Information processing method and information processing device

Abstract

Provided is an information processing system having excellent convenience, usability, and reliability. The information processing system has a function which, when an account title and a descriptive text thereof have been added to a database, or when a descriptive text of an account title has been modified, collects account titles having similar descriptive texts and transaction data in which the account titles are registered from the database. The information processing system has a function for performing a first process for selecting a re-registration proposal for an account title relating to the collected transaction data, from among the collected account titles on the basis of the descriptive texts. The information processing system has a function for performing a second process for collecting transaction data for which an inappropriate re-registration proposal has been presented, and presenting the reason why the re-registration proposal has been presented as a re-registration proposal for an account title. The first process and the second process are performed using a language model. After the second process, the user of the information processing system can modify an account title registered in the database.

Description

Information processing method and information processing device

[0001] One aspect of the present invention relates to an information processing method, an information processing device, 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 work support method and an accounting work support system using a language model.

[0002] One embodiment of the present invention is not limited to the above technical field, and examples of the technical field of one embodiment of the present invention include semiconductor devices, display devices, light-emitting devices, power storage devices, memory devices, electronic devices, lighting devices, input devices (e.g., touch sensors), input / output devices (e.g., touch panels), driving methods thereof, and manufacturing methods thereof.

[0003] In accounting work, account items are used to classify transaction details and prepare financial statements. Patent Document 1 discloses a method for registering account items for transactions based on the contents of transaction receipts and journal entry rules.

[0004] In recent years, the development of language models using neural networks has been actively carried out, and large-scale language models (LLMs) in particular have attracted attention. A large-scale language model is a natural language processing model trained using a large amount of data. A large-scale language model can realize a dialogue model that responds to user instructions, for example. Non-Patent Document 1 discloses GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) as a large-scale language model, and also discloses ChatGPT as a dialogue model.

[0005] The use of large-scale language models has significantly increased the capabilities of natural language processing models. However, as language models become larger, it is difficult to incorporate and operate language models in-house due to the equipment and cost involved. Therefore, one way to use language models is to use external services that provide language models.

[0006] JP 2020-16914 A

[0007] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet <URL: https: / / arxiv.org / abs / 2304.01852>

[0008] When adding an account item, it may be necessary to re-register an account item for a transaction for which an account item has already been registered. Even when an account item is not added, it may be necessary to re-register an account item, for example, to ensure consistency between account items across multiple transactions. In this case, it requires deep knowledge of accounting work and a great deal of effort for the person in charge to re-register an appropriate account item based on the content of the transaction.

[0009] Therefore, an object of one embodiment of the present invention is to provide an information processing method, an information processing device, and an information processing system that automate the re-registration of account items related to transactions. Another object of one embodiment of the present invention is to provide an information processing method, an information processing device, and an information processing system that allow a user to perform accounting work with less effort. Another object of one embodiment of the present invention is to provide an information processing method, an information processing device, and an information processing system that are highly convenient, useful, and reliable. Another object of one embodiment of the present invention is to provide a novel information processing method, an information processing device, and an information processing system.

[0010] Note that the description of these problems does not preclude the existence of other problems. One embodiment of the present invention does not necessarily have to solve all of these problems. Problems other than these can be extracted from the description in the specification, drawings, and claims.

[0011] One aspect of the present invention is an information processing method using a database, in which a data table including a plurality of records and a plurality of first transaction data are registered in the database, each of the plurality of records including a first account item and a first explanation that is an explanation of the first account item, and in each of the plurality of first transaction data, one of the plurality of first account items is registered as a second account item, and the explanation of the first account item corresponding to the second account item is set as the second explanation, and in a first step, a third account item and an explanation of the third account item are registered. and a third explanatory statement, which is a statement, are added to the data table; in a second step, at least a portion of a plurality of records are collected based on the first explanatory statement and the third explanatory statement, and a first list is generated that includes the first account item and the first explanatory statement and the third account item and the third explanatory statement included in the collected records; in a third step, first transaction data in which the first account item included in the first list is registered is collected as second transaction data, and a second list is generated that includes the second transaction data; and in a fourth step, the first list is generated based on the first explanatory statement and the third explanatory statement. a fifth step of generating a first prompt having a list, a second list, and a first instruction sentence, the first instruction sentence being an instruction sentence for causing the language model to select and present a fourth account item, which is an account item to be re-registered in the second transaction data, from the first account item and the third account item included in the first list based on the second transaction data and the first explanation sentence and the third explanation sentence included in the first list; a fifth step of generating a first response sentence using the language model based on the first prompt; and a sixth step of generating a first response sentence using the fourth account item and the third explanation sentence included in the first list based on the second transaction data and the third explanation sentence included in the first list. and a fourth explanation which is an explanation of the first account item or the third account item corresponding to the account item of the second transaction data, are presented to the user for each second transaction data, and in a seventh step, a determination result as to whether the fourth account item is valid or not is accepted, and in an eighth step, the second transaction data for which it is determined that the fourth account item is invalid is set as third transaction data, and a second prompt is generated which has the third transaction data, the second account item and the fourth account item related to the third transaction data, the second explanation and the fourth explanation, and a second instruction, and the second instruction isThe instruction sentence is for causing the language model to present the reason why the fourth account item was presented as a re-registration proposal for the account item related to the third transaction data, based on the third transaction data, the second explanation sentence, and the fourth explanation sentence, and in a ninth step, the information processing method generates a second response sentence using the language model based on the second prompt.

[0012] Alternatively, in the above aspect, in the tenth step, the reason may be presented to the user, in the eleventh step, corrections to the first explanatory sentence and the third explanatory sentence may be accepted, and in the twelfth step, the corrected explanatory sentences of the first explanatory sentence and the third explanatory sentence may be registered in the data table, and then the second step may be performed again.

[0013] Alternatively, in the above aspect, in the tenth step, second transaction data may be presented to the user in which one or both of the second account item and the fourth account item are identical to the second account item or the fourth account item related to the third transaction data.

[0014] Alternatively, in the above aspect, in the second step, the similarity between each of the multiple first descriptions and the third description may be calculated, and records including first descriptions whose similarity is equal to or greater than a certain value may be collected.

[0015] Alternatively, in the above aspect, a thirteenth step may be performed between the seventh step and the eighth step, and in the thirteenth step, for second transaction data for which the re-registered fourth account item is determined to be appropriate, the fourth account item may be registered in the database as the account item related to the second transaction data.

[0016] Alternatively, one aspect of the present invention includes a database, a reception unit, and a processing unit, and the database has registered therein a data table including a plurality of records and a plurality of first transaction data, each of the plurality of records including a first account item and a first explanation that is an explanation of the first account item, and in each of the plurality of first transaction data, one of the plurality of first account items is registered as a second account item, and the explanation of the first account item corresponding to the second account item is set as the second explanation, and the reception unit receives a third account item and a third explanation that is an explanation of the third account item. and supplying it to the processing unit, the processing unit having a function of adding the third account item and the third explanation received by the receiving unit to the data table, the processing unit having a function of collecting at least a portion of the plurality of records based on the first explanation and the third explanation, and generating a first list including the first account item and the first explanation and the third account item and the third explanation included in the collected records, the processing unit having a function of collecting first transaction data in which the first account item included in the first list is registered, and generating second transaction data including the second transaction data. The processing unit has a function of generating a first prompt having a first list, a second list, and a first instruction sentence, the first instruction sentence being an instruction sentence for causing the language model to select and present a fourth account item, which is an account item to be re-registered in the second transaction data, from the first account item and the third account item included in the first list based on the second transaction data and the first explanation sentence and the third explanation sentence included in the first list, and the ... The processing unit has a function of prompting the user to determine whether the fourth account item included in the response sentence and a fourth explanation which is an explanation of the first account item or the third account item corresponding to the fourth account item for each second transaction data, by presenting the user with the fourth account item included in the response sentence and a fourth explanation which is an explanation of the first account item or the third account item corresponding to the fourth account item, and the processing unit has a function of treating the second transaction data for which the fourth account item is determined to be invalid as third transaction data, and generating a second prompt having the third transaction data, the second account item and the fourth account item related to the third transaction data, the second explanation and the fourth explanation, and a second instruction sentence;The second instruction sentence is an instruction sentence for causing the language model to present the reason why the fourth account item was presented as a re-registration proposal for the account item related to the third transaction data, based on the third transaction data, the second explanation sentence, and the fourth explanation sentence, and the processing unit is an information processing device having a function of prompting the user to correct the first explanation sentence and the third explanation sentence by presenting to the user the reason contained in the second response sentence obtained by sending a second prompt to the language model via a network.

[0017] Alternatively, in the above aspect, the processing unit may have a function of registering the corrected first description in the data table when the user corrects the first description, and the processing unit may have a function of registering the corrected third description in the data table when the user corrects the third description.

[0018] Alternatively, in the above aspect, the processing unit may have a function of presenting to the user second transaction data in which one or both of the second account item and the fourth account item are identical to the second account item or the fourth account item related to the third transaction data.

[0019] Alternatively, in the above aspect, the processing unit may have a function of calculating the similarity of each of the multiple first descriptions to the third description, and collecting records including first descriptions whose similarity is equal to or greater than a certain value.

[0020] Alternatively, in the above aspect, the processing unit may have a function of registering the fourth account item in the database as an account item related to the second transaction data for second transaction data for which the re-registered fourth account item is judged to be appropriate.

[0021] Alternatively, in the above aspect, each of the first to third transaction data may include a product name and a transaction purpose.

[0022] According to one aspect of the present invention, it is possible to provide an information processing method, an information processing device, and an information processing system that automate the re-registration of account items related to transactions. Furthermore, according to one aspect of the present invention, it is possible to provide an information processing method, an information processing device, and an information processing system that allow users to perform accounting tasks with less effort. Furthermore, according to one aspect of the present invention, it is possible to provide an information processing method, an information processing device, and an information processing system that are highly convenient, useful, and reliable. Furthermore, according to one aspect of the present invention, it is possible to provide a novel information processing method, an information processing device, and an information processing system.

[0023] Note that the description of these effects does not preclude the existence of other effects. One embodiment of the present invention does not necessarily have all of these effects. Effects other than these can be extracted from the description in the specification, drawings, and claims.

[0024] FIG. 1 is a schematic diagram showing an example of an information processing system. FIG. 2A is a schematic diagram showing an example of transaction data. FIG. 2B is a schematic diagram showing an example of a data table. FIG. 3 is a flowchart showing an example of an information processing method. FIG. 4 is a flowchart showing an example of an information processing method. FIG. 5A is a schematic diagram showing an example of input data. FIG. 5B is a schematic diagram showing an example of a data table. FIGS. 6A and 6B are schematic diagrams showing examples of lists. FIG. 7 is a schematic diagram showing an example of a prompt. FIG. 8 is a schematic diagram showing an example of a response sentence. FIG. 9 is a schematic diagram showing an example of a screen layout. FIG. 10A is a schematic diagram showing an example of a prompt. FIG. 10B is a schematic diagram showing an example of a response sentence. FIG. 11 is a schematic diagram showing an example of a screen layout. FIG. 12 is a schematic diagram showing an example of a screen layout. FIG. 13 is a block diagram showing an example of an information processing system. FIG. 14 is a schematic diagram showing an example of an information processing system.

[0025] 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 readily understood by those skilled in the art that various changes can be made in form and detail without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0026] In the configuration of the invention described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and repeated explanations thereof will be omitted. Furthermore, when referring to similar functions, the same hatching pattern may be used and no particular reference numeral may be assigned.

[0027] Furthermore, for ease of understanding, the position, size, range, etc. of each component shown in the drawings may not represent the actual position, size, range, etc. Therefore, the disclosed invention is not necessarily limited to the position, size, range, etc. disclosed in the drawings.

[0028] In this specification, the ordinal numbers such as "first" and "second" are used for convenience and do not limit the number of components or the order of the components (for example, the order of processes or the order of stacking). Furthermore, the ordinal numbers assigned to components in one part of this specification may not match the ordinal numbers assigned to the same components in other parts of this specification or in the claims.

[0029] In this specification, when the same symbol is used for multiple elements, and particularly when it is necessary to distinguish between them, an identification symbol such as “_1”, “[n]”, or “[m, n]” may be added to the symbol.

[0030] In this specification, goods may be either tangible or intangible. For example, intangible goods are sometimes called services. Therefore, the goods described in this specification may sometimes be referred to as services.

[0031] In this embodiment, an information processing method, an information processing device, and an information processing system according to one embodiment of the present invention will be described with reference to the drawings. Specifically, the information processing method, the information processing device, and the information processing system can be used for accounting work.

[0032] In this specification and the like, an information processing method, an information processing device, and an information processing system that can be used for accounting work are referred to as an accounting work support method, an accounting work support device, and an accounting work support system, respectively.

[0033] An information processing system according to one embodiment of the present invention includes an information terminal, a first information processing device, and a second information processing device, which are connected to each other via a network. The second information processing device has a function of performing processing using a language model. An information processing method according to one embodiment of the present invention is an information processing method using the information processing system.

[0034] In accounting work, account items are used to classify transaction details. Account items are registered in a database along with descriptions of the account items. In other words, a data table containing account items and descriptions of the account items is registered in the database. Transaction data representing the transaction details is also registered in the database. The transaction data includes the names of the products involved in the transaction, the purpose of the transaction, etc.

[0035] In one aspect of the information processing method of the present invention, when an account item and its explanation not included in the data table are input to a first information processing device, the first information processing device adds and registers the account item and its explanation to the data table. Also, when the explanation of an account item included in the data table is corrected and the corrected explanation is input to the first information processing device, the first information processing device registers the corrected explanation in the data table. Next, the first information processing device collects, from the data table, account items with similar added or corrected explanations and the explanations of the account items. Next, the first information processing device collects, from a database, transaction data in which the collected account items are registered. Then, a second information processing device performs a first process in which a re-registration proposal for an account item related to the collected transaction data is selected from the collected account items based on the explanation. The first process can be performed using a language model.

[0036] After the first processing, the first information processing device can prompt the user of the information terminal to determine whether the proposed re-registration of an account item is appropriate for each of the collected transaction data. For transaction data for which the proposed re-registration of an account item is determined to be appropriate, the first information processing device re-registers the account item related to the transaction data by registering the proposed re-registration in the database.

[0037] The first information processing device collects transaction data for which a re-registration proposal for an account item is determined to be inappropriate. The second information processing device then performs a second process for presenting, for the transaction data for which a re-registration proposal for an account item is determined to be inappropriate, the reason for presenting the re-registration proposal as a re-registration proposal for the account item, based on the transaction data, a description of the account item before re-registration, and a description of the account item presented as the re-registration proposal. The second process can be performed using a language model.

[0038] After the second process, the first information processing device can present to the user of the information terminal the reason why the re-registration proposal was presented as a re-registration proposal for the account item. This allows the first information processing device to prompt the user to revise the account item registered in the data table. Specifically, the first information processing device can prompt the user to revise the description of the account item before re-registration and the description of the account item presented as a re-registration proposal. As a result, if the description of the account item is revised, the first information processing device collects the account item, its description, and transaction data from the database using the above-described method. The second information processing device then performs the above-described first process again.

[0039] As described above, the information processing method of one embodiment of the present invention can automate the re-registration of account items related to transactions. Furthermore, for transaction data in which an inappropriate re-registration proposal is presented, the reason why the re-registration proposal was presented as the re-registration proposal for the account item can be presented to the user of the information terminal. This allows the user to easily modify the description of the account item so that the second information processing device can present an appropriate account item as the re-registration proposal. As described above, by using the information processing method of one embodiment of the present invention, accounting work can be performed with little effort. Furthermore, the information processing method of one embodiment of the present invention can be an information processing method that is highly convenient, useful, and reliable. Furthermore, the information processing device and information processing system of one embodiment of the present invention can be an information processing device and information processing system that allows the user to perform accounting work with little effort, and can be an information processing device and information processing system that is highly convenient, useful, and reliable.

[0040] <Configuration Example 1 of Information Processing System> Fig. 1 is a schematic diagram showing an example of an information processing system 10 that is an information processing system according to one aspect of the present invention. The information processing system 10 includes an information processing device 40, an information terminal 20, and an information processing device 50. In the information processing system 10, the information processing device 40, the information terminal 20, and the information processing device 50 are connected via a network 30. Fig. 1 shows information terminal 20a, information terminal 20b, information terminal 20c, and information terminal 20d as examples of the information terminal 20.

[0041] A user of the information processing system 10 can access the information processing device 40 from the information terminal 20. The user can then receive a service using an information processing method according to one aspect of the present invention, i.e., an information processing method using the information processing system 10. Specifically, the user of the information processing system 10 can be a user of the information terminal 20.

[0042] The user can use the information processing device 40, for example, by using dedicated software or an application installed on the information terminal 20. Alternatively, the user can use the information processing device 40, for example, from a web browser on the information terminal 20.

[0043] An organization such as a company that provides a service using an information processing method according to one aspect of the present invention (hereinafter also referred to as a service provider) can provide the service using the information processing device 40 .

[0044] The information processing device 40 is a device that can execute processing using an information processing method according to one aspect of the present invention. In FIG. 1, a server computer is illustrated as an example.

[0045] The information processing device 40 has a reception unit 41, a processing unit 43, and a database 45. The reception unit 41 has a function of receiving data from outside the information processing device 40. The reception unit 41 receives data from the information terminal 20, for example, via the network 30. The reception unit 41 also receives data from the information processing device 50, for example, via the network 30. The data supplied to the reception unit 41 can be supplied to the processing unit 43, for example.

[0046] The processing unit 43 has a function of performing processes such as calculation, analysis, and inference, etc. The processing unit 43 has a function of performing processes such as calculation, analysis, and inference, etc., using data supplied from, for example, one or both of the receiving unit 41 and the database 45.

[0047] The information processing device 40, specifically the processing unit 43, may use artificial intelligence (AI) for at least some of the processing. In this case, it is preferable that the information processing device 40 particularly uses an artificial neural network (ANN, hereinafter simply referred to as a neural network) model. The neural network model is realized by a circuit (hardware) or a program (software).

[0048] In this specification, a neural network model refers to a general model that mimics the neural network of a living organism, determines the connection strength between neurons through learning, and has problem-solving capabilities. A neural network model has an input layer, an intermediate layer (hidden layer), and an output layer.

[0049] In this specification and the like, when describing a neural network model, determining the connection strengths (also called weighting coefficients) between neurons from existing information may be referred to as "learning."

[0050] In this specification and the like, constructing a neural network model using connection strengths obtained by learning and deriving a new conclusion from it may be referred to as "inference."

[0051] 1 shows an example in which the database 45 is provided in the information processing device 40, but the database 45 may be provided outside the information processing device 40, or outside the information processing system 10. Alternatively, the database may be provided in two or more of the following locations: inside the information processing device 40, outside the information processing device 40 and inside the information processing system 10, and outside the information processing system 10. For example, the database 45 may be provided in a distributed manner in two or more of the following locations: inside the information processing device 40, outside the information processing device 40 and inside the information processing system 10, and outside the information processing system 10.

[0052] The information processing device 40 can perform information processing such as calculations using data input from the information terminal 20 via the network 30. The information processing device 40 can transmit the results of the information processing to the information terminal 20 via the network 30. This can reduce the calculation load on the information terminal 20.

[0053] The information processing device 40 can input data to the information processing device 50 via the network 30. The information processing device 50 can perform information processing such as calculations using the input data. The information processing device 50 can transmit the results of the information processing to the information processing device 40 via the network 30. This can reduce the calculation load on the information processing device 40. The information processing device 40 can then transmit the data received from the information processing device 50 or data generated based on the data to the information terminal 20 via the network 30.

[0054] The information terminal 20 is an information terminal such as a computer used by a user, and may also be referred to as a client computer. FIG. 1 illustrates, as examples of the information terminal 20, information terminal 20a, which is a desktop computer; information terminal 20b, which is a notebook computer; information terminal 20c, which is a smartphone; and information terminal 20d, which is a tablet computer. Note that information terminal 20d can also be used as a notebook computer by connecting it to a housing 21 having a keyboard. The number of information terminals connected to the information processing device 40 is not particularly limited. While FIG. 1 illustrates four information terminals, the number of information terminals may be one, two, three, five, or more. Examples of such information terminals include desktop information terminals, notebook information terminals, tablet information terminals, and mobile information terminals such as smartphones.

[0055] The information terminal 20 may have a display unit. This allows the information terminal 20 to present information to the user. The information terminal 20 may present, for example, the result of information processing by the information processing device 40 to the user. The information terminal 20 may also present the result of information processing by the information processing device 50 to the user.

[0056] The information processing device 40 is a large computer such as a server computer or a supercomputer. The information processing device 40 is a computer with higher processing power than the information terminal 20. The information processing device 40 can function as a parallel computer. By using the information processing device 40 as a parallel computer, it is possible to perform large-scale calculations required for AI learning and inference, for example. Furthermore, the information processing device 40 may be capable of performing processing using a natural language processing model using AI.

[0057] The information processing device 50 is a large computer such as a server computer or a supercomputer. The information processing device 50 is a computer with higher processing power than the information terminal 20. The information processing device 50 is also a computer with higher processing power than the information processing device 40. It is preferable that the information processing device 50 has a function as a parallel computer. By using the information processing device 50 as a parallel computer, it is possible to perform large-scale calculations required for AI learning and inference, for example. Note that when both the information processing device 40 and the information processing device 50 have a function as a parallel computer, the information processing device 50 has a higher processing power and can perform large-scale calculations than the information processing device 40.

[0058] The information processing device 50 can perform processing using a natural language processing model that uses AI. Examples of natural language processing models that use AI include BERT (Bidirectional Encoder Representations from Transformers) and T5 (Text-to-Text Transfer Transformer). The information processing device 50 can also perform processing using a model that uses a large-scale language model. Examples of large-scale language models include GPT-3, GPT-3.5, GPT-4 (registered trademark), LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), and PaLM2, and it is preferable to use GPT-4 (registered trademark).

[0059] The information processing device 50 can execute processing using a general-purpose AI model that can perform various tasks. When the information processing device 40 and the information processing device 50 can each execute processing using a model that uses a large-scale language model, the information processing device 50 can execute processing using a larger-scale AI model than the information processing device 40.

[0060] An intranet or an extranet can be used as the network 30. The network 30 can be a computer network such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), or a global area network (GAN).

[0061] Furthermore, when wireless communication is performed, communication standards such as the fourth generation mobile communication system (4G), fifth generation mobile communication system (5G), and sixth generation mobile communication system (6G), or specifications standardized by the IEEE such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), can be used as communication protocols or communication technologies.

[0062] <Example of Information Processing Method> An example of an information processing method according to one embodiment of the present invention will be described below. Specifically, an example of an information processing method using the information processing system 10 shown in FIG.

[0063] 2A and 2B are schematic diagrams illustrating examples of the configuration of data registered in the database 45. In the information processing method of one embodiment of the present invention, the data illustrated in FIG. 2A and the data illustrated in FIG. 2B are used.

[0064] FIG. 2A is a schematic diagram showing an example of data 100. A plurality of pieces of data 100 are registered in database 45. Data 100 includes transaction data 120 and item 127. Transaction data 120 is data that represents transaction details. Transaction data 120 includes items 121, 123, and 125. In the example shown in FIG. 2A, the name of item 121 is the product name, the name of item 123 is the purpose of the transaction, the name of item 125 is the transaction date and time, and the name of item 127 is the account item.

[0065] Note that transaction data 120 may include items other than items 121, 123, and 125 shown in FIG. 2A. For example, at least one of the following may be included: transaction number, amount, business partner, name of sales representative, discount information, quotation expiration date, and email address. Note that at least one of these may be included in item 125. In other words, transaction data 120 may include two or more types of item 125.

[0066] As described above, item 127 can be an account item. An account item is registered in transaction data 120 and can be used to classify transaction data 120. Note that item 127 is not limited to an account item as long as it can be used to classify transaction data 120. The same applies to items that can be used as account items, which will be described later. Note that item 127 may be included in transaction data 120.

[0067] The transaction data 120 is not limited to information related to transactions. In this case, for example, the transaction data 120 can simply be called data. Also, the item 121 can be a name, the item 123 a purpose, the item 125 a date and time, and the item 127 a classification.

[0068] 2B is a schematic diagram showing an example of the data table 101. The first row of the data table 101 represents an item name, and each row from the second row onwards represents a record 115. In the example shown in FIG. 2B, the record 115 includes an item 111, an item 112, and an item 113. FIG. 2B shows examples of a record 115[1], a record 115[2], a record 115[3], and a record 115[4].

[0069] In this specification, a record refers to one of the units that make up a data table. One record can store one row of data.

[0070] 2B shows an example in which the name of item 111 is a department, the name of item 112 is an account, and the name of item 113 is a description. Note that data table 101 may include items other than items 111, 112, and 113. Data table 101 may include, for example, a code number registered for each record. Note that data table 101 does not have to include item 111.

[0071] Item 111 indicates, for example, the department in which a transaction is conducted. A department can be, for example, a department, branch office, sales office, or subsidiary within a company. Item 111 can also be a classification of an account item. In this case, item 111 included in record 115 can be, for example, any of assets, liabilities, net assets, revenue, and expenses. Item 111 can also be a classification of an account item. For example, the classification of an account item classified as "expenses" can be cost of sales, selling, general and administrative expenses, non-operating expenses, and extraordinary losses. Note that while FIG. 2B shows an example in which there is one type of item 111, data table 101 may include two or more types of item 111.

[0072] As described above, the item 112 can be an account item. In an information processing method according to one aspect of the present invention, one of the items 112 included in the data table 101 is registered in the transaction data 120 shown in Fig. 2A. That is, one of the items 112 included in the data table 101 is set as the item 127 shown in Fig. 2A.

[0073] Item 113 may be a description of item 112. Item 113 may be, for example, a specific example of a transaction for which an account item is registered. In an information processing method according to one aspect of the present invention, an item 127 to be registered in transaction data 120 is selected from items 112 based on transaction data 120 and item 113. Each of the multiple transaction data 120 shown in FIG. 2A has one of the multiple items 112 shown in FIG. 2B registered as item 127.

[0074] In the example shown in FIG. 2B , items 111, 112, and 113 of record 115[1] are respectively set to "CC1 portion," "KK1 fee," and "EE purchase price, FF expenses, etc.". Also, items 111, 112, and 113 of record 115[2] are respectively set to "CC1 portion," "KK2 fee," and "EE fee." Also, items 111, 112, and 113 of record 115[3] are respectively set to "CC1 portion," "DD3 fee," and "GG participation fee, etc." Furthermore, items 111, 112, and 113 of record 115[4] are respectively set to "CC2 portion," "DD4 fee," and "HH, etc."

[0075] In this specification, the transaction data 120 shown in Figure 2A may be referred to as first transaction data. The account items and their explanations shown in Figure 2B may be referred to as first account items and first explanations, respectively. The account items shown in Figure 2A may be referred to as second account items, and the explanations of the second account items may be referred to as second explanations.

[0076] 3 and 4 are flowcharts illustrating an example of an information processing method according to one embodiment of the present invention. In FIG. 4, it is indicated whether each process is performed by the information terminal 20, the information processing device 40, or the information processing device 50.

[0077] Before the process shown in step S11 in Fig. 3 is performed, step S31 shown in Fig. 4 is performed. In step S31, the user of the information terminal 20 inputs an account item and its explanation to the information processing device 40. In other words, in step S31, the information terminal 20 accepts the account item and its explanation, and transmits the accepted account item and its explanation to the information processing device 40. The user of the information terminal 20 may be, for example, an accountant. Furthermore, if there are multiple accountants, the user of the information terminal 20 may be one of the accountants. Furthermore, the user of the information terminal 20 may be different from the accountant.

[0078] FIG. 5A is a schematic diagram showing an example of input data 103, which is data input to the information processing device 40. The input data 103 includes items 111A, 112A, and 113A. In the example shown in FIG. 5A, item 111A is a department, item 112A is an account, and item 113A is a description. That is, items of the same type as the items included in the data table 101 shown in FIG. 2B are included in the input data 103. As will be described in detail later, the items included in the input data 103 are added to the data table 101 shown in FIG. 2B. Furthermore, the data table 101 is modified based on the items included in the input data 103. Note that if the data table 101 includes items other than items 111, 112, and 113, items of the same type as the items can be included in the input data 103. Here, the input data 103 may include multiple items of each of items 111A, 112A, and 113A. The input data 103 is also called query data.

[0079] In the example shown in Fig. 5A, item 111A is "cc1 department", item 112A is "aaa expense", and item 113A is "ee, ff related." In other words, in the input data 103 shown in Fig. 5A, the department is "cc1 department", the account item is "aaa expense", and the description of the account item is "ee, ff related."

[0080] [Step S11] In step S11, the information processing device 40 accepts input data 103. Specifically, the reception unit 41 included in the information processing device 40 accepts the input data 103 transmitted from the information terminal 20. In the example shown in Fig. 5A , the reception unit 41 accepts the input data 103 in which the item 111A representing the department is "cc1 department," the item 112A representing the account subject is "aaa expense," and the item 113A representing the description of the account subject is "ee, ff related."

[0081] In this specification, item 112A may be referred to as a third account item, and item 113A may be referred to as a third explanation.

[0082] After the receiving unit 41 receives the input data 103, the input data 103 is registered in the data table 101. In other words, the items included in the input data 103 are added to the data table 101. FIG. 5B is a schematic diagram showing an example of the data table 101 in which the input data 103 is registered. FIG. 5B shows an example in which the input data 103 is registered in the data table 101 as record 115[5]. Specifically, FIG. 5B shows an example in which the items 111A, 112A, and 113A included in the input data 103 are added to the data table 101 as items 111, 112, and 113 of record 115[5]. FIG. 5B shows an example in which the item 111 included in record 115[5] is "cc1 part," the item 112 is "aaa expense," and the item 113 is "ee, ff related." 5B, the record 115[5], which is the record 115 added in step S11, is hatched. Also, if the input data 103 includes, for example, multiple items 112A, multiple records 115 are added to the data table 101.

[0083] Item 112A shown in FIG. 5A may match one of the multiple items 112 included in data table 101 shown in FIG. 5B. In this case, for example, items 111 and 113 of record 115 including item 112 that matches item 112A are modified to items 111A and 113A, respectively. This allows, for example, the modified department to be registered in data table 101, and the modified description to be registered in data table 101. For example, if item 111A included in input data 103 is "cc1 department," item 112A is "kk1 expense," and item 113A is "ee, ff related," item 113 included in record 115[1] is modified to "ee, ff related." As described above, the information processing method shown in FIGS. 3 and 4 can be applied not only when adding a new account item to data table 101, but also when modifying the description of an already registered account item.

[0084] [Step S12] In step S12, the information processing device 40 collects at least some of the multiple records 115 based on the items 113 included in the data table 101 shown in FIG. 5B . For example, the processing unit 43 of the information processing device 40 collects records 115 including items 113 similar to item 113A. For example, the information processing device 40 calculates the similarity of each of the multiple items 113 included in the data table 101 to the item 113A. Thereafter, the information processing device 40 collects records 115 including items 113 whose similarity is equal to or greater than a certain value. Note that when the input data 103 includes multiple items 112A and 113A, the information processing device 40 can collect, for example, records 115 including at least one item 113 whose similarity to the item 113A is equal to or greater than a certain value.

[0085] The similarity can be calculated based on, for example, the degree of similarity between the appearance of the item 113 and the item 113A (which can also be said to be the degree of similarity between character strings). Alternatively, the items 113 and 113A may be vectorized (quantified) and the similarity between the two vectors may be calculated. The similarity between the item 113 and the item 113A may also be calculated by calculating the distance between the two vectors.

[0086] Various methods can be used to vectorize the items 113 and 113A. For example, morphological analysis and / or compound word analysis can be performed to divide the items 113 and 113A into phrases or words. Then, the items 113 and 113A can be vectorized from the divided phrases or words. Examples of such vectorization methods include Bag-of-Words and TF-IDF (Term Frequency-Inverse Document Frequency).

[0087] Furthermore, for example, a model that converts a sentence into a distributed representation can be learned by machine learning, and the distributed representations of item 113 and item 113A can be obtained using the model. For example, a neural network can be used as the model. Examples of neural network models that can be used to obtain distributed representations include Doc2Vec, fastText, BERT (Bidirectional Encoder Representations from Transformer), and SentenceBERT.

[0088] Methods for calculating the similarity between two vectors include cosine similarity, covariance, unbiased covariance, Pearson's product-moment correlation coefficient, etc. Among these, it is particularly preferable to use cosine similarity.

[0089] Methods for finding the distance between two vectors include Euclidean distance, standard (normalized, average) Euclidean distance, Mahalanobis distance, Manhattan distance, Chebyshev distance, Minkowski distance, and the like.

[0090] Here, the information processing device 40 may determine the records 115 to be collected based not only on the similarity of the item 113 to the item 113A but also on the item 111. The information processing device 40 can collect, for example, records 115 in which the item 111 has desired content. The information processing device 40 can collect, for example, records 115 in which the item 111 has desired content and the similarity of the item 113 to the item 113A is equal to or greater than a certain value. The information processing device 40 can collect records 115 in which the item 111 is identical to, for example, the item 111A and the similarity of the item 113 to the item 113A is equal to or greater than a certain value. Note that the records 115 to be collected by the information processing device 40 may be specified based on a predetermined search expression. For example, the user of the information terminal 20 can specify the item 111 based on a predetermined search expression. In this case, the information processing device 40 can collect records 115 that include the specified item 111 and in which the similarity of the item 113 to the item 113A is equal to or greater than a certain value. Furthermore, the user of the information terminal 20 may specify the item 113 in addition to the item 111 based on a predetermined search expression. In this case, the information processing device 40 can collect records 115 including the specified items 111 and 113.

[0091] After collecting the records 115, the information processing device 40 generates a list 105 including the collected records 115. FIG. 6A is a schematic diagram showing an example of the list 105.

[0092] FIG. 6A illustrates an example in which list 105 includes records 115[1], 115[2], and 115[5] shown in FIG. 5B, but does not include records 115[3] and 115[4]. List 105 includes items 111, 112, and 113 included in record 115 collected by information processing device 40. Here, the contents of items 111, 112, and 113 included in record 115[5] shown in FIG. 6A are the same as the contents of items 111A, 112A, and 113A shown in FIG. 5A, respectively. Therefore, it can be said that list 105 includes items 111A, 112A, and 113A. It is not necessary to include item 111 in list 105. In this case, list 105 may be configured not to include item 111A.

[0093] By narrowing down the records 115 to be included in the list 105 based on, for example, the item 111, the number of items 113 for which similarity to the item 113A is calculated can be reduced. This reduces the time required for step S12. Furthermore, the processing time for subsequent steps that use the list 105 can also be reduced.

[0094] [Step S13] In step S13, the information processing device 40 collects at least one of the multiple data 100 shown in FIG. 2A based on the list 105. For example, the processing unit 43 of the information processing device 40 collects transaction data 120 in which the item 112 included in the list 105 is registered as the item 127. The information processing device 40 collects, for example, transaction data 120 in which the account item included in the list 105 is registered.

[0095] In this specification and the like, the transaction data 120 collected by the information processing device 40 may be referred to as second transaction data.

[0096] After collecting transaction data 120, information processing device 40 generates list 107 including collected transaction data 120. Transaction data 120 included in list 107 can be referred to as second transaction data. Information processing device 40 can be referred to as generating list 107 including second transaction data in step S13.

[0097] FIG. 6B is a schematic diagram showing an example of list 107. FIG. 6B illustrates an example in which transaction data 120, transaction data 120[1] through transaction data 120[n] (n is an integer equal to or greater than 1; in the example shown in FIG. 6B, n is an integer equal to or greater than 3), are included in list 107. In FIG. 6B, items 121, 123, and 125 included in transaction data 120[1] are designated as items 121[1], 123[1], and 125[1], respectively. Furthermore, items 121, 123, and 125 included in transaction data 120[2] are designated as items 121[2], 123[2], and 125[2], respectively. Furthermore, items 121, 123, and 125 included in transaction data 120[n] are designated as items 121[n], 123[n], and 125[n], respectively. Note that items 121, 123, 125, and 127 shown in Figure 6B are the product name, transaction purpose, transaction date and time, and account item, respectively, similar to items 121, 123, 125, and 127 shown in Figure 2A.

[0098] The list 107 includes items 127, such as account items, registered in the transaction data 120. In Fig. 6B, the items 127 registered in the transaction data 120[1], the transaction data 120[2], and the transaction data 120[n] are respectively referred to as item 127[1], item 127[2], and item 127[n]. Items 127[1] through 127[n] can be any of the items 112 included in the list 105 shown in Fig. 6A.

[0099] In the example shown in FIG. 6B, items 121[1], 123[1], 125[1], and 127[1] are set to "abc1," "for bb1," "dd1, Jan. yyyy," and "kk1 expense," respectively. Also, items 121[2], 123[2], 125[2], and 127[2] are set to "abc2," "for bb2," "dd2, Feb. yyyy," and "kk2 expense," respectively. Furthermore, items 121[n], 123[n], 125[n], and 127[n] are set to "a1b2ca5," "b1bb3b6," "dd1, d2, Feb. yyyy," and "kk2 expense," respectively.

[0100] Here, the information processing device 40 may determine the transaction data 120 to be collected based not only on the item 127 registered in the transaction data 120 but also on the item 125. The information processing device 40 can collect, for example, transaction data 120 in which the item 125 is a desired content. The information processing device 40 can collect, for example, transaction data 120 in which the item 125 is a desired content and in which the item 112 included in the list 105 is registered as the item 127. The information processing device 40 can collect transaction data 120 in which the item 125 is within a range specified by, for example, the user of the information terminal 20 and in which the item 112 included in the list 105 is registered as the item 127. The transaction data 120 to be collected by the information processing device 40 may be specified based on a predetermined search expression. For example, the user of the information terminal 20 can specify the item 125 based on a predetermined search expression. In this case, the information processing device 40 can collect transaction data 120 that includes the specified item 125 and in which the item 112 included in the list 105 is registered as the item 127.

[0101] FIG. 6B illustrates an example in which the information processing device 40 collects transaction data 120 representing transactions whose transaction date and time is in year yyyy and generates list 107. It should be noted that item 125 need not be included in list 107 shown in FIG. 6B . Regardless of whether the information processing device 40 uses item 125 to determine the transaction data 120 to collect or does not use item 125, item 125 may or may not be included in list 107. Furthermore, for example, if multiple pieces of transaction data 120 are registered in database 45, each of which has the same items 121 and 123 but different items 125, list 107 may include only one of the multiple pieces of transaction data 120. For example, if item 125 is the transaction date and time, list 107 may include transaction data 120 representing the oldest or newest transaction within a range of transaction dates and times specified by the user of information terminal 20.

[0102] [Step S14] In step S14, the information processing device 40 generates a prompt 210. Specifically, the processing unit 43 of the information processing device 40 generates the prompt 210 for presenting a re-registration proposal for the account item related to the transaction data 120.

[0103] In this specification, a prompt corresponds to an input sentence that causes a language model to perform a desired operation. When a prompt is given, the language model generates a response sentence based on the prompt. The prompt includes an instruction sentence. The instruction sentence can be rephrased as a question sentence, an imperative sentence, or the like. It is preferable that the instruction sentence be registered in advance by a developer or a service provider. By registering the instruction sentence included in the prompt in advance, it becomes easier to obtain a desired answer from the language model.

[0104] 7 is a schematic diagram showing an example of a prompt 210. The prompt 210 has an instruction statement 211, a list 105, and a list 107. In FIG. 7, the title of the list 105 is "List of Account Titles."

[0105] The instruction statement 211 is an instruction statement for causing the language model to suggest an account item to be re-registered in the transaction data 120[i] (i is an integer between 1 and n) included in the list 107. The account item to be suggested can be determined based on the transaction data 120[i] and the item 113 included in the list 105. The account item to be suggested can be selected from the item 112 included in the list 105. In the example shown in FIG. 7 , the instruction statement 211 can be an instruction statement for suggesting an account item to be re-registered in the transaction data 120[i] included in the list 107. In this case, the account item to be suggested can be determined based on the transaction data 120[i] and the item 113[1], the item 113[2], and the item 113[5]. The account item to be suggested can be selected from the item 112[1], the item 112[2], and the item 112[5]. The instruction 211 may be, for example, "Please select an account item from the list of account items for the following item name and transaction purpose."

[0106] In this specification, the account item to be re-registered in the transaction data 120 may be referred to as the fourth account item. The explanation for the fourth account item may also be referred to as the fourth explanation. In this case, the instruction 211 can be said to be an instruction for causing the language model to present the fourth account item. The fourth account item can be determined based on the transaction data 120[i] and the first explanation and the third explanation included in the list 105. The presented account item can be selected from the first account item and the third account item included in the list 105.

[0107] 7 shows an example in which the list 105 included in the prompt 210 does not include the item 111 shown in FIG. 6A. Also, FIG. 7 shows an example in which the list 107 included in the prompt 210 does not include the item 125 shown in FIG. 6B. As described above, it is possible to prevent the amount of text in the prompt 210 from increasing. This makes it easier to obtain a response sentence from a language model in later processing. It is also possible to shorten the time it takes to generate a response sentence using a language model. Note that the prompt 210 may include either item 111 or item 125.

[0108] The list 105 included in the prompt 210 preferably contains text. In Figure 7, the list 105 included in the prompt 210 is shown in a non-tabular format. For example, the character string "Account Title," which is the name of the item 112, is entered for each of the items 112[1], 112[2], and 112[5]. Similarly, the list 107 included in the prompt 210 preferably contains text.

[0109] [Step S15] In step S15, the information processing device 40 transmits the prompt 210 to the language model of the information processing device 50 via the network 30 (step S15a shown in FIG. 4). As a result, the information processing device 50 generates a response sentence 220 using the language model based on the prompt 210. The response sentence 220 includes, for example, an account item selected based on the information included in the prompt 210. The information processing device 50 transmits the response sentence 220 to the information processing device 40 via the network 30 (step S15b shown in FIG. 4). The reception unit 41 of the information processing device 40 receives the response sentence 220 transmitted from the information processing device 50. As a result, the information processing device 40 acquires the response sentence 220 (step S15c shown in FIG. 4).

[0110] 8 is a schematic diagram showing an example of a response sentence 220. In addition to transaction data 120[1] through 120[n] shown in FIG. 7, response sentence 220 includes items 128[1] through 128[n] and items 129[1] through 129[n]. That is, response sentence 220 includes items 121[1] through 121[n], items 123[1] through 123[n], items 128[1] through 128[n], and items 129[1] through 129[n]. Here, items 128[1] through 128[n] are collectively referred to as items 128, and items 129[1] through 129[n] are collectively referred to as items 129.

[0111] Items 128[1] through 128[n] can be proposed re-registration of, for example, account items to transaction data 120[1] through 120[n], respectively. In this case, items 128[1] through 128[n] can be considered the fourth account item. Items 129[1] through 129[n] can be used as descriptions of items 128[1] through 128[n], respectively. In other words, item 129 can be used as a description of the account item presented as a re-registration proposal. In the example shown in FIG. 8, the name of item 128 is used as the account item, and the name of item 129 is used as the account item description.

[0112] Items 129[1] through 129[n] can be considered the fourth explanatory text. Items 128[1] through 128[n] can be any of items 112[1], 112[2], and 112[5] included in prompt 210 shown in Figure 7. Items 129[1] through 129[n] can be any of items 113[1], 113[2], and 113[5] included in prompt 210 shown in Figure 7.

[0113] In the example shown in Figure 8, items 128[1] and 128[2] are set to "aaa expense," which is different from item 127[1] and item 127[2] shown in Figure 6B, respectively. That is, this example shows an example in which the language model presents "aaa expense," which is different from item 127[1] and item 127[2], as a re-registration proposal for account items related to transaction data 120[1] and transaction data 120[2]. Also, in the example shown in Figure 8, item 128[n] is set to "kk2 expense," similar to item 127[n] shown in Figure 6B. That is, this example shows an example in which the language model presents, as a re-registration proposal for account items related to transaction data 120[n], the account item "kk2 expense," which is the same as item 127[n], which is an account item already registered in transaction data 120[n]. Note that Figure 8 shows an example in which the language model presents item 112A shown in Figure 5A, i.e., the account item added to data table 101 in step S11, as a re-registration proposal, but account items other than item 112A may also be presented as re-registration proposals.

[0114] In the example shown in Fig. 8, items 129[1] and 129[2] are set to "ee, ff related," which is the description of the account item "aaa expense" shown in Fig. 7. Also, item 129[n] is set to "ee fee," which is the description of the account item "kk2 expense" shown in Fig. 7.

[0115] [Step S16] In step S16, the information processing device 40 prompts the user of the information terminal 20 to determine whether the proposed re-registration of the item 128, for example, the account item, is appropriate. For example, the processing unit 43 of the information processing device 40 transmits information included in the response sentence 220 shown in FIG. 8 to the information terminal 20, whereby the information is displayed on the display unit of the information terminal 20.

[0116] 9 is a schematic diagram showing an example of a screen layout displayed on the display unit 23 of the information terminal 20 as a result of the information processing device 40 performing the process in step S16. FIG. 9 can also be considered an example of a graphical user interface (GUI) related to the information processing system 10. The forms, icons, tables, etc. in the drawings related to the GUI exemplified in this embodiment, such as FIG. 9, are merely examples and are not particularly limited. The GUI can be configured as a web page that a user of the information terminal 20 accesses via a network. Alternatively, the GUI can be configured as a screen of a program application executed on the information terminal 20 used by the user.

[0117] As shown in Fig. 9, the display unit 23 displays items 121, 123, 128, and 129 included in transaction data 120[1] through 120[n]. In Fig. 9, these items are displayed as a list 130. In the example shown in Fig. 9, the title of the list 130 is "Transaction List" and it is displayed in a table format. In the example shown in Fig. 9, the first line of the list 130 shows the item name, and the second and subsequent lines show transaction data 120[1] through 120[n], respectively.

[0118] 9, an area 131 is provided in each row of the list 130 from the second row onward. For example, a check box can be displayed in the area 131 for each row. Note that instead of the check boxes, buttons such as radio buttons or text boxes may be displayed. In the example shown in FIG. 9, the area 131, item 121, item 123, item 128, and item 129 are displayed in this order from the left.

[0119] Here, it is preferable to highlight rows indicating transaction data 120 in which item 128 differs from item 127 shown in FIG. 6B . Examples of highlighting methods include adding a hatching pattern to the background of the row, making the background color of the row different from that of other rows, making at least one of the text color, text size, and font different from that of other rows, making the text in the row bold, or underlining the text in the row. As a result, the user of the information terminal 20 can easily recognize transaction data 120 in which an account item different from an already registered account item is presented as a re-registration proposal for the account item. In the example shown in FIG. 9 , a hatching pattern is added to rows indicating transaction data 120 in which item 128 differs from item 127 shown in FIG. 6B .

[0120] Item 127 shown in FIG. 6B , for example, the account title before re-registration, may be displayed on the display unit 23. For example, item 127 may be displayed between item 123 and item 128. That is, a column displaying item 127 may be provided in the list 130 between the column displaying item 123 and the column displaying item 128. Alternatively, when a user of the information terminal 20 selects transaction data 120 displayed on the display unit 23, item 127 of the selected transaction data 120 may be displayed on the display unit 23. Selection of transaction data 120 may be performed using, for example, a mouse or a keyboard. Furthermore, if the information terminal 20 is provided with a touch sensor, the user of the information terminal 20 can select transaction data 120 by touching the display unit 23. Note that the display unit 23 may display not only item 127 but also a description of item 127, for example, a description of the account title before re-registration.

[0121] In the example shown in Fig. 9, the button 133 is displayed. In Fig. 9, the button 133 displays "Register".

[0122] As described above, in step S16, the items 128 and 129 are presented to the user of the information terminal 20 for each transaction data 120, thereby performing processing to prompt the user to determine whether the items 128 are valid. Specifically, the transaction data 120 can be the transaction data 120 included in the list 107 shown in FIG. 6B.

[0123] After step S16 shown in FIG. 3 is performed, step S32 shown in FIG. 4 is performed. In step S32, the user of the information terminal 20 determines whether the item 128, for example, the proposed re-registration of an account item, is appropriate. For example, the user of the information terminal 20 checks the list 130 shown in FIG. 9 to determine whether the item 128 is appropriate for each transaction data 120. In the example shown in FIG. 9, the user of the information terminal 20 determines whether the item 128 is appropriate for each transaction data 120[1] to 120[n]. The user of the information terminal 20 can select transaction data 120 for which the item 128 is appropriate, for example, by checking a checkbox in area 131. After selecting transaction data 120 for which the item 128 is appropriate, the user of the information terminal 20 selects button 133. As a result, data indicating that the item 128 of the selected transaction data 120 is appropriate and the item 128 of the non-selected transaction data 120 is inappropriate is transmitted to the information processing device 40. In other words, the information terminal 20 accepts the data and transmits the accepted data to the information processing device 40. Note that a check box displayed in the area 131 of the transaction data 120 for which the item 128 is invalid may be checked. In this case, when the button 133 is selected, data indicating that the item 128 of the non-selected transaction data 120 is valid and that the item 128 of the selected transaction data 120 is invalid is transmitted to the information processing device 40.

[0124] The button 133 can be selected by the user of the information terminal 20, for example, by clicking or touching the button 133. The button 133 can also be selected using, for example, a keyboard. The button 133 does not have to be displayed on the display unit 23. For example, a form may be displayed on the display unit 23. In this case, the user of the information terminal 20 inputs text into the form representing transaction data 120 for which the item 128 is valid and transaction data 120 for which the item 128 is invalid. This allows the information terminal 20 to transmit data representing transaction data 120 for which the item 128 is valid and transaction data 120 for which the item 128 is invalid to the information processing device 40. The above also applies to other buttons displayed on the display unit 23.

[0125] 9, the checkboxes for transaction data 120[1] and 120[n] are checked, and the checkbox for transaction data 120[2] is not checked. When the user of information terminal 20 selects button 133 in this state, data indicating that items 128 of transaction data 120[1] and 120[n] are valid and item 128 of transaction data 120[2] is invalid is transmitted to information processing device 40.

[0126] The information processing device 40 or the information processing device 50 may determine whether the item 128 is valid. For example, the information processing device 40 or the information processing device 50 can determine whether the item 128 is valid by using a neural network model. For example, in addition to the items 121, 123, 128, and 129 shown in FIG. 9 , the item 127, which is the account item before re-registration shown in FIG. 6B , and the explanation of the item 127 are input to the neural network model. This allows the information processing device 40 or the information processing device 50 to determine whether the item 128 is valid.

[0127] [Step S17] After step S32 shown in Fig. 4 is performed, step S17 shown in Fig. 3 is performed. In step S17, the information processing device 40 receives a determination result as to whether the item 128 is valid. Specifically, the receiving unit 41 of the information processing device 40 receives data indicating that the item 128 of the transaction data 120 selected by the user of the information terminal 20 in step S32 is valid and that the item 128 of the transaction data 120 not selected is invalid, for example.

[0128] [Step S18] In step S18, the information processing device 40 registers the proposed reregistration of an item 128, for example, an account item, as an account item related to the transaction data 120 for which the proposed reregistration is appropriate. Specifically, the processing unit 43 of the information processing device 40 registers the proposed reregistration of the account item, i.e., the proposed reregistration presented by the language model in step S15, in the database 45 as an account item related to the transaction data 120. In the example shown in FIG. 9 , the item 128 of the transaction data 120[1], "aaa expense," is registered in the database 45 as an account item related to the transaction data 120[1]. Furthermore, the item 128 of the transaction data 120[n], "kk2 expense," is registered in the database 45 as an account item related to the transaction data 120[n]. In this way, the information processing device 40 can reregister an account item for the transaction data 120 for which the proposed reregistration of the account item is determined to be appropriate.

[0129] [Step S19] In step S19, the information processing device 40 determines whether all of the items 128, for example, the proposed re-registration of account items, are valid. For example, in step S32 shown in FIG. 4, if data indicating that all of the items 128 of the transaction data 120[1] through 120[n] are valid is transmitted to the information processing device 40, the processing unit 43 of the information processing device 40 determines that all of the items 128 are valid. If it is determined that all of the items 128 are valid, the information processing system 10 terminates processing. If it is determined that an invalid item 128 exists, the information processing system 10 performs processing from step S20 onward.

[0130] [Step S20] In step S20, the information processing device 40 collects transaction data 120 for which the item 128 is determined to be inappropriate. For example, the processing unit 43 of the information processing device 40 collects transaction data 120 for which the proposed re-registration of an account item is determined to be inappropriate. The information processing device 40 can generate a list (not shown) including the collected transaction data 120. In the example shown in FIG. 9, transaction data 120[2] is included in the list.

[0131] In this specification, the transaction data 120 in which the item 128 is determined to be invalid is referred to as the third transaction data. The third transaction data may be the transaction data 120 collected by the information processing device 40 in step S20.

[0132] [Step S21] In step S21, the information processing device 40 generates a prompt 230. Specifically, the processing unit 43 of the information processing device 40 generates the prompt 230 for presenting the reason why the language model presented item 128 as a re-registration proposal for the account item related to the third transaction data in step S15. The processing unit 43 of the information processing device 40 generates the prompt 230 for presenting the reason why, for example, item 128 shown in FIG. 8 differs from item 127 shown in FIG. 6B for the third transaction data.

[0133] FIG. 10A is a schematic diagram illustrating an example of a prompt 230. The prompt 230 includes an instruction statement 231, a list 106, transaction data 120 collected in step S20, and items 127 and 128 related to the transaction data 120 collected in step S20. In the example shown in FIG. 10A, transaction data 120, item 127, and item 128 include transaction data 120[2], item 127[2], and item 128[2], respectively. Transaction data 120[2] includes items 121[2] and 123[2]. In the example shown in FIG. 10A, the item name of item 127 is "Account Title (Before Re-registration)," and the item name of item 128 is "Account Title (After Re-registration)." Here, data including transaction data 120, item 127, and item 128 is referred to as data 140. Specifically, data including transaction data 120[i], item 127[i], and item 128[i] is referred to as data 140[i]. An example of data 140[2] is shown in FIG. 10A. Note that the prompt 230 may include multiple pieces of data 140.

[0134] List 106 includes item 112 that is the same as item 127 included in prompt 230, and item 112 that is the same as item 128. List 106 also includes item 113, which is an explanation of these items 112. In the example shown in FIG. 10A , item 127[2] is "kk2 expense," so item 112[2], which is also "kk2 expense," and item 113[2], which is an explanation of item 112[2], are included in list 106. Also, because item 128[2] is "aaa expense," item 112[5], which is also "aaa expense," and item 113[5], which is an explanation of item 112[5], are included in list 106. Note that in FIG. 10A , the title of list 106 is "List of Account Titles."

[0135] The instruction statement 231 is an instruction statement for presenting the reason why the language model presented item 128 as a re-registration proposal for the account item related to the transaction data 120 included in the prompt 230 in step S15. The reason can be presented based on the transaction data 120, the explanation for item 127, and the explanation for item 128. In the example shown in FIG. 10A , the instruction statement 231 can be an instruction statement for presenting the reason why item 128[2] was presented as a re-registration proposal for the account item related to the transaction data 120[2]. In the example shown in FIG. 10A , the reason can be presented based on the transaction data 120[2], item 113[2], which can be the explanation for item 127[2], and item 113[5], which can be the explanation for item 128[2]. The instruction statement 231 can be, for example, "Please explain why you registered the account items as follows for the following transactions."

[0136] 10A shows an example in which the list 106 included in the prompt 230 does not include item 111. Also, FIG. 10A shows an example in which the transaction data 120 included in the prompt 230 does not include item 125. Furthermore, it is preferable that the list 106 included in the prompt 230 includes text.

[0137] [Step S22] In step S22, the information processing device 40 transmits the prompt 230 to the language model of the information processing device 50 via the network 30 (step S22a shown in FIG. 4). As a result, the information processing device 50 generates a response sentence 240 using the language model based on the prompt 230.

[0138] FIG. 10B is a schematic diagram showing an example of a response sentence 240. The response sentence 240 includes an item 241. The item 241 can be the reason why the language model presented the item 128 as a proposed account item re-registration in step S15 for the transaction data 120 included in the prompt 230. In the example shown in FIG. 10B, the item 241 is "For the reason gg, the account item for the transaction with the product name "abc2" and the transaction purpose "for bb2" is "aaa expense" rather than "kk2 expense."

[0139] The information processing device 50 transmits the response sentence 240 to the information processing device 40 via the network 30 (step S22b shown in FIG. 4). The reception unit 41 of the information processing device 40 receives the response sentence 240 transmitted from the information processing device 50. In this way, the information processing device 40 acquires the response sentence 240 (step S22c shown in FIG. 4).

[0140] In an information processing method according to one aspect of the present invention, a series of processes are performed using, for example, a list of account items and transaction data 120. Therefore, it is preferable that the language model used in the process of step S15 is the same as the language model used in the process of step S22. In other words, it is preferable that prompt 230 be sent to the language model that accepts prompt 210. With this configuration, the accuracy of response sentence 220 and the accuracy of response sentence 240 can be maintained constant.

[0141] The language model used in the processing of step S15 may be different from the language model used in the processing of step S22. That is, the configuration may be such that prompt 210 is sent to a first language model and prompt 230 is sent to a second language model different from the first language model. With such a configuration, the processing using the first language model and the processing using the second language model can be performed using different information processing devices, specifically different information processing devices 50. This reduces the computational load per information processing device.

[0142] [Step S23] In step S23, the information processing device 40 prompts the user of the information terminal 20 to correct the item 113. For example, the processing unit 43 of the information processing device 40 transmits information included in the response sentence 240 shown in FIG. 10B to the information terminal 20, whereby the information is displayed on the display unit of the information terminal 20.

[0143] FIG. 11 is a schematic diagram showing an example of a screen layout displayed on the display unit 23 as a result of the information processing device 40 performing the process in step S23. As shown in FIG. 11 , an item 241 and a list 151 are displayed on the display unit 23. The list 151 includes records 115 that include at least one of the items 127 and 128 included in the prompt 230 shown in FIG. 10A , namely, the item 112. In the example shown in FIG. 11 , the title of the list 151 is "List of Account Items," and the list is displayed in a table format. In the example shown in FIG. 11 , the first line of the list 151 indicates the item name, and each of the second and subsequent lines indicates a record 115.

[0144] In the example shown in FIG. 10A , item 127[2] is “kk2 expense,” and therefore record 115[2] including item 112 that is also “kk2 expense” is included in list 151 shown in FIG. 11 . Also, in the example shown in FIG. 10A , item 128[2] is “aaa expense,” and therefore record 115[5] including item 112 that is also “aaa expense” is included in list 151 shown in FIG. 11 . Records 115 including items 112 that are different from both items 127 and 128 may also be included in list 151. For example, all records 115 included in list 105 shown in FIG. 6A may be included in list 151. Alternatively, records 115 that are not included in list 105 but are included in data table 101 shown in FIG. 5B may also be included in list 151. For example, records 115 including the same item 111 as item 111 included in list 105 may also be included in list 151. It should be noted that the list 151 does not necessarily have to include the item 111 .

[0145] In the example shown in FIG. 11 , a form 141 for correcting the item 113 is displayed in the area where the item 113 is displayed. The form 141 is also referred to as an input form, area, field, or input field. For example, when a user of the information terminal 20 selects a record 115 displayed on the display unit 23, a form 141 for correcting the item 113 of the selected record 115 can be displayed. The record 115 can be selected using, for example, a mouse or a keyboard. Furthermore, when a touch sensor is provided in the information terminal 20, the user of the information terminal 20 can select the record 115 by touching the display unit 23. In the example shown in FIG. 11 , the form 141 is displayed in the area where the item 113 of record 115 [5] is displayed. Note that in FIG. 11 , a cursor indicating the position where characters are to be entered is shown in the form 141.

[0146] In the example shown in Fig. 11, the button 143 is displayed. In Fig. 11, the button 143 displays "Edit".

[0147] 11, for example, at least some of the transaction data 120[1] to 120[n] shown in FIG. 9 may be displayed on the display unit 23. In the example shown in FIG. 11, a list 153 is displayed. The list 153 includes transaction data in which the same account item as the item 112 included in the list 151 is included in one or both of the items 127 and 128. In the example shown in FIG. 11, items 121, 123, 127, and 128 are displayed as the transaction data. Therefore, data 140 is displayed as the transaction data in the list 153. In the example shown in FIG. 11, data 140[1], data 140[2], and data 140[n] are displayed as the data 140.

[0148] In Fig. 11, the title of list 153 is "(Reference) Transaction List" and it is shown in a table format. In the example shown in Fig. 11, the first line of list 153 shows the item name, and the second and subsequent lines show data 140. Note that Fig. 11 shows an example in which list 153 does not include item 125, similar to list 130 shown in Fig. 9.

[0149] By displaying the list 153 on the display unit 23, it is possible to present to the user of the information terminal 20, for example, transaction data 120 among the transaction data 120[1] to 120[n] shown in Fig. 9, in which one or both of the items 127 and 128 are the same as the items 127 or 128 related to the transaction data 120 included in the prompt 230 shown in Fig. 10A. This allows the user of the information terminal 20 to revise the description of the account item by referring to the transaction data 120 related to the account item whose description is a candidate for revision.

[0150] In this specification and the like, presenting information contained in data is simply referred to as presenting data.

[0151] The description of item 127 and the description of item 128 may be included in list 153. Specifically, list 153 may be provided with a column for displaying the description of item 127 and a column for displaying the description of item 128. Alternatively, when a user of information terminal 20 selects data 140 displayed on display unit 23, one or both of the description of item 127 and the description of item 128 included in the selected data 140 may be displayed on display unit 23. Furthermore, when the user of information terminal 20 selects item 127, the description of the selected item 127 may be displayed on display unit 23, and when the user of information terminal 20 selects item 128, the description of the selected item 128 may be displayed on display unit 23. The above selection may be made using, for example, a mouse or a keyboard. Furthermore, when the information terminal 20 is provided with a touch sensor, the user of information terminal 20 can make the above selection by touching the display unit 23.

[0152] 11 shows an example in which list 153 is displayed below button 143, but this is not a limitation of the present invention. For example, list 153 may be displayed below list 151, and button 143 may be displayed below list 153.

[0153] As described above, in step S23, the information processing device 40 presents the item 241, which is the reason why the item 128 was presented as a re-registration proposal for the account item, to the user of the information terminal 20. This allows the information processing device 40 to perform processing to prompt the user of the information terminal 20 to correct the item 113 registered in the data table 101 shown in FIG. 5B.

[0154] 12 is a schematic diagram showing an example of a screen layout displayed on the display unit 23 by the information processing device 40 performing the process in step S23 when there are two pieces of transaction data 120 whose items 128 are determined to be invalid among the transaction data 120[1] to 120[n] shown in FIG. 9. The following mainly describes the differences from FIG. 11, and omits the description of similarities as appropriate.

[0155] In the example shown in FIG. 12, two items 241 are displayed. That is, for each of the multiple transaction data 120 for which item 128 was determined to be inappropriate, the reason why item 128 was presented as a proposed account item re-registration is displayed on the display unit 23. In FIG. 12, the two items 241 are distinguished by being written as item 241[1] and item 241[2]. In the example shown in FIG. 12, item 241[1] is described as "For reason gg, the account item for the transaction with the product name "abc2" and the transaction purpose "for bb2" is more appropriate than the account item "aaa expense" than the account item "kk2 expense," just like item 241 shown in FIG. 11. Also, item 241[2] is described as "Furthermore, for reason hh, the account item for the transaction with the product name "abcde" and the transaction purpose "for use in fgh" is more appropriate than the account item "aaa2 expense" than the account item "kk1 expense."

[0156] 12 includes the account items "aaa expense" and "kk2 expense" included in item 241[1], as well as the account items "aaa2 expense" and "kk1 expense" included in item 241[2]. Specifically, list 151 includes not only records 115 whose item 112 is "aaa expense" and records 115 whose item 112 is "kk2 expense," but also records 115 whose item 112 is "aaa2 expense" and records 115 whose item 112 is "kk1 expense." In the example shown in FIG. 12, item 111 of record 115 whose item 112 is "aaa2 expense" is set to "cc1 part," and item 113 is set to "expenses related to pq."

[0157] 12 is displayed on the display unit 23 in step S23, the list 106 shown in FIG. 10A includes not only items 112[2] and 112[5] as items 112, but also "KK1 expense" and "AAA2 expense." The list 106 also includes not only items 112[2] and 112[5] as items 113, but also the description of "KK1 expense": "Purchase price of EE, expenses for FF, etc." and the description of "AAA2 expense": "Expenses related to PD." The prompt 230 shown in FIG. 10A also includes data 140[2], as well as data 140 in which item 121 is "abcde," item 123 is "for use with fgh," item 127 is "KK1 expense," and item 128 is "AAA2 expense."

[0158] 12 includes data 140 in which one or both of items 127 and 128 are any of "kk1 fee," "kk2 fee," "aaa fee," and "aaa2 fee," which are items 112 included in list 151. In addition to the data 140 shown in Fig. 11, list 153 shown in Fig. 12 includes data 140 in which items 121, 123, 127, and 128 are "abcd3," "assuming bdf," "ikm fee," and "aaa2 fee," respectively, and data 140 in which items 121, 123, 127, and 128 are "abcd3," "assuming bdf," "ikm fee," and "aaa2 fee," respectively. In the example shown in FIG. 12 , in data 140 with the product name "abcd3", item 128 is different from item 127, but item 128 is determined to be appropriate, so there is no need to modify the description of "ikm expense" and it is not included in list 151. "ikm expense" is an account item included in data 140 with the product name "abcd3". Note that "ikm expense" may also be included in list 151. For example, it is possible that both item 127 and item 128 are included in list 151 for some data 140, and that neither item 127 nor item 128 are included in list 151 for other data 140.

[0159] Among the transaction data 120[1] through 120[n], there may be three or more pieces of transaction data 120 for which the item 128 is determined to be invalid. Even in this case, see FIG. 12 for an example of the screen layout displayed on the display unit 23 by the information processing device 40 performing the process in step S23. For example, three or more items 241 may be displayed.

[0160] The content included in item 241 may be displayed in tabular form on the display unit 23. For example, the information processing device 40 can convert item 241 included in response sentence 240 shown in FIG. 10B into tabular form, thereby displaying the content included in item 241 in tabular form on the display unit 23. For example, a table in which the product name, transaction purpose, account item before re-registration, and a re-registration proposal for the account item are stored in each row as the content included in item 241 can be displayed on the display unit 23. By displaying the content included in item 241 in tabular form on the display unit 23, particularly when multiple items 241 are displayed on the display unit 23, the user of the information terminal 20 can easily recognize, for each transaction data, the reason why item 128 was presented as a re-registration proposal for the account item, for example.

[0161] Furthermore, for at least a portion of the transaction data 120 for which the item 128 is determined to be invalid, the item 241 may not be displayed. Whether or not to display the item 241 can be selected by the user of the information terminal 20, for example, in step S32 shown in Fig. 4. This can shorten the time required to generate the response sentence 240 shown in Fig. 10B in step S22. Also, the amount of text in the prompt 230 shown in Fig. 10A can be reduced.

[0162] After step S23 shown in Fig. 3 is performed, step S33 shown in Fig. 4 is performed. In step S33, the user of the information terminal 20 modifies the item 113, for example, the item 113 included in the list 151. In the examples shown in Figs. 11 and 12, the user of the information terminal 20 modifies the item 113 by inputting an explanation of the account item into form 141. After modifying the item 113, the user of the information terminal 20 selects button 143. As a result, data representing the modified item 113 is transmitted to the information processing device 40. In other words, the information terminal 20 receives data representing the modified item 113 and transmits the received data to the information processing device 40.

[0163] [Step S24] In step S24, the information processing device 40 accepts the correction of the item 113. Specifically, the accepting unit 41 included in the information processing device 40 accepts data representing the corrected item 113. More specifically, the accepting unit 41 included in the information processing device 40 accepts the data representing the corrected item 113 transmitted from the information terminal 20.

[0164] [Step S25] In step S25, the information processing device 40, specifically the processing unit 43 included in the information processing device 40, registers the corrected item 113 in the data table 101 shown in Fig. 5B. In other words, the information processing device 40 corrects the item 113 registered in the data table 101. Thereafter, the information processing system 10 performs step S12 and the subsequent processes again.

[0165] As described above, the information processing method of one aspect of the present invention can automate the re-registration of account items related to transactions. Furthermore, for transaction data in which an inappropriate re-registration proposal is presented, the reason why the re-registration proposal was presented as the re-registration proposal for the account item can be presented to the user of the information terminal. This allows the user to easily revise the description of the account item so that the language model can present an appropriate account item as the re-registration proposal.

[0166] 3, the receiving unit 41 of the information processing device 40 may receive one or more records 115 registered in the data table 101 shown in FIG. 2B. In this case, the items 111A, 112A, and 113A included in the input data 103 shown in FIG. 5A are all the same as the items 111, 112, and 113 included in the data table 101. For example, the records 115 registered in the data table 101 may be clustered based on the item 112, and input data 103 may be generated for each cluster. For example, records 115 including similar items 112 may be included in the same cluster.

[0167] In the above case, in step S11, the receiving unit 41 can receive, for example, the records 115 belonging to the first cluster collectively as the input data 103. Thereafter, the information processing system 10 performs the processes from step S12 onward shown in Fig. 3, and when the processes are completed, can receive the records 115 belonging to the second cluster collectively and perform the processes from step S12 onward again.

[0168] As described above, the user of the information terminal 20 can check whether the account items registered in each of the multiple transaction data 120, for example, with the same or similar product name and transaction purpose, are valid, and if they are invalid, can re-register the account items. The user of the information terminal 20 can check that the same account items are registered in all of the multiple transaction data 120, for example, with the same product name and transaction purpose. Then, if an account item different from that registered in the other transaction data 120 is registered in some transaction data 120, the user of the information terminal 20 can re-register the account items.

[0169] Clustering can be performed based on the similarity between items 112. For example, records 115 including items 112 that are highly similar to each other can be included in the same cluster. The similarity between items 112 can be calculated using a method similar to the method that can be used to calculate the similarity of item 113 to item 113A.

[0170] As described above, by using the information processing method of one embodiment of the present invention, accounting work can be performed with less effort. Furthermore, the information processing method of one embodiment of the present invention can be an information processing method with excellent convenience, usefulness, and reliability. Furthermore, the information processing device and information processing system of one embodiment of the present invention can be an information processing device and information processing system that can perform accounting work with less effort, and can also be an information processing device and information processing system with excellent convenience, usefulness, and reliability.

[0171] The above is an example of the information processing method according to one embodiment of the present invention.

[0172] <Configuration Example 2 of Information Processing System> Fig. 13 is a block diagram showing a configuration example of the information processing system 10. In Fig. 13, the configuration example of the information processing device 40 will be mainly described.

[0173] The information processing device 40 includes a receiving unit 41, a storage unit 44, a processing unit 43, an output unit 47, and a transmission path 49. The information processing device 40 may include a database 45.

[0174] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in the block diagrams. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions. For example, part of the processing unit 43 may function as the reception unit 41. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 43 may be executed by different servers depending on the processing.

[0175] [Accepting Unit 41] The accepting unit 41 has a function of accepting data from outside the information processing device 40. The data accepted by the accepting unit 41 is preferably text data.

[0176] For example, the reception unit 41 has a function of receiving data from the information terminal 20 via the network 30. Examples of the data include input data 103, data indicating whether the proposed re-registration of the account item presented by the language data is appropriate, and data indicating an explanation of the account item. Furthermore, for example, the reception unit 41 has a function of receiving data from the information processing device 50 via the network 30. Examples of the data include a response sentence 220 and a response sentence 240. The data received by the reception unit 41 is supplied to one or both of the memory unit 44 and the processing unit 43 via the transmission path 49.

[0177] [Storage Unit 44] The storage unit 44 has a function of storing a program executed by the processing unit 43. The storage unit 44 may also have a function of storing data generated by the processing unit 43 (e.g., calculation results, analysis results, inference results), data input to the reception unit 41, etc.

[0178] The storage unit 44 preferably has a function of storing an instruction sentence in the prompt. For details of the instruction sentence in the prompt, please refer to the description of the information processing method according to one aspect of the present invention.

[0179] The storage unit 44 preferably includes a database 45. The database 45 stores, for example, data 100 shown in FIG. 2A and a data table 101 shown in FIG. 2B. As described above, the data 100 includes transaction data 120 and items 127, such as account items, registered in the transaction data 120. The transaction data 120 registered in the database 45 may be referred to as first transaction data.

[0180] The data table 101 includes a record 115. The record 115 includes an item 111, an item 112, and an item 113. That is, the record 115 can include, for example, a department, an account item, and an explanation of the account item. The information processing device 40 has a function of retrieving data from the database 45 and a function of recording data in the database 45.

[0181] The information processing device 40 may have a database 45 outside the storage unit 44. The information processing device 40 may have a function to retrieve data from a database 45 that exists outside the storage unit 44, outside the information processing device 40, or outside the information processing system 10. The information processing device 40 may also have a function to record data in a database 45 that exists outside the storage unit 44, outside the information processing device 40, or outside the information processing system 10. The information processing device 40 may also have a function to retrieve data from both its own database and an external database. The information processing device 40 may also have a function to record data in both its own database and an external database.

[0182] A file server may be used instead of the database. For example, when using files stored in a file server, it is preferable that the database has paths to files stored in the file server.

[0183] Furthermore, the information processing device 40 may have a function of extracting at least one piece of data from data managed by the information terminal 20 or an IMAP server or the like.

[0184] The storage unit 44 includes at least one of a volatile memory and a nonvolatile memory. Examples of the volatile memory include a dynamic random access memory (DRAM) and a static random access memory (SRAM). Examples of the nonvolatile memory include a resistive random access memory (ReRAM), a phase change random access memory (PRAM), a ferroelectric random access memory (FeRAM), a magnetoresistive random access memory (MRAM), and a flash memory. The storage unit 44 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 44 may also include a recording media drive. Examples of recording media drives include a hard disk drive (HDD) and a solid state drive (SSD).

[0185] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)." NOSRAM refers to a memory in which memory cells are two-transistor (2T) or three-transistor (3T) gain cells and transistors (also called OS transistors) that use metal oxide in their channel formation regions. OS transistors have an extremely small leakage current, i.e., a current that flows between the source and drain in an off state. NOSRAM can be used as a nonvolatile memory by retaining a charge corresponding to data in the memory cell using its extremely small leakage current characteristic. In particular, NOSRAM can read stored data without destroying it (nondestructive readout), making it suitable for arithmetic processing in which only data read operations are repeated a large number of times. NOSRAM can increase its data capacity by stacking layers, and therefore can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0186] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM" and refers to a RAM having 1T (transistor) 1C (capacitor) type memory cells. DOSRAM is a DRAM formed using OS transistors, and is a memory that temporarily stores information sent from an external device. DOSRAM is a memory that takes advantage of the low off-state current of OS transistors.

[0187] In this specification and the like, a metal oxide refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply as OSs), and the like. For example, when a metal oxide is used for a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor.

[0188] The metal oxide included in the channel formation region preferably contains indium (In). When the metal oxide included in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide included in the channel formation region is preferably an oxide semiconductor containing element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, a combination of two or more of the above elements may be used as element M. The element M is, for example, an element having a high bond energy with oxygen. For example, it is an element having a higher bond energy with oxygen than indium. The metal oxide contained in the channel formation region is preferably a metal oxide containing zinc (Zn), since zinc-containing metal oxides may be easily crystallized.

[0189] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium, but 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.

[0190] [Processing Unit 43] The processing unit 43 has a function of performing processes such as calculation, analysis, and inference using data supplied from at least one of the reception unit 41, the storage unit 44, and the database 45. The processing unit 43 can supply the generated data (e.g., calculation results, analysis results, and inference results) to at least one of the storage unit 44, the database 45, and the output unit 47.

[0191] The processing unit 43 has a function of acquiring data from one or both of the storage unit 44 and the database 45. The processing unit 43 also has a function of recording or registering data in one or both of the storage unit 44 and the database 45.

[0192] The processing unit 43 has a function of adding the input data 103 shown in Fig. 5A to the data table 101 as record 115 as shown in Fig. 5B. The processing unit 43 has a function of adding, for example, the department, account item, and account item description included in the input data 103 to the data table 101 as items 111, 112, and 113, respectively.

[0193] The processing unit 43 has a function of collecting at least some of the records 115 included in the data table 101 based on the items 113 shown in Fig. 5B and generating a list 105 as shown in Fig. 6A. The processing unit 43 has a function of calculating, for example, the similarity of each of the multiple items 113 included in the data table 101 shown in Fig. 5B to the item 113A shown in Fig. 5A and collecting records 115 including the items 113 whose similarity is equal to or greater than a certain value.

[0194] The processing unit 43 has a function of collecting transaction data 120 in which the items 112 included in the list 105 are registered, and generating a list 107 as shown in Fig. 6B. The transaction data 120 included in the list 107 may be referred to as second transaction data.

[0195] The processing unit 43 has a function of generating a prompt 210 having a list 105, a list 107, and an instruction statement 211, as shown in FIG. 7. The instruction statement 211 is an instruction statement for causing the language model to select and present an account item to be re-registered in the transaction data 120[i] included in the list 107 from the items 112 included in the list 105. The account item can be selected based on the transaction data 120[i] and the items 113 included in the list 105. As shown in FIG. 2A, the transaction data 120 can have an item 121 that is a product name and an item 123 that is a transaction purpose. The transaction data 120 can also have an item 125 that is a transaction date and time.

[0196] The processing unit 43 has a function of presenting the items 128 and 129 included in the response sentence 220 as shown in Fig. 8 to the user of the information processing system 10 for each transaction data 120. This allows the processing unit 43 to prompt the user of the information processing system 10 to determine whether the items 128 are appropriate. The processing unit 43 can acquire the response sentence 220 by transmitting a prompt 210 to the language model of the information processing device 50 via the network 30.

[0197] The processing unit 43 has a function of registering the item 128 in the database 45 as an account item related to the transaction data 120 for which the user of the information processing system 10 has determined that the item 128 is valid. The processing unit 43 has a function of generating a prompt 230, as shown in FIG. 10A , which includes the transaction data 120 for which the user of the information processing system 10 has determined that the item 128 is invalid, the items 127 and 128 related to the transaction data 120, an explanation for the item 127, an explanation for the item 128, and an instruction statement 231. As described above, the transaction data 120 for which the user of the information processing system 10 has determined that the item 128 is invalid may be referred to as third transaction data. The instruction statement 231 is an instruction statement for causing the language model to present the reason why the item 128 has been presented as a re-registration proposal for the account item related to the transaction data 120 included in the prompt 230. The language model can present the reason based on the transaction data 120, the description of item 127, and the description of item 128.

[0198] The processing unit 43 has a function of presenting the item 241 included in the response sentence 240 shown in FIG. 10B to the user of the information processing system 10. As a result, the processing unit 43 can prompt the user of the information terminal 20 to correct the item 113 registered in the data table 101 shown in FIG. 5B. In this case, the processing unit 43 can present the user of the information processing system 10 with second transaction data in which one or both of the items 127 and 128 are identical to the items 127 and 128 related to the third transaction data. When the user of the information processing system 10 corrects the item 113, the processing unit 43 has a function of registering the corrected item 113 in the data table 101. The processing unit 43 can acquire the response sentence 240 by transmitting a prompt 230 to the language model of the information processing device 50 via the network 30.

[0199] The processing unit 43 may include, for example, an arithmetic circuit, a central processing unit (CPU), and a graphics processing unit (GPU).

[0200] The processing unit 43 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 43 may also have a quantum processor. The processing unit 43 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of the memory area of ​​the processor and the storage unit 44.

[0201] The processing unit 43 may have a main memory. The main memory may include at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read only memory (ROM). The main memory may also include at least one of the above-mentioned NOSRAM and DOSRAM.

[0202] The RAM may be, for example, a DRAM or an SRAM, and a virtual memory space is allocated and used as a working space for the processing unit 43. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 44 are loaded into the RAM for execution. The data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 43.

[0203] The ROM can store a BIOS (Basic Input / Output System), firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROMs include UV-EPROMs (Ultra-Violet Erasable Programmable Read Only Memories), which allow stored data to be erased by exposure to ultraviolet light, EEPROMs (Electrically Erasable Programmable Read Only Memories), and flash memories.

[0204] The processing unit 43 can have at least one of an OS transistor, a transistor having silicon in a channel formation region (Si transistor), and a transistor having a layered two-dimensional material such as graphene or transition metal dichalcogenide (TMD) in a channel formation region.

[0205] The processing unit 43 preferably includes an OS transistor. Because an OS transistor has an extremely small off-state current, using the OS transistor as a switch for retaining charge (data) flowing into a capacitor functioning as a memory element can ensure a long data retention period. By utilizing this characteristic in at least one of the register and cache memory of the processing unit, the processing unit can be operated only when necessary and can be turned off at other times by saving information from the previous processing in the memory element. In other words, normally-off computing is possible, thereby enabling low power consumption of the information processing system 10.

[0206] [Output Unit 47] The output unit 47 has a function of outputting data based on the processing result of the processing unit 43. The output unit 47 can supply at least one of the calculation result, analysis result, and inference result of the processing unit 43 to the outside of the information processing device 40.

[0207] The output unit 47 has a function of outputting data to the outside of the information processing device 40. For example, the output unit 47 has a function of outputting data to the information processing device 50 via the network 30. The output unit 47 has a function of outputting data generated by the processing unit 43 to the information processing device 50. The data can be created based on data received from the information terminal 20, for example. Examples of data output to the information processing device 50 include a prompt 210 and a prompt 230.

[0208] Furthermore, for example, the output unit 47 has a function of outputting data to the information terminal 20 via the network 30. The output unit 47 can output data generated by the processing unit 43 to the information terminal 20. The data can be created based on data received from the information processing device 50, for example. Alternatively, the output unit 47 can output the data itself received from the information processing device 50 to the information terminal 20. Examples of data to be output to the information terminal 20 include a response sentence 220 and a response sentence 240.

[0209] The data can be output, for example, by displaying it on the display screen of the information terminal 20, or by outputting a file in a format such as txt, docx, xml, pdf, or csv.

[0210] [Transmission Path 49] The transmission path 49 has a function of transmitting data. Data can be transmitted and received between the reception unit 41, the storage unit 44, the processing unit 43, and the output unit 47 via the transmission path 49.

[0211] <Configuration Example 3 of Information Processing System> Fig. 14 is a schematic diagram showing an example of the information processing system 10 that is different from Fig. 1. In the information processing system 10 shown in Fig. 14, an information processing device 40 and a plurality of information terminals 20 are connected via a network 31. Furthermore, the information processing device 40 is connected to an information processing device 50 via a network 33. In Fig. 14, the above-mentioned information terminals 20a to 20d are shown as examples of the information terminals 20.

[0212] A user of the information processing system 10 can access the information processing device 40 from the information terminal 20. The user can then receive a service using the information processing method according to one aspect of the present invention.

[0213] In the information processing system 10 shown in Figure 14, the data flow between the information terminal 20 and the information processing device 40, and the data flow between the information processing device 40 and the information processing device 50 can be understood by referring to the explanation in Figure 1 by replacing network 31 and network 33 with network 30, respectively.

[0214] An organization such as a company that provides a service using the information processing method of one embodiment of the present invention (hereinafter also referred to as a service provider) can provide the service using the information processing device 40. The service provider does not need to prepare the information processing device 50 on its own, but can use the information processing device 50 via the network 33.

[0215] Network 31 is a computer network smaller than network 33. Typically, network 31 is a local network, and network 33 is a global network. It is preferable to use an intranet or an extranet as network 31. It is preferable to use the Internet, which is the foundation of the World Wide Web (WWW), as network 33. In this embodiment, an example will be mainly described in which an intranet is used as network 31 and the Internet is used as network 33.

[0216] Alternatively, the network 31 and the network 33 may be computer networks such as PAN, LAN, CAN, MAN, WAN, and GAN.

[0217] The information processing system 10 shown in FIG. 14 is suitable for a case where a user who uses an information terminal 20 and a service provider belong to the same organization such as a company.

[0218] For example, it is preferable that data is transmitted and received between the information terminal 20 and the information processing device 40 using a network 31 established within an organization such as a company. It is also preferable that data is transmitted and received between the information processing device 40 and the information processing device 50 using a network 33 (typically the Internet). This allows applications, tools, services, etc. provided outside the organization to be used more safely than when the information terminal 20 is directly connected to the information processing device 50 via the Internet.

[0219] A plurality of configuration examples shown in this embodiment mode can be combined as appropriate.

[0220] 10: Information processing system, 20: Information terminal, 20a: Information terminal, 20b: Information terminal, 20c: Information terminal, 20d: Information terminal, 21: Housing, 23: Display unit, 30: Network, 31: Network, 33: Network, 40: Information processing device, 41: Reception unit, 43: Processing unit, 44: Storage unit, 45: Database, 47: Output unit, 49: Transmission path, 50: Information processing device, 100: Data, 101: Data table, 103: Input data, 105: List, 106: List, 107: List, 111: Item Item, 111A: Item, 112: Item, 112A: Item, 113: Item, 113A: Item, 115: Record, 120: Transaction Data, 121: Item, 123: Item, 125: Item, 127: Item, 128: Item, 129: Item, 130: List, 131: Area, 133: Button, 140: Data, 141: Form, 143: Button, 151: List, 153: List, 210: Prompt, 211: Instruction, 220: Response, 230: Prompt, 231: Instruction, 240: Response, 241: Item

Claims

An information processing method using a database, comprising: The database includes a data table including a plurality of records and a plurality of first transaction data. Each of the plurality of records includes a first account item and a first explanation that is an explanation of the first account item, In each of the plurality of first transaction data, any one of the plurality of first account items is registered as a second account item, The explanation of the first account item corresponding to the second account item is set as a second explanation; In a first step, a third account title and a third explanation that is an explanation of the third account title are added to the data table; In a second step, at least a portion of the records is collected based on the first description and the third description, and a first list is generated that includes the first account title and the first description and the third account title and the third description included in the collected records; In a third step, the first transaction data in which the first account item included in the first list is registered is collected as second transaction data, and a second list including the second transaction data is generated; In a fourth step, a first prompt is generated having the first list, the second list, and a first instruction; the first instruction sentence is an instruction sentence for causing a language model to select and present a fourth account item, which is an account item to be re-registered in the second transaction data, from the first account item and the third account item included in the first list based on the second transaction data and the first explanatory sentence and the third explanatory sentence included in the first list; In a fifth step, a first response sentence is generated using the language model based on the first prompt; In a sixth step, the fourth account item and a fourth explanation which is an explanation of the first account item or the third account item corresponding to the fourth account item are presented to a user for each of the second transaction data; In a seventh step, a judgment result as to whether the fourth account item is valid is received; In an eighth step, the second transaction data in which the fourth account item is determined to be invalid is treated as third transaction data, and a second prompt is generated having the third transaction data, the second account item and the fourth account item related to the third transaction data, the second explanation, the fourth explanation, and a second instruction; the second instruction sentence is an instruction sentence for causing the language model to present a reason why the fourth account item was presented as a re-registration proposal for the account item related to the third transaction data, based on the third transaction data, the second explanatory sentence, and the fourth explanatory sentence; In a ninth step, a second response sentence is generated using the language model based on the second prompt. 　 In claim 1, In a tenth step, presenting the reason to the user; In an eleventh step, a correction of the first explanatory sentence and the third explanatory sentence is accepted; In a twelfth step, the information processing method further comprises registering a corrected explanatory sentence out of the first explanatory sentence and the third explanatory sentence in the data table, and then performing the second step again. 　 In claim 2, An information processing method in which, in the tenth step, the second transaction data is presented to the user, in which one or both of the second account item and the fourth account item are the same as the second account item or the fourth account item related to the third transaction data. 　 In claim 1, In the second step, an information processing method is provided in which a similarity between each of the multiple first description sentences and the third description sentence is calculated, and the records including the first description sentences whose similarity is equal to or greater than a certain value are collected. 　 In claim 1, A thirteenth step is carried out between the seventh step and the eighth step, An information processing method in which, for the second transaction data in which the re-registered fourth account item is judged to be valid in the thirteenth step, the fourth account item is registered in the database as an account item related to the second transaction data. 　 In any one of claims 1 to 5, An information processing method, wherein the first to third transaction data each include a product name and a transaction purpose. 　 The apparatus includes a database, a reception unit, and a processing unit, The database includes a data table including a plurality of records and a plurality of first transaction data. Each of the plurality of records includes a first account item and a first explanation that is an explanation of the first account item, In each of the plurality of first transaction data, any one of the plurality of first account items is registered as a second account item, The explanation of the first account item corresponding to the second account item is set as a second explanation; the reception unit has a function of receiving a third account item and a third explanatory text that is an explanatory text of the third account item, and supplying the third account item and the third explanatory text to the processing unit; the processing unit has a function of adding the third account subject and the third explanation accepted by the acceptance unit to the data table, the processing unit has a function of collecting at least a portion of the records based on the first explanatory text and the third explanatory text, and generating a first list including the first account title and the first explanatory text, and the third account title and the third explanatory text, which are included in the collected records; The processing unit has a function of collecting the first transaction data in which the first account item included in the first list is registered, as second transaction data, and generating a second list including the second transaction data; the processor has a function of generating a first prompt having the first list, the second list, and a first instruction sentence; the first instruction sentence is an instruction sentence for causing a language model to select and present a fourth account item, which is an account item to be re-registered in the second transaction data, from the first account item and the third account item included in the first list based on the second transaction data and the first explanatory sentence and the third explanatory sentence included in the first list; the processing unit has a function of prompting the user to determine whether the fourth account item is appropriate by presenting to the user, for each of the second transaction data, the fourth account item included in a first response sentence acquired by transmitting the first prompt to the language model via a network and a fourth explanation which is an explanation of the first account item or the third account item corresponding to the fourth account item; the processing unit has a function of treating the second transaction data, in which the fourth account item is determined to be invalid, as third transaction data, and generating a second prompt having the third transaction data, the second account item and the fourth account item related to the third transaction data, the second explanatory text and the fourth explanatory text, and a second instruction text; the second instruction sentence is an instruction sentence for causing the language model to present a reason why the fourth account item was presented as a re-registration proposal for the account item related to the third transaction data, based on the third transaction data, the second explanatory sentence, and the fourth explanatory sentence; The information processing device has a function of prompting the user to revise the first explanatory sentence and the third explanatory sentence by presenting to the user the reason contained in the second response sentence obtained by sending the second prompt to the language model via the network. 　 In claim 7, the processing unit has a function of, when the user corrects the first explanatory text, registering the corrected first explanatory text in the data table; The processing unit is an information processing device having a function of, when the user modifies the third explanatory text, registering the modified third explanatory text in the data table. 　 In claim 7, The processing unit is an information processing device having a function of presenting to the user the second transaction data in which one or both of the second account item and the fourth account item are the same as the second account item or the fourth account item related to the third transaction data. 　 In claim 7, The processing unit is an information processing device having a function of calculating a similarity between each of the multiple first description sentences and the third description sentence, and collecting the records including the first description sentences whose similarity is equal to or greater than a certain value. 　 In claim 7, The processing unit is an information processing device having a function of registering the fourth account item in the database as an account item related to the second transaction data for the second transaction data in which the re-registered fourth account item is judged to be valid. 　 In any one of claims 7 to 11, The first to third transaction data each include a product name and a transaction purpose.

Images