This application is based on and claims priority under 35 USC 119 from Japanese Patent Application No. 2020-214206 filed Dec. 23, 2020.
The present disclosure relates to an information processing apparatus, an information processing method, and a non-transitory computer readable medium.
Japanese Patent No. 6342583 discloses a technique relating to an accounting process apparatus that automatically makes a journal entry to an account title corresponding to a content of a transaction. The accounting process apparatus includes: an automatic journal entry unit that has learned using machine learning to output account title candidates corresponding to a content of a transaction and reliability of the respective account title candidates as a journal entry result; a journal entry data generation unit that generates journal entry data including account title candidates corresponding to the content of a transaction and reliability of the respective account title candidates based on the journal entry result output from the automatic journal entry unit; and a journal entry presentation unit that presents to a user the account title candidates and the reliability of the respective account title candidates based on the journal entry data generated by the journal entry data generation unit in such a way that one of the account title candidates is selectable. The journal entry data generation unit generates the journal entry data by determining, of the journal entry result output from the automatic journal entry unit, an account title candidate that is a bookkeeping error for the content of the transaction and by attaching additional information representing that this account title candidate is a booking error, and the journal entry presentation unit presents to a user the account title candidate that is a bookkeeping error based on the additional information using a representation different from a representation of the other account title candidates.
There are information processing apparatuses that manage electronic ledgers, financial statements, and the like. Such an information processing apparatus sometimes includes, for example, a function that makes an estimate of the account title in the accounting relating to a voucher and presents estimated account titles when the voucher relating to a transaction is input. When only the account titles are presented, there is no information for assessing the presented account titles.
Aspects of non-limiting embodiments of the present disclosure relate to an information processing apparatus and an information processing method, each of which presents information for assessing the account titles, and further relates to a non-transitory computer readable medium storing a program therefor. Aspects of certain non-limiting embodiments of the present disclosure overcome the above disadvantages and/or other disadvantages not described above. However, aspects of the non-limiting embodiments are not required to overcome the disadvantages described above, and aspects of the non-limiting embodiments of the present disclosure may not overcome any of the disadvantages described above.
According to an aspect of the present disclosure, there is provided an information processing apparatus including a processor configured to present an account title relating to information obtained from a voucher together with related information relating to the account title.
An exemplary embodiment of the present disclosure will be described in detail based on the following figures, wherein:
Hereinafter, an exemplary embodiment for implementing the present disclosure are described in detail with reference to the drawings.
Referring to
As illustrated in
The CPU 11 controls the entirety of the information processing apparatus 10. The ROM 12 stores therein various programs including an information processing program to be used in the present exemplary embodiment, data, and the like. The RAM 13 is a memory to be used as a work area at the time of executing various programs. The CPU 11 performs a process to display one or more account titles and information relating to the one or more account titles (hereinafter, referred to as “related information”) by loading one or more programs stored in the ROM 12 into the RAM 13 and executing the one or more programs. The storage 14 is, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. Note that the storage 14 may store the information processing program and the like. The input unit 15 is a mouse, a keyboard, and the like for receiving input of characters. The monitor 16 displays one or more account titles and related information. The communication I/F 17 transmits and receives data.
Next, referring to
As illustrated in
The acquisition unit 21 obtains image data generated by reading a document that serves as a voucher of a transaction in an accounting process or the like. Here, the document that serves as a voucher is a document such as an invoice, a receipt, a business form, or the like, which indicates that a transaction has been conducted. Note that the present exemplary embodiment is described using the embodiment in which the image data is obtained. However, the exemplary embodiment is not limited thereto. Alternatively, information relating to a transaction input by a user, information relating to a user stored in the memory unit 23 which will be described below, image data obtained in the past, past information relating to the identical transaction, and the like may be obtained.
The analysis unit 22 obtains information included in the image data (document) by applying an optical character recognition (OCR) process to the obtained image data and extracts a string of characters therefrom. Here, the information included in the image data (document) is, for example, the date of a transaction, an amount, the name of a product to be described in the description, the name of a client, the name of an organization conducting the transaction, the name of a person in charge of the transaction, the organization to which the person in charge of the transaction belongs, and the like. Note that the analysis unit 22 according to the present exemplary embodiment is described using the embodiment in which the information is extracted from the image data in the form of a string of characters. However, the exemplary embodiment is not limited thereto. Alternatively, the type of the document in the image data may be identified by using the extracted information. For example, a document may be identified by extracting a string of characters located at a predetermined position such as a title or the like written on the document, or a document may be discerned by extracting an identifier or the like for discerning the document, or a document may be discerned from the position of a string of characters, a ruled line, or the like included in the document. Note that in the following part, image data pertaining to a transaction input by a user, information relating to a transaction input by a user, and information extracted from the image data by the analysis unit 22 are referred to as “transaction information”.
The memory unit 23 stores therein past image data, past transaction information, account titles pertaining to the past transaction information, reference materials relating to the account titles such as accounting rules, laws and regulations relating to accounting, management indicators, or the like (hereinafter, referred to as “reference material”).
As the past transaction information, the memory unit 23 stores image data input in the past, the transaction information pertaining to the image data input in the past, and the account titles pertaining to past transactions in connection with each other. Specifically, the memory unit 23 stores, for example, a data structure 31 relating to account titles illustrated in
Furthermore, the memory unit 23 stores, for example, a data structure 32 relating to conditions illustrated in
Using input image data and transaction information pertaining to the image data, the estimation unit 24 makes an estimate of the account title pertaining to the transaction information and the value representing the accuracy of an estimated account title (hereinbelow, referred to as “reliability”).
Specifically, the estimation unit 24 is a neural network that has learned in order to make an estimate of the account title pertaining to a transaction using image data of past transactions and past transaction information as input data and using account titles pertaining to the past transactions as training data. For example, the estimation unit 24 makes an estimate of the account title pertaining to the transaction information and the reliability thereof by identifying similar transaction information in the past using the date, the amount, the name of a product to be described in the description, the name of a client, the name of an organization conducting the transaction, or the like of the transaction included in the transaction information. Furthermore, the estimation unit 24 searches the memory unit 23 for image data similar to the obtained image data, identifies past similar transaction information, and makes an estimate of the account title pertaining to the transaction information and the reliability thereof. Furthermore, the estimation unit 24 makes an estimate of the account title pertaining to the transaction information and the reliability thereof using the data structure 31 relating to account titles stored in the memory unit 23.
The search unit 25 searches the memory unit 23 for related information relating to an account title estimated by the estimation unit 24. Specifically, the search unit 25 obtains, as the related information, past transaction information stored in the memory unit 23 using pieces of information linked with each other in the data structure 31 relating to account titles. Furthermore, the search unit 25 obtains, as the related information, the reference material and the past transaction information stored in the memory unit 23 using transaction information and the estimated account title. Furthermore, the search unit 25 searches for image data similar to the obtained image data and obtains, as the related information, past transaction information pertaining to the similar image data.
The presentation unit 26 presents one or more account titles and reliability thereof estimated by the estimation unit 24 and related information retrieved by the search unit 25. As an example, as illustrated in
The presentation unit 26 displays related information retrieved by the search unit 25 at the related information of the account title display screen 40. As an example, as illustrated in
When the pressing down of the link 41 pertaining to the past transaction information is detected, the presentation unit 26 displays a history display screen 50 illustrated in
Furthermore, in the account title display screen 40 illustrated in
Furthermore, in the account title display screen 40 illustrated in
Furthermore, the presentation unit 26 presents, as related information, a presentation sentence regarding a condition relating to the account title using the data structure 32 relating to conditions illustrated in
Therefore, the related information has a plurality of modes depending on the attribute of the related information as “history 1” illustrated in
Note that the data structure 31 relating to account titles and the data structure 32 relating to conditions according to the present exemplary embodiment may be generated in advance by a user by setting pieces of information in such a manner as to be linked with each other or may be generated as a result of learning of past transaction information by the estimation unit 24. Furthermore, information pertaining to the data structure 31 relating to account titles and the data structure 32 relating to conditions may be added, modified, or changed by a user or may be added, modified, or changed as a result of learning by the estimation unit 24.
Next, referring to
In step S101, the CPU 11 obtains transaction information from image data or the like input by a user.
In step S102, the CPU 11 makes an estimate of the account title using the transaction information.
In step S103, the CPU 11 determines whether or not there is a data structure 32 relating to conditions for the estimated account title. When there is a data structure 32 relating to conditions (step S103: YES), the CPU 11 proceeds to step S104. On the other hand, when there is no data structure 32 relating to conditions (step S103: NO), the CPU 11 proceeds to step S105.
In step S104, the CPU 11 executes a process to generate a presentation sentence relating to a condition as related information. Note that the process to generate related information relating to a condition is described in detail using
In step S105, the CPU 11 searches past transaction information, reference materials, and a data structure 31 relating to the account title, which are stored, for information relating to the account title as the related information and generates a presentation sentence relating to the account title.
In step S106, the CPU 11 determines whether or not there is another estimated account title. When there is no other account title (step S106: YES), the CPU 11 proceeds to step S107. On the other hand, when there is another account title (step S106: NO), the CPU 11 obtains another account title and proceeds to step S103.
In step S107, the CPU 11 presents the generated presentation sentence as related information.
Next, referring to
In step S201, the CPU 11 obtains the data structure 32 relating to conditions for the estimated account title.
In step S202, the CPU 11 obtains a prerequisite condition from the data structure 32 relating to conditions.
In step S203, the CPU 11 derives information relating to the prerequisite condition from transaction information and determines whether or not the derived information satisfies the prerequisite condition. When the prerequisite condition is satisfied (step S203: YES), the CPU 11 proceeds to step S205. On the other hand, when the prerequisite condition is not satisfied (step S203: NO), the CPU 11 proceeds to step S204.
In step S204, the CPU 11 generates a presentation sentence for satisfaction of the condition. Here, the presentation sentence for satisfaction of a condition is a presentation sentence relating to transaction information that did not satisfy a prerequisite condition or a compulsory condition. For example, when the condition is not satisfied because the profit and loss is “loss” in the data structure 32 relating to conditions illustrated in
In step S205, the CPU 11 determines whether or not there is another prerequisite condition in the data structure 32 relating to conditions. When there is no other prerequisite condition in the data structure 32 relating to conditions (step S205: YES), the CPU 11 proceeds to step S206. On the other hand, when there is another prerequisite condition in the data structure 32 relating to conditions (step S205: NO), the CPU 11 proceeds to step S202.
In step S206, the CPU 11 obtains a compulsory condition from the data structure 32 relating to conditions.
In step S207, the CPU 11 derives information relating to the compulsory condition from transaction information and determines whether or not the derived information satisfies the compulsory condition. When the compulsory condition is satisfied (step S207: YES), the CPU 11 proceeds to step S208. On the other hand, when the compulsory condition is not satisfied (step S207: NO), the CPU 11 proceeds to step S204.
In step S208, the CPU 11 determines whether or not there is another compulsory condition in the data structure 32 relating to conditions. When there is no other compulsory condition in the data structure 32 relating to conditions (step S208: YES), the CPU 11 proceeds to step S209. On the other hand, when there is another compulsory condition in the data structure 32 relating to conditions (step S208: NO), the CPU 11 proceeds to step S206 and obtains another compulsory condition.
In step S209, the CPU 11 generates a presentation sentence for the case where a condition is satisfied. Here, the presentation sentence for the case where a condition is satisfied is a presentation sentence relating to transaction information that satisfied requirements of a prerequisite condition and a compulsory condition in the data structure 32 relating to conditions. For example, when the prerequisite condition and the compulsory condition in the data structure 32 relating to conditions illustrated in FIG. 4 are satisfied, the presentation sentence “The blue return system allows one-time depreciation of the fixed assets” is generated. Furthermore, when a specific numerical value of profit or the like is derived, the presentation sentence “When making profit, the tax amount can be reduced by depreciation. Currently, the profit is XX.” is generated. Here, a derived numerical value is entered in “XX”.
As described above, the present exemplary embodiment may allow the account titles and the information for assessing the account titles to be presented.
Note that the present exemplary embodiment is described using the embodiment in which the account title is estimated by using the transaction information extracted from the image data. However, the exemplary embodiment is not limited thereto. The account title may alternatively be estimated from the type of a document by analyzing the type of a document from a layout of the document depicted in the image data. That is to say, information representing the layout of a document may be linked with the account title in the data structure relating to account titles according to the present exemplary embodiment, and the account title may be estimated from the information representing the layout of a document.
Furthermore, the data structure according to the present exemplary embodiment is described using the embodiment in which as information, words such as “buildings”, “repair expense”, and the like are linked with each other. However, the exemplary embodiment is not limited thereto. As the information, pieces of image data may be linked with each other, or contents described in reference materials such as accounting rules, the statute book, and the like and pages describing such contents may be linked with each other.
Although the present disclosure has been described using the exemplary embodiment described above, the present disclosure is not limited to the scope described in the exemplary embodiment described above. Various changes and improvements may be made to the exemplary embodiment without departing the scope of the present disclosure, and configurations obtained by making these changes and improvements are also included in the technical scope of the present disclosure.
In the exemplary embodiments above, the term “processor” refers to hardware in a broad sense. Examples of the processor include general processors (e.g., CPU: Central Processing Unit) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, and programmable logic device).
In the embodiments above, the term “processor” is broad enough to encompass one processor or plural processors in collaboration which are located physically apart from each other but may work cooperatively. The order of operations of the processor is not limited to the one described in the embodiment above and may be changed.
Furthermore, the present exemplary embodiment is described using the embodiment in which the information processing program is installed in the storage 14. However, the exemplary embodiment is not limited thereto. The information processing program according to the present exemplary embodiment may alternatively be provided in the form of a computer readable storage medium storing the information processing program according to the present exemplary embodiment. For example, the information processing program according to the present disclosure may be provided in the form of an optical disc such as a compact disc (CD)-ROM, a digital versatile disc (DVD)-ROM, or the like, storing the information processing program according to the present disclosure. The information processing program according to the present disclosure may be provided in the form of a semiconductor memory such as a universal serial bus (USB) memory, a memory card, or the like, storing the information processing program according to the present disclosure. Alternatively, the information processing program according to the present exemplary embodiment may be obtained from an external apparatus via a communication channel connected to the communication I/F 17.
The foregoing description of the exemplary embodiments of the present disclosure has been provided for the purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Obviously, many modifications and variations will be apparent to practitioners skilled in the art. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, thereby enabling others skilled in the art to understand the disclosure for various embodiments and with the various modifications as are suited to the particular use contemplated. It is intended that the scope of the disclosure be defined by the following claims and their equivalents.
Number | Date | Country | Kind |
---|---|---|---|
2020-214206 | Dec 2020 | JP | national |