Accounting system
The accounting system addresses inefficiencies in voucher processing by using a language model to automate the collation and registration of voucher and transaction data, significantly improving work efficiency and reducing errors.
Patent Information
- Application Number
- JP2024215434
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-12-15
- Filing Date
- 2024-12-10
- Publication Date
- 2025-06-26
AI Technical Summary
Existing accounting systems face inefficiencies in processing vouchers, as they require manual verification of paper vouchers, leading to low work efficiency and potential input errors.
An accounting system utilizing a language model to automate the processing of vouchers by collating transaction data with voucher data, identifying matches, extracting additional information, and registering it in the database.
The system enhances the efficiency of accounting processes by automating the association of paper vouchers with transaction data and registering additional information, thereby reducing manual labor and errors.
Smart Images

Figure 2025096211000001_ABST
Abstract
Description
Technical Field
[0001] One aspect of the present invention relates to an information processing method, an information processing apparatus, and an information processing system. One aspect of the present invention relates to an information processing method and an information processing system using a language model. Specifically, one aspect of the present invention relates to an accounting system using a language model.
[0002] Note that one aspect of the present invention is not limited to the above technical field. Examples of the technical field of one aspect of the present invention include semiconductor devices, display devices, light-emitting devices, power storage devices, storage devices, electronic devices, lighting devices, input devices (for example, touch sensors), input / output devices (for example, touch panels), their driving methods, or their manufacturing methods.
Background Art
[0003] As accounting processes related to vouchers, there are accounting data input operations, auditing operations for accounting reports, and the like. Accounting software that supports voucher accounting processes is becoming more widespread. However, since vouchers are often in paper form, these operations need to be performed while checking each voucher one by one even when using accounting software. Therefore, the work efficiency is low, and there is also a possibility of input errors.
[0004] To improve the work efficiency related to paper vouchers and reduce input errors, various software has been developed. For example, Patent Document 1 discloses a system that can determine whether there is an error in optical character recognition (OCR) when a paper voucher is captured as image data and OCR is performed on the image data.
Prior Art Documents
Patent Documents
[0005]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0006] Even when using accounting software having the functions as described above, there are still many areas for improvement in the accounting processes related to vouchers.
[0007] For example, there may be information described in paper vouchers but not in the transaction data registered in the database. Such information needs to be added to the transaction data again. Also, there may be cases where, despite the information necessary for accounting, both the vouchers and the transaction data are lacking. In such cases, it is necessary to inquire about the missing information to any of the relevant parties such as the supplier, the customer, or the accounting department.
[0008] In any case, the judgment and work of the accounting staff are required, leading to a decrease in work efficiency.
[0009] Therefore, one aspect of the present invention is to provide a system, software, information processing apparatus, or accounting processing method capable of enhancing the efficiency of accounting processes related to vouchers. Another aspect of the present invention is to provide a system, software, information processing apparatus, or accounting processing method capable of enhancing the efficiency of associating paper vouchers with transaction data registered in a database. Another aspect of the present invention is to provide a system, software, information processing apparatus, or accounting processing method capable of enhancing the efficiency of registering the information described in paper vouchers in a database. Another aspect of the present invention is to provide a system, software, information processing apparatus, or accounting processing method capable of supporting the fulfillment of information necessary for accounting.
[0010] Note that the description of these problems does not preclude the existence of other problems. Note that one aspect of the present invention does not need to solve all of these problems. Note that other problems will become apparent from the descriptions in the specification, drawings, claims, etc., and it is possible to extract these other problems from the descriptions in the specification, drawings, claims, etc.
Means for Solving the Problems
[0011] One aspect of the present invention is an accounting system having a reception unit, a first processing unit, a database, and a second processing unit. The reception unit has a function of receiving voucher data and a function of receiving approval or disapproval of a proposal presented from the first processing unit. The second processing unit has a function of performing processing using a language model. The first processing unit has a first function and a second function. The first function is to acquire a plurality of transaction data for which vouchers are not registered from the database, create a first instruction statement, and the first instruction statement is to collate the plurality of transaction data with the voucher data and instruct to identify the transaction data that matches the voucher data. The first instruction statement is input to the second processing unit, and a first output is acquired from the second processing unit. From the first output, a proposal for associating the voucher data with the transaction data is presented to the reception unit, and the association approved by the reception unit is registered in the database. The second function is to create a second instruction statement, and the second instruction statement is to instruct to extract additional information included in the voucher data and not included in the transaction data. The second instruction statement is input to the second processing unit, and a second output is acquired from the second processing unit. From the second output, the function is to register the additional information in the transaction data.
[0012] Also, in the above, it is preferable that the additional information is one or more selected from name, name of organization, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information.
[0013] In addition, in the above, the first processing unit has a third function, and the third function is not included in the combination of the transaction data and the voucher data for which the association is registered, and extracts items necessary for accounting and presents them to the reception unit as deficiency information. This is preferably the function.
[0014] In addition, in the above, the first processing unit has a fourth function, and the fourth function creates a third instruction statement. The third instruction statement collates the deficiency information and the transaction data, and generates a statement that instructs to generate a sentence requesting the input of the deficiency information. It is preferably the function of inputting the third instruction statement into the second processing unit, obtaining the third output from the second processing unit, and presenting the third output to the reception unit.
[0015] Another aspect of the present invention is an accounting system having a reception unit and a processing unit. The reception unit has a function of receiving voucher data and a function of receiving approval or disapproval of a proposal presented from the processing unit. The processing unit has a database in which transaction data is stored, and has a first function and a second function. The first function acquires a plurality of transaction data for which vouchers are not registered from the database, collates the plurality of transaction data with the voucher data, identifies the transaction data that matches the voucher data, presents a proposal to link the voucher data and the transaction data to the reception unit, and registers the association approved by the reception unit in the database. The second function extracts additional information included in the voucher data and not included in the transaction data, and registers the additional information in the transaction data.
[0016] In addition, in the above, the additional information is preferably one or more selected from name, title, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information.
[0017] In addition, in the above, the processing unit has a third function, and the third function is not included in the combination of the transaction data and the voucher data for which the association is registered, and extracts items necessary for accounting and presents them to the reception unit as deficiency information. This is preferably the function.
[0018] Further, in the above, the processing unit has a fourth function, and the fourth function preferably collates shortage information with transaction data, generates a sentence requesting input of the shortage information, and presents the sentence requesting input of the shortage information to the receiving unit.
Advantages of the Invention
[0019] According to one aspect of the present invention, it is possible to provide software capable of improving the efficiency of accounting processing related to vouchers. Further, one aspect of the present invention can provide software capable of improving the efficiency of linking paper vouchers with transaction data registered in a database. Further, one aspect of the present invention can provide software capable of improving the efficiency of registering information described on paper vouchers in a database. Further, one aspect of the present invention can provide software capable of supporting the fulfillment of information necessary for accounting.
[0020] Note that the effects of one aspect of the present invention are not limited to the effects listed above. The effects listed above do not prevent the existence of other effects. Note that other effects are effects not mentioned in this item as described below. Effects not mentioned in this item can be derived by those skilled in the art from the descriptions in the specification, drawings, etc., and can be appropriately extracted from these descriptions. Note that one aspect of the present invention has at least one of the effects listed above and / or other effects. Therefore, one aspect of the present invention may not have the effects listed above in some cases.
Brief Description of the Drawings
[0021]
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
[0022] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be easily understood by those skilled in the art that the form and details can be variously changed without departing from the spirit and scope of the present invention. Therefore, the present invention should not be construed as being limited to the description of the embodiments shown below.
[0023] In the configuration of the invention described below, the same reference numerals are commonly used among different drawings for the same part or parts having the same or similar functions, and the repeated description thereof will be omitted. In addition, when referring to similar functions, the hatch patterns may be the same, and there may be cases where no particular reference numerals are attached.
[0024] Also, the positions, sizes, ranges, etc. of the respective configurations shown in the drawings may not represent the actual positions, sizes, ranges, etc. for the sake of simplicity of understanding. For this reason, the disclosed invention is not necessarily limited to the positions, sizes, ranges, etc. disclosed in the drawings.
[0025] In addition, it should be noted that the ordinal numbers "first", "second", and "third" used in this specification are for avoiding confusion of components and are not numerically limiting.
[0026] In this specification and the like, the character string information described in the voucher may simply be referred to as the voucher. In other words, when simply referring to the voucher, it may refer to the character string information described in the voucher.
[0027] (Embodiment 1) In this embodiment, an accounting system according to an aspect of the present invention will be described with reference to FIGS. 1(A) to 5.
[0028] <Accounting System> First, the configuration and functions of an accounting system according to an aspect of the present invention will be described with reference to FIGS. 1(A) and 1(B). An accounting system according to an aspect of the present invention is a system for collating a plurality of transaction data and voucher data, identifying and associating the transaction data that matches the voucher data, and extracting and registering additional information that is included in the voucher data but not included in the transaction data.
[0029] The accounting system includes at least a processing unit. FIG. 1(A) is a diagram showing the configuration of the accounting system 100. The accounting system 100 includes a first processing unit 101, a second processing unit 102, a reception unit 103, and a database 104. In the drawings attached to this specification, the components are classified by function and shown as independent blocks in a block diagram. However, it is difficult to completely separate the actual components by function, and one component may be related to multiple functions. Also, one function may be related to multiple components. For example, the processing performed by the first processing unit 101 or the second processing unit 102 may be executed on different servers depending on the processing.
[0030] The accounting system 100 can be provided in an information processing apparatus such as a computer used by a user. Alternatively, a first processing unit 101, a second processing unit 102, a database 104, etc. can be provided in a server, and it can be used via a network 120 from a client PC that functions as a reception unit 103.
[0031] The reception unit 103 has a function of receiving data. Such data includes accounting data including voucher data and transaction data, text data, etc. The reception unit 103 has a function of receiving at least voucher data. Further, the reception unit 103 has a function of receiving approval or disapproval from the user for a proposal presented from the first processing unit 101. Also, it has a function of receiving confirmation from the user for the content presented from the first processing unit 101. As the reception unit 103, for example, a communication port may be used, or an input device such as a computer equipped with a communication function, a display screen, an input device, etc. may be used.
[0032] In the present embodiment, the voucher data is image data of a voucher or character data (also referred to as string data) extracted therefrom by optical character recognition (OCR). The voucher data may include misrecords etc. resulting from OCR reading errors. Also, there may be cases where there are variations in notation between the voucher data and the transaction data even though they indicate the same content. In this specification etc., variation in notation refers to a state where notations are mixed for words having the same meaning or content. For example, there may be cases where different character types such as hiragana, katakana, and kanji are mixed, cases where different kanji fonts such as old-style and new-style kanji are mixed, cases where different furigana are mixed, cases where abbreviations and official names are mixed, etc.
[0033] Also, the transaction data is information such as name, company name, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information. Instead of consumption tax, value-added tax, sales tax, commodity tax, value-added tax, or business tax, etc. can also be used. Further, information such as registration source, transaction means, overview, ledger account, and subsidiary account may be added.
[0034] The transaction data and the voucher data are preferably included in a format that can be expressed as a character string such as CSV format, TSV format, JSON format, HTML format, etc.
[0035] For example, the reception unit 103 has a function of receiving voucher data. Or the reception unit 103 has a function of receiving image data of a voucher. Or the reception unit 103 has a function of receiving character data extracted from a voucher.
[0036] The database 104 has a function of registering accounting data including transaction data. Also, the database 104 has a function of registering voucher data. It also has a function of registering the association between certain transaction data and certain voucher data. These transaction data may lack information necessary for accounting for various reasons such as before the transaction is completed or there are input deficiencies.
[0037] The second processing unit 102 has a function of performing processing using a language model. The language model can also be referred to as a large language model (LLM), a text generation model, a dialogue model, etc. A large language model is a natural language processing model trained using a large amount of data. With a large language model, for example, a dialogue model that answers user instructions can be realized. For example, large language models such as GPT-3, GPT-3.5, GPT-4 (registered trademark), LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), Llama2, etc. can be used.
[0038] The first processing unit 101 has a function of acquiring the data received by the reception unit 103. It also has a function of accessing the database 104 and acquiring a plurality of transaction data. It also has a function of creating an instruction text for input to the second processing unit 102. It also has a function of inputting the instruction text to the second processing unit 102 and acquiring an output from the second processing unit 102. It also has a function of presenting the information obtained from the output to the reception unit 103. The first processing unit 101 has at least a first function including the above combination of functions and a second function.
[0039] As a first function, the first processing unit 101 has a function of acquiring a plurality of transaction data in which vouchers are not registered from the database 104. It may acquire all transaction data in which vouchers are not registered, but it is preferable in terms of processing speed to acquire only a part. For example, it is preferable that the transaction data is limited transaction data such as the period during which the transaction data was registered. Also, when limiting by conditions such as the registered period, it is also possible to acquire the transaction data including the transaction data in which vouchers are registered. In this case, when collating the vouchers and the transaction data in a later process, if a certain transaction data has already been registered, it is possible to present that fact to the reception unit 103. The conditions such as the registered period can be specified by the user in advance.
[0040] Also, as a first function, the first processing unit 101 has a function of creating a first instruction text. The instruction text is also called a prompt. The first instruction text preferably includes content instructing the second processing unit 102 to collate a plurality of transaction data acquired from the database and voucher data acquired from the reception unit 103 and identify the transaction data that matches the voucher data. The first instruction text preferably includes a plurality of transaction data in a format that can be expressed as a character string acquired from the database and the voucher data. By including these data in the first instruction text, the second processing unit 102 can output an answer through natural language processing.
[0041] Since the voucher data may contain incorrect entries, notation variations, etc., in addition to the above, it is preferable that the first instruction text includes instructions to report any non - match in the case where the voucher data does not exactly match the transaction data. Note that in this case, exact match means an exact match of the content of a certain item included in the transaction data, not an exact match of all items.
[0042] Also, as a first function, the first processing unit 101 has a function of inputting the first instruction text to the second processing unit 102.
[0043] The second processing unit 102 has a function of generating an answer to the input instruction text through processing using a language model and outputting the answer. By using a large - scale language model, even if there are incorrect entries, notation variations, etc. resulting from reading errors, it is possible to output, as the answer, the result of performing appropriate data collation after recognizing that these are incorrect entries and notation variations. Here, the answer to the first instruction text is taken as the first output. It is preferable that the first output includes the combination of transaction data that matches the voucher data if it can be identified, or a statement to that effect if it cannot be identified. Also, it is preferable that the content pointing out any incorrect entries, notation variations, etc. is included.
[0044] Also, as a first function, the first processing unit 101 has a function of obtaining the first output from the second processing unit 102.
[0045] When the combination of the matched voucher data and transaction data is included in the first output, the reception unit 103 has a function of presenting a proposal to associate the voucher data and the transaction data. Also, it is preferable that the first processing unit 101 has a function of presenting the pointed - out incorrect entries, notation variations, etc. to the reception unit 103 when there are such pointed - out issues in the first output.
[0046] The user can approve or disapprove the proposal to associate the voucher data and transaction data presented by the reception unit 103.
[0047] The reception unit 103 also has a function of receiving approval or disapproval from the user. It also has a function of receiving confirmation from the user regarding the content presented by the first processing unit 101. The approval or disapproval and confirmation of the user can be performed via the input device 130.
[0048] As a first function, the first processing unit 101 also has a function of registering in the database 104 the association between the credential data and the transaction data that the reception unit 103 has received approval for.
[0049] Furthermore, as a second function, the first processing unit 101 has a function of creating a second instruction statement. The second instruction statement preferably includes content instructing to extract additional information that is included in the credential data and not included in the transaction data among the combinations of the credential data and the transaction data for which the association has been registered. The additional information is, for example, one or more selected from the name, title, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information. It may also be one or more selected from the registration source, transaction means, overview, product name, account item, and subsidiary item.
[0050] Furthermore, as a second function, the first processing unit 101 has a function of inputting the second instruction statement to the second processing unit 102.
[0051] The second processing unit 102 has a function of generating an answer to the input instruction statement through processing using a language model and outputting the answer. Here, the answer to the second instruction statement is regarded as the second output. The second output preferably includes the additional information if there is any.
[0052] As a second function, the first processing unit 101 also has a function of obtaining the second output from the second processing unit 102.
[0053] As a second function, when there is additional information in the second output, the first processing unit 101 has a function of registering the additional information in the transaction data.
[0054] The registration of additional information may be performed after obtaining user approval. When obtaining user approval, it is preferable that the first processing unit 101 has, as a second function, a function of causing the reception unit 103 to present a proposal for additional information, and a function of registering the additional information received and approved by the reception unit 103 in the transaction data.
[0055] Furthermore, the first processing unit 101 can have a third function.
[0056] As a third function, it is preferable that the first processing unit 101 has a function of extracting items that are not included in the combination of the transaction data and the voucher data for which the association has been registered and are necessary for accounting, and presenting them to the reception unit 103 as deficiency information. Alternatively, as a third function, it is preferable that the first processing unit 101 has a function of extracting items that are not included in the transaction data and are necessary for accounting, and presenting them to the reception unit 103 as deficiency information.
[0057] Furthermore, the first processing unit 101 can have a fourth function.
[0058] As a fourth function, the first processing unit 101 has a function of creating a third instruction statement. The third instruction statement preferably includes content that instructs to collate the deficiency information obtained in the third function with the transaction data and generate a sentence requesting input of the deficiency information, etc. In this specification, etc., the "sentence" refers to something composed of one or more "sentences". Therefore, the "sentence" also includes the "sentence".
[0059] Also, as a fourth function, the first processing unit 101 has a function of inputting the third instruction statement to the second processing unit 102.
[0060] The second processing unit 102 has a function of generating an answer to the input instruction sentence through processing using a language model and outputting the answer. By using a large language model, a natural sentence can be created. Here, the answer to the third instruction sentence is taken as the third output. The third output preferably includes, for example, information such as contact details and names cited from transaction data and a sentence requesting notification of a registration number when the registration number is insufficient. Also, when there is a discrepancy in the amount, it preferably includes information such as contact details and names cited from transaction data and a sentence requesting confirmation regarding the amount.
[0061] Also, as a fourth function, the first processing unit 101 has a function of acquiring the third output from the second processing unit 102.
[0062] Also, as a fourth function, the first processing unit 101 has a function of presenting the third output at the reception unit 103.
[0063] The user can use the sentence of the third output presented at the reception unit 103 to request the relevant parties to supply the information necessary for accounting.
[0064] FIG. 1(B) is a diagram showing the configuration of the first processing unit 101. As shown in FIG. 1(B), the first processing unit 101 may include a data processing unit 101a, an instruction sentence processing unit 101b, and a display processing unit 101c.
[0065] The data processing unit 101a has a function of accessing the database 104 and acquiring and registering data.
[0066] The instruction sentence processing unit 101b has a function of creating an instruction sentence to be input to the second processing unit 102. It also has a function of acquiring an output from the second processing unit 102 and creating or extracting data. For example, it has functions such as creating data related to a display to be created by the display processing unit 101c and extracting data for registration in the database 104.
[0067] The display processing unit 101c has a function of creating display content to be presented to the reception unit 103 and a function of acquiring the content received by the reception unit 103.
[0068] In the first processing unit 101 shown in FIG. 1(B), it is classified according to each function that the first processing unit 101 has and is independent of each other. However, some or all of the functions that the first processing unit 101 has do not have to be independent. Further, the configuration of the processing unit according to an aspect of the present invention is not limited to the configuration of the first processing unit 101 shown in FIG. 1(B).
[0069] The network 120 shown in FIG. 1(A) is a computer network such as the Internet, which is the basis of the World Wide Web (WWW), an intranet, an extranet, a PAN (Personal Area Network), a LAN (Local Area Network), a CAN (Campus Area Network), a MAN (Metropolitan Area Network), a WAN (Wide Area Network), a GAN (Global Area Network), etc. Note that the network 120 includes wired or wireless communication. Further, the network 120 includes a bus such as a USB (Universal Serial Bus) and short-range wireless communication such as Bluetooth (registered trademark).
[0070] The input device 130 has a function of reading a document such as a paper medium and generating it as an electronic document. As the input device 130, for example, an image scanner, a digital camera, etc. can be used. In the present embodiment, the document is, for example, a certificate.
[0071] The optical character reader 110 has a function of extracting a character string (character string that has been imaged) included in an image as text data from the image data by OCR.
[0072] For example, an image scanner can be used as the input device 130, and by combining it with the optical character reader 110, paper-based vouchers can be converted into voucher files containing text data.
[0073] Alternatively, the input device 130 may be a device for inputting data. As the input device 130, for example, a keyboard, a pointing device, a touch panel, etc. can be used. By using the input device 130, the user can input accounting data and the like.
[0074] The output device 140 has a function of outputting the data output from the first processing unit 101. As the output device 140, for example, a display, a projector, a printer, an audio output device, a memory, etc. can be used.
[0075] The above is the description of the configuration and functions of the accounting system 100. By having such a configuration and functions, it is possible to provide a system for collating a plurality of transaction data and voucher data, identifying and associating the transaction data that matches the voucher data, and extracting and registering additional information that is included in the voucher data but not in the transaction data.
[0076] <Accounting processing method> Next, an example of an accounting processing method using the accounting system 100 according to an aspect of the present invention will be described with reference to the flowcharts of FIGS. 2 and 3. FIGS. 2 to 5 are also flowcharts for explaining the flow of processing executed by the accounting system according to an aspect of the present invention.
[0077] In the accounting processing method shown in FIGS. 2 and 3, paper-based vouchers are prepared before starting. The vouchers may be one, but it is preferable to have a plurality to improve the efficiency of accounting processing.
[0078] Also, a plurality of transaction data registered in the database 104 are prepared.
[0079] The accounting processing method shown in FIGS. 2 and 3 includes at least steps S101 to S116, steps S209 to S210, step S220, and step S401.
[0080] Step S101 shown in FIG. 2 is a step in which a user causes a paper medium voucher to be read. For example, using an input device 130 such as an image scanner and an optical character reader 110, the paper medium voucher can be read and converted into voucher data in a form that can be expressed as a character string. Alternatively, the voucher data may be input using a keyboard as the input device 130.
[0081] Step S102 is a step in which the reception unit 103 receives the voucher data. When there is a plurality of voucher data, all the voucher data is received.
[0082] Step S103 is a step in which the first processing unit 101 selects the voucher data to be collated. When there is a plurality of received voucher data, one of the unprocessed ones is selected.
[0083] Step S104 is a step in which the first processing unit 101 acquires a plurality of transaction data for which vouchers are not registered from the database 104. Although it is possible to acquire all the transaction data for which vouchers are not registered, it is preferable in terms of processing speed to acquire only a part. For example, it is preferable that the transaction data is limited transaction data such as the period during which the transaction data was registered. Also, when limiting by conditions such as the registered period, it is also possible to acquire the transaction data including the transaction data for which vouchers are registered.
[0084] Step S105 is a step in which the first processing unit 101 creates a first instruction statement and inputs it to the second processing unit 102. The first instruction statement preferably includes content that instructs the second processing unit 102 to collate a plurality of transaction data obtained from the database with the voucher data received by the reception unit 103 and identify the transaction data that matches the voucher data. The first instruction statement preferably includes a plurality of transaction data in a form that can be expressed as a character string, which is obtained from the database, and the voucher data. By including these data in the first instruction statement, the second processing unit 102 can output an answer only by natural language processing. Furthermore, since the voucher data may include misrecords, notation variations, etc., the first instruction statement preferably includes content that instructs to report when it does not exactly match the transaction data.
[0085] Step S106 is a step in which the second processing unit 102 outputs a first output, which is an answer to the input first instruction statement. By using a large language model, even if misrecords, notation variations, etc. resulting from reading errors are included, after recognizing that these are misrecords and notation variations, the result of performing appropriate data collation can be output as an answer. That is, step S106 can also be said to be a step of collating data. The first output preferably includes the combination when the transaction data that matches the voucher data can be identified, and the fact that it cannot be identified when it cannot be identified. Also, when there are misrecords, notation variations, etc., it preferably includes content that points them out.
[0086] Step S107 is a step in which the first processing unit 101 obtains the first output from the second processing unit 102 and determines whether the transaction data that matches the voucher data can be identified. If the first processing unit 101 determines that it can be identified (Yes), it proceeds to step S108. If the first processing unit 101 determines that it cannot be identified (No), it proceeds to step S208 in FIG. 3 as indicated by the connector A.
[0087] Step S108 shown in FIG. 2 is a step in which the receiving unit 103 presents a proposal to associate the credential data identified as matching in step S107 with the transaction data. As an example of the presentation method, the display content created by the display processing unit 101c is displayed on the display screen of the receiving unit 103. Further, when there are pointed out misstatements, notation variations, etc. in the first output, it is preferable to also present such pointed out content to the receiving unit 103.
[0088] Step S109 is a step in which the user approves or disapproves the proposal to associate the credential data and the transaction data presented by the receiving unit 103. If approved (Yes), the process proceeds to step S110. If disapproved (No), the process proceeds to step S220.
[0089] Step S110 is a step in which the receiving unit 103 receives the approval of the user.
[0090] Step S111 is a step in which the first processing unit 101 registers the association between the credential data and the transaction data, which the receiving unit 103 has received approval for, in the database 104.
[0091] Step S112 is a step in which the first processing unit 101 creates a second instruction statement and inputs it to the second processing unit 102. The second instruction statement preferably includes content instructing to extract additional information that is included in the credential data and not included in the transaction data among the combinations of the credential data and the transaction data for which the association has been registered. The additional information is, for example, one or more selected from name, title, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information. It may also be one or more selected from registration source, transaction means, overview, product name, account item, and subsidiary account item.
[0092] Step S113 is a step in which the second processing unit 102 outputs a second output that is an answer to the input second instruction statement. The second output preferably includes the additional information if there is any.
[0093] Step S114 is a step in which the first processing unit 101 acquires the second output from the second processing unit 102 and determines whether there is additional information in the second output. If the first processing unit 101 determines that there is additional information, it proceeds to step S115. If the first processing unit 101 determines that there is no additional information, it proceeds to step S116.
[0094] Step S115 is a step in which the first processing unit 101 registers the additional information in the transaction data on the database 104. Note that, between step S114 and step S115, a step of receiving approval or disapproval from the user for the registration of the additional information may be added.
[0095] Step S116 is a step in which the first processing unit 101 determines whether there is voucher data to be processed next, that is, whether there is unprocessed voucher data among the voucher data received in step S102. If the first processing unit 101 determines that there is voucher data to be processed next, it proceeds to step S103. If the first processing unit 101 determines that there is no voucher data to be processed next, it proceeds to step S401.
[0096] Step S220 is a step in which the reception unit 103 receives the user's disapproval.
[0097] Step S401 is a step in which the user confirms the end of the accounting process.
[0098] Step S208 shown in FIG. 3 is a step in which the reception unit 103 presents that no transaction data matching the voucher data has been identified.
[0099] Step S209 is a step in which the user confirms that no transaction data matching the voucher data has been identified.
[0100] Step S210 is a step in which the reception unit 103 receives the user's confirmation. After step S210, it proceeds to step S116 in FIG. 2 as shown by the connector B.
[0101] Steps S103 to S108 and step S110 enable the first function of the first processing unit 101 described above. Also, steps S112 to S115 enable the second function.
[0102] The above is an explanation of an example of the accounting processing method. Note that the accounting processing method according to one aspect of the present invention is not limited to the method described with reference to FIGS. 2 and 3. For example, it is more preferable to adopt an accounting processing method in which the steps shown in FIG. 4 or FIG. 5 are added to the above.
[0103] FIG. 4 is a flowchart for explaining steps S301 to S404, which are added between step S115 and step S116 shown in FIG. 2.
[0104] Step S301 is a step in which the first processing unit 101 determines whether there is any item that is not included in the deficiency information, that is, the combination of transaction data and voucher data for which the association is registered, and is necessary for accounting. If the first processing unit 101 determines that there is deficiency information, it proceeds to step S303. If the first processing unit 101 determines that there is no deficiency information, it proceeds to step S116.
[0105] Step S303 is a step in which the reception unit 103 presents the deficiency information to the user.
[0106] Step S404 is a step in which the user confirms the deficiency information.
[0107] Steps S301 and S303 enable the third function described above.
[0108] FIG. 5 is a flowchart for explaining steps S301 to S310, which are added between step S115 and step S116 shown in FIG. 2. Steps 301 and 303 can be referred to for the description of FIG. 3.
[0109] Step S304 is a step of determining whether the user creates a sentence requesting to fill in the deficiency information. If creating, proceed to step S306. If not creating, proceed to step S116.
[0110] Step S306 is a step in which the first processing unit 101 creates a third instruction sentence and inputs it to the second processing unit 102. The third instruction sentence preferably includes content instructing to collate the deficiency information obtained by the third function with the transaction data and generate a sentence requesting input of the deficiency information or the like.
[0111] Step S307 is a step in which the second processing unit 102 outputs a third output which is an answer to the input third instruction sentence. The third output preferably includes, for example, a contact and name etc. quoted from the transaction data and a sentence requesting to notify the registration number when the registration number is insufficient. Also, when there is a discrepancy in the amount, it preferably includes a contact and name etc. quoted from the transaction data and a sentence requesting confirmation regarding the amount.
[0112] Step S308 is a step in which the first processing unit 101 acquires the third output.
[0113] Step S309 is a step in which the reception unit 103 presents the third output. The user acquires the sentence of the third output presented by the reception unit 103 (step S310), and can request the relevant parties to fill in the information necessary for accounting.
[0114] This embodiment can be implemented in appropriate combination with at least some of the other embodiments described in this specification.
[0115] (Embodiment 2) In this embodiment, another example of the accounting system according to one aspect of the present invention will be described with reference to FIGS. 6 to 8.
[0116] <Another example of the accounting system> The accounting system according to one aspect of the present invention is not limited to the configuration and functions shown in Embodiment 1. For example, the first processing unit 101, the second processing unit 102, and the database 104 may not be separated from each other.
[0117] FIG. 6(A) is a diagram showing the configuration of the accounting system 100A. The accounting system 100A includes a reception unit 103 and a processing unit 105. The processing unit 105 has the functions of the first processing unit 101, the second processing unit 102, and the database 104. Elements with the same reference numerals as those in the accounting system 100 have common configurations and functions, and the description in Embodiment 1 can be referred to.
[0118] The accounting system 100A can access the processing unit 105 via the network 120 from, for example, a client PC that functions as the reception unit 103.
[0119] FIG. 6(B) is a diagram showing the configuration of the processing unit 105. As shown in FIG. 6(B), the processing unit 105 may include a data processing unit 105a, an instruction text processing unit 105b, a display processing unit 105c, a response generation unit 105d, and a database 105e.
[0120] The data processing unit 105a has a function of accessing the database 105e and acquiring and registering data.
[0121] The instruction text processing unit 105b has a function of creating an instruction text. It also has a function of creating or extracting data from the output response.
[0122] The display processing unit 105c has a function of creating display content to be presented to the reception unit 103 and a function of acquiring the content received by the reception unit 103.
[0123] The response generation unit 105d has a function of performing processing using a language model. The description of the second processing unit 102 in the previous embodiment can be referred to.
[0124] The database 105e has a function of registering accounting data including transaction data. The database 105e also has a function of registering voucher data. The description of the database 104 in the previous embodiment can be referred to.
[0125] As a first function, the processing unit 105 has a function of acquiring a plurality of transaction data for which vouchers are not registered from the database 105e. It is possible to acquire all the transaction data for which vouchers are not registered, but it is preferable in terms of processing speed to acquire only a part. For example, it is preferable that the transaction data is limited transaction data such as the period during which the transaction data was registered. Also, when limiting by conditions such as the registered period, it is possible to acquire the transaction data including the transaction data for which vouchers are registered. In this case, when collating a certain voucher with the transaction data, if it has already been registered in a certain transaction data, it is possible to present that fact to the reception unit 103.
[0126] The processing unit 105 has a function of collating a plurality of transaction data acquired from the database with the voucher data acquired from the reception unit 103 and specifying the transaction data that matches the voucher data. It is also preferable to have a function of pointing out any misrecording, notation variation, etc.
[0127] For example, by using a large language model, even if there are misrecordings, notation variations, etc. resulting from reading errors, it is possible to perform appropriate data collation after recognizing that these are misrecordings and notation variations.
[0128] As a first function, the processing unit 105 also has a function of registering the association between the voucher data and the transaction data, which has been approved by the reception unit 103, in the database 105e.
[0129] As a second function, the processing unit 105 has a function of extracting additional information if there is any. As a second function, the processing unit 105 also has a function of registering the additional information in the transaction data if there is any.
[0130] In addition, the registration of additional information may be performed after obtaining user approval. When obtaining user approval, the processing unit 105 preferably has, as a second function, a function of causing the reception unit 103 to present a proposal for additional information, and a function of registering the additional information approved by the reception unit 103 in the transaction data.
[0131] Furthermore, the processing unit 105 can have a third function. As the third function, it preferably has a function of extracting items that are not included in the combination of the transaction data and the supporting data for which the association has been registered and are necessary for accounting, and presenting them to the reception unit 103 as deficiency information. Alternatively, as the third function, it preferably has a function of extracting items that are not included in the transaction data and are necessary for accounting, and presenting them to the reception unit 103 as deficiency information.
[0132] Furthermore, the processing unit 105 can have a fourth function. As the fourth function, it preferably has a function of collating the deficiency information obtained in the third function with the transaction data, generating a sentence requesting input of the deficiency information, etc., and presenting it at the reception unit 103.
[0133] <Another example of the accounting processing method> Next, an example of an accounting processing method using the accounting system 100A according to an aspect of the present invention will be described with reference to the flowcharts of FIGS. 3, 7, and 8. FIGS. 3, 7, and 8 are also flowcharts for explaining the flow of processing executed by the accounting system according to an aspect of the present invention.
[0134] In the present embodiment, the steps different from the accounting processing method described in Embodiment 1 will be mainly described. For the same steps, the description in Embodiment 1 can be referred to.
[0135] The accounting processing method shown in FIG. 7 has steps S503 to S507, step S511, step S512, and steps S514 to S516 as steps different from those in Embodiment 1. The accounting processing method shown in FIG. 7 has steps S503 to S508 instead of steps S103 to S108, and has steps S510 to S516 instead of steps S110 to S116, which is different from the accounting processing method described in Embodiment 1.
[0136] Step S503 shown in FIG. 7 is a step in which the processing unit 105 selects voucher data to be collated. When there are a plurality of received voucher data, one of the unprocessed ones is selected.
[0137] Step S504 is a step in which the processing unit 105 acquires a plurality of transaction data for which vouchers are not registered from the database 105e. Details can refer to the description of step S104.
[0138] Step S506 is a step in which the processing unit 105 acquires a plurality of transaction data for which vouchers are not registered from the database 105e, collates them with the voucher data acquired from the reception unit 103, and identifies the transaction data that matches the voucher data. At this time, it is preferable to perform the collation using a large language model. By using a large language model, even if there are misrecords, notation variations, etc. resulting from reading errors, it is possible to perform appropriate data collation after recognizing that these are misrecords and notation variations. Also, when there are misrecords, notation variations, etc., it is preferable to point them out.
[0139] Step S507 is a step in which the processing unit 105 determines whether transaction data that matches the voucher data can be identified as a result of the collation. If it is determined that it can be identified, the process proceeds to step S108. If it is determined that it cannot be identified, the process proceeds to step S208 in FIG. 3 as indicated by the connector A.
[0140] Step S511 is a step in which the processing unit 105 registers the association between the voucher data and the transaction data, which the reception unit 103 has received approval for, in the database 105e.
[0141] Step S512 is a step in which the processing unit 105 extracts additional information that is included in the voucher data but not in the transaction data from among the combinations of the voucher data and the transaction data for which the association has been registered. Details of the additional information can be referred to the description of step S112.
[0142] Step S514 is a step in which the processing unit 105 determines whether there is any additional information. If the processing unit 105 determines that there is additional information, it proceeds to step S515. If the processing unit 105 determines that there is no additional information, it proceeds to step S516.
[0143] Step S515 is a step in which the processing unit 105 registers the additional information in the transaction data on the database 105e.
[0144] Step S516 is a step in which the processing unit 105 determines whether there is any voucher data to be processed next. If the processing unit 105 determines that there is voucher data to be processed next, it proceeds to step S503. If the processing unit 105 determines that there is no voucher data to be processed next, it proceeds to step S401.
[0145] The above is an explanation of another example of the accounting processing method. Note that the accounting processing method according to an aspect of the present invention is not limited to the above, and for example, an accounting processing method with the steps shown in FIG. 8 added may be performed.
[0146] FIG. 8 is a flowchart for explaining step S601, step S303, step S304, step S607, step S309, and step S310, which are added between step S515 and step S516 shown in FIG. 7.
[0147] Step S601 is a step in which the processing unit 105 determines whether there is any missing information, that is, whether there is an item that is not included in the combination of transaction data and voucher data for which the association is registered and is necessary for accounting. If the processing unit 105 determines that there is missing information, the process proceeds to step S303. If the processing unit 105 determines that there is no missing information, the process proceeds to step S516.
[0148] Step S607 is a step in which the processing unit 105 collates the missing information and the transaction data, and generates a sentence requesting input of the missing information. At this time, it is preferable to perform the collation using a large language model. By using a large language model, a natural sentence can be created.
[0149] Regarding step S309 and step S310, the description in Embodiment 1 can be referred to.
[0150] This embodiment can be implemented in appropriate combination with at least a part of other embodiments described in this specification.
[0151] (Embodiment 3) In this embodiment, the details of the hardware that can be used in the accounting system according to an aspect of the present invention will be described.
[0152] [First Processing Unit 101] The first processing unit 101 has a function of performing processing using the data supplied from the reception unit 103, the second processing unit 102, the database 104, etc. The first processing unit 101 can supply the processing result to the reception unit 103, the second processing unit 102, the database 104, etc.
[0153] In the first processing unit 101, a transistor having a metal oxide in the channel formation region may be used. Since the off-current of the transistor is extremely small, by using the transistor as a switch for holding the charge (data) flowing into the capacitive element that functions as a memory element, the data holding period can be ensured over a long term. By using this characteristic in at least one of the register and the cache memory included in the first processing unit 101, the first processing unit 101 can be operated only when necessary, and in other cases, the first processing unit 101 can be turned off by saving the information of the previous process in the memory element. That is, normally-off computing becomes possible, and power consumption of the accounting system can be reduced.
[0154] Note that, in this specification and the like, a transistor using an oxide semiconductor in the channel formation region is called an Oxide Semiconductor transistor (OS transistor). The channel formation region of the OS transistor preferably has a metal oxide.
[0155] The metal oxide included in the channel formation region preferably contains indium (In). When the metal oxide included in the channel formation region is a metal oxide containing indium, the carrier mobility (electron mobility) of the OS transistor increases. Further, the metal oxide included in the channel formation region preferably contains element M. Element M is preferably aluminum (Al), gallium (Ga), or tin (Sn). Other elements applicable to element M include boron (B), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), tungsten (W), and the like. However, in some cases, a plurality of the aforementioned elements may be combined as element M. Element M is, for example, an element having a high binding energy with oxygen. For example, it is an element having a higher binding energy with oxygen than indium. Further, the metal oxide included in the channel formation region preferably contains zinc (Zn). A metal oxide containing zinc may be likely to crystallize.
[0156] The metal oxide included in the channel formation region is not limited to a metal oxide containing indium. The metal oxide included in the channel formation region may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.
[0157] Further, a transistor including silicon in the channel formation region may be used in the first processing unit 101.
[0158] Further, a transistor including an oxide semiconductor in the channel formation region and a transistor including silicon in the channel formation region may be used in combination in the first processing unit 101.
[0159] The first processing unit 101 includes, for example, an arithmetic circuit or a central processing unit (CPU).
[0160] The first processing unit 101 may have a microprocessor such as a DSP (Digital Signal Processor) or a GPU (Graphics Processing Unit). The microprocessor may be configured to be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The first processing unit 101 can perform various data processing and program controls by interpreting and executing instructions from various programs by the processor. Programs executable by the processor are stored in at least one of the memory area of the processor and the second processing unit 102.
[0161] The first processing unit 101 may have a main memory. The main memory has at least one of a volatile memory such as a RAM (Random Access Memory) and a non-volatile memory such as a ROM (Read Only Memory).
[0162] As the RAM, for example, a DRAM (Dynamic Random Access Memory), an SRAM (Static Random Access Memory), etc. are used, and a memory space is virtually allocated and used as the working space of the first processing unit 101.
[0163] The ROM can store the BIOS (Basic Input / Output System), firmware, etc. that do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), EPROM (Erasable Programmable Read Only Memory), etc. Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory) that enables erasure of stored data by ultraviolet irradiation, EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory, etc.
[0164] [Second processing unit 102] The second processing unit 102 has a function of performing processing using a large language model. Therefore, the second processing unit 102 has a function of storing a large language model. Preferably, the second processing unit 102 has higher processing power than the first processing unit 101. The second processing unit 102 has, for example, an arithmetic circuit or a CPU, etc. The second processing unit 102 may have a microprocessor such as a DSP or a GPU.
[0165] The second processing unit 102 has at least one of a volatile memory and a non-volatile memory. The second processing unit 102 may have, for example, a volatile memory such as DRAM or SRAM. The second processing unit 102 may have, for example, a non-volatile memory such as ReRAM (Resistive Random Access Memory, also referred to as a resistive change memory), PRAM (Phase change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory, also referred to as a magnetic resistance memory), or a flash memory. Further, the second processing unit 102 may have a recording media drive such as a hard disk drive (HDD) and a solid state drive (SSD).
[0166] Also, the second processing unit 102 can have a transistor having a metal oxide in the channel formation region described in the first processing unit 101. Since the OS transistor has an extremely small off-current, a memory including the transistor can be suitably used as a non-volatile memory for holding analog data. By storing the weight data in the neural network in the analog memory, a plurality of multiply-accumulate operations can be executed in parallel using an analog arithmetic circuit. Therefore, by using an analog memory including a transistor having a metal oxide in the second processing unit 102, it is possible to greatly reduce the power consumption when performing processing using a large language model.
[0167] [Database 104] The database 104 has a function of registering accounting data including a plurality of transaction data. The database 104 has at least one of the volatile memory and the non-volatile memory described in the second processing unit 102.
[0168] Note that the first processing unit 101, the second processing unit 102, and the database 104 do not necessarily have to be separated from each other. For example, like the accounting system 100A, it may have a processing unit 105 having the functions of the first processing unit 101, the second processing unit 102, and the database 104.
[0169] Note that the memories of the first processing unit 101, the second processing unit 102, and the database 104 can each be regarded as an example of a non-transitory computer-readable storage medium.
[0170] [Network 120] The network 120 has a function of transmitting various data. Transmission and reception of data among the reception unit 103, the optical character reader 110, the input device 130, the output device 140, the first processing unit 101, the second processing unit 102, the database 104, etc. can be performed via the network 120. For example, voucher data, transaction data, input and output, etc. are transmitted and received via a transmission path.
[0171] This embodiment can be implemented in appropriate combination with at least a part of other embodiments described in this specification.
Explanation of Reference Numerals
[0172] 100 Accounting system 100A Accounting system 101 First processing unit 101a Data processing unit 101b Instruction processing unit 101c Display processing unit 102 Second processing unit 103 Reception unit 104 Database 105 Processing unit 105a Data processing unit 105b Instruction processing unit 105c Display processing unit 105d Answer generation unit 105e Database 110 Optical character reader 120 Network 130 Input Device 140 Output Device
Claims
1. A transaction system having a reception unit, a first processing unit, a database, and a second processing unit, The reception unit has a function of receiving evidence data and a function of receiving approval or disapproval of the proposal presented by the first processing unit; the second processing unit has a function of performing processing using a language model; The first processing unit has a first function and a second function, The first function is a function of obtaining from the database a plurality of transaction data for which no supporting evidence is registered, creating a first instruction statement, the first instruction statement being an instruction to compare the plurality of transaction data with the supporting evidence data and to identify transaction data that matches the supporting evidence data, inputting the first instruction statement to the second processing unit, obtaining a first output from the second processing unit, presenting to the reception unit a proposal to link the supporting evidence data with the transaction data from the first output, and registering the linking approved by the reception unit in the database; The second function is a function of creating a second instruction sentence, the second instruction sentence instructing to extract additional information that is included in the evidence data and not included in the transaction data, inputting the second instruction sentence to the second processing unit, obtaining a second output from the second processing unit, and registering the additional information in the transaction data from the second output; Accounting system.
2. In claim 1, An accounting system in which the additional information is one or more selected from the group consisting of name, title, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information.
3. In claim 2, The first processing unit has a third function, The third function of the accounting system is to extract items that are not included in the combination of the registered transaction data and the supporting data and that are necessary for accounting, and present them to the reception unit as missing information.
4. In claim 3, The first processing unit has a fourth function, The fourth function is An accounting system having a function of creating a third instruction sentence, the third instruction sentence instructing to compare the missing information with the transaction data and generate a sentence requesting input of the missing information, inputting the third instruction sentence to the second processing unit, obtaining a third output from the second processing unit, and presenting the third output to the reception unit.
5. A transaction system having a reception unit and a processing unit, The reception unit has a function of receiving evidence data and a function of receiving approval or disapproval of the proposal presented by the processing unit, The processing unit has a database in which transaction data is stored, and has a first function and a second function; The first function is a function of acquiring multiple transaction data for which no supporting evidence is registered from the database, comparing the multiple transaction data with the supporting evidence data, identifying transaction data that matches the supporting evidence data, presenting a proposal to link the supporting evidence data with the transaction data to the reception unit, and registering the linking approved by the reception unit in the database; The second function is A function of extracting additional information that is included in the evidence data and not included in the transaction data, and registering the additional information in the transaction data. Accounting system.
6. In claim 5, An accounting system in which the additional information is one or more selected from the group consisting of name, title, registration number, transaction date, transaction content, amount, applicable tax rate, consumption tax amount, transfer destination, transfer fee, and contact information.
7. In claim 6, The processing unit has a third function, The third function of the accounting system is to extract items that are not included in the combination of the registered transaction data and the supporting data and that are necessary for accounting, and present them to the reception unit as missing information.
8. In claim 7, The processing unit has a fourth function, The fourth function of the accounting system is to compare the missing information with the transaction data, generate a message requesting the input of the missing information, and present the message requesting the input of the missing information to the reception unit.
Citation Information
Patent Citations
Voucher verification method and voucher verification system
WO2022101735A1