 121 by using external information other than expense information, or expense information other than the expense information received by the expense receiving unit 121; and a result output unit 141 that outputs the inspection result acquired by the inspection unit 131. The expense inspection device properly performs an inspection of an improper expense application.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an expense checking device that checks for fraudulent expense information submitted and outputs the results of the check. [Background technology]

[0002] Conventionally, there have been accounting systems that can check the objectivity and consistency of transaction data between companies, between companies and individuals, or socially (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-97669 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, inappropriate expense claims could not be properly inspected. [Means for solving the problem]

[0005] The expense verification device of the first invention is an expense verification device that includes an expense acceptance unit that accepts expense information that specifies the content of an expense application, an inspection unit that inspects the expense information accepted by the expense acceptance unit for fraud using external information other than the expense information or expense information other than the expense information accepted by the expense acceptance unit, and obtains the inspection results, and a result output unit that outputs the inspection results obtained by the inspection unit.

[0006] With this configuration, by using external information or expense information other than the expense information claimed, it is possible to properly inspect inappropriate expense claims.

[0007] In addition, the expense inspection device of the second invention is an expense inspection device in which, compared to the first invention, the expense acceptance unit accepts expense information in association with an applicant identifier that identifies the applicant for the expenses, the external information is information corresponding to each of two or more applicants and has an applicant set including two or more applicant information associated with the applicant identifier, and the inspection unit obtains from the applicant set the applicant information associated with the applicant identifier associated with the expense information accepted by the expense acceptance unit, uses the applicant information to inspect the expense information accepted by the expense acceptance unit for fraud, and obtains the inspection results.

[0008] With this configuration, by using the applicant information, it is possible to properly check for inappropriate expense applications.

[0009] Furthermore, in the expense inspection device of the third invention, compared to the second invention, the expense information has usage date information that identifies the days on which expenses were used, the applicant information has one or more pieces of attendance information including work date information that identifies the days on which an applicant identified by an applicant identifier worked, and the inspection unit is attendance information that corresponds to the applicant identifier associated with the expense information, and uses the attendance information that includes the same work date information as the usage date information to inspect the expense information accepted by the expense acceptance unit for fraud and obtain the inspection results.

[0010] With this configuration, by using the applicant's attendance information, it is possible to properly check for inappropriate expense claims.

[0011] Furthermore, in the expense inspection device of the fourth invention, compared to the second invention, the expense information has usage date information that identifies the date on which expenses were used, the applicant information has one or more entry / exit information that identifies the date and time when the applicant, identified by the applicant identifier, entered and left his / her workplace, and the inspection unit is the entry / exit information that corresponds to the applicant identifier that is associated with the expense information, and is an expense inspection device that inspects the expense information accepted by the expense acceptance unit for fraud using the entry / exit information that corresponds to the date identified by the usage date information in the expense information, and obtains the inspection results.

[0012] With this configuration, by using the applicant's entry and exit information, it is possible to properly check for inappropriate expense claims.

[0013] Furthermore, in the expense inspection device of the fifth invention, compared to the second invention, the expense information has usage date information that identifies the days on which expenses were used, the applicant information has sales activity information that includes business day information that identifies the days on which the applicant's business activities were carried out and one or more location identifiers that identify the locations visited, and the inspection unit is sales activity information that corresponds to the applicant identifier that is associated with the expense information accepted by the expense acceptance unit, and is an expense inspection device that inspects the expense information accepted by the expense acceptance unit for fraud using one or more location identifiers that have the same business day information as the usage date information held by the expense information, and obtains the inspection results.

[0014] With this configuration, by using the applicant's business activity information, it is possible to properly check for inappropriate expense claims.

[0015] Furthermore, in the expense verification device of the sixth invention, compared to the second invention, the expense information has usage date information that identifies the date on which the expenses were used, the applicant information has card detail information that is information showing the details of the credit card used by the applicant and is information that includes usage date information that is the date on which the credit card was used, and the verification unit is card detail information that corresponds to an applicant identifier that is associated with the expense information received by the expense acceptance unit, and uses card detail information that has the same usage date information as the usage date information contained in the expense information to verify fraud in the expense information received by the expense acceptance unit and obtains the verification results.

[0016] With this configuration, by using the applicant's credit card statement information, it is possible to properly check for inappropriate expense claims.

[0017] In addition, the expense inspection device of the seventh invention is an expense inspection device in which, compared to the second invention, the expense information has usage date information that identifies the date on which the expenses were used, the applicant information is one or more business vehicle location information that identifies the location of the business vehicle used by the applicant and has one or more business vehicle location information that is associated with the usage date information that identifies the date on which the business vehicle was used, the inspection unit is one or more business vehicle location information that is associated with the applicant identifier that is associated with the expense information accepted by the expense acceptance unit and acquires one or more business vehicle location information that is associated with the same usage date information as the usage date information held by the expense information, and uses the business vehicle location information to inspect the expense information for fraud and acquires the inspection results.

[0018] With this configuration, by using the applicant's business vehicle location information, inappropriate expense claims can be properly inspected.

[0019] In addition, the expense verification device of the eighth invention differs from the second invention in that the expense information corresponds to an expense type identifier indicating the type of expense, the applicant information has owned card information regarding a card owned by the applicant, and further includes a card usage expense storage unit in which one or more expense type identifiers for which payment by card is planned are stored, and the verification unit verify whether the expense type identifier corresponding to the expense information accepted by the expense acceptance unit is stored in the card usage expense storage unit as an expense type identifier corresponding to the owned card information associated with the applicant identifier associated with the expense information accepted by the expense acceptance unit, and obtains the verification result.

[0020] With this configuration, by using the information on the card owned by the applicant, it is possible to properly check for inappropriate expense claims.

[0021] In addition, the expense verification device of the ninth invention is an expense verification device in which, compared to the first invention, the external information includes company regulation information relating to the regulations of the company to which the applicant belongs, and the verification unit uses the company regulation information to verify whether the expense information accepted by the expense acceptance unit conforms to the company regulations and obtains the verification results.

[0022] With this configuration, by using company regulation information, inappropriate expense claims can be properly inspected.

[0023] Furthermore, the expense inspection device of the tenth invention is an expense inspection device in which, compared to the first invention, the expense information includes transportation cost information having date of use information that identifies the date on which the expense was incurred and one or more section information having a departure identifier, an arrival identifier, and fare information, the external information includes transportation means information including calculation information for calculating transportation costs, and the inspection unit uses the expense information and transportation means information accepted by the expense acceptance unit to inspect for fraudulent transportation costs and obtain the inspection results.

[0024] With this configuration, by using the transportation information, it is possible to properly check inappropriate expense claims.

[0025] Furthermore, the expense verification device of the eleventh invention is an expense verification device in which, compared to the first invention, the external information has a store set, which is one or more store information having a store identifier that identifies the store, the expense information has a store identifier that identifies the store that spent the expense, and the verification unit uses the store identifier contained in the expense information accepted by the expense acceptance unit and the store information contained in the store set to verify fraud in the expense information and obtains the verification results.

[0026] With this configuration, by using the store collection, inspections can be properly carried out for inappropriate expense claims.

[0027] Furthermore, the expense verification device of the twelfth invention is an expense verification device in which, compared to the eleventh invention, the store information has amount information, the expense information has expenditure amount information that specifies the amount spent, and the verification unit uses the amount information that pairs with the store identifier contained in the expense information accepted by the expense acceptance unit and the expenditure amount information contained in the expense information to verify fraud in the expense information and obtain the verification results.

[0028] This configuration allows appropriate detection of inappropriate expenditures at the store.

[0029] In addition, the expense inspection device of the thirteenth invention is an expense inspection device in which, compared to the first invention, the expense information has a recipient identifier that identifies the recipient that used the expenses, the external information has one or more recipient information regarding potential recipients of the expenses, and the inspection unit uses the recipient identifier contained in the expense information accepted by the expense acceptance unit and the one or more recipient information contained in the external information to inspect the expense information for fraud and obtain the inspection results.

[0030] With this configuration, inappropriate expenditures to inappropriate parties can be appropriately detected.

[0031] Furthermore, the expense inspection device of the fourteenth invention differs from the first invention in that the expense information has an expense type identifier indicating travel expenses and usage date information, the external information has one or more of one or more pieces of attendance information including work day information and one or more pieces of entry / exit information specifying the date and time of entry / exit, and the inspection unit obtains the attendance information or entry / exit information corresponding to the applicant identifier and usage date information associated with the expense information accepted by the expense acceptance unit, and uses the attendance information or entry / exit information to inspect for fraudulent travel expenses and obtain the inspection results.

[0032] With this configuration, inappropriate travel expenses can be properly detected.

[0033] Furthermore, the expense inspection device of the fifteenth invention differs from the first invention in that the expense information includes transportation expense information having date of use information that identifies the date on which the expenses were incurred and one or more section information each having a departure identifier, an arrival identifier, and fare information, the external information is transportation means information including calculation information for calculating transportation expenses, or a set of applicants having one or more applicant information, the applicant information includes regular route information that identifies the section of the applicant's regular commuter pass, or business activity information including business day information that identifies the date of the applicant's business activities and one or more location identifiers that identify the locations visited, and the inspection unit obtains applicant information associated with the applicant identifier that is associated with the expense information related to transportation expenses received by the expense acceptance unit, and uses the applicant information, or the applicant information and the transportation information, to inspect for fraud related to transportation expense claims and obtain the inspection results.

[0034] With this configuration, inappropriate transportation expenses can be properly detected.

[0035] In addition, the expense verification device of the sixteenth invention is an expense verification device in which, compared to the first invention, the verification unit determines whether the expense information received by the expense reception unit and one or more pieces of past expense information stored in the expense information storage unit and associated with the same applicant identifier as the applicant identifier associated with the expense information are similar enough to satisfy predetermined conditions, and obtains the verification result.

[0036] This configuration allows for appropriate detection of duplicate applications, reuse of receipts, etc.

[0037] The expense inspection device of the seventeenth invention differs from the second invention in that the expense information includes usage date information that specifies the days on which the applicant stayed at the accommodation facility, the applicant information includes attendance information that includes one or more pairs of one or more working date information that specifies the days on which the applicant worked and working hour information that specifies the time periods on which the applicant worked, or one or more entry / exit information that specifies the dates and times on which the applicant entered and left the workplace, the external information includes company regulation information that includes overtime time information that specifies the overtime hours at which accommodation is permitted, the inspection unit is an expense inspection device that obtains the working date information or entry / exit information that corresponds to the applicant identifier associated with the expense information and the end of work time information or entry / exit information that pairs with the working date information that matches the usage date information in the expense information, and uses the working hour information or work end time and the overtime time information to determine whether accommodation at the accommodation facility is permitted and obtains the inspection results.

[0038] This configuration allows for proper detection of fraudulent claims for accommodation expenses.

[0039] In addition, the expense verification device of the 18th invention is an expense verification device in which, compared to the first invention, the expense information is associated with an applicant identifier, includes usage date information that identifies the date the expense was used, and has a store identifier that identifies the store where the expense was spent, and the verification unit inspects two or more pieces of expense information associated with one applicant identifier, determines whether the number of expense information having the same usage date information is large enough to satisfy a predetermined condition, and obtains the verification result.

[0040] This configuration makes it possible to properly detect fraudulent claims for after-party expenses.

[0041] In addition, the expense verification device of the 19th invention, compared to the first invention, further includes a statistical processing unit that performs statistical processing based on two or more pieces of expense information stored in an expense information storage unit in which two or more pieces of expense information corresponding to an applicant identifier are stored, and obtains the statistical processing results, and the verification unit is an expense verification device that verifies whether the statistical processing results satisfy predetermined conditions and obtains the verification results.

[0042] With this configuration, by using the results of statistical processing based on two or more pieces of expense information, it is possible to appropriately check for inappropriate expense applications.

[0043] Furthermore, the expense verification device of the twentieth invention is an expense verification device in which, compared to the nineteenth invention, the expense information has a store identifier that identifies the store where the expense was spent, the statistical processing unit is two or more pieces of expense information stored in the expense information storage unit, and uses the store identifiers included in the two or more pieces of expense information corresponding to one applicant identifier to obtain store frequency information regarding the frequency of use of the store identified by the store identifier, and the verification unit is an expense verification device that verifies whether the store frequency information obtained by the statistical processing unit satisfies predetermined conditions and obtains the verification results.

[0044] With this configuration, it is possible to detect whether a particular store is frequently used.

[0045] Furthermore, the expense verification device of the twenty-first invention is an expense verification device in which, compared to the nineteenth invention, the expense information has a destination identifier that identifies the destination to which expenses were paid, the statistical processing unit is two or more pieces of expense information stored in the expense information storage unit, and the statistical processing unit acquires entertainment frequency information regarding the frequency of expenditures on the destination identified by the destination identifier using the destination identifier included in the two or more pieces of expense information corresponding to one applicant identifier, and the inspection unit inspects whether the entertainment frequency information acquired by the statistical processing unit satisfies predetermined conditions and obtains the inspection results.

[0046] With this configuration, it is possible to detect whether expenditures made to a specific party are frequent.

[0047] Furthermore, the expense verification device of the twenty-second invention is an expense verification device in which, compared to the nineteenth invention, the statistical processing unit acquires, in association with one applicant identifier, a number of fraudulent incidents, which is the result of an examination of expense information corresponding to one applicant identifier and is the number of times an examination result corresponding to fraud has been obtained, and the inspection unit inspects whether the number of fraudulent incidents acquired by the statistical processing unit satisfies predetermined conditions, and acquires the inspection result.

[0048] This configuration makes it possible to detect frequent fraud by a particular person.

[0049] Furthermore, the expense inspection device of the twenty-third invention is an expense inspection device in which, compared to the eleventh invention, the company specification information has approver information that specifies who may be an approver of expenses, the expense information has an approver identifier that identifies the approver of expenses, and the inspection unit inspects whether the approver identified by the approver identifier is the approver specified by the approver information and obtains the inspection results.

[0050] With this configuration, it is possible to detect whether the approver for the expense request does not meet the requirements.

[0051] In addition, the expense inspection device of the twenty-fourth invention is an expense inspection device in which, compared to the first invention, the applicant information includes one or more pieces of attendance information including work day information specifying the days on which the applicant identified by the applicant identifier worked, one or more pieces of entry and exit information specifying the dates and times when the applicant identified by the applicant identifier entered and left his or her workplace, one or more pieces of business activity information having business day information specifying the days of the applicant's business activities and one or more location identifiers specifying the locations visited, and one or more pieces of business vehicle location information specifying the location of the business vehicle used by the applicant, and one or more pieces of business vehicle location information associated with the use date information specifying the days on which the business vehicle was used, and the inspection unit uses the applicant information corresponding to one applicant identifier to determine whether expense information corresponding to the applicant information is present in the expense information storage unit in which one or more pieces of expense information associated with one applicant identifier is stored, and inspects for omissions in the application to determine whether expenses corresponding to the applicant information have been applied for, and obtains the inspection results.

[0052] This configuration makes it possible to detect missed expense claims.

[0053] Furthermore, the expense inspection device of the 25th invention is an expense inspection device in which, compared to any one of the first to 24th inventions, the expense information includes a receipt image, the inspection unit includes an image inspection means for inspecting the receipt image and obtaining the image inspection results, and the result output unit outputs the image inspection results.

[0054] This configuration allows for appropriate inspection of receipt images.

[0055] In addition, the expense inspection device of the 26th invention is an expense inspection device in which, compared to the 25th invention, the image inspection means acquires one or more character strings from a receipt image, determines whether each of the one or more character strings satisfies a predetermined condition, and acquires the image inspection results.

[0056] This configuration allows for proper inspection of the information written on the receipt image.

[0057] Furthermore, the expense inspection device of the 27th invention is an expense inspection device in which, compared to the 26th invention, the receipt image has a timestamp, and the image inspection means acquires the timestamp possessed by the receipt image, acquires the receipt issue date corresponding to the receipt image, determines whether the date specified by the timestamp is a predetermined period of time or more from the receipt issue date, and acquires the image inspection results.

[0058] With this configuration, it is possible to check for defects in the time stamp of the receipt image.

[0059] In addition, the expense inspection device of the 28th invention is an expense inspection device in which, compared to the 25th invention, the image inspection means uses character recognition technology to obtain a character recognition score along with one or more character strings from a receipt image accepted by the expense acceptance unit, and if the score is low enough to satisfy a predetermined condition, performs one of two processings: a first blurring process that determines that the receipt image is blurred; or a second blurring process that uses a machine learning algorithm to input one or more blurred receipt images and one or more clear receipt images to obtain a judgment result as to whether the receipt image is blurred or clear, and a learning device that uses the receipt image accepted by the expense acceptance unit to obtain a judgment result using a machine learning algorithm.

[0060] This configuration allows inspection of blurred receipt images.

[0061] Furthermore, the expense inspection device of the 29th invention is an expense inspection device in which, compared to the 25th invention, the external information includes company regulation information relating to the regulations of the company to which the applicant belongs, the company regulation information has payment method information that specifies unacceptable payment methods, and the image inspection means obtains the payment method information, which is a string of characters, from the receipt image, inspects whether the payment method information is payment method information contained in the company regulation information, and obtains the image inspection results.

[0062] This configuration allows for checking for inappropriate payment methods.

[0063] Furthermore, the expense inspection device of the 30th invention is an expense inspection device in which, compared to the 25th invention, the image inspection means uses a learning device that inputs one or more receipt images in which the amount has been falsified by hand and one or more receipt images in which the amount has not been falsified using a machine learning algorithm to obtain a judgment result as to whether the amount has been falsified or not, and uses the receipt images accepted by the expense acceptance unit to perform prediction processing using a machine learning algorithm to obtain an image inspection result indicating whether the amount written on the receipt image has been falsified by hand.

[0064] This configuration makes it possible to check for forged handwritten amounts.

[0065] The expense verification device of the thirty-first invention is an expense verification device in which, compared to the first to thirty-first inventions, external information or expense information is associated with an organization identifier that identifies an organization, an expense receiving unit receives the expense information associated with the organization identifier from an expense management device, an inspection unit uses the external information associated with the organization identifier or expense information other than the expense information received by the expense receiving unit to inspect the expense information received by the expense receiving unit for fraud using the expense information associated with the organization identifier, and obtains the inspection results, and a result output unit transmits the inspection results obtained by the inspection unit to the expense management device. Note that here, it is preferable that the expense receiving unit receives expense information associated with the organization identifier from each of two or more expense management devices.

[0066] This configuration allows the expense management device to be provided with an expense application inspection function. [Effects of the Invention]

[0067] According to the expense checking device of the present invention, inappropriate expense claims can be checked appropriately. [Brief explanation of the drawings]

[0068] [Figure 1] Conceptual diagram of information system A in embodiment 1 [Figure 2]Block diagram of Information System A [Figure 3] Block diagram of the expense verification device 1 that constitutes the information system A [Figure 4] A flowchart illustrating an example of the operation of the expense inspection device 1. [Figure 5] A flowchart illustrating an example of the inspection process [Figure 6] A flowchart illustrating an example of the statistical testing process [Figure 7] Flowchart illustrating an example of the leakage inspection process [Figure 8] Figure showing an example of the output [Figure 9] Figure showing an example of the output [Figure 10] Block diagram of another system including the expense inspection device 1. [Figure 11] Overview of the computer system [Figure 12] Block diagram of the computer system DETAILED DESCRIPTION OF THE INVENTION

[0069] Hereinafter, embodiments 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, and therefore, repeated description may be omitted.

[0070] (Embodiment 1) In this embodiment, an information system including an expense inspection device is described that accepts expense information, uses external information or previously applied expense information to inspect for fraud, and outputs the inspection results. The external information is information other than expense information, and includes, for example, a set of applicants (described later), company policy information (described later), a set of restaurants (described later), a set of adult entertainment establishments (described later), a set of recipients (described later), card usage expense information (described later), and transportation information (described later). The targets of fraud inspection include, for example, business trip expenses, transportation expenses, duplicate applications, inspection of reused receipts, accommodation expenses, and after-party expenses.

[0071] In this embodiment, an information system including an expense inspection device that inspects for fraud using statistical processing results obtained from information corresponding to two or more pieces of expense information and outputs the inspection results is described. The statistical processing results may include, for example, the frequency of use of a specific store, the frequency of providing benefits to a specific party, and the number of times a specific person has committed fraud.

[0072] In this embodiment, an information system including an expense checking device that checks whether an approver of an expense application meets the requirements will be described.

[0073] This embodiment also describes an information system including an expense inspection device that inspects receipt images. The inspection of receipt images includes, for example, inspection of incomplete information written on the receipt image, inspection of incomplete timestamps on the receipt image, inspection of blurred receipt images, inspection of inappropriate payment methods written on the receipt image, and inspection of forged handwritten amounts on the receipt image.

[0074] Furthermore, in this embodiment, an information system including an expense checking device that uses external information to detect omissions in claims for expenses that should be claimed will be described.

[0075] 1 is a conceptual diagram of an information system A according to this embodiment. The information system A comprises an expense verification device 1, one or more applicant terminals 2, and one or more external servers 3.

[0076] The expense checking device 1 is a device that checks the applied expense information. The expense checking device 1 is usually a so-called server, such as a cloud server, an ASP server, etc. The type of the expense checking device 1 is not important.

[0077] The applicant terminal 2 is a terminal used by an applicant. An applicant is a user who applies for expenses. The applicant terminal 2 may be, for example, a personal computer, a tablet terminal, a smartphone, or the like, and the type of the terminal does not matter.

[0078] The external server 3 is a device that stores external information, which will be described later, and provides the external information to the expense verification device 1. All or part of the external information, which will be described later, may be present in the expense verification device 1. If all of the external information, which will be described later, is present in the expense verification device 1, the external server 3 is not required. The external server 3 is typically a so-called server, such as a cloud server or an ASP server. The type of the external server 3 is not important.

[0079] The expense verification device 1, the applicant terminal 2, and the external server 3 are usually capable of communicating with each other via a network such as the Internet or a dedicated line.

[0080] Fig. 2 is a block diagram of an information system A according to this embodiment. Fig. 3 is a block diagram of an expense verification device 1 constituting the information system A.

[0081] The expense verification 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, for example, an expense information storage unit 111, an applicant group storage unit 112, a company regulation information storage unit 113, a restaurant group storage unit 114, an adult entertainment establishment group storage unit 115, a counterparty group storage unit 116, a card usage expense storage unit 117, and a transportation information storage unit 118. The applicant group storage unit 112 includes a personal information storage unit 1121, an attendance information storage unit 1122, an entrance / exit information storage unit 1123, a business activity information storage unit 1124, a card statement information storage unit 1125, and a business vehicle location information storage unit 1126. The transportation information storage unit 118 includes a calculation information storage unit 1181 and a map information storage unit 1182. The reception unit 12 includes an expense reception unit 121. The processing unit 13 includes an inspection unit 131 and a statistical processing unit 132. The inspection unit 131 includes an image inspection means 1311. The output unit 14 includes a result output unit 141.

[0082] The applicant terminal 2 includes a first storage unit 21, a first reception unit 22, a first processing unit 23, a first transmission unit 24, a first reception unit 25, and a first output unit 26.

[0083] The expense information storage unit 111, applicant group storage unit 112, company regulation information storage unit 113, restaurant group storage unit 114, adult entertainment establishment group storage unit 115, destination group storage unit 116, card usage expense storage unit 117, and transportation information storage unit 118 in the expense verification device 1 may be present in other external devices.

[0084] It is preferable that the external server 3 stores any one of a restaurant collection storage unit 114, an adult entertainment establishment collection storage unit 115, a destination collection storage unit 116, a card usage fee storage unit 117, and a transportation information storage unit 118.

[0085] In addition, the inspection unit 131 may perform the inspection process described below using various information in the storage unit 11, or may perform the inspection process described below using various information stored in the external server 3 or information transmitted from the external server 3.

[0086] The external server 3 is a server that receives an inquiry including, for example, information identifying a departure station (an example of a departure identifier described later) and information identifying an arrival station (an example of an arrival identifier described later), and outputs one or more transportation fares. The external server 3 has a calculation information storage unit 1181 that stores fare calculation information described later. The external server 3 is also a JORDAN (registered trademark) server (URL "https: / / www.jorudan.co.jp / ") or a NAVITIME (registered trademark) server (URL "https: / / www.navitime.co.jp / ").

[0087] The external server 3 is, for example, a server that receives an inquiry including a departure identifier and an arrival identifier and outputs a taxi fare. The external server 3 has a calculation information storage unit 1181 that stores taxi fare calculation information, which will be described later, and a map information storage unit 1182. The external server 3 is also a taxisite server (URL "https: / / www.taxisite.com / far / ").

[0088] Various types of information are stored in the storage unit 11. The various types of information include, for example, expense information (to be described later) and external information (to be described later).

[0089] The expense information storage unit 111 stores expense information. The expense information storage unit 111 typically stores two or more pieces of expense information. Expense information is information that identifies the content of the claimed expense. Expense information includes, for example, expenditure amount information, destination identifier, store identifier, recipient identifier, usage date information, payment method identifier, account, summary, and approver identifier. Expenditure amount information is information that identifies the amount used as an expense. The destination identifier is information that indicates the destination of the receipt and is information that identifies the company or other entity that will pay the amount. The store identifier is information that identifies the store that used the expense. The store identifier is, for example, the store name, store ID, store URL, or store telephone number. The recipient identifier is information that identifies the recipient that used the expense. The recipient identifier is information that identifies the recipient to whom a benefit such as entertainment or a gift was provided. The recipient identifier is, for example, the organization name (e.g., company name or organization name), name, and recipient ID. Usage date information is information that identifies the date on which the expense was used. The payment method identifier is information that identifies the payment method. The payment method identifier is, for example, "cash," "credit card," "electronic money," "○○ PAY," etc. The item is information that identifies the classification of the expense. The item may also be called an expense type identifier. The item is, for example, business trip expenses, travel expenses (or transportation expenses), accommodation expenses, business trip expenses, entertainment expenses, and meeting expenses. The approver identifier is information that identifies the person who approves the expenses. The approver identifier is, for example, an applicant identifier or a position identifier. The applicant identifier is information that identifies the applicant who applied for the expenses, such as a name or ID. The position identifier is information that identifies a position, such as a position name (e.g., "department manager," "director"), or ID. The expense information in the expense information storage unit 111 is usually associated with an applicant identifier.

[0090] If the expense information is information on transportation expenses, the expense information includes, for example, transportation expense information having date of use information and one or more section information each having a departure identifier, an arrival identifier, and fare information. It is preferable that the expense information includes an expense type identifier indicating transportation expenses. If the expense information is information on business trip expenses, the expense information includes, for example, date of use information. It is preferable that the expense information includes an expense type identifier indicating business trip expenses. If the expense information is information on accommodation expenses, the expense information includes, for example, date of use information specifying the date of stay at an accommodation facility. If the expense information is entertainment expenses or meeting expenses, the expense information is, for example, associated with an applicant identifier and includes date of use information and a store identifier identifying the store where the expenses were spent.

[0091] The expense information may include a receipt image. The receipt image is an image of a receipt. For example, the receipt image is an image obtained by photographing a receipt. It goes without saying that the data structure of the receipt image is not important, such as JPEG or GIF.

[0092] The expense information includes, for example, participant information and number of people information. The participant information is information (e.g., name) that identifies people who participated in the use of the expense (e.g., people who ate and drank). The number of people information is the number of people who participated in the use of the expense.

[0093] Applicant sets are stored in applicant set storage unit 112. Applicant sets are information unique to each applicant. Applicant sets are, for example, a set of personal information (to be described later), a set of attendance information (to be described later), a set of entrance / exit information (to be described later), a set of business activity information (to be described later), a set of card statement information (to be described later), or a set of business vehicle location information (to be described later).

[0094] The personal information storage unit 1121 stores one or more pieces of personal information. The personal information is information about the applicant. An applicant identifier is associated with the personal information. The personal information includes, for example, the applicant's name, the name of the company to which the applicant belongs, the company ID, the name of the department to which the applicant belongs, the department ID, a position identifier that identifies the position, regular period information that identifies the period of the applicant's regular period, the number of fraudulent attempts, and an email address. The number of fraudulent attempts is the number of times the applicant has submitted a fraudulent expense claim, or the number of times the applicant's fraud has been detected. The email address is understood broadly as long as it is information that identifies the destination to which information is sent, and may be a social media ID, etc.

[0095] In addition, two pieces of information are said to correspond if the other piece of information can be obtained from the first piece of information, for example, if the first piece of information and the other piece of information are linked, if the first piece of information and the other piece of information are stored in the same buffer, or if the first piece of information contains the other piece of information.

[0096] The attendance information storage unit 1122 stores one or more pieces of attendance information. The attendance information is information related to the attendance of an applicant. The attendance information is usually associated with an applicant identifier. The attendance information includes work day information. The work day information is information for identifying the days on which an applicant identified by the corresponding applicant identifier worked. The work day information usually indicates work days, but may also indicate non-work days. If the work day information indicates non-work days, days other than the days indicated by the work day information are work days. The attendance information usually includes work time information that identifies the hours worked. The work time information includes, for example, the start time and end time of work. The attendance information in the attendance information storage unit 1122 is, for example, information received from an external server 3 (attendance management server). The attendance management server (attendance management system) is a server that manages employee attendance, and is a device related to publicly known technology, so a detailed description will be omitted.

[0097] The entry / exit information storage unit 1123 stores one or more pieces of entry / exit information. The entry / exit information is information related to the entry / exit of an applicant. Entry / exit refers to the applicant's entry into and exit from their workplace (which may also be referred to as their work location). Entry may also refer to coming into the workplace to start work on a work day, and exit may refer to leaving the workplace after work ends on a work day. Entry / exit information is usually associated with an applicant identifier. Entry / exit information includes, for example, work day information and work hour information. Work hour information includes, for example, the start time and end time of work. Work hour information includes, for example, information specifying the hours worked. Entry / exit information is information configured by punching a time card and entering work or leaving work into an entry / exit system. Note that the entry / exit information may be the same as the attendance information. The entry / exit information in the entry / exit information storage unit 1123 is, for example, information received from an external server 3 (an entry / exit management server). The entrance / exit management server (entrance / exit management system) is a device according to publicly known technology, and therefore a detailed description thereof will be omitted.

[0098] The sales activity information storage unit 1124 stores one or more pieces of sales activity information. Sales activity information is information related to sales activities. Sales activity information is, for example, information from a daily sales report. Sales activity information is usually associated with an applicant identifier. Sales activity information includes business day information and one or more location identifiers. Sales activity information may include a character string indicating the content of the sales activity. Business day information is information that identifies the day on which the applicant engaged in business activities. Location identifiers are information that identify the locations visited. Location identifiers are, for example, (latitude, longitude), company name, location name, place name, station name, bus stop name, etc. The data structure of the sales activity information is not important.

[0099] The card statement information storage unit 1125 stores one or more pieces of card statement information. Card statement information is information showing the details of the credit card used by the applicant. Card statement information is usually associated with an applicant identifier. Card statement information includes, for example, usage date information, a payee identifier (e.g., a store identifier) ​​that identifies the payee, amount information, and a card identifier. The card identifier is information that identifies the card, such as a card number. The card statement information in the card statement information storage unit 1125 is, for example, information received from an external server 3 (card management company server).

[0100] The business vehicle location information storage unit 1126 stores one or more pieces of business vehicle location information. Business vehicle location information is information that identifies the location of a business vehicle used by an applicant. Business vehicle location information is usually associated with an applicant identifier. Business vehicle location information is associated with usage date information that identifies the date on which the business vehicle was used. Business vehicle location information is, for example, (latitude, longitude), but may also be a location identifier. Business vehicle location information is associated with, for example, a business vehicle identifier that identifies the business vehicle.

[0101] The company regulation information storage unit 113 stores company regulation information. The company regulation information is information indicating company regulations. The company regulation information is information related to the regulations of the company to which the applicant belongs. The company regulation information includes, for example, overtime time information, one or more approver information, and one or more payment method information.

[0102] The overtime information is information that specifies the overtime hours during which overnight stays are permitted. Examples of overtime information include "11 PM" and "after midnight."

[0103] The approver information is information that identifies the person who can approve the expense. The approver information is, for example, an approver identifier that identifies the approver (e.g., applicant identifier, name), or a position identifier that identifies the approver's position (e.g., "department manager" or "director").

[0104] The payment method information is information that specifies unacceptable payment methods, such as "XX PAY," "electronic money," and "credit card."

[0105] The restaurant set storage unit 114 stores a restaurant set. The restaurant set has one or more pieces of restaurant information. The restaurant information is information about the restaurant. The restaurant information has, for example, a restaurant identifier that identifies the restaurant and price information. The restaurant information may also have address information, telephone number information, etc. The restaurant identifier is, for example, the restaurant name or ID. The price information is, for example, information that specifies an appropriate amount to spend at a restaurant. The price information is, for example, information about the amount spent by one person at the restaurant. The price information is, for example, information that indicates the average amount spent by one person at the restaurant. The price information may be, for example, information that specifies the upper limit of the amount to spend by one person at the restaurant. The price information may be, for example, information that specifies the upper limit of the amount to spend in one transaction.

[0106] The adult entertainment establishment set storage unit 115 stores an adult entertainment establishment set. The adult entertainment establishment set has one or more pieces of adult entertainment establishment information. The adult entertainment establishment information has, for example, an adult entertainment establishment identifier that identifies the adult entertainment establishment. The adult entertainment establishment information may also have price information, address information, telephone number information, etc. The adult entertainment establishment information is, for example, information that specifies establishments that the applicant is not permitted to visit.

[0107] The recipient set storage unit 116 stores a recipient set. The recipient set has one or more recipient information. The recipient information has, for example, a recipient identifier and an affiliation identifier that identifies the recipient's affiliation. The recipient information is, for example, information on a civil servant. The recipient information is, for example, information on a member of parliament. The recipient information is, for example, information that specifies a person to whom the applicant must not provide a benefit. Incidentally, providing a benefit is, for example, the act of providing entertainment or giving a gift.

[0108] The card usage expense storage unit 117 stores one or more expense type identifiers for which payment is planned by card. The expense type identifier may be associated with a card type identifier. The card type identifier is information that identifies the type of card. Examples of card type identifiers are "EX-IC card" and "corporate card." Examples of expense type identifiers are "Shinkansen" indicating the fare for the Shinkansen, and "entertainment expenses."

[0109] The transportation information storage unit 118 stores transportation information. The transportation information is information for calculating transportation costs when using transportation such as a train, bus, airplane, or taxi. The transportation information includes calculation information, which will be described later. The transportation information includes, for example, map information, which will be described later.

[0110] The calculation information storage unit 1181 stores calculation information. The calculation information is, for example, fare calculation information and taxi fare calculation information. The fare calculation information is, for example, information for calculating the fare for transportation such as train, bus, or airplane. The fare calculation information is, for example, information having one or more pairs of a departure identifier, an arrival identifier, and fare information. The departure identifier and the arrival identifier are, for example, a station name, an airport name, a bus stop name, a station ID, an airport ID, or a bus stop ID. The taxi fare calculation information is information for calculating a taxi fare. The taxi fare calculation information is, for example, an arithmetic formula for calculating a taxi fare using a distance as an input. The taxi fare calculation information is, for example, information having one or more pairs of a distance and a taxi fare.

[0111] Map information is stored in the map information storage unit 1182. The map information is, for example, information on a map used for navigation. The map information is, for example, information in KIWI format.

[0112] The reception unit 12 receives various types of information and instructions. Here, reception typically refers to reception from a terminal such as the applicant terminal 2. However, reception may also include the concept of receiving information input from an input device such as a keyboard, mouse, or touch panel, or information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0113] The expense accepting unit 121 accepts one or more pieces of expense information. The expense accepting unit 121 normally accepts expense information in association with an applicant identifier. The expense accepting unit 121 accepts, for example, expense information and an applicant identifier. The expense accepting unit 121 may accept, for example, one or more pieces of expense information for each of one or more applicants. The expense information is accepted, for example, from an applicant terminal, but may also be accepted from an administrator terminal (not shown), may be read from a recording medium, or may be accepted as input by the applicant.

[0114] It is preferable that the expense accepting unit 121 accepts expense information having a receipt image. The expense accepting unit 121 may accept the receipt image and information other than the receipt image that constitutes the expense information separately. However, the receipt image and the information other than the receipt image are accepted so as to correspond to each other.

[0115] The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by an inspection unit 131 and a statistical processing unit 132.

[0116] The inspection unit 131 inspects the expense information received by the expense receiving unit 121 for fraud and obtains the inspection results. The inspection unit 131 may also inspect the expense information stored in the expense information storage unit 111 for fraud and obtain the inspection results. The expense information stored in the expense information storage unit 111 is expense information received by the expense receiving unit 121. The inspection result is information related to the result of the inspection of the expense information. The inspection result includes, for example, information indicating whether or not the expense information is fraudulent. The inspection result includes, for example, part or all of the fraudulent expense information. The inspection result is, for example, information indicating that the expense information is not fraudulent (that the expense information is legitimate). The inspection result includes, for example, one or more pieces of information from among an expense information identifier, an applicant identifier, an expense type identifier, amount information, an inspection content identifier, and an application date. The expense information identifier is information that identifies the expense information, such as an ID. The inspection content identifier is information that identifies the inspection content. The inspection content identifier is usually stored in the storage unit 11 in association with the inspection process described below. The inspection content identifiers are, for example, "expenses for days other than work days," "illegible business trip expenses," "illegible accommodation expenses," "accommodation expenses for days when accommodation is not permitted," "illegible transportation expenses," and "split receipts." Note that the contents and data structure of the inspection content identifiers are not important.

[0117] The inspection unit 131 inspects the expense information received by the expense receiving unit 121 for fraud, for example, using external information, and obtains the inspection results. The external information is information other than the expense information. The external information used by the inspection unit 131 may be stored in the storage unit 11 of the expense inspection device 1, or may be stored in the external server 3.

[0118] The inspection unit 131 inspects the expense information received by the expense receiving unit 121 for fraud, for example, by using expense information other than the expense information received by the expense receiving unit 121, and obtains the inspection result. The expense information other than the expense information received by the expense receiving unit 121 is, for example, expense information stored in the expense information storage unit 111, but may also be expense information stored in the external server 3.

[0119] The inspection unit 131, for example, obtains applicant information associated with an applicant identifier associated with expense information accepted by the expense acceptance unit 121 from the applicant set, and uses the applicant information to inspect the expense information accepted by the expense acceptance unit 121 for fraud and obtains the inspection results. The applicant set is, for example, information stored in the applicant set storage unit 112, but may also be information stored in an external device (not shown). The applicant information is information associated with an applicant identifier, and is, for example, attendance information, entrance / exit information, business activity information, card statement information, and business vehicle location information.

[0120] The image inspection means 1311 inspects the receipt image included in the expense information received by the expense receiving unit 121, and obtains the image inspection result. Note that the image inspection result is an example of the inspection result.

[0121] The image inspection means 1311 acquires one or more character strings from the receipt image, and uses the one or more character strings to inspect whether the receipt image is authentic and acquires the image inspection result. The image inspection means 1311 uses one or more of character recognition processing and machine learning processing to acquire one or more character strings from the receipt image.

[0122] In this specification, any algorithm may be used in the machine learning process. Examples of machine learning include deep learning, decision trees, random forests, SVM, and SVR. Examples of modules used in machine learning include TensorFlow modules and TinySVM. (1) Character recognition processing method

[0123] The image inspection means 1311 performs character recognition processing on, for example, a receipt image to acquire one or more character strings. The process of performing character recognition processing and acquiring information constituting expense information from a receipt image is a publicly known technique. The image inspection means 1311 determines whether the acquired character string is payment amount information, store identifier, recipient identifier, use date information, account, summary, or payment method information, and acquires the character string by associating it with information identifying the type of information (which may also be called a class, category, etc.). The technique for determining the class of an acquired character string is an information classification problem (clustering problem) and is a publicly known technique.

[0124] The image inspection means 1311, for example, configures a learning device that performs a binary classification of whether or not a character string belongs to a class by performing a machine learning learning process for each class, with two or more character strings that belong to each class as positive examples and one or more character strings that do not belong to that class as negative examples.The image inspection means 1311 then performs a machine learning prediction process using two or more learning devices for each of one or more character strings acquired from the receipt image, obtains a prediction result and score for each class, and determines the class with the highest class-belonging score as the class to which the character string belongs.

[0125] The image inspection means 1311 also configures a single learning device that performs learning processing using teacher data having two or more pairs of character strings and classes, and performs multi-value classification to output classes. Next, the image inspection means 1311 uses the learning device to perform machine learning prediction processing on one or more character strings acquired from the receipt image, and determines the class to which each character string belongs.

[0126] The image inspection means 1311 uses, for example, a large amount of training data, which is a pair of character strings and classes, to acquire a learning device for classifying character strings using a module that performs learning processing in a machine learning algorithm. (2) Machine learning processing method

[0127] The image inspection means 1311 performs learning processing using a machine learning algorithm using, for example, a receipt image and two or more pieces of training data each having one or more pairs of a character string and a class, to acquire a learning device. Note that this learning device is a learning device that receives a receipt image as input and outputs one or more pairs of a character string and a class.

[0128] Next, the image inspection means 1311 provides the acquired learning device and the receipt image contained in the expense information accepted by the expense acceptance unit 121 to a module that performs prediction processing in the machine learning algorithm, and acquires one or more pairs of strings and classes. (3) A method that uses both character recognition processing and machine learning processing

[0129] The image inspection means 1311, for example, uses both (1) and (2) above to obtain character strings for each class, and if there is no match between the processes (1) and (2) for each class, it uses the score obtained by the character recognition process and the score obtained by the machine learning process to obtain the character string with the higher score that satisfies the condition.

[0130] Furthermore, using one or more character strings acquired by any of the above methods (1) to (3), the image inspection means 1311 determines whether each of the one or more character strings satisfies a predetermined condition and acquires the image inspection result. The one or more character strings are, for example, payment amount information, store identifier, counterparty identifier, use date information, account, summary, or payment method information.

[0131] The image inspection means 1311 performs a learning process using a machine learning algorithm with training data including, for example, negative examples that are one or more fraudulent receipt images and positive examples that are one or more legitimate receipt images, thereby constructing a learning device. Next, the image inspection means 1311 provides the receipt images included in the expense information accepted by the expense acceptance unit 121 and the learning device to a module that performs machine learning prediction processing, performs prediction processing, and obtains a prediction result of whether or not the receipt is fraudulent. The learning device may, for example, be a learning device for detecting fraudulent manipulation of the amount on the receipt, a learning device for checking whether or not the receipt has been signed, or a learning device for detecting blurred receipt images. The learning device is typically a learning device for binary classification of whether or not the receipt is fraudulent.

[0132] The statistical processing unit 132 performs statistical processing based on one or more pieces of expense information stored in the expense information storage unit 111, which is one or more pieces of expense information associated with an applicant identifier that corresponds to the accepted expense information, and obtains the statistical processing results. For example, for each applicant identifier, the statistical processing unit 132 performs statistical processing based on one or more pieces of expense information associated with the applicant identifier and stored in the expense information storage unit, and obtains the statistical processing results. Note that the timing at which the statistical processing unit 132 performs statistical processing does not matter. For example, the statistical processing unit 132 performs statistical processing upon receiving a user instruction. For example, the statistical processing unit 132 performs statistical processing upon receiving expense information.

[0133] The statistical processing unit 132 acquires store frequency information, for example, using a store identifier included in two or more pieces of expense information stored in the expense information storage unit 111 and corresponding to one applicant identifier. Store frequency information is information relating to the frequency of use of a store identified by one store identifier. Store frequency information is information indicating the frequency of use. Store frequency information is, for example, information indicating the total number of times used, or information indicating the number of times used in a unit period. The unit period is, for example, one month, six months, or one year. It is preferable that the statistical processing unit 132 acquires store frequency information for each applicant identifier.

[0134] The statistical processing unit 132 acquires entertainment frequency information using a counterparty identifier included in two or more pieces of expense information stored in the expense information storage unit 111 and associated with one applicant identifier. Entertainment frequency information is information relating to the frequency of expenditures to a counterparty identified by one counterparty identifier. Expenditures to a counterparty are payments for providing a benefit to the counterparty, such as payments for entertainment to the counterparty or payments for souvenirs to the counterparty. Entertainment frequency information is information indicating the frequency of providing a benefit. Entertainment frequency information is, for example, information indicating the total number of times a benefit has been provided, or information indicating the number of times a benefit has been provided in a unit period. It is preferable that the statistical processing unit 132 acquires entertainment frequency information for each applicant identifier.

[0135] The statistical processing unit 132 acquires the number of fraudulent incidents, which is the number of times that an investigation result corresponding to fraud has been obtained, in association with one applicant identifier, as the investigation result for expense information corresponding to one applicant identifier. It is preferable that the statistical processing unit 132 acquires the number of fraudulent incidents for each applicant identifier.

[0136] The result output unit 141 outputs the inspection results acquired by the inspection unit 131. The result output unit 141 outputs the image inspection results acquired by the image inspection means 1311.

[0137] The result output unit 141 outputs the statistical processing results acquired by the statistical processing unit 132. The result output unit 141 outputs the statistical processing results in association with the applicant identifier, for example.

[0138] Various types of information are stored in first storage unit 21 constituting applicant terminal 2. The various types of information include, for example, an applicant identifier and expense information.

[0139] The first receiving unit 22 receives various instructions and information. The various instructions and information include, for example, expense information and response information. The response information is information that indicates a response to the test result.

[0140] The first processing unit 23 performs various types of processing. For example, the various types of processing are processing for converting instructions and information received by the first receiving 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 first receiving unit 25 into information with a data structure to be output.

[0141] The first transmission unit 24 transmits various instructions and information, such as expense information, an applicant identifier, and response information.

[0142] The first receiving unit 25 receives various types of information, such as test results and image test results.

[0143] The first output unit 26 outputs various types of information, such as test results and image test results.

[0144] Here, output is a concept that includes displaying on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, and delivery of processing results to other processing devices or other programs. (Specific example of inspection process)

[0145] Specific examples of inspections performed by the inspection unit 131 are described below. Note that, although the following mainly describes cases where there is fraud, if there is no fraud, the inspection unit 131 normally obtains an inspection result indicating that the information is "legitimate." Furthermore, if the information is legitimate, the inspection unit 131 normally stores the expense information subject to inspection in the expense information storage unit 111 in association with the applicant identifier.

[0146] The information contained in the expense information used by the inspection unit 131 for inspection may be a character string accepted by the expense accepting unit 121, or may be information acquired from a receipt image accepted by the expense accepting unit 121. The character string accepted by the expense accepting unit 121 is, for example, information entered by the applicant. (1) Inspection using attendance information

[0147] The inspection unit 131 acquires, from the attendance information storage unit 1122, attendance information that is associated with the applicant identifier associated with the expense information accepted by the expense accepting unit 121 and that includes work date information that is the same as the use date information included in the expense information accepted by the expense accepting unit 121. Next, the inspection unit 131 uses the attendance information to inspect the expense information accepted by the expense accepting unit 121 for fraud and acquires the inspection results. (1-1) Inspection of expenses other than those on working days

[0148] The inspection unit 131 acquires, from the attendance information storage unit 1122, attendance information that is associated with the applicant identifier associated with the expense information accepted by the expense accepting unit 121, and that includes work day information that is the same as the use date information included in the expense information accepted by the expense accepting unit 121, for example. Next, the inspection unit 131 determines whether the attendance information is information for a day that is not a work day. If the information is information for a day that is not a work day, the inspection unit 131 acquires an inspection result that indicates that the expense is an "illegal expense for a day that is not a work day." The inspection unit 131 determines that the attendance information is information for a day that is not a work day based on, for example, whether the attendance information includes "information indicating a holiday" or whether the attendance information does not include a work start time and a work end time. (1-2) Inspection of fraudulent travel expenses

[0149] The inspection unit 131 acquires the applicant identifier and use date information associated with the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 acquires the attendance information corresponding to the acquired applicant identifier and use date information from the attendance information storage unit 1122. Next, if the inspection unit 131 determines that the acquired attendance information is not information indicating a business trip, it acquires an inspection result indicating "fake business trip fraud." Examples of cases in which "the attendance information is not information indicating a business trip" include (a) when the attendance information does not contain information indicating a "business trip," and (b) when the attendance information contains information on the start time and end time of work. (1-3) Inspection of fraudulent accommodation fees

[0150] The inspection unit 131 acquires the applicant identifier and use date information associated with the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 acquires working hours information from the working day information corresponding to the acquired applicant identifier and use date information. Next, the inspection unit 131 uses the acquired working hours information to determine whether or not the accommodation facility is permitted to accommodate the applicant and acquires the inspection result.

[0151] More specifically, the inspection unit 131 compares the work end time included in the work time information with overtime information indicating the overtime hours during which overnight stays are permitted, and determines whether or not the predetermined accommodation conditions are met. If the inspection unit 131 determines that the accommodation conditions are not met, it acquires an inspection result indicating that "the accommodation fee is a fraudulent claim." The accommodation conditions are conditions that use the overtime information and the work end time, such as "overtime information = < work end time" or "overtime information < work end time." (2) Inspection using entry and exit information

[0152] The inspection unit 131 obtains from the entrance / exit information storage unit 1123 the entrance / exit information associated with the applicant identifier associated with the expense information, which corresponds to the date specified by the date of use information contained in the expense information, and uses the entrance / exit information to inspect the expense information accepted by the expense acceptance unit 121 for fraud and obtains the inspection results. (2-1) Inspection of expenses other than those on working days

[0153] The inspection unit 131 acquires the applicant identifier and use date information associated with the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 performs a process of acquiring the entry / exit information corresponding to the acquired applicant identifier and use date information from the entry / exit information storage unit 1123. Next, the inspection unit 131 determines whether the entry / exit information is information for a day that is not a workday. If the information is information for a day that is not a workday, the inspection unit 131 acquires an inspection result indicating that the expense is an "unauthorized expense for a day that is not a workday." Note that the inspection unit 131 determines that the entry / exit information is information for a day that is not a workday based on, for example, whether the entry / exit information includes "information indicating that it is a holiday" or does not include the start and end times of work. (2-2) Inspection of fraudulent travel expenses

[0154] The inspection unit 131 acquires the applicant identifier and the date of use information associated with the expense information received by the expense reception unit 121. Next, the inspection unit 131 performs a process of acquiring the entrance / exit information corresponding to the acquired applicant identifier and the date of use information from the entrance / exit information storage unit 1123. Next, if the inspection unit 131 determines that the result of the entrance / exit information acquisition process does not indicate a business trip, it acquires an inspection result indicating a "fake business trip." Note that examples of cases in which "the result of the entrance / exit information acquisition process does not indicate a business trip" include (a) when the entrance / exit information is acquired, and (b) when the work start time and work end time information contained in the acquired entrance / exit information are the work start time information and work end time information for regular work. Note that the work start time information and work end time information for regular work are stored, for example, in company-defined information. (2-3) Inspection of fraudulent accommodation fees

[0155] The inspection unit 131 acquires the applicant identifier and use date information associated with the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 acquires the end time of work from the entry / exit information corresponding to the acquired applicant identifier and use date information. Next, the inspection unit 131 uses the acquired end time of work to determine whether or not the stay at the accommodation facility is permitted, and acquires the inspection result.

[0156] More specifically, the inspection unit 131 compares the end time of work with overtime information indicating the overtime hours during which overnight stays are permitted, and determines whether or not the predetermined overnight stay conditions are met. If the inspection unit 131 determines that the overnight stay conditions are not met, it obtains an inspection result indicating that the accommodation fee is a fraudulent claim. The overtime work time information is stored, for example, in company regulation information. (3) Inspection using sales activity information

[0157] The inspection unit 131 obtains from the sales activity information storage unit 1124 one or more location identifiers contained in the sales activity information that correspond to the applicant identifier associated with the expense information received by the expense reception unit 121 and that have the same business day information as the use date information contained in the expense information, and uses the one or more location identifiers to inspect the expense information received by the expense reception unit 121 for fraud and obtains the inspection results. (3-1) Inspection of transportation expense fraud (i)

[0158] The inspection unit 131 provides information indicating the company's location and one or more location identifiers contained in the sales activity information to a travel expense calculation module, and acquires one or more travel expenses using the calculation information for calculating travel expenses. It is preferable that the travel expenses acquired here are the cheapest travel expenses. Acquiring two or more travel expenses occurs when there are two or more travel routes. Since the technology for acquiring travel expenses and the technology for acquiring the cheapest travel expenses are well-known technologies, detailed explanations are omitted. The inspection unit 131 also acquires expenditure amount information from the expense information accepted by the expense acceptance unit 121.

[0159] Next, the inspection unit 131 uses the expenditure information and the acquired transportation expenses to determine whether the expenditure information satisfies predetermined conditions for legitimate transportation expenses. If the conditions for legitimate transportation expenses are not met, the inspection unit 131 obtains an inspection result indicating that the transportation expense claim is fraudulent. Note that the conditions for legitimate transportation expenses are, for example, "expense information = lowest transportation expense," "expense information matches one or more transportation expenses," and "expense information <= one or more transportation expenses." (3-2) Inspection of transportation expense fraud (ii)

[0160] The inspection unit 131 acquires transportation expense information having a departure identifier and an arrival identifier from the expense information accepted by the expense acceptance unit 121. The inspection unit 131 also acquires one or more location identifiers included in the sales activity information. The inspection unit 131 then determines whether the distance between the departure identifier and any of the location identifiers is close enough to satisfy a predetermined condition. If the distances between the departure identifier and all of the location identifiers do not satisfy the predetermined condition, the inspection unit 131 acquires an inspection result indicating that the transportation expense claim is fraudulent. The inspection unit 131 determines whether the distance between the arrival identifier and any of the location identifiers is close enough to satisfy a predetermined condition. If the distances between the arrival identifier and all of the location identifiers do not satisfy the predetermined condition, the inspection unit 131 acquires an inspection result indicating that the transportation expense claim is fraudulent.

[0161] The technique for calculating the distance between the departure identifier or the arrival identifier and each point identifier is a known technique. (4) Inspection using card statement information

[0162] The inspection unit 131 obtains card statement information corresponding to the applicant identifier associated with the expense information accepted by the expense acceptance unit 121 from the card statement information storage unit 1125, which card statement information has the same date of use information as the date of use information contained in the expense information, and uses the card statement information to inspect the expense information accepted by the expense acceptance unit 121 for fraud and obtains the inspection results. (4-1) Inspection of receipt division

[0163] The inspection unit 131 acquires card statement information that is associated with the applicant identifier associated with the expense information accepted by the expense acceptance unit 121 and that has the same date of use information as the date of use information contained in the expense information from the card statement information storage unit 1125. If the inspection unit 131 determines that it has been able to acquire two or more pieces of card statement information and that the store identifiers contained in each of the two or more pieces of card statement information are the same, it acquires an inspection result indicating that "receipt splitting is fraudulent." (4-2) Inspection of taxi use after company drinking parties

[0164] The inspection unit 131 acquires card statement information associated with the applicant identifier associated with the expense information accepted by the expense acceptance unit 121. The inspection unit 131 also uses the information contained in the card statement information to determine whether the expense is for taxi use. If the expense is for taxi use, the inspection unit 131 acquires one or more pieces of participant information (e.g., the names of the participants) contained in the expense information that includes the same date of use information as the date of use information contained in the card statement information. Next, the inspection unit 131 determines whether all of the one or more pieces of participant information correspond to personal information held in the personal information storage unit 1121 (employee database) (e.g., whether the names of the participants are included). If all of the one or more pieces of participant information correspond to personal information, the inspection unit 131 acquires an inspection result indicating that the expense is "taxi use after an office drinking party." (5) Inspection using commercial vehicle location information

[0165] The inspection unit 131 acquires, from the sales vehicle location information storage unit 1126, one or more pieces of sales vehicle location information that are associated with the applicant identifier associated with the expense information accepted by the expense acceptance unit 121 and that are associated with the same date of use information as the date of use information contained in the expense information. Next, the inspection unit 131 uses the sales vehicle location information to inspect the expense information for fraud and acquires the inspection results. (5-1) Inspection of unauthorized use of business vehicles (inspection of unauthorized locations)

[0166] The inspection unit 131 determines whether the acquired one or more pieces of commercial vehicle location information are close enough to a predetermined fraudulent location (e.g., a tourist spot) to satisfy a predetermined condition. If it is determined that the location information is close enough to satisfy the predetermined condition, the inspection unit 131 acquires an inspection result indicating that the commercial vehicle is being used fraudulently. Note that the information on the predetermined fraudulent location is included in, for example, company regulation information. (6) Inspection using card usage expense information

[0167] The inspection unit 131 inspects whether the expense type identifier associated with the expense information received by the expense reception unit 121 is stored in the card usage expense storage unit 117 as the expense type identifier corresponding to the owned card information associated with the applicant identifier associated with the expense information received by the expense reception unit 121, and acquires the inspection result. Note that, for example, it is assumed that the card usage expense storage unit 117 stores information indicating that a credit card is used for dining expenses or entertainment expenses. (7) Inspection using company-specified information

[0168] The inspection unit 131 uses the company specification information stored in the company specification information storage unit 113 to inspect whether the expense information received by the expense reception unit 121 conforms to the company specification specified by the company specification information, and acquires the inspection result. Specific examples of inspections using company specification information include (2-2), (2-3), (13-1) and (13-2) described below, (14-3)(a) described below, and (14-4)(a) described below. (8) Inspection using transportation information

[0169] The inspection unit 131 inspects for fraudulent travel expenses using the expense information received by the expense receiving unit 121 and the transportation information stored in the transportation information storage unit 118, and obtains the inspection results. (8-1) Examination of train, bus, or airplane travel fare fraud

[0170] The inspection unit 131 acquires applicant information associated with the applicant identifier associated with the expense information regarding transportation expenses received by the expense reception unit 121, and uses the applicant information, or the applicant information and the means of transportation information, to inspect for fraud regarding the claim of transportation expenses and acquires the inspection results.

[0171] More specifically, the inspection unit 131 acquires transportation expense information having one or more section information each having a departure identifier, an arrival identifier, and fare information from the expense information accepted by the expense acceptance unit 121. Next, the departure identifier and arrival identifier of each of the one or more section information are provided to a transportation expense calculation module, and one or more transportation expenses are acquired using the calculation information for calculating the transportation expenses. Here, it is preferable that the transportation expense acquired is the cheapest transportation expense. Acquiring two or more transportation expenses occurs when there are two or more travel routes. Furthermore, since the technology for acquiring transportation expenses and the technology for acquiring the cheapest transportation expenses are well-known technologies, detailed explanations are omitted. Furthermore, it is preferable that the transportation expenses are acquired using an external server 3.

[0172] Furthermore, the checking unit 131 acquires expenditure amount information from the expense information received by the expense receiving unit 121 .

[0173] Next, the inspection unit 131 uses the fare information and the transportation expenses to determine whether the fare information satisfies predetermined conditions for legitimate transportation expenses. If the conditions for legitimate transportation expenses are not met, the inspection result indicates that the transportation expense claim is fraudulent. Note that the conditions for legitimate transportation expenses are, for example, "fare information = lowest transportation expense," "fare information matches one or more transportation expenses," and "fare information <= one or more transportation expenses." (8-2) Inspection of taxi fare fraud

[0174] The inspection unit 131 acquires applicant information associated with the applicant identifier associated with the expense information regarding taxi fares received by the expense reception unit 121, and uses the applicant information, or the applicant information and the means of transportation information, to inspect for fraud regarding the claim of transportation expenses and acquires the inspection results.

[0175] More specifically, the inspection unit 131 acquires transportation expense information having a departure identifier, an arrival identifier, and expenditure amount information from the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 acquires the traveled distance using the departure identifier, arrival identifier, and map information contained in the transportation expense information. Next, the inspection unit 131 acquires the taxi fare using the distance and calculation information for calculating the taxi fare. Note that the technology for acquiring the taxi fare is well known, so a detailed description will be omitted here. Furthermore, it is preferable to acquire the taxi fare using an external server 3.

[0176] Furthermore, the checking unit 131 acquires expenditure amount information from the expense information received by the expense receiving unit 121 .

[0177] Next, the inspection unit 131 uses the expenditure information and the taxi fare to determine whether the expenditure information satisfies predetermined conditions for a legitimate taxi fare. If the conditions for a legitimate taxi fare are not met, the inspection result indicates that the travel expense claim is fraudulent. Note that the conditions for a legitimate travel expense are, for example, "expenditure information = taxi fare," "expenditure information - taxi fare <= threshold," and "expenditure information - taxi fare < threshold." (8-3) Inspection of overlap with regular route

[0178] The inspection unit 131 acquires, from the personal information storage unit 1121, regular route information associated with the applicant identifier associated with the expense information related to transportation expenses accepted by the expense acceptance unit 121. Next, the inspection unit 131 acquires transportation expense information having one or more route information each having a departure identifier and an arrival identifier from the expense information accepted by the expense acceptance unit 121.

[0179] Next, the inspection unit 131 determines whether or not there is an overlap between the section specified by the commuter pass section information and the sections specified by one or more pieces of section information, using the transportation information. For example, the inspection unit 131 uses the transportation information to create a set of station names (station name group 1) in which the station names in the section of one or more pieces of section information are arranged in order. Then, the inspection unit 131 uses the transportation information to acquire a set of station names (station name group 2) in which the station names in the section specified by the commuter pass section information are arranged in order. Then, the inspection unit 131 determines whether or not two or more consecutive identical station names are included in station name group 1 and station name group 2. If two or more consecutive identical station names are included, the inspection unit 131 acquires an inspection result indicating that "the requested transportation expenses include the commuter pass section." (9) Inspection using store information

[0180] The inspection unit 131 inspects the expense information for fraud using the store identifier contained in the expense information received by the expense receiving unit 121 and the store information contained in the store set, and obtains the inspection result. The store set is, for example, a restaurant set in the restaurant set storage unit 114 or a restaurant set in the adult entertainment establishment set storage unit 115, but it may also be a restaurant set or adult entertainment establishment set present in an external device (not shown). (9-1) Inspection of store fraud (use of adult entertainment establishments, etc.)

[0181] For example, inspection unit 131 acquires a shop identifier included in the expense information accepted by expense acceptance unit 121. Next, inspection unit 131 inspects whether the acquired shop identifier (adult entertainment establishment identifier) ​​is stored in adult entertainment establishment collection storage unit 115, and if it is stored, acquires an inspection result indicating "fraudulent use of expenses at an adult entertainment establishment that should not be visited." It should be noted that such inspection result preferably includes adult entertainment establishment information including the shop identifier in adult entertainment establishment collection storage unit 115. (9-2) Inspection of monetary irregularities (a) Examination of the total amount

[0182] For example, the inspection unit 131 acquires, from the restaurant collection storage unit 114, amount information paired with a store identifier contained in the expense information received by the expense receiving unit 121. Next, the inspection unit 131 acquires, for example, expenditure amount information contained in the expense information received by the expense receiving unit 121. Next, the inspection unit 131 compares the acquired expenditure amount information with the acquired amount information to determine whether the information indicates an amount high enough to satisfy a predetermined condition. If the information indicates an amount high enough to satisfy a predetermined condition, the inspection unit 131 acquires an inspection result indicating that an "incorrect amount of expenses was used." Note that the predetermined condition is, for example, "expense amount information - amount information >= threshold," "expense amount information - amount information > threshold," "expense amount information / amount information >= threshold," or "expense amount information / amount information > threshold." Note that it goes without saying that each threshold may be different. (9-3) Inspection of whether entertainment expenses include use of restaurants

[0183] The inspection unit 131, for example, acquires the expense type identifier of the expense information accepted by the expense accepting unit 121. Next, the inspection unit 131 determines whether the expense type identifier corresponds to "entertainment expenses." If it corresponds to "entertainment expenses," the inspection unit 131 acquires the store identifier included in the expense information accepted by the expense accepting unit 121. Next, the inspection unit 131 determines whether the store identifier is an identifier for a restaurant. If it is not an identifier for a restaurant, the inspection unit 131 acquires an inspection result indicating that "this is a fraudulent entertainment expense claim."

[0184] The inspection unit 131 determines whether a store identifier is a restaurant identifier, for example, based on whether the store identifier is stored in the restaurant cluster storage unit 114. The inspection unit 131 also performs a web search using the store identifier as a key, and determines whether a store identifier is a restaurant identifier based on whether the acquired web page contains information indicating a restaurant (for example, izakaya, Italian, name of a dish, etc.). Other methods may also be used for clustering store identifiers. In other words, any algorithm may be used to determine whether a store identifier is a restaurant identifier. (b) Examination of per capita amounts

[0185] The inspection unit 131, for example, acquires amount information paired with a store identifier contained in the expense information received by the expense receiving unit 121 from the restaurant collection storage unit 114. Next, the inspection unit 131, for example, acquires expenditure amount information contained in the expense information received by the expense receiving unit 121. The inspection unit 131 also acquires, for example, number of people information contained in the expense information received by the expense receiving unit 121 or number of people information acquired from participant information contained in the expense information. Next, the inspection unit 131 uses the acquired expenditure amount information and the acquired amount information and number of people information to determine whether the amount per person is high enough to satisfy a predetermined condition. Then, if the amount per person is high enough to satisfy the predetermined condition, the inspection unit 131 acquires an inspection result indicating that "an improper amount of expenses was spent." The predetermined conditions are, for example, "(expenditure amount information / number of people information)-amount information>=threshold", "(expenditure amount information / number of people information)-amount information>threshold", "(expenditure amount information / number of people information) / amount information>=threshold", and "(expenditure amount information / number of people information) / amount information>threshold". It goes without saying that each threshold may be different. (10) Inspection using counterparty information

[0186] The inspection unit 131 inspects the expense information for fraud using the destination identifier contained in the expense information accepted by the expense acceptance unit 121 and one or more destination information contained in the external information, and obtains the inspection result. The one or more destination information is, for example, a destination set. The destination set is, for example, the destination set in the destination set storage unit 116. (10-1) Inspection of benefits given to public officials

[0187] The inspection unit 131 acquires the counterparty identifier contained in the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 determines whether the acquired counterparty identifier exists in the counterparty set storage unit 116, which stores information on public servants. If it exists, the inspection unit 131 acquires an inspection result indicating "illegal provision of an illegal benefit to a public servant." (10-2) Inspection of benefits given to Diet members

[0188] The inspection unit 131 acquires the counterparty identifier contained in the expense information accepted by the expense acceptance unit 121. Next, the inspection unit 131 determines whether the acquired counterparty identifier exists in the counterparty set storage unit 116 in which information on assembly members is stored. If it exists, the inspection unit 131 acquires an inspection result indicating "illegal provision of an illegal benefit to an assembly member." (11) Inspection using past expense information (11-1) Inspection of duplicate applications

[0189] The inspection unit 131 determines whether the expense information received by the expense reception unit 121 is similar enough to one or more pieces of past expense information stored in the expense information storage unit 111 and associated with the same applicant identifier as the applicant identifier associated with the expense information, and obtains the inspection result.

[0190] Two pieces of expense information are "similar enough to satisfy a predetermined condition" if, for example, (a) at least a predetermined number of pieces of information match among the expenditure amount information, store identifier, recipient identifier, use date information, subject, summary, and approver identifier contained in the expense information accepted by the expense accepting unit 121, or (b) one or more pieces of predetermined information all match. Note that the one or more pieces of predetermined information are one or more pieces of information among the expenditure amount information, store identifier, and recipient identifier contained in the expense information accepted by the expense accepting unit 121. (11-2) Inspection of reuse of receipts

[0191] When the inspection unit 131 determines that the receipt image included in the expense information accepted by the expense accepting unit 121 is similar enough to the receipt image included in the past expense information stored in the expense information storage unit 111 to satisfy a predetermined condition, the inspection unit 131 obtains an inspection result indicating that "the receipt is being reused fraudulently." Note that the receipt image included in the past expense information used for inspection by the inspection unit 131 is preferably a receipt image associated with the same applicant identifier as the applicant identifier associated with the expense information accepted by the expense accepting unit 121 (a receipt image used in the past by the applicant himself / herself), but may also be a receipt image associated with a different applicant identifier. Specifically, for example, receipt reuse is inspected using one of the following methods (a) and (b). (a) Using image similarity

[0192] For example, the inspection unit 131 obtains the similarity between a receipt image included in the expense information received by the expense receiving unit 121 and a receipt image included in one or more pieces of past expense information stored in the expense information storage unit 111, and if the similarity is equal to or greater than a threshold, obtains an inspection result indicating "illegal reuse of receipts." Note that the inspection result may include past expense information that was determined to be reused, receipt images included in past expense information that was determined to be reused, etc. (b) Machine learning

[0193] The inspection unit 131 configures a learning device through machine learning processing using training data that has, for example, one or more pairs of two receipt images that have been judged by a person to be reused receipts as positive examples and one or more pairs of two different receipts as negative examples. Note that this learning device is a learning device that outputs whether or not the receipts are reused (whether or not they are the same).

[0194] Next, the inspection unit 131 performs machine learning prediction processing using the learning device, the receipt images included in the expense information accepted by the expense accepting unit 121, and past receipt images in the expense information storage unit 111, and if an output result indicating reuse is obtained, obtains an inspection result indicating that "the receipt reuse is fraudulent." Note that the past receipt images in the expense information storage unit 111 are preferably receipt images associated with an applicant identifier corresponding to the expense information accepted by the expense accepting unit 121. (11-3) Checking the number of expense claims on the same day

[0195] The inspection unit 131 inspects two or more pieces of expense information associated with one applicant identifier, determines whether the number of pieces of expense information having the same use date information is large enough to satisfy a predetermined condition, and acquires the inspection result. If the number of pieces of expense information is large enough to satisfy the predetermined condition, the inspection unit 131 acquires the inspection result indicating that the information is fraudulent.

[0196] The number of expense records that correspond to one applicant identifier and have the same date of use information may be obtained by the statistical processing unit 132. (11-4) Inspection of fraudulent expenditures for after-parties

[0197] The inspection unit 131 inspects two or more pieces of expense information associated with one applicant identifier, determines whether the number of pieces of expense information with the same date of use but different restaurant identifiers is large enough to satisfy a predetermined condition, and obtains the inspection result. For example, if there are expense claims for two or more restaurants on the same day, this means that expenses were used for an after-party as well, and obtains the inspection result that it is "fraudulent expenditure for an after-party." (12) Inspection using statistical processing results

[0198] The inspection unit 131 inspects whether or not the statistical processing result acquired by the statistical processing unit 132 satisfies a predetermined condition, and acquires the inspection result. (12-1) Inspection using store frequency information

[0199] The inspection unit 131 inspects whether the store frequency information acquired by the statistical processing unit 132 is large enough to satisfy a predetermined condition, and acquires an inspection result. If the store frequency information is large enough to satisfy a predetermined store frequency condition, the inspection unit 131 acquires an inspection result indicating that "one store is being used too much." The store frequency condition is an example of an invalid condition. Examples of the store frequency condition are "store frequency information >= threshold" and "store frequency information > threshold." The store frequency condition is stored in the storage unit 11, for example. (12-2) Inspection using entertainment frequency information

[0200] The inspection unit 131 inspects whether the entertainment frequency information acquired by the statistical processing unit 132 satisfies a predetermined condition, and acquires the inspection result. When the entertainment frequency information has a value large enough to satisfy the predetermined entertainment frequency condition, the inspection unit 131 acquires an inspection result indicating that "the number of times entertainment has been provided to a single client is too many (possibility of collusion, etc.)." The entertainment frequency condition is an example of an improper condition. Examples of entertainment frequency conditions are "entertainment frequency information >= threshold" and "entertainment frequency information > threshold." The entertainment frequency condition is stored, for example, in the storage unit 11. (12-3) Inspection of the number of fraudulent transactions by an applicant

[0201] The inspection unit 131 inspects whether the number of fraudulent attempts obtained by the statistical processing unit 132 satisfies a predetermined condition, that is, a fraud count condition, and obtains an inspection result indicating that "the applicant has committed many fraudulent attempts." The predetermined condition is, for example, "the number of fraudulent attempts up to now is equal to or greater than a threshold value," or "the number of fraudulent attempts in a unit period (e.g., one year, three years) is equal to or greater than a threshold value." The fraud count condition is one example of a fraud condition. Examples of the fraud count condition are "number of fraudulent attempts >= threshold value" and "number of fraudulent attempts > threshold value." The fraud count condition is stored in the storage unit 11, for example. (13) Detection of fraud by expense claim approvers

[0202] The checking unit 131 checks whether the approver identified by the approver identifier included in the accepted expense information is the approver specified by the approver information, and acquires the check result. (13-1) When the approvers who can approve are managed

[0203] For example, the inspection unit 131 determines whether the approver identifier contained in the accepted expense information is included in the approver information stored in the company specification information storage unit 113, and if not, obtains an inspection result indicating that the approver is an "unauthorized approver." (13-2) When approval positions are managed

[0204] For example, the inspection unit 131 obtains a job title identifier that pairs with the approver identifier contained in the accepted expense information from the personal information storage unit 1121, and determines whether the job title identifier is included in the approver information stored in the company specification information storage unit 113.If not, the inspection unit 131 obtains an inspection result indicating that the approver is an "unauthorized approver." (14) Detection of missing applications

[0205] The inspection unit 131 uses applicant information corresponding to one applicant identifier to determine whether expense information corresponding to the applicant information exists in the expense information storage unit 111, which stores one or more pieces of expense information associated with one applicant identifier, and performs an inspection to determine whether an application for expenses corresponding to the applicant information has been submitted, and obtains the inspection results. Note that applicant information includes, for example, attendance information, entrance / exit information, business activity information, card statement information, and business vehicle location information. (14-1) Detection of missed applications using attendance information (a) Failure to declare labor wage expenses

[0206] The inspection unit 131 acquires attendance information corresponding to one applicant identifier from the attendance information storage unit 1122. Next, the inspection unit 131 determines whether the acquired attendance information corresponds to attendance outside the salary range. Next, if it is determined that the attendance information corresponds to attendance outside the salary range, the inspection unit 131 determines whether expense information corresponding to one applicant identifier, having the same usage date information as the working date information contained in the attendance information, and having an expense type identifier indicating wages (for example, "labor wages") exists in the expense information storage unit 111. If it is determined that the expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the attendance information have not been claimed."

[0207] To determine whether the acquired attendance information is attendance outside the salary range, the inspection unit 131, for example, acquires the day of the week information contained in the attendance information, and if the day of the week information is a day that is not a working day (for example, Saturday, Sunday, or public holiday), it determines that the acquired attendance information is attendance outside the salary range. The inspection unit 131, for example, acquires an applicant identifier corresponding to the attendance information, and if the applicant type information paired with the applicant identifier is predetermined information (for example, "part-time worker" or "casual"), it determines that the acquired attendance information is attendance outside the salary range. Note that the applicant type information is information contained in the personal information in the personal information storage unit 1121. (b) Failure to apply for travel expenses

[0208] The inspection unit 131 acquires attendance information corresponding to one applicant identifier from the attendance information storage unit 1122. Next, the inspection unit 131 determines whether the acquired attendance information corresponds to a business trip. If the attendance information corresponds to a business trip, the inspection unit 131 determines whether expense information corresponding to one applicant identifier, having the same date of use information as the work date information contained in the attendance information, and having an expense type identifier for expenses claimed at the time of the business trip (for example, "business trip expenses" or "travel expenses") exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the business trip have not been claimed."

[0209] For example, the inspection unit 131 determines that the attendance information corresponds to a business trip if the attendance information has a business trip flag indicating that the information is a business trip. Furthermore, the inspection unit 131 determines that the attendance information corresponds to a business trip if the attendance information does not have start time information or end time information. Furthermore, the inspection unit 131 determines that the attendance information corresponds to a business trip if the attendance information has a location identifier indicating the destination of the business trip. (c) Failure to apply for overseas daily allowance

[0210] The inspection unit 131 acquires attendance information corresponding to one applicant identifier from the attendance information storage unit 1122. Next, the inspection unit 131 determines whether the acquired attendance information corresponds to an overseas business trip. If the attendance information corresponds to an overseas business trip, the inspection unit 131 determines whether expense information corresponding to one applicant identifier, having the same date of use information as the work date information contained in the attendance information, and having an expense type identifier for expenses claimed for an overseas business trip (for example, "overseas daily allowance" or "overseas business trip allowance") exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result stating that "expenses corresponding to the overseas business trip have not been claimed."

[0211] For example, if the attendance information has an overseas business trip flag indicating an overseas business trip, the inspection unit 131 determines that the attendance information corresponds to an overseas business trip. Also, for example, if the attendance information has a location identifier indicating the destination of the overseas business trip, the inspection unit 131 determines that the attendance information corresponds to an overseas business trip.

[0212] In addition, the inspection unit 131 may, for example, obtain the amount information of the regulations for overseas business trips contained in the company regulation information storage unit 113, compare it with the amount information of the corresponding expense information, and if there is a mismatch, obtain an inspection result indicating "fraudulent application of overseas daily allowance."

[0213] Furthermore, the inspection unit 131 acquires, for example, sales activity information corresponding to a single applicant identifier from the sales activity information storage unit 1124. If the inspection unit 131 determines that the location identifier contained in the sales activity information is a location identifier corresponding to an overseas business trip, it acquires the business day information contained in the sales activity information. Next, the inspection unit 131 determines whether or not expense information corresponding to a single applicant identifier, having the same usage date information as the acquired business day information, and having an expense type identifier for expenses claimed for an overseas business trip exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the overseas business trip have not been claimed." (14-2) Detecting missing applications using entrance and exit information (a) Failure to declare labor wage expenses

[0214] The inspection unit 131 acquires entry / exit information corresponding to a single applicant identifier from the entry / exit information storage unit 1123. Next, the inspection unit 131 determines whether the acquired entry / exit information corresponds to work that is not included in the salary range. Next, if it is determined that the entry / exit information corresponds to work that is not included in the salary range, the inspection unit 131 determines whether expense information corresponding to a single applicant identifier, having usage date information that is the same as the work date information contained in the entry / exit information, and having an expense type identifier indicating labor wages (for example, "labor wages") exists in the expense information storage unit 111. If it is determined that the expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result stating that "expenses corresponding to the entry / exit information have not been claimed."

[0215] To determine whether the acquired entry / exit information represents work attendance outside the salary range, the inspection unit 131, for example, acquires the day of the week information contained in the entry / exit information, and if the day of the week information represents a day that is not a working day (for example, Saturday, Sunday, or public holiday), determines that the acquired entry / exit information represents work attendance outside the salary range. The inspection unit 131, for example, acquires an applicant identifier corresponding to the entry / exit information, and if the applicant type information paired with the applicant identifier is predetermined information (for example, "part-time" or "casual"), determines that the acquired entry / exit information represents work attendance outside the salary range. (b) Failure to apply for travel expenses

[0216] The inspection unit 131 acquires entry / exit information corresponding to one applicant identifier from the entry / exit information storage unit 1123. Next, the inspection unit 131 determines whether the acquired entry / exit information corresponds to a business trip. If the entry / exit information corresponds to a business trip, the inspection unit 131 determines whether expense information corresponding to one applicant identifier, having the same date of use as the work date information contained in the entry / exit information, and having an expense type identifier for expenses claimed for the business trip (for example, "business trip expenses" or "travel expenses") exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the business trip have not been claimed."

[0217] For example, if the entry / exit information does not have start time information or end time information, the inspection unit 131 determines that the entry / exit information corresponds to a business trip. For example, if the entry / exit information does not have start time information or end time information, and the inspection unit 131 determines that the entry / exit information corresponds to a business trip, the inspection unit 131 determines that the entry / exit information does not have start time information or end time information, and that the attendance information, which corresponds to one applicant identifier and has the same work day information as the use date information, is information indicating attendance (not absence). (14-3) Detecting missed applications using sales activity information (a) Failure to apply for travel expenses

[0218] The inspection unit 131 acquires sales activity information corresponding to one applicant identifier from the sales activity information storage unit 1124. Next, the inspection unit 131 determines whether the acquired sales activity information corresponds to a business trip. If the sales activity information corresponds to a business trip, the inspection unit 131 determines whether expense information corresponding to the one applicant identifier, having the same date of use information as the business day information contained in the sales activity information, and having an expense type identifier for expenses claimed during the business trip (for example, "business trip expenses" or "travel expenses") exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the business trip have not been claimed."

[0219] The inspection unit 131 uses, for example, a location identifier included in the sales activity information and predetermined company location information to obtain the distance between the location identified by the location identifier and the company using map information stored in the map information storage unit 1182, and if it determines that the distance is equal to or greater than the distance at which business trip expenses are incurred, it determines that the sales activity information corresponds to a business trip. Information on the minimum distance at which business trip expenses are incurred is stored, for example, in the company specification information storage unit 113.

[0220] Furthermore, for example, if the sales activity information includes a location identifier, the checking unit 131 determines that the sales activity information is information corresponding to a business trip.

[0221] The algorithm for determining whether the sales activity information corresponds to a business trip is not limited to a specific one. The sales activity information may have a flag indicating whether it is a business trip or not. (b) Failure to apply for travel expenses

[0222] The inspection unit 131 acquires one or more location identifiers contained in the sales activity information corresponding to one applicant identifier from the sales activity information storage unit 1124. Next, the inspection unit 131 determines whether or not travel expenses will be incurred using pre-stored company location information and the acquired one or more location identifiers. If it determines that travel expenses will be incurred, the inspection unit 131 determines whether or not expense information having the same usage date information as the business day information contained in the sales activity information and an expense type identifier of "travel expenses" exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that the "travel expenses have not been claimed."

[0223] The inspection unit 131 determines whether or not transportation expenses will be incurred by using, for example, the calculation information in the calculation information storage unit 1181. Specifically, the inspection unit 131 provides, for example, company location information and a location identifier to a calculation module that calculates transportation expenses, and determines whether or not transportation expense information is output. The inspection unit 131 also obtains, for example, the distance between the company location information and the location identifier by using map information, and determines whether or not transportation expenses will be incurred by determining whether or not the distance is equal to or greater than a threshold. The calculation module is a publicly known technology. (14-4) Detection of missed applications using business vehicle location information (a) Failure to apply for travel expenses

[0224] The inspection unit 131 acquires one or more pieces of business vehicle location information corresponding to one applicant identifier and one piece of usage date information from the business vehicle location information storage unit 1126. Next, the inspection unit 131 determines whether the acquired one or more pieces of business vehicle location information correspond to a business trip. If the business vehicle location information corresponds to a business trip, the inspection unit 131 determines whether expense information corresponding to the one applicant identifier, having the same usage date information as the one piece of usage date information corresponding to the business vehicle location information, and having an expense type identifier (e.g., "business trip expenses") for expenses claimed at the time of the business trip exists in the expense information storage unit 111. If the inspection unit 131 determines that such expense information does not exist in the expense information storage unit 111, the inspection unit 131 acquires an inspection result indicating that "expenses corresponding to the business trip have not been claimed."

[0225] The inspection unit 131 uses, for example, one or more pieces of sales vehicle location information and pre-stored company location information to obtain the maximum value of the distance between the location indicated by the sales vehicle location information and the company using map information in the map information storage unit 1182, and if it determines that the maximum value of the distance is equal to or greater than the distance at which business trip expenses are incurred, it determines that the sales activity information corresponds to a business trip. Information on the minimum distance at which business trip expenses are incurred is stored, for example, in the company specification information storage unit 113.

[0226] Furthermore, the inspection unit 131 determines that the business activity information corresponds to a business trip when, for example, there is a business trip flag associated with one or more pieces of sales vehicle location information. The business trip flag is a flag indicating that the business trip is a business trip.

[0227] The output unit 14 outputs various types of information. Examples of such information include test results, image test results, and statistical processing results. Here, output typically means transmission to the applicant terminal 2, but it may also mean transmission to another device such as an accounting terminal, storage in the expense verification device 1, or display on a display. (15) Receipt image inspection performed by the image inspection means 1311

[0228] The image inspection means 1311 performs, for example, one or more of character recognition processing and machine learning processing (such as any of the above methods (1) to (3)), acquires one or more character strings, determines whether each of the one or more character strings satisfies a predetermined condition, and acquires the image inspection result. The one or more character strings are, for example, any of payment amount information, store identifier, counterparty identifier, use date information, account, summary, and payment method information.

[0229] Examples of inspections performed by the image inspection means 1311 are the following (15-1) to (15-9). The image inspection means 1311 performs, for example, one or more of the inspections (15-1) to (15-9) and obtains image inspection results. Note that (15-1) to (15-9) are examples of receipt image inspections. (15-1) Check for mismatch between receipt image and expense information string

[0230] The image inspection means 1311 acquires one or more pairs of character strings and classes from a receipt image included in the expense information accepted by the expense accepting unit 121. Next, for each pair, the inspection unit 131 acquires a character string (e.g., payment amount information, store identifier, recipient identifier, date of use information, account, summary, or payment method information) included in the expense information accepted by the expense accepting unit 121 that corresponds to the class included in the pair. Next, the inspection unit 131 compares, for each pair, the character string of one class acquired from the receipt image with the character string of the same class included in the expense information accepted by the expense accepting unit 121, and determines whether or not they have a predetermined relationship. If they do not have the predetermined relationship, the inspection unit 131 acquires an inspection result indicating fraud.

[0231] The predetermined relationship is a match, but similar enough to satisfy predetermined conditions (for example, the similarity is above a threshold, the only difference is between "(Co., Ltd.") and "Co., Ltd.", the only difference is the spelling, etc.). (15-2) Inspection of monetary processing (a) When character recognition processing is used

[0232] The image inspection means 1311, for example, uses character recognition technology to obtain a character string and a score for the amount area from the receipt image, and if it determines that the score is low enough to satisfy a predetermined condition, it determines that the amount on the receipt has been altered. Note that the image inspection means 1311, for example, obtains all characters on the receipt image using character recognition technology, detects the character "￥" from the set of characters, and obtains the string of numbers next to the character "￥" as payment amount information. (b) When machine learning processing is used

[0233] The image inspection means 1311, for example, constitutes a learning device that uses one or more receipt images with handwritten falsified amounts and one or more receipt images without falsified amounts as training data, performs learning processing using a machine learning algorithm, and obtains an inspection result as to whether or not the amount has been falsified using the receipt images as input.

[0234] Next, the image inspection means 1311 performs prediction processing using a machine learning algorithm, for example, using the receipt image accepted by the expense acceptance unit 121 and a learning device, and obtains image inspection results indicating whether the amount written on the receipt image has been handwritten or forged. (15-3) Inspection of inappropriate tax classifications, etc.

[0235] The image inspection means 1311 acquires two or more character strings from the receipt image. Next, the image inspection means 1311 determines whether the two or more character strings match a predetermined fraudulent pattern. If they match a fraudulent pattern, the image inspection means 1311 acquires an inspection result indicating fraud.

[0236] An example of a fraudulent pattern is when a character string corresponding to the class "summary" includes the character string "gift" and a character string corresponding to the class "tax category" includes "10%." Such a fraudulent pattern is a tax category fraud. For example, when the image inspection means 1311 determines, using the acquired character string, that a character string corresponding to the class "summary" includes "gift" and a character string corresponding to the class "tax category" includes "10%," it acquires an image inspection result indicating "tax category fraud." (15-4) Inspection of address errors

[0237] The image inspection means 1311 acquires one or more character strings from the receipt image in association with the class.

[0238] Next, if the image inspection means 1311 determines that the character string corresponding to the class "addressee" does not match the company name stored in the storage unit 11, it acquires an image inspection result indicating that the addressee on the receipt is incomplete. Also, for example, if the image inspection means 1311 uses the acquired character string to determine that the character string corresponding to the class "addressee" is an inappropriate character string such as "Dear Sir / Madam" stored in the storage unit 11, it acquires an image inspection result indicating that the addressee on the receipt is incomplete. (15-5) Inspection of receipt signature

[0239] The image inspection means 1311 constructs a learning device using a machine learning algorithm, for example, using training data in which one or more receipts with a signature are treated as positive examples and one or more receipts without a signature are treated as negative examples.The image inspection means 1311 then performs a prediction process using the received receipt image and the learning device to obtain information indicating whether or not a signature is present.If the image inspection means 1311 determines that a signature is absent, it obtains an image inspection result indicating the defect of the receipt being missing a signature. (15-6) Inspection of blurred receipt images (a) When character recognition processing is used (first blurring process)

[0240] The image inspection means 1311 performs a first blurring process using character recognition technology to acquire a character recognition score along with one or more character strings from the receipt image accepted by the expense accepting unit 121, and determines that the receipt image is blurred if the score is low enough to satisfy a predetermined condition. Note that the technology for performing character recognition, acquiring character strings, and outputting a character recognition score (which can also be called likelihood) is publicly known. (b) When machine learning processing is used (second blurring process)

[0241] The image inspection means 1311 performs a learning process on one or more blurred receipt images and one or more clear receipt images using a machine learning algorithm to form a learning device. Note that this learning device is a learning device that receives a receipt image as input and obtains a determination result as to whether the receipt image is blurred or clear.

[0242] Next, the image inspection means 1311 uses the receipt image received by the expense reception unit 121 and the learning device to perform prediction processing using a machine learning algorithm, and obtains an inspection result as to whether the receipt image is blurred or clear. (15-7) Inspection of payment methods

[0243] The image inspection means 1311 acquires the payment method information (for example, "○○ PAY"), which is a character string, from the receipt image, inspects whether the payment method information is the payment method information included in the company specification information, and acquires the image inspection result. The company specification information is stored in the company specification information storage unit 113. (15-8) Inspection of handwritten receipts for square stamps (a) When machine learning processing is used

[0244] The image inspection means 1311 performs learning processing using a machine learning algorithm, taking, for example, one or more handwritten receipt images with a square stamp as positive examples and one or more receipt images without a square stamp as negative examples, to form a learning device. Note that this learning device is a learning device that takes a receipt image as input and outputs whether or not a square stamp is present.

[0245] Next, the image inspection means 1311 performs prediction processing using a machine learning algorithm using the received receipt image and the learning device, and obtains an image inspection result indicating whether or not a square stamp is affixed. (b) When using image recognition processing

[0246] The image inspection means 1311 performs character recognition processing on the received receipt image to determine whether handwritten characters are present (for example, whether the score is equal to or less than a threshold). If it is determined that handwritten characters are present, the image inspection means 1311 determines, for example, by image recognition, whether a square mark with a pixel value in a red area and a roughly rectangular outline is present. If it is determined that a square mark is not present, the image inspection means 1311 obtains an image inspection result indicating that no square mark is present. (15-9) Checking timestamp

[0247] The image inspection unit 1311 acquires the date information indicated by the timestamp of the received receipt image. The date information indicates the date on which the timestamp was added to the receipt image.

[0248] Next, the image inspection means 1311 acquires the receipt issue date corresponding to the received receipt image.

[0249] Next, the image inspection means 1311 determines whether the date indicated by the acquired date information is a predetermined period of time or more from the receipt issuance date, and acquires the image inspection result. The predetermined period of time or more is, for example, "3 days or more" or "4 days or more."

[0250] The image inspection means 1311 normally acquires the receipt issue date from the receipt image, but may acquire the receipt issue date as a character string included in the expense information accepted by the expense acceptance unit 121. The technology for adding a timestamp to a receipt image and the technology for acquiring the timestamp contained in a receipt image are publicly known technologies.

[0251] The storage unit 11, expense information storage unit 111, applicant group storage unit 112, company regulation information storage unit 113, restaurant group storage unit 114, adult entertainment establishment group storage unit 115, counterparty group storage unit 116, card usage expense storage unit 117, transportation information storage unit 118, personal information storage unit 1121, attendance information storage unit 1122, entry and exit information storage unit 1123, business activity information storage unit 1124, card statement information storage unit 1125, business vehicle location information storage unit 1126, calculation information storage unit 1181, map information storage unit 1182, and first storage unit 21 are preferably non-volatile recording media, but can also be realized with volatile recording media.

[0252] 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 input via an input device may be stored in the storage unit 11 etc.

[0253] The reception unit 12, expense reception unit 121, and first reception unit 25 are usually realized by wireless or wired communication means, but may also be realized by means for receiving broadcasts.

[0254] The processing unit 13, the inspection unit 131, the statistical processing unit 132, the image inspection means 1311, and the first processing unit 23 can usually be realized by a processor, a memory, etc. The processing procedure of the processing unit 13 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). The processor may be of any type, such as an MPU, a CPU, or a GPU.

[0255] The output unit 14, the result output unit 141, and the first transmission unit 24 are usually realized by wireless or wired communication means, but may also be realized by broadcasting means.

[0256] The first receiving 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.

[0257] The first output unit 26 may or may not be considered to include an output device such as a display, a speaker, etc. The first output unit 26 may be realized by driver software for an output device, or by a combination of driver software for an output device and the output device, etc. Equipped with.

[0258] Next, an example of the operation of the expense verification device 1 will be described with reference to the flowchart of FIG.

[0259] (Step S401) The expense receiving unit 121 determines whether or not expense information associated with the application form identifier has been received from the applicant terminal 2. If expense information has been received, the process proceeds to step S402; if expense information has not been received, the process proceeds to step S406.

[0260] (Step S402) The processing unit 13 performs an inspection process on the expense information received in step S401. The inspection process is a process for inspecting the expense application for fraud. An example of the inspection process will be described with reference to the flowchart in FIG.

[0261] (Step S403) The inspection unit 131 determines whether the inspection result acquired in step S402 is "authentic." If it is "authentic," the process proceeds to step S404. If it is not "authentic," the process proceeds to step S405.

[0262] (Step S404) The processing unit 13 or a storage unit (not shown) associates the expense information received in step S401 with the application form identifier and stores it in the expense information storage unit 111. Return to step S401. Note that in step S404, the result output unit 141 may send an inspection result indicating that the expense information is "legitimate" to the applicant terminal 2 that sent the expense information.

[0263] (Step S405) The result output unit 141 sends the inspection results acquired in step S402 to the applicant terminal 2 that sent the expense information. Return to step S401. Note that in step S405, the inspection unit 131 may increment the number of fraudulent attempts corresponding to the applicant identifier that corresponds to the expense information by 1. Also, in step S405, the processing unit 13 or a storage unit (not shown) may store the expense information received in step S401 in the expense information storage unit 111 in association with the application form identifier.

[0264] (Step S406) The processing unit 13 determines whether it is time to perform a statistical check. If it is time to perform a statistical check, the process proceeds to step S407, and if it is not time to perform a statistical check, the process proceeds to step S414.

[0265] The processing unit 13 acquires the time from a clock (not shown), and if the time is after a predetermined time, determines that it is time to perform a statistical check. Furthermore, the processing unit 13 determines that it is time to perform a statistical check when an instruction for a statistical check is received. Furthermore, a statistical check is a check for fraud using the results of statistical processing of expense information. It is preferable that the statistical check be performed periodically (for example, once a month).

[0266] (Step S407) The processing unit 13 assigns 1 to the counter i.

[0267] (Step S408) The processing unit 13 determines whether or not the i-th applicant identifier exists in the expense information storage unit 111. If the i-th applicant identifier exists, the process proceeds to step S409; if the i-th applicant identifier does not exist, the process proceeds to step S412. Whether or not the i-th applicant identifier exists depends on whether or not the i-th applicant to be inspected exists.

[0268] (Step S409) The processing unit 13 performs statistical processing on the expense information corresponding to the i-th applicant identifier, and uses the statistical processing results to check for fraud in the expense application. An example of such statistical inspection processing will be described using the flowchart in FIG.

[0269] (Step S410) Processing unit 13 outputs the test results acquired in step S409 in association with the i-th applicant identifier. Processing unit 13 stores the test results in storage unit 11 in association with, for example, the i-th applicant identifier. Processing unit 13 also transmits the test results associated with, for example, the i-th applicant identifier to a terminal (not shown).

[0270] (Step S411) The processing unit 13 increments the counter i by 1. The process returns to step S408.

[0271] (Step S412) The statistical processing unit 132 generates a statistical processing result to be output.

[0272] (Step S413) The result output unit 141 outputs the statistical processing result constructed in step S412. Return to step S401. Note that outputting the statistical processing result means, for example, storing the statistical processing result in the storage unit 11 or transmitting the statistical processing result to a terminal (not shown).

[0273] (Step S414) The processing unit 13 determines whether it is time to perform an omission report check. If it is time to perform an omission report check, the processing proceeds to step S415, and if it is not time to perform an omission report check, the processing returns to step S401.

[0274] The processing unit 13 acquires the time from a clock (not shown), and if the time is after a predetermined time, determines that it is time to conduct a declaration omission check. Furthermore, the processing unit 13 determines that it is time to conduct a declaration omission check when an instruction to conduct a declaration omission check is received. Furthermore, a declaration omission check is a check for omissions in expense claims. It is preferable that the declaration omission check be conducted periodically (for example, once a month).

[0275] (Step S415) The processing unit 13 checks for omissions in the expense application. An example of the omission check process will be described with reference to the flowchart of FIG.

[0276] (Step S416) The result output unit 141 outputs the test results of the leak test acquired in step S415. Return to step S401. Here, outputting the test results means, for example, storing the test results in the storage unit 11, sending the results to an applicant identified by the applicant identifier corresponding to the leak, or sending the results to a terminal (not shown).

[0277] In the flowchart of FIG. 4, the process ends when the power is turned off or an interrupt occurs to end the process.

[0278] Next, an example of the inspection process in step S402 will be described with reference to the flowchart in FIG.

[0279] (Step S501) The inspection unit 131 determines whether or not a receipt image is included in the received expense information. If a receipt image is included, the process proceeds to step S502, and if a receipt image is not included, the process proceeds to step S505.

[0280] (Step S502) The image inspection means 1311 acquires one or more pairs of character strings and classes from the receipt image. Note that this process has been described above, so a detailed description thereof will be omitted here.

[0281] (Step S503) The image inspection means 1311 inspects the receipt image and obtains the inspection result.

[0282] The receipt image inspection is, for example, one or more of the inspections (15-1) to (15-9) described above.

[0283] (Step S504) The inspection unit 131 performs a common inspection and acquires the inspection result. The common inspection is an inspection that does not depend on the expense type identifier (which may be a subject) of the expense information.

[0284] Common inspections include, for example, (1-1) and (2-1) inspections of expenses other than those on working days, (4-1) inspections of split receipts, (5-1) inspections of fraudulent use of business vehicles, (6) inspections using card usage expense information, (10) inspections using recipient information, (11-1) inspections of duplicate applications, (11-2) inspections of reused receipts, (11-3) inspections of a large number of expense applications on the same day, and (13) detection of fraud by expense application approvers.

[0285] (Step S505) The checking unit 131 acquires an expense type identifier from the received expense information.

[0286] (Step S506) The inspection unit 131 determines whether the expense type identifier acquired in step S505 is "transportation expenses (travel expenses may be used)." If it is "transportation expenses," the process proceeds to step S507, and if it is not "transportation expenses," the process proceeds to step S508.

[0287] (Step S507) The inspection unit 131 performs an entertainment expense inspection process and obtains the inspection result. Then, the process proceeds to step S514.

[0288] The transportation expense inspection process is a process for inspections specific to transportation expenses. Examples of the transportation expense inspection process include the above-mentioned (3-1) inspection of transportation expense fraud (i), (3-2) inspection of transportation expense fraud (ii), (4-2) inspection of taxi use after company drinking parties, (8-1) inspection of train, bus, or airplane transportation expense fraud, (8-2) inspection of taxi fare fraud, and (8-3) inspection of overlap with regular route.

[0289] (Step S508) The inspection unit 131 determines whether the expense type identifier acquired in step S505 is "entertainment expenses (or entertainment expenses)." If it is "entertainment expenses," the process proceeds to step S509, and if it is not "entertainment expenses," the process proceeds to step S510.

[0290] (Step S509) The inspection unit 131 performs an entertainment expense inspection process and acquires the inspection result. Then, the process proceeds to step S514.

[0291] The entertainment expense inspection process is a process for inspections specific to entertainment expenses. Examples of entertainment expense inspection processes include (9-1) inspection of store fraud (use of adult entertainment establishments, etc.), (9-2) inspection of amount fraud, (9-3) inspection of whether entertainment expenses include use of restaurants, (10) inspection using counterparty information, and (11-4) inspection of fraudulent expenditures for after-parties.

[0292] (Step S510) The inspection unit 131 determines whether the expense type identifier acquired in step S505 is "accommodation expenses." If it is "accommodation expenses," the process proceeds to step S511. If it is not "accommodation expenses," the process proceeds to step S512.

[0293] (Step S511) The inspection unit 131 performs accommodation fee inspection processing and acquires the inspection result. Then, the process proceeds to step S514.

[0294] The accommodation expense inspection process is a process for inspection specific to accommodation expenses. Examples of the accommodation expense inspection process include (1-3) inspection of accommodation expense fraud and (2-3) inspection of accommodation expense fraud.

[0295] (Step S512) The inspection unit 131 determines whether the expense type identifier acquired in step S505 is "travel expenses." If it is "travel expenses," the process proceeds to step S513, and if it is not "travel expenses," the process proceeds to step S512.

[0296] (Step S513) The inspection unit 131 performs a travel expense inspection process and acquires the inspection result. Then, the process proceeds to step S514.

[0297] The travel expense inspection process is a process for inspection specific to travel expenses. Examples of the travel expense inspection process include (1-2) Inspection of fraudulent travel expenses and (2-2) Inspection of fraudulent travel expenses.

[0298] (Step S514) The inspection unit 131 uses the acquired inspection result to compose an inspection result to be output, and returns to the upper-level processing.

[0299] For example, if one or more fraudulent inspection results are obtained, the inspection unit 131 generates an inspection result that includes all inspection results for fraudulent cases. Also, if no fraudulent inspection results are obtained, the inspection unit 131 generates an inspection result that indicates "legitimate."

[0300] Next, an example of the statistical inspection process in step S409 will be described with reference to the flowchart in FIG.

[0301] (Step S601) The statistical processing unit 132 assigns 1 to a counter i.

[0302] (Step S602) The statistical processing unit 132 determines whether the i-th store identifier exists among the one or more pieces of expense information corresponding to the applicant identifier to be inspected (the i-th applicant identifier in step S408) and among the store identifiers in the one or more pieces of expense information in the expense information storage unit 111. If the i-th store identifier exists, the process proceeds to step S603; if the i-th store identifier does not exist, the process proceeds to step S607.

[0303] The i-th store identifier is the i-th store identifier among the store identifiers in one or more pieces of expense information corresponding to the applicant identifier of the subject of inspection, after unique processing. The period of the expense information to be inspected may be predetermined, or may be the entire period.

[0304] (Step S603) The statistical processing unit 132 obtains the number of expense records that correspond to the applicant identifier to be inspected and that include the i-th store identifier. The statistical processing unit 132 uses this number to obtain store frequency information. Note that the store frequency information may be the same value as the number, or may be a value obtained by dividing the number by a period. The store frequency information is usually a value calculated using an increasing function that uses the number as a parameter.

[0305] (Step S604) The inspection unit 131 determines whether the store frequency information acquired in step S603 is large enough to satisfy a predetermined store frequency condition. If the store frequency condition is satisfied, the process proceeds to step S605. If the store frequency condition is not satisfied, the process proceeds to step S606.

[0306] (Step S605) The inspection unit 131 obtains an inspection result indicating "too much use of one store" and an inspection result having the i-th store identifier, in association with the applicant identifier of the inspection target. Note that the inspection unit 131 may increment the number of fraudulent attempts corresponding to the applicant identifier of the inspection target by 1.

[0307] (Step S606) The statistical processing unit 132 increments the counter i, and then returns to step S602.

[0308] (Step S607) The statistical processing unit 132 assigns 1 to the counter i.

[0309] (Step S608) The statistical processing unit 132 determines whether the i-th recipient identifier exists in the one or more pieces of expense information corresponding to the applicant identifier to be inspected, which is the store identifier in the one or more pieces of expense information in the expense information storage unit 111. If the i-th recipient identifier exists, proceed to step S609; if the i-th recipient identifier does not exist, proceed to step S613.

[0310] The i-th recipient identifier is the i-th recipient identifier among the recipient identifiers in one or more expense information items corresponding to the applicant identifier of the subject of inspection, which have been uniquely processed. The period of the expense information to be inspected may be predetermined, or may be the entire period.

[0311] (Step S609) The statistical processing unit 132 obtains the number of expense records that correspond to the applicant identifier to be inspected and that include the i-th recipient identifier. The statistical processing unit 132 uses this number to obtain recipient frequency information. Note that the recipient frequency information may be the same value as the number, or may be a value obtained by dividing the number by a period. The recipient frequency information is usually a value calculated using an increasing function that uses the number as a parameter.

[0312] (Step S610) The inspection unit 131 determines whether the destination frequency information acquired in step S603 is large enough to satisfy a predetermined destination frequency condition. If the destination frequency condition is satisfied, the process proceeds to step S611. If the destination frequency condition is not satisfied, the process proceeds to step S612.

[0313] (Step S611) The inspection unit 131 obtains an inspection result indicating "too many entertainments, etc., with one customer" and an inspection result having the i-th customer identifier, in association with the applicant identifier of the inspection target. Note that the inspection unit 131 may increment the number of fraudulent attempts corresponding to the applicant identifier of the inspection target by 1.

[0314] (Step S612) The statistical processing unit 132 increments the counter i, and then returns to step S608.

[0315] (Step S613) The checking unit 131 obtains from the personal information storage unit 1121 the number of fraudulent attempts corresponding to the applicant identifier to be checked.

[0316] (Step S614) The inspection unit 131 determines whether the number of fraudulent attempts acquired in step S613 satisfies the condition for the number of fraudulent attempts. If the condition for the number of fraudulent attempts is met, the process proceeds to step S615, and if the condition for the number of fraudulent attempts is not met, the process proceeds to step S616.

[0317] (Step S615) The inspection unit 131 acquires an inspection result indicating that "the applicant has committed many fraudulent acts" in association with the applicant identifier of the inspected applicant. Note that the inspection result may be only the applicant identifier of the applicant who committed many fraudulent acts.

[0318] (Step S616) The inspection unit 131 determines whether or not the inspection result for fraud has been acquired as a result of the statistical inspection. If the inspection result has been acquired, the process returns to the upper process, and if the inspection result has not been acquired, the process proceeds to step S617.

[0319] (Step S617) The inspection unit 131 assigns "valid" to the variable "inspection result", and returns to the upper level processing.

[0320] Next, an example of the leak test process in step S415 will be described with reference to the flowchart of FIG.

[0321] (Step S701) The verification unit 131 assigns 1 to a counter i. The counter i is the counter of the applicant to be verified.

[0322] (Step S702) The inspection unit 131 determines whether the i-th applicant identifier exists in the storage unit 11. If the i-th applicant identifier exists, the process proceeds to step S703; if the i-th applicant identifier does not exist, the process returns to the upper level processing. The i-th applicant identifier is the identifier of the i-th applicant to be inspected.

[0323] (Step S703) The inspection unit 131 assigns 1 to the counter j. The counter j is the counter for the day to be inspected.

[0324] (Step S704) The inspection unit 131 determines whether or not there is day information indicating the jth day to be inspected. If there is day information indicating the jth day, the process proceeds to step S705; if there is no day information, the process proceeds to step S722. It is assumed that the day on which the leak inspection will be performed is predetermined, and information specifying the day on which the leak inspection will be performed is stored in a buffer (not shown).

[0325] (Step S705) The inspection unit 131 determines whether attendance information corresponding to the i-th applicant identifier and having the same working day information as the day information indicating the j-th day exists in the attendance information storage unit 1122. If it exists, proceed to step S706; if it does not exist, proceed to step S709.

[0326] (Step S706) The inspection unit 131 acquires attendance information that corresponds to the i-th applicant identifier and has the same working day information as the day information indicating the j-th day from the attendance information storage unit 1122. The inspection unit 131 uses the acquired attendance information to inspect for omissions in expense claims. This inspection is, for example, the process described in "(14-1) Detecting Omissions in Claims Using Attendance Information."

[0327] (Step S707) The inspection unit 131 determines whether or not there is a leak as a result of the inspection in step S706. If there is a leak, the process proceeds to step S708, and if there is no leak, the process proceeds to step S709.

[0328] (Step S708) The inspection unit 131 acquires the inspection result indicating that there was an omission and the details of the omission, in association with the i-th applicant identifier and the j-th day information.

[0329] (Step S709) The inspection unit 131 determines whether entry / exit information corresponding to the i-th applicant identifier and having the same workday information as the day information indicating the j-th day exists in the entry / exit information storage unit 1123. If it exists, the process proceeds to step S710; if it does not exist, the process proceeds to step S713.

[0330] (Step S710) The inspection unit 131 obtains entry / exit information that corresponds to the i-th applicant identifier and has the same work day information as the day information indicating the j-th day from the entry / exit information storage unit 1123. The inspection unit 131 uses the obtained entry / exit information to inspect for omissions in expense applications. This inspection is, for example, the process described in "(14-2) Detecting Omissions in Applications Using Entry / Exit Information."

[0331] (Step S711) The inspection unit 131 determines whether or not there is a leak as a result of the inspection in step S710. If there is a leak, the process proceeds to step S712, and if there is no leak, the process proceeds to step S713.

[0332] (Step S712) The inspection unit 131 acquires the inspection result indicating that there was an omission and the details of the omission, in association with the i-th applicant identifier and the j-th day information.

[0333] (Step S713) The inspection unit 131 determines whether or not sales activity information corresponding to the i-th applicant identifier and having the same business day information as the day information indicating the j-th day exists in the sales activity information storage unit 1124. If it exists, the process proceeds to step S714; if it does not exist, the process proceeds to step S717.

[0334] (Step S714) The inspection unit 131 acquires sales activity information that corresponds to the i-th applicant identifier and has business day information that is the same as the day information indicating the j-th day from the sales activity information storage unit 1124. The inspection unit 131 uses the acquired sales activity information to inspect for omissions in expense claims. This inspection is, for example, the process described in "(14-3) Detecting Omissions in Claims Using Sales Activity Information."

[0335] (Step S715) The inspection unit 131 determines whether or not there is a leak as a result of the inspection in step S714. If there is a leak, the process proceeds to step S716, and if there is no leak, the process proceeds to step S717.

[0336] (Step S716) The inspection unit 131 acquires the inspection result indicating that there was an omission and the details of the omission, in association with the i-th applicant identifier and the j-th day information.

[0337] (Step S717) The inspection unit 131 determines whether or not sales vehicle location information corresponding to the i-th applicant identifier and having the same business day information as the day information indicating the j-th day exists in the sales vehicle location information storage unit 1126. If it exists, the process proceeds to step S718; if it does not exist, the process proceeds to step S721.

[0338] (Step S718) The inspection unit 131 obtains one or more pieces of sales vehicle location information corresponding to the i-th applicant identifier and having the same business day information as the day information indicating the j-th day from the sales vehicle location information storage unit 1126. The inspection unit 131 uses the one or more pieces of sales vehicle location information obtained to inspect for missing expense claims. This inspection is, for example, the process described in "(14-4) Detecting missing claims using sales vehicle location information."

[0339] (Step S719) The inspection unit 131 determines whether or not there is a leak as a result of the inspection in step S718. If there is a leak, the process proceeds to step S720, and if there is no leak, the process proceeds to step S721.

[0340] (Step S720) The inspection unit 131 acquires the inspection results indicating that there was an omission and the details of the omission, in association with the i-th applicant identifier and the j-th day information.

[0341] (Step S721) The inspection unit 131 increments the counter j by 1. The process returns to step S704.

[0342] (Step S722) The inspection unit 131 constructs an inspection result corresponding to the i-th applicant identifier. The inspection unit 131 temporarily stores the inspection result, for example, in association with the i-th applicant identifier. The inspection result includes, for example, the results of one or more inspections for omissions. If there are no omissions, the inspection result is information indicating "no omissions."

[0343] (Step S723) The inspection unit 131 increments the counter i by 1. The process returns to step S702.

[0344] Next, an example of the operation of the applicant terminal 2 will be described. The first accepting unit 22 of the applicant terminal 2 accepts input of expense information from a user. Next, the first processing unit 23 reads out the applicant identifier stored in the first storage unit 21. Then, the first processing unit 23 composes transmission information including the accepted expense information and the read applicant identifier. Next, the first transmitting unit 24 transmits the transmission information including the expense information and the applicant identifier to the expense verification device 1.

[0345] Next, the first receiving unit 25 receives the inspection result from the expense inspection device 1. The first processing unit 23 is configured to output the received inspection result. The first output unit 26 outputs the inspection result. (Example of statistical processing results)

[0346] An example of the statistical processing result acquired by the statistical processing unit 132 of the expense verification apparatus 1 in this embodiment and output by the result output unit 141 will be described below.

[0347] (Example 1) The statistical processing unit 132 performs statistical processing on each applicant's expense information for a certain period (for example, one month in December 2019), which is expense information in the expense information storage unit 111, and obtains store frequency information for each applicant identifier and store identifier. The statistical processing unit 132 also obtains the number of expense information items for each applicant identifier.

[0348] Then, the statistical processing unit 132 obtains the statistical processing results in which the store frequency information for each applicant identifier and each store identifier is plotted on a graph with the store frequency information on the vertical axis and the number of expense information for each applicant identifier on the horizontal axis.

[0349] Furthermore, the statistical processing unit 132 determines that the risk is high if the store frequency condition "store frequency information >= 3" in the storage unit 11 is met. High risk can also be said to mean fraud. Then, the statistical processing unit 132 acquires the applicant identifier of the applicant determined to be high risk, the store identifier of the store to be used, and the store frequency information.

[0350] Then, the statistical processing unit 132 generates a statistical processing result to be output as a result of the above processing.

[0351] Next, the result output unit 141 outputs the statistical processing results (801, 802). An example of such output is shown in FIG.

[0352] 8, 801 is the statistical processing result in which store frequency information is plotted on a graph. The vertical axis of 801 is the maximum number of applications by person and store (store frequency information). The horizontal axis of 801 is the number of applications by person.

[0353] Also, 802 is a table made up of records having applicant identifiers (applicants), store names, and store frequency information (number of cases) corresponding to store frequency information determined to be high risk.

[0354] (Example 2) Specific example 2 is an example of acquiring information when a person is on a business trip but still has time stamps.

[0355] For example, for each applicant identifier, if the attendance information indicates a business trip, or if expense information for business trip expenses or transportation expenses has been applied for, the statistical processing unit 132 determines that the day corresponding to the work day information contained in the attendance information or the usage date information contained in the expense information is the day of the business trip.

[0356] Next, the statistical processing unit 132 acquires the frequency (for example, the number of times in a certain month) of the existence (stamping) of work start times and work end times, which are entry / exit information that includes the same work day information as the work day information contained in the attendance information or the use date information contained in the expense information. Such information is the frequency of time stamping during a business trip.

[0357] Furthermore, the statistical processing unit 132 obtains, for example, for each applicant identifier, the average value of the difference between the working hours indicated in each monthly attendance information and the working hours indicated in the entry / exit information that includes the same working day information as the working day information contained in the attendance information. This information is the discrepancy between the attendance information and the time stamp.

[0358] Then, the statistical processing unit 132 creates a statistical processing result, which is a graph in which dots representing applicant identifiers are plotted on a graph with the horizontal axis representing the frequency of time-stamping during business trips and the vertical axis representing the discrepancy between attendance information and time-stamping, for each applicant identifier.

[0359] Next, the result output unit 141 outputs the statistical processing results. An example of such output is shown in Figure 9. In Figure 9, the applicants corresponding to the dots in area 901 are applicants who are likely to be committing fraud.

[0360] As described above, according to this embodiment, by using external information or expense information other than the expense information applied for, it is possible to appropriately inspect inappropriate expense applications.

[0361] Furthermore, according to this embodiment, by using the applicant information, it is possible to appropriately check inappropriate expense applications.

[0362] Furthermore, according to this embodiment, by using the applicant's attendance information, inappropriate expense claims can be properly inspected.

[0363] Furthermore, according to this embodiment, by using the applicant's entry and exit information, it is possible to properly check inappropriate expense applications.

[0364] Furthermore, according to this embodiment, by using the applicant's business activity information, it is possible to appropriately inspect inappropriate expense applications.

[0365] Furthermore, according to this embodiment, by using the applicant's credit card statement information, it is possible to appropriately check for inappropriate expense claims.

[0366] Furthermore, according to this embodiment, by using the applicant's business vehicle location information, inappropriate expense claims can be properly inspected.

[0367] Furthermore, according to this embodiment, by using information on a card owned by an applicant, it is possible to appropriately check for inappropriate expense claims.

[0368] Furthermore, according to this embodiment, by using company regulation information, inappropriate expense claims can be properly inspected.

[0369] Furthermore, according to this embodiment, by using the transportation information, it is possible to appropriately check inappropriate expense claims.

[0370] Furthermore, according to this embodiment, by using a store collection, it is possible to appropriately check for inappropriate expense claims.

[0371] Furthermore, according to this embodiment, inappropriate expenditures on inappropriate parties can be appropriately detected.

[0372] Furthermore, according to this embodiment, it is possible to appropriately detect inappropriate business trip expenses, inappropriate transportation expenses, duplicate applications, reuse of receipts, fraudulent accommodation expenses, fraudulent after-party expenses, and the like.

[0373] Furthermore, according to this embodiment, by using the results of statistical processing based on two or more pieces of expense information, it is possible to appropriately check for inappropriate expense applications.

[0374] Furthermore, according to this embodiment, it is possible to detect whether a particular store is frequently used.

[0375] Furthermore, according to this embodiment, it is possible to detect whether expenditures made to a specific party are frequent.

[0376] Furthermore, according to this embodiment, it is possible to detect whether a particular person is committing fraud frequently.

[0377] Furthermore, according to this embodiment, it is possible to detect whether the approver of the expense application does not meet the requirements.

[0378] Furthermore, according to this embodiment, it is possible to detect omissions in expense applications.

[0379] Furthermore, according to this embodiment, receipt images can be appropriately inspected.

[0380] Furthermore, according to this embodiment, the details written on the receipt image can be appropriately inspected.

[0381] Furthermore, according to this embodiment, it is possible to check for defects in the time stamp of the receipt image.

[0382] Furthermore, according to this embodiment, it is possible to inspect an unclear receipt image.

[0383] Furthermore, according to this embodiment, it is possible to check for inappropriate payment methods.

[0384] Furthermore, according to this embodiment, it is possible to check for forged handwritten amounts.

[0385] In this embodiment, the expense verification device 1 preferably functions as a device that receives expense information from one or more external expense management devices 4, verifies the expense information, and transmits the verification results to the expense management device. In this case, the expense verification device 1 has, for example, the structure shown in FIG. 10. In other words, in this case, the applicant set storage unit 112, company specification information storage unit 113, card usage expense storage unit 117, personal information storage unit 1121, attendance information storage unit 1122, entrance / exit information storage unit 1123, sales activity information storage unit 1124, card statement information storage unit 1125, and sales vehicle location information storage unit 1126 of the expense verification device 1 exist, for example, for each organization identifier. In other words, the applicant set, company specification information, card usage expense information, personal information, attendance information, entrance / exit information, sales activity information, card statement information, and sales vehicle location information are associated with the organization identifier.

[0386] Furthermore, the expense information that the expense verification device 1 receives from the expense management device 4 is associated with an organization identifier. When the expense verification device 1 receives expense information from the expense management device 4, the verification unit 131 performs verification using an applicant set, etc., that is associated with the organization identifier corresponding to the expense information, and obtains the verification results. The result output unit 141 then transmits the verification results to the expense management device 4. Note that the organization identifier is information that identifies an organization, such as a company name or company ID. An organization is, for example, a company, organization, or department.

[0387] Furthermore, the expense management device 4, which receives expense information from the applicant terminal 2, transmits the expense information to the expense verification device 1 to verify the expense information. In response to the transmission of the expense information, the expense management device 4 receives the verification result from the expense verification device 1. The expense management device 4 then stores the expense information only if the verification result is legitimate. Furthermore, if the verification result is fraudulent, the expense management device 4 transmits the verification result to the applicant terminal 2.

[0388] The above-described system configuration having the expense verification device 1 and one or more expense management devices 4 allows the expense verification device 1 to function as an expense information verification server. Furthermore, by using the expense verification device 1, the expense management device 4 can obtain an expense verification function in addition to the conventional expense information management function.

[0389] Furthermore, the expense checking device 1 can receive two or more pieces of expense information from one or two or more expense management devices 4, and can also perform the statistical processing described above by including an expense information storage unit 111 for each organization.

[0390] The processing in this embodiment may be implemented by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software implementing the expense verification device in this embodiment is the following program. In other words, this program causes a computer to function as an expense reception unit that receives expense information specifying the content of an expense request, an inspection unit that inspects the expense information received by the expense reception unit for fraud using external information other than expense information or expense information other than the expense information received by the expense reception unit and obtains the inspection results, and a result output unit that outputs the inspection results obtained by the inspection unit.

[0391] 11 shows the appearance of a computer that executes the programs described in this specification to realize the expense verification device 1 and other embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 11 is an overview of this computer system 300, and FIG. 12 is a block diagram of the system 300.

[0392] In FIG. 11, computer system 300 includes computer 301 including a CD-ROM drive, keyboard 302, mouse 303, and monitor 304.

[0393] 12, 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.

[0394] A program that causes computer system 300 to execute the functions of expense verification device 1 and the like of the above-described embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and then transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 when executed. The program may also be loaded directly from CD-ROM 3101 or the network.

[0395] The program does not necessarily include an operating system (OS) or third-party programs that cause the computer 301 to execute the functions of the expense verification device 1 of the above-described embodiment. The program need only include instructions that call appropriate functions (modules) in a controlled manner to achieve the desired results. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0396] 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 transmission step (processing that can only be performed by hardware).

[0397] Furthermore, the computer that executes the above program may be a single computer or multiple computers. That is, centralized processing or distributed processing may be performed. That is, the expense verification device 1 may be a standalone device or may be composed of two or more devices.

[0398] 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.

[0399] Furthermore, 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.

[0400] 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]

[0401] As described above, the expense checking device according to the present invention has the effect of being able to properly check inappropriate expense applications, and is useful as an expense checking device, etc. [Explanation of symbols]

[0402] 1. Expense inspection device 2. Applicant's terminal 3 External Server 4. Expense Management Device 11 Storage area 12 Reception 13 Processing section 14 Output section 21 First storage area 22 First Reception Department 23 First Processing Section 24 First Transmission Unit 25 First Receiving Unit 26 First output section 111 Expense information storage section 112 Applicant Set Storage Unit 113 Company Regulations Information Storage Unit 114 Restaurant Assembly Storage Area 115 Brothel Collection Storage Area 116 Destination collection storage section 117 Card usage expense storage section 118 Transportation information storage unit 121 Expenses Reception Department 131 Inspection Department 132 Statistical Processing Unit 141 Result output section 1121 Personal Information Storage Unit 1122 Attendance information storage unit 1123 Entry / Exit Information Storage Unit 1124 Sales activity information storage section 1125 Card statement information storage section 1126 Commercial vehicle location information storage unit 1181 Calculation information storage unit 1182 Map information storage section 1311 Imaging inspection means

Claims

1. an expense reception unit that receives expense information, which is information specifying the content of an expense application and is information including a receipt image, in association with an applicant identifier that identifies the applicant of the expense; an image inspection means for determining whether or not one or more character strings acquired from the receipt image included in the expense information accepted by the expense acceptance unit satisfy a predetermined condition, and acquiring an inspection result; and a result output unit that outputs the inspection results acquired by the image inspection means.

2. The image inspection means 2. The expense verification device according to claim 1, further comprising: acquiring payment method information from the receipt image; inspecting whether the payment method information specifies an unacceptable payment method; and acquiring the inspection result.

3. The image inspection means The expense inspection device of claim 1, wherein one or more pairs of a character string and a class are obtained from the receipt image contained in the expense information received by the expense reception unit, and for each pair, a character string contained in the expense information received by the expense reception unit corresponding to the class contained in the pair is obtained, and for each pair, the character string of one class obtained from the receipt image is compared with a character string of the same class contained in the expense information, and a determination is made as to whether or not they have a predetermined relationship, and the inspection result is obtained based on the determination result.

4. The image inspection means 2. The expense inspection device according to claim 1, further comprising: a determination unit for determining whether the amount on the receipt image has been forged by hand; and a determination unit for determining whether the amount on the receipt image has been forged by hand;

5. The image inspection means The expense verification device of claim 1, wherein the device obtains two or more character strings from the receipt image, determines whether the two or more character strings match a predetermined fraudulent pattern, and obtains the verification result based on the determination result.

6. The image inspection means An expense inspection device as described in claim 1, wherein if it is determined that a character string corresponding to the class "addressee" from the receipt image is an inappropriate character string stored in the storage unit, or if it is determined that a character string corresponding to the class "addressee" does not exist, it obtains an inspection result indicating that the addressee on the receipt is incomplete.

7. The image inspection means 2. The expense inspection device according to claim 1, wherein the receipt image is judged to be a handwritten receipt image without a square stamp, and the inspection result is obtained based on the judgment result.

8. The image inspection means An expense inspection device as described in claim 1, which obtains date information indicated by a timestamp in the receipt image, obtains the receipt issue date corresponding to the receipt image, determines whether the date indicated by the date information is a predetermined period or more from the receipt issue date, and obtains the inspection result.

9. An expense checking method, in which all of the processes performed by the expense checking device according to any one of claims 1 to 8 are carried out by a computer.

10. Computer, A program for causing the expense inspection device according to any one of claims 1 to 8 to function.

Images