Business support system, business support method, and program

Abstract

To enhance user convenience.SOLUTION: A registered data acquisition unit (201) of a business support system (1) acquires registered data registered in a business support system, which can support user's business. A user-input information acquisition unit (202) acquires user-input information related to an electronic document to be generated based on a user's input. A generation-related processing execution unit (203) executes generation-related processing related to generation of the electronic document based on the registered data, user-input information, and AI. A provision unit (204) provides the electronic document to the user.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a business support system, a business support method, and a program. [Background technology]

[0002] In a conventional business support system capable of supporting a user's business, the user may create electronic documents such as invoices or reports. For example, Patent Document 1 describes a PDF for viewing generation system that extracts another embedded PDF embedded in a Portable Document Format (PDF) and rendering data from the PDF, stores them on a cloud server, creates links based on the PDF, the embedded PDF, and the rendering data, and generates a PDF for viewing on the cloud server. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-172386 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the technology of Patent Document 1, users must themselves prepare the PDF from which the PDF for viewing is generated, which is time-consuming for the user. This also applies to electronic documents other than PDFs that are created by business support systems. With the conventional technology, it is time-consuming for users to create electronic documents in business support systems, and therefore user convenience cannot be sufficiently improved.

[0005] One of the purposes of the present disclosure is to improve user convenience. [Means for solving the problem]

[0006] A business support system according to one aspect of the present disclosure includes a registered data acquisition unit that acquires registered data registered in a business support system capable of supporting a user's business, a user input information acquisition unit that acquires user input information regarding an electronic document to be generated based on input from the user, a generation-related process execution unit that executes generation-related processes related to the generation of the electronic document based on the registered data, the user input information, and AI, and a provision unit that provides the electronic document to the user. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to improve convenience for users. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of a hardware configuration of a business support system. [Figure 2] FIG. 10 is a diagram illustrating an example of a business support screen displayed on a user terminal. [Figure 3] FIG. 10 is a diagram illustrating an example of a business support screen displayed on a user terminal. [Figure 4] FIG. 2 is a diagram illustrating an example of functions realized by the business support system. [Figure 5] FIG. 1 is a diagram illustrating an example of AI used in generating a digital document. [Figure 6] FIG. 10 is a diagram illustrating an example of a business support database. [Figure 7] FIG. 2 is a diagram illustrating an example of processing executed in the business support system. [Figure 8] FIG. 10 is a diagram illustrating an example of functions realized by a modified example of a business support system. [Figure 9] FIG. 10 is a diagram showing an example of how a user modifies an electronic document. [Figure 10] FIG. 10 is a diagram illustrating an example of a process for correcting an electronic document. DETAILED DESCRIPTION OF THE INVENTION

[0009] [1. Hardware configuration] An example of an embodiment of a business support system, a business support method, and a program according to the present disclosure will be described. FIG. 1 is a diagram illustrating an example of the hardware configuration of the business support system. For example, the business support system 1 includes a voice conversion server 10, a generation-related server 20, a business support server 30, and a user terminal 40. Each of the voice conversion server 10, the generation-related server 20, the business support server 30, and the user terminal 40 is connected to a network N such as the Internet or a LAN. While FIG. 1 illustrates one of each of the voice conversion server 10, the generation-related server 20, the business support server 30, and the user terminal 40, there may be multiple of at least one of these.

[0010] The voice conversion server 10 is a server computer that executes the voice conversion process described below. For example, the voice conversion server 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 includes at least one processor. The storage unit 12 includes at least one of a volatile memory such as RAM and a non-volatile memory such as a flash memory. The communication unit 13 includes at least one of a communication interface for wired communication and a communication interface for wireless communication.

[0011] The production-related server 20 is a server computer that executes the production-related processing described below. For example, the production-related server 20 includes a control unit 21, a storage unit 22, and a communication unit 23. The hardware configurations of the control unit 21, the storage unit 22, and the communication unit 23 may be similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0012] The business support server 30 is a server computer that executes business support processing described below. For example, the business support server 30 includes a control unit 31, a storage unit 32, and a communication unit 33. The hardware configurations of the control unit 31, the storage unit 32, and the communication unit 33 may be similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0013] The user terminal 40 is a user's computer. For example, the user terminal 40 is a personal computer, a tablet terminal, a smartphone, or a wearable terminal. The user terminal 40 includes a control unit 41, a memory unit 42, a communication unit 43, an operation unit 44, a display unit 45, an audio input unit 46, and an audio output unit 47. The hardware configurations of the control unit 41, the memory unit 42, and the communication unit 43 may be similar to those of the control unit 11, the memory unit 12, and the communication unit 13, respectively. The operation unit 44 includes an input device such as a mouse or a touch panel. The display unit 45 includes an LCD or organic EL display. The audio input unit 46 includes at least one microphone. The audio output unit 47 includes at least one speaker.

[0014] The programs stored in the storage units 12, 22, 32, and 42 may be supplied via a network N. The hardware configurations of the voice conversion server 10, the generation-related server 20, the business support server 30, and the user terminal 40 are not limited to the example shown in FIG. 1. For example, at least one of the voice conversion server 10, the generation-related server 20, the business support server 30, and the user terminal 40 may include at least one of a reading unit (e.g., a memory card slot) that reads a computer-readable information storage medium and an input / output unit (e.g., a USB terminal) for direct connection to an external device. A program stored in an information storage medium may be supplied to at least one of the voice conversion server 10, the generation-related server 20, the business support server 30, and the user terminal 40 via at least one of the reading unit and the input / output unit.

[0015] Furthermore, the business support system 1 only needs to include at least one computer. The computers included in the business support system 1 are not limited to the example of Figure 1. For example, the business support system 1 may include only the generation-related server 20 and the business support server 30. In this case, the voice conversion server 10 and the user terminal 40 exist outside the business support system 1. The business support system 1 may only include the generation-related server 20. In this case, the voice conversion server 10, the business support server 30, and the user terminal 40 exist outside the business support system 1. The business support system 1 may include the generation-related server 20 and other server computers.

[0016] [2. Overview of the business support system] In this embodiment, the business support system 1 is capable of supporting a user's business. Furthermore, in this embodiment, an example is given in which the business support system 1 is capable of supporting a user's business with no-code or low-code, but the business support system 1 may also be capable of supporting a user's business based on code entered by the user. In other words, the business support system 1 may be a system that is not classified as a system capable of supporting a user's business with no-code or low-code.

[0017] No-code means that the user does not input any code. In other words, no-code means that the user does not need to input any code to use the business support system 1. Low-code means that the user inputs only the minimum amount of code necessary. In other words, the user only needs to input the minimum amount of code necessary to use the business support system 1.

[0018] Code is an instruction for a computer. In other words, code is information that enables a computer to understand a user's instructions. The code may be any code used in the field of computer software. For example, the code may be programming language code, CSS (Cascading Style Sheets) code, database language code, markup language code, or other code. Programming languages ​​also include languages ​​known as scripting languages. The code in this embodiment may be any of the various types of code that those skilled in the computer software field would call code.

[0019] The business support system 1 being able to support the user's business with no code means that the business support system 1 can execute the business support process described below based on pre-prepared code without the user having to enter any code. The business support system 1 being able to support the user's business with low code means that if the user enters only the minimum necessary code, the business support system 1 can execute the business support process described below based on the minimum necessary code entered by the user and the pre-prepared code.

[0020] The meanings of the terms no-code and low-code may be those generally known. A person skilled in the field of computer software can understand the meanings of no-code and low-code based on the common general technical knowledge at the time of filing. No-code and low-code may have a well-known meaning that can be understood by a person skilled in the art based on the common general technical knowledge at the time of filing. For example, the minimum amount of code required for low-code may be an amount that can be understood by a person skilled in the art based on the common general technical knowledge at the time of filing. For example, the minimum amount of code required for low-code may be approximately 1 to 100 lines, or may be 101 lines or more.

[0021] For example, the business support system 1 has various business support functions for supporting a user's business. The business support functions are functions realized by a program developed for business support. The types of business support functions may be known. For example, the business support functions may be a database function for a user to store data in a database, a communication function for a user to communicate with other users, a schedule function for a user to manage a schedule, an email management function for a user to manage emails, or other functions.

[0022] In this embodiment, the business support system 1 provides a cloud-based groupware to the user as an example. The business support system 1 may also provide an on-premise groupware to the user. The business support system 1 may also provide a service to the user that supports business operations but is not classified as groupware. For example, an organization such as a company to which the user belongs contracts with the business support system 1. As a member of the organization, the user uses the business support functions of the business support system 1. When the user logs in to the business support system 1 from the browser of the user terminal 40, the user terminal 40 displays a business support screen on the display unit 45, which allows the user to use the business support functions. The business support screen may be displayed on a program dedicated to the business support system 1, rather than on a browser.

[0023] 2 and 3 are diagrams showing an example of a business support screen displayed on the user terminal 40. In this embodiment, a case where a user uses a database function is taken as an example. For example, the user uses an app, which is a type of database. The user can store any data related to the user's business in the app. For example, the user can store not only data stored in the app's fields but also other data in the app. For example, the user can store comments to other users, files such as documents or images, or other data in the app. The app can also be said to have a complex business support function that not only has a database function but also a communication function, a file management function, and the like.

[0024] For example, when a user selects an app, the user terminal 40 displays on the display unit 45 a business support screen SC showing a list L of records, which are units of data that make up the app, as shown in the upper part of FIG. 2. In the example at the top of FIG. 2, records of an invoice management app in which the user manages invoices are shown in list L. When the user selects a record in list L, the user terminal 40 displays details of the record on the business support screen SC. For example, the user can update the record from the business support screen SC.

[0025] In this embodiment, a user can create an app with no-code or low-code. For example, a user can create an app without entering code by performing simple configuration tasks such as field settings. A user can use a pre-prepared default app without performing configuration tasks. A user can expand the business support functions of an app by entering the minimum necessary code. In other words, a user can create a low-code app by expanding the business support functions of an app created with no-code. Expanding business support functions can also be called customizing the business support functions.

[0026] For example, the records displayed in list L store information necessary to create an invoice. An invoice is an example of an electronic document. Therefore, any reference to an invoice can be read as an electronic document. A user creates an invoice based on the information stored in the record. The invoice may be in any format. For example, the invoice may be in a document file format such as PDF, a file format readable by spreadsheet software, an image file format, a markup language file format such as HTML or XML, or any other format.

[0027] For example, a user may input code for creating an invoice from information stored in a record and create a program as an extension of the app. In this case, the business support server 30 or the user terminal 40 can execute the program created by the user and generate an invoice. However, it is difficult for users with little or no knowledge of programming languages ​​to create a program. Even for users with knowledge of programming languages, creating a program is time-consuming.

[0028] Therefore, the business support system 1 of this embodiment has an electronic document generation function that uses AI (Artificial Intelligence) to generate electronic documents, such as invoices. The electronic document generation function is a type of business support function. The electronic document generation function may be a default function of the business support system 1 (a function that all users can use from the beginning), but in this embodiment, it is a plug-in that can be added at the user's discretion. A user who wishes to use the electronic document generation function adds the electronic document generation function using a plug-in. A plug-in is a collection of programs and data for the electronic document generation function. When a user adds a plug-in, the user can use the programs and data for the electronic document generation function.

[0029] AI is a program with artificial intelligence that assists users in their work. There are various definitions of AI, and the AI ​​of this embodiment may be AI defined by various known definitions. The AI ​​may be AI called generative AI or conversational AI. For example, the AI ​​may be a large-scale language model, a machine learning model not classified as a large-scale language model, a program called a bot, or other programs. There are various definitions of machine learning, and the machine learning of this embodiment may be machine learning defined by various known definitions. The machine learning may be any of supervised learning, semi-supervised learning, and unsupervised learning.

[0030] In this embodiment, a case where a large-scale language model corresponds to an AI is taken as an example. For example, a user gives instructions to an AI using text (characters) or voice. In the example at the top of FIG. 2, the user selects icon I to start voice input and speaks. When the voice input unit 46 detects the user's voice, the user terminal 40 executes a process to convert the user's voice into text with the voice conversion server 10. Once the user's voice is converted into text, the user terminal 40 displays the text in an input form F, as shown at the bottom of FIG. 2. If the text is incorrect, the user can correct the text by operating the operation unit 44. The user can also manually input text into the input form F without using voice input.

[0031] In the example at the bottom of Figure 2, the user gives an instruction such as "Create an invoice with record number 00001." Record numbers are numbers used to identify individual records. For example, record numbers are automatically assigned in the order in which the records are created. When the user selects button B1, the production-related server 20 uses AI to generate an invoice according to the record specified by the user. As shown at the top of Figure 3, the business support screen SC enters a state where it is waiting for the generation of an electronic document. The instructions entered by the user are displayed in display area A1 of the business support screen SC.

[0032] For example, when the AI ​​generates an invoice, the production-related server 20 sends an API request to the business support server 30 indicating that the invoice generated by the AI ​​should be deployed to an app. The AI ​​may generate the API request. The business support server 30 receives the API request from the production-related server 20. The business support server 30 deploys the invoice to the app based on the API request. This allows the user terminal 40 to display the invoice in the environment of the business support system 1. As shown in the lower part of Figure 3, the user terminal 40 displays the invoice generated by the AI ​​in the display area A2 of the business support screen SC.

[0033] For example, when the user selects button B2, the business support screen SC enters invoice editing mode. The user can edit the invoice from the business support screen SC in edit mode. Editing of the invoice may be performed using a known editor. The editor may be operable on a browser. The editor may operate as an extension of the browser. For example, if the invoice is in a document format such as PDF, the user terminal 40 edits the invoice based on a known document editor. If the invoice is in another format such as an image, the user terminal 40 may edit the invoice using a known editor that can edit files in other formats. When the user selects button B3, the invoice is saved in the app.

[0034] As described above, when a user inputs instructions for the AI, the production-related server 20 generates an invoice in accordance with the instructions. The production-related server 20 sends an API request to the business support server 30 indicating that the invoice generated by the AI ​​should be deployed. The business support server 30 executes the processing requested in the API request and deploys the invoice. This allows the user to easily create an invoice without having to create the invoice themselves or enter a code, thereby improving user convenience. The business support system 1 will be described in detail below.

[0035] [3. Functions realized by the business support system] FIG. 4 is a diagram showing an example of functions realized by the business support system 1. As shown in FIG.

[0036] [3-1. Functions realized by the voice conversion server] For example, the voice conversion server 10 includes a data storage unit 100 and a voice conversion unit 101. The data storage unit 100 is realized by a storage unit 12. The voice conversion unit 101 is realized by a control unit 11. Note that if voice input is not performed, the business support system 1 does not need to include the voice conversion server 10.

[0037] [Data storage section] The data storage unit 100 stores data necessary for the speech conversion process. For example, the data storage unit 100 stores a speech conversion program that indicates the speech conversion process. The speech conversion process is at least one of a process of converting speech to text and a process of converting text to speech. In this embodiment, an example is given in which the speech conversion process includes both of these processes, but the speech conversion process may include only one of these processes. A speech conversion program for converting speech to text and a speech conversion program for converting text to speech may be separate programs. The speech conversion program may be a known program. For example, the speech conversion program may be a program using a pattern matching method that utilizes speech waveform patterns, a machine learning method, or other methods.

[0038] [Voice conversion section] The speech conversion unit 101 executes speech conversion processing based on a speech conversion program. For example, the speech conversion server 10 acquires input speech data indicating speech input by a user from a user terminal 40. The data format of the input speech data may be a known format. The speech conversion unit 101 converts the speech input by the user into text based on the speech data and the speech conversion program. The speech conversion unit 101 transmits input text data indicating the text of the speech input by the user to the user terminal 40. The speech conversion unit 101 may transmit the input text data to the production-related server 20, the business support server 30, or another computer.

[0039] For example, the speech conversion unit 101 acquires answer text data indicating the text of an answer from the AI ​​from the generation-related server 20, the business support server 30, or another computer. The speech conversion unit 101 converts the text of the answer from the AI ​​into speech based on the answer text data and a speech conversion program. The speech conversion unit 101 transmits answer voice data indicating the speech of the text of the answer from the AI ​​to the user terminal 40. The user terminal 40 acquires the answer voice data from the speech conversion server 10. The user terminal 40 outputs the answer from the AI ​​as voice from the voice output unit 47 based on the answer voice data. The user terminal 40 may acquire the answer text data from the speech conversion server 10, the generation-related server 20, the business support server 30, or another computer. The user terminal 40 may display the answer from the AI ​​in the display area A1 of the business support screen SC based on the answer text data.

[0040] [3-2. Functions realized by the generation-related servers] For example, the production-related server 20 includes a data storage unit 200, a registered data acquisition unit 201, a user-input information acquisition unit 202, a production-related process execution unit 203, and a providing unit 204. The data storage unit 200 is realized by the storage unit 22. The registered data acquisition unit 201, the user-input information acquisition unit 202, the production-related process execution unit 203, and the providing unit 204 are each realized by the control unit 21.

[0041] [Data storage section] The data storage unit 200 stores data necessary for the generation-related processing. For example, the data storage unit 200 may store information (e.g., a URL or IP address) that can identify an API endpoint of an API in the business support server 30. In this embodiment, an example is given in which the generation-related server 20 uses an AI of an external service that cooperates with the business support system 1, so the data storage unit 200 does not store the AI ​​itself, but the data storage unit 200 may store the AI ​​itself. That is, in this embodiment, an example is given in which actual data of the AI ​​is stored in the system of another service, but the data storage unit 200 may store actual data of the AI.

[0042] FIG. 5 is a diagram showing an example of AI used in generating electronic documents. For example, the AI ​​includes a program that indicates a series of processes such as calculating an embedded representation, and parameters referenced by the program. The embedded representation is information that enables the AI ​​to understand the meaning of data. For example, the embedded representation is expressed as a multidimensional vector. The embedded representation is also sometimes called a feature that indicates the characteristics of the data. The embedded representation may be expressed in a format other than a multidimensional vector. The AI ​​may include other data other than the parameters (for example, data equivalent to a dictionary of terms). The other data is referenced by the program. The other data may be data separate from the AI. The AI ​​calculates the embedded representation of input data input to it based on the parameters, and produces output according to the embedded representation. For example, the parameters are weights and biases.

[0043] The AI ​​programs and parameters may be publicly known programs and parameters. For example, the AI ​​programs and parameters may be programs and parameters used in large-scale language models such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers), programs and parameters used in machine learning models such as neural networks or GANs (Generative Adversarial Networks), programs and parameters used in generative AI or interactive AI that do not fall into these categories, or other programs and parameters. The AI ​​programs and parameters may be various programs and parameters that a person skilled in the computer software field would understand based on the common general technical knowledge at the time of filing.

[0044] In this embodiment, a large-scale language model (e.g., GPT) will be described as an example of AI, and therefore the AI ​​program refers to a process of analyzing input data input to the AI. AI parameters are parameters such as weights and biases that the AI ​​refers to in order to analyze the meaning of natural language. The AI ​​performs language analysis of the input data input to itself based on the parameters adjusted through learning, and outputs according to the results of the language analysis. For example, the AI ​​divides the natural language text represented by the input data into multiple tokens. The AI ​​calculates embedded expressions that indicate the meaning of each token based on the parameters. The AI ​​understands the meaning of natural language based on the order of the embedded expressions of each token. The AI ​​may make predictions according to the order of the embedded expressions of each token, as necessary. The AI ​​outputs output data according to the order of the embedded expressions.

[0045] In this embodiment, an example is given in which the AI ​​has learned various codes related to data generation (e.g., codes in a database language). The AI ​​may only learn electronic documents that the business support system 1 can handle, but in this embodiment, it is assumed that the AI ​​has also learned other electronic documents. The AI ​​may be able to handle various electronic documents. The AI ​​may have learned a large number of natural languages ​​other than electronic documents (e.g., programming languages). For example, output data from the AI ​​may vary depending on the input data. If the input data is a question, the output data indicates an answer to the question. If the input data is an instruction to generate an electronic document, the output data includes the electronic document. In this case, the output data may include not only the electronic document but also an explanation of the electronic document. The output data may include any type of information.

[0046] As shown in FIG. 5 , in this embodiment, an example is given in which input data to an AI includes registration data and user-input information, as described below. The input data may include any information. The input data is not limited to the example in this embodiment. In this embodiment, an example is given in which output data includes an electronic document. For example, the output data may include information other than an electronic document (e.g., a response from the AI). The output data from the AI ​​may include code used to generate an electronic document, rather than an electronic document. The output data does not have to include an electronic document. For example, if the output data does not include an electronic document, the generation-related process execution unit 203, described below, may generate an API request requesting the generation of an electronic document based on the output data. For example, if the output data is code, such as a script, generated by the AI ​​and includes only code for generating an electronic document, the generation-related process execution unit 203 may generate an API request for executing the code, based on the output data, which is code, such as a script, generated by the AI. The API request is sent to another computer, such as the business support server 30, and the other computer generates an electronic document based on the API request.

[0047] [Registration Data Acquisition Section] The registered data acquisition unit 201 acquires registered data registered in the business support system 1 that can support the user's business. The registered data is data that is referenced for generating an electronic document. For example, all or part of the contents of the registered data may be included in the electronic document. All or part of the contents of the registered data may not be included in the electronic document as is, but may be processed in some way before being included in the electronic document. The registered data registered in the business support system 1 is data stored by the business support system 1. The registered data may be any data that the user can use.

[0048] In this embodiment, an example is given in which an application record corresponds to registration data. Therefore, any description of a record can be read as registration data. Furthermore, although an example is given in which each record corresponds to registration data, multiple records may correspond to one piece of registration data. Registration data may be the entire record or a part of the record. For example, registration data may be only a part of the record that indicates specific values ​​of fields. Registration data may include not only specific values ​​of fields but also other parts such as files or comments registered in the record.

[0049] In this embodiment, an example is taken of a case where the registration data is stored in a business support database DB described below. Therefore, the registration data acquisition unit 201 acquires the registration data from the business support database DB. For example, the registration data acquisition unit 201 acquires registration data specified by the user from among a large number of registration data stored in the business support database DB. In the examples of Figures 2 and 3, the user input information includes acquisition target identification information for identifying the registration data to be acquired by the registration data acquisition unit 201. The acquisition target identification information may be any information such as a record number. The registration data acquisition unit 201 acquires the registration data identified by the acquisition target identification information.

[0050] The method by which the registration data acquisition unit 201 identifies the registration data to be acquired is not limited to the above example. That is, the registration data acquisition unit 201 may identify the registration data to be acquired by other methods than by using the registration data specified by the user. For example, when the user selects a specific record from the list L, details of the record selected by the user are displayed on the business support screen SC. In this state, if the user instructs the generation of an electronic document, the registration data acquisition unit 201 may identify the record currently displayed on the business support screen SC as the registration data to be acquired. The registration data acquisition unit 201 acquires acquisition target identification information, such as the record number of the record currently displayed on the business support screen SC, from the user terminal 40.

[0051] Furthermore, when the registration data is data other than the app records, the registration data acquisition unit 201 may acquire the registration data registered as the other data. For example, the registration data acquisition unit 201 may acquire, as the registration data, records of a database other than the app. The registration data acquisition unit 201 may acquire, as the registration data, registration data of a business support function other than the database function, an example of which is an app. For example, the registration data acquisition unit 201 may acquire, as the registration data, posting data related to posts by users entered using the communication function, schedule data related to schedules managed using the schedule function, email data related to emails managed using the email management function, or other data.

[0052] Furthermore, if the registration data is stored in a database other than the business support database DB, the registration data acquisition unit 201 may acquire the registration data from the other database. If the registration data is stored in the data storage unit 200, the registration data acquisition unit 201 may acquire the registration data from the data storage unit 200. If the registration data is stored in a computer other than the production-related server 20 and the business support server 30, or in an external information storage medium, the registration data acquisition unit 201 may acquire the registration data from the other computer or external information storage medium.

[0053] [User input information acquisition section] The user input information acquisition unit 202 acquires user input information related to the electronic document to be generated based on the user's input. In this embodiment, an example is given in which the user inputs voice through the voice input unit 46, but the user may also input through the operation unit 44. For example, the user may input instructions to the AI ​​through the operation unit 44. The user may also input by selecting a part (for example, an image such as a button or a check box) as a user interface.

[0054] User input information is an instruction to the AI. User input information can also be referred to as the user's intention. User input information is sometimes called a prompt for the AI. Information included in the input data other than the user input information can also be referred to as supplementary information input to the AI ​​along with the prompt. There are various definitions of the word "prompt," but if information input to the AI ​​corresponds to a prompt, then information other than the user input information also corresponds to a prompt. The definition of the word "prompt" may be any of various known definitions. In this embodiment, the user input information is written in natural language, but it may also be information in which the meaning of the natural language is vectorized.

[0055] For example, a user inputs a natural language indicating the type of electronic document they want to generate. In the examples of Figures 2 and 3, the user inputs the type of electronic document, "invoice," in natural language. The AI ​​may be capable of handling multiple types of electronic documents. For example, the AI ​​may be capable of handling estimates, receipts, reports, proposals, minutes, company regulations, contracts, forms not classified as any of these, or other types of electronic documents. The user inputs a natural language indicating at least one of the multiple types of electronic documents.

[0056] Note that the user may input using a method other than natural language. For example, a list of types of electronic documents that the AI ​​can handle may be displayed on the business support screen SC, and the user may select a type of electronic document from the list. The user input information indicates the type of electronic document selected by the user. The business support screen SC may display buttons indicating individual types of electronic documents instead of a list. The user may specify the type of electronic document to be generated by selecting the button.

[0057] In this embodiment, an example is taken of a case where the text entered into input form F when the user selects button B1 corresponds to the user input information. Therefore, the user input information is text that indicates the content related to the electronic document that the user wants to generate. When the user selects button B1, the user terminal 40 transmits the user input information, which is the text entered into input form F, to the generation-related server 20. The user input information acquisition unit 202 acquires the user input information from the user terminal 40. The user input information acquisition unit 202 may acquire only one piece of user input information, or may acquire multiple pieces of user input information.

[0058] Note that the user input information may not be text in a natural language, but may be the voice input by the user. In this case, the user input information acquisition unit 202 may acquire the user input information, which is voice, from the user terminal 40 and then request the voice conversion server 10 to convert the user input information into text. The user input information acquisition unit 202 acquires the user input information converted into text from the voice conversion server 10. In this embodiment, since the AI ​​is a large-scale language model, the information converted into text is input to the AI. The user input information acquisition unit 202 may acquire the user input information indirectly via the voice conversion server 10, the business support server 30, or another computer, rather than acquiring the user input information directly from the user terminal 40.

[0059] [Generation-related processing execution unit] The generation-related process execution unit 203 executes generation-related processes. The generation-related processes are processes related to the generation of an electronic document. In this embodiment, the process of generating the electronic document itself corresponds to the generation-related process, but the generation-related process may also be pre-processing that is executed before the generation of the electronic document. For example, the pre-processing may be the generation of a file (e.g., a CSV (Comma-Separated Values) file) to be imported into the electronic document, the generation of a program for generating the electronic document, the generation of an API request requesting the generation of the electronic document, or other processes.

[0060] In this embodiment, the generation-related process execution unit 203 executes generation-related processes related to the generation of an electronic document based on the registered data, user input information, and the AI. For example, the generation-related process execution unit 203 inputs input data including the registered data and user input information to the AI. In this embodiment, since the AI ​​is stored in an external system, the generation-related process execution unit 203 transmits the input data to the external system. If the AI ​​is stored in the data storage unit 200, the generation-related process execution unit 203 simply inputs the input data to the AI ​​stored in the data storage unit 200.

[0061] For example, the AI ​​calculates the embedding representation of input data based on parameters adjusted by previously performed learning. In this embodiment, a large-scale language model, such as GPT, corresponds to the AI, so the AI ​​divides the input data into tokens based on the parameters and calculates the embedding representation of each token. If necessary, the AI ​​predicts the continuation based on the order of the embedded representations of the tokens. The AI ​​outputs an electronic document as output data based on this order. The AI ​​may output output data including not only an electronic document but also text of a response to the user. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. In this embodiment, this series of processes corresponds to the generation-related process.

[0062] For example, the registered data indicates the content to be included in an electronic document. In the examples of Figures 2 and 3, the field values ​​of the record stored in the app correspond to the content to be included in an electronic document, such as an invoice. Since AI is pre-trained with a large amount of training data, including training electronic documents, it can understand such registered data through language analysis and select the content to be included in the electronic document as needed. Furthermore, since the user input information is acquired based on the user's input, the user input information indicates the content of the electronic document desired by the user. In the examples of Figures 2 and 3, the user input information indicates specific content, such as the user's request for an invoice with record number 00001. The AI ​​can understand such user input information through language analysis and generate the electronic document desired by the user.

[0063] Although the AI ​​generating an electronic document based on the registered data of the business support system 1 is a novel configuration at the time of filing, the technology itself for the AI ​​generating an electronic document based on a prompt may be a publicly known technology at the time of filing. Therefore, a person skilled in the art would be able to understand the process for the AI ​​of this embodiment to generate an electronic document to an extent that it can be implemented based on the description of this embodiment and the common general technical knowledge at the time of filing.

[0064] Furthermore, the generation-related process is not limited to the process of generating the electronic document itself. The generation-related process may be any process somehow related to the generation of the electronic document. For example, the generation-related process may be pre-processing for generating the electronic document. The generation-related process execution unit 203 may execute, as the generation-related process, a process of generating data such as CSV. In this case, the providing unit 204, which will be described later, may import the data such as CSV into a default electronic document (electronic document template) to generate the electronic document and provide it to the user. The data may be in a format that can be imported into the electronic document, and is not limited to CSV.

[0065] For example, the generation-related process may be a process of generating an API request for requesting the generation of an electronic document. The generation-related process execution unit 203 transmits the API request generated by the generation-related process to the business support server 30. Upon receiving the API request, the business support server 30 may execute the API request to generate the electronic document. A program required for generating the electronic document may be attached to the API request or may be stored in advance in the business support server 30. The business support server 30 may execute the program to generate the electronic document.

[0066] For example, the generation-related process may be a process of generating code for generating an electronic document (for example, code in a programming language such as Python, or code in a database language). An example of this generation-related process will be described in Variation 6 below.

[0067] The generation-related process execution unit 203 may input input data to the AI ​​that includes information other than the registered data and user-input information. For example, since the AI ​​may not be able to recognize what kind of electronic document should be generated, or even whether an electronic document should be generated at all, based on the user-input information alone, a default prompt may be provided that indicates to the AI ​​which electronic document to generate. The default prompt is stored in the data storage unit 200. For example, the default prompt may indicate a natural language sentence such as "Please generate an electronic document based on the user's instructions." The default prompt may also indicate the type of electronic document. The generation-related process execution unit 203 inputs input data including such a default prompt to the AI. The AI ​​can recognize what it should do by calculating an embedded expression according to the default prompt.

[0068] [Provider] The providing unit 204 provides an electronic document to a user. Providing an electronic document by the providing unit 204 means that the providing unit 204 transmits the data of the electronic document to the user terminal 40. The providing unit 204 may transmit the data of the electronic document directly to the user terminal 40, or may transmit the data of the electronic document indirectly via another computer such as the business support server 30. In this embodiment, since the electronic document is displayed on the browser of the user terminal 40, the providing unit 204 directly or indirectly transmits data (e.g., HTML data) required to display the electronic document to the user terminal 40, as an example.

[0069] In this embodiment, the electronic document generated by the generation-related process execution unit 203 is deployed by the business support server 30 and then transmitted to the user terminal 40. Deploying refers to the expansion of the electronic document into the environment of the business support system 1. A known process may be used for deploying the electronic document. In the examples of FIGS. 2 and 3, deploying refers to the expansion of the electronic document into the environment of an application selected by the user. For example, the providing unit 204 requests the business support server 30 to deploy the electronic document generated by the generation-related process execution unit 203. Upon receiving the deployment request, the business support server 30 deploys the electronic document requested by the generation-related server 20. For example, the business support server 30 performs deployment by embedding the data of the electronic document in display data (e.g., HTML data) of the business support screen SC. The electronic document may be embedded at any position in the display data. In the example at the bottom of FIG. 3, the electronic document is displayed in a pop-up display area A2 on the business support screen SC, but the electronic document may be displayed in any other format.

[0070] For example, once the user confirms that an electronic document has been generated in accordance with the user's wishes, the user performs an operation to save the electronic document. In this case, the business support server 30 stores the electronic document in the data storage unit 300 in association with the user. The user can use the electronic document stored in the data storage unit 300. For example, when the user again invokes the app that generated the electronic document using AI, the electronic document is registered as a record in the display data of the business support screen SC of the app. The user can also modify or delete the electronic document stored in the data storage unit 300. The providing unit 204 may transmit the electronic document to the user terminal 40 without saving it in the app. In this case, the user terminal 40 downloads and saves the electronic document provided by the providing unit 204.

[0071] [3-3. Functions realized by the business support server] For example, the business support server 30 includes a data storage unit 300 and a business support unit 301. The data storage unit 300 is realized by the storage unit 32. The business support unit 301 is realized by the control unit 31.

[0072] [Data storage section] The data storage unit 300 stores data necessary for business support processing. For example, the data storage unit 300 stores a business support database DB that stores various data of the business support system 1. In this embodiment, a situation in which a user extends the function of an app is taken as an example, and therefore a case in which various data of the app is stored in the business support database DB is taken as an example.

[0073] Fig. 6 is a diagram showing an example of a business support database DB. For example, the business support database DB stores application IDs, application names, application setting data, and registration data. The data stored in the business support database DB is not limited to the example in Fig. 6. For example, the business support database DB may store registration data of business support functions other than applications (for example, registration data of threads through which users communicate with each other, registration data of schedules, or registration data of emails).

[0074] The app ID is an ID that can identify an app. The app name is the name of the app, and the app setting data indicates the app settings specified by the user using no-code or low-code. For example, the app setting data may be the above-mentioned field settings, graph settings, list L display settings, access rights settings, or other settings. Code generated by AI may be saved as part of the app setting data. The registration data can be registered, changed, or deleted by the user. In this embodiment, an example is taken where the data of an app record corresponds to the registration data. When a user creates a new app, data such as the app ID of the new app is stored in the business support database DB. When a user updates an app, the registration data of the app in the business support database DB is updated.

[0075] For example, the data storage unit 300 stores a program for a business support function and actual data for each of a plurality of APIs. The actual data for the API includes a program that performs various processes such as acquiring or transmitting data, and data such as settings referenced by the program. The program for the business support function can also be called by processing the program included in the actual data for the API. The actual data for the API may be similar to data used in known APIs. The data storage unit 300 may also store data necessary for the business support server 30 to receive an API request (e.g., information that can identify the API endpoints of each of a plurality of APIs).

[0076] The data stored in the data storage unit 300 is not limited to the above examples. The data storage unit 300 may store any data necessary for supporting business operations. For example, the data storage unit 300 may store data necessary for displaying the business support screen SC (e.g., HTML data or image data), or data necessary for deploying electronic documents (e.g., a deployment program).

[0077] [Business Support Department] The business support unit 301 executes business support processing to support a user's business. The business support processing is processing for providing a business support function to a user. For example, the business support processing is processing for displaying a business support screen SC on the user terminal 40. In this embodiment, since the electronic document generated by the generation-related server 20 is provided to the user in the application environment, the business support processing may be processing for deploying the electronic document generated by the AI ​​and displaying the electronic document on the business support screen SC. Details of the processing for displaying the business support screen SC and the processing for deploying the electronic document generated by the AI ​​are as described above.

[0078] [3-4. Functions implemented on user devices] For example, the user terminal 40 includes a data storage unit 400, a display control unit 401, and an operation reception unit 402. The data storage unit 400 is realized by the storage unit 42. The display control unit 401 and the operation reception unit 402 are each realized by the control unit 41.

[0079] [Data storage section] The data storage unit 400 stores data for business support. For example, the data storage unit 400 stores a browser for displaying various screens of the business support system 1. For example, the data storage unit 400 stores an application dedicated to the business support system 1. The data storage unit 400 stores display data for the business support screen SC.

[0080] [Display control section] The display control unit 401 causes the display unit 45 to display various screens in the business support system 1. For example, the display control unit 401 causes the display unit 45 to display a business support screen SC based on data received from the speech conversion server 10, the generation-related server 20, or the business support server 30.

[0081] [Operation reception section] The operation reception unit 402 receives various operations in the business support system 1. For example, the operation reception unit 402 receives operations on the business support screen SC. Data indicating the operation content received by the operation reception unit 402 is transmitted to the voice conversion server 10, the generation-related server 20, or the business support server 30 as appropriate.

[0082] [4. Processing performed by the business support system] FIG. 7 is a diagram showing an example of processing executed in the business support system 1. The processing of FIG. 7 is executed by the control units 11, 21, 31, and 41 executing programs stored in the storage units 12, 22, 32, and 42, respectively. Each processing of FIG. 7 is an example of processing included in a business support method. FIG. 7 shows an example of processing when an electronic document is generated. Note that in FIG. 7, the user terminal 40 may communicate indirectly with the speech conversion server 10 and the generation-related server 20 via the business support server 30, rather than directly with each other.

[0083] 7, the user terminal 40 executes processing with the business support server 30 to display a business support screen SC of an application selected by the user (S1). In S1, the business support server 30 generates display data for the business support screen SC of the application selected by the user based on the business support database DB and transmits the display data to the user terminal 40. Upon receiving the display data for the business support screen SC, the user terminal 40 displays the business support screen SC on the display unit 45. Thereafter, the user instructs the AI ​​to generate an electronic document, following the flow of FIGS. 2 and 3.

[0084] When the user terminal 40 receives a voice input from the user via the voice input unit 46, it transmits input voice data indicating the voice input by the user to the voice conversion server 10 (S2). The voice conversion server 10 acquires the input voice data from the user terminal 40 (S3). The voice conversion server 10 executes a voice conversion process based on the voice conversion program and the input voice data (S4). The voice conversion server 10 transmits input text data indicating the text of the voice input by the user (S5). The user terminal 40 acquires the input text data from the voice conversion server 10 (S6).

[0085] When the user selects button B1, the user terminal 40 transmits user-input information to the production-related server 20 (S7). In S7, the user terminal 40 requests the production-related server 20 to generate an electronic document. In S7, the application ID of the application for which the electronic document is to be generated is also transmitted. The production-related server 20 acquires the user-input information, etc. from the user terminal 40 (S8). The production-related server 20 executes processing to acquire registration data with the business support server 30 (S9). In S9, the production-related server 20 identifies the record number of the record for which the user has instructed the generation of an electronic document based on the user-input information. The production-related server 20 transmits the record number to the business support server 30. The business support server 30 references the business support database DB and acquires registration data, which is the data of the record with the record number. The business support server 30 transmits the acquired registration data to the production-related server 20. The production-related server 20 acquires the registration data from the business support server 30.

[0086] The production-related server 20 executes a production-related process based on input data including the user input information acquired in S8 and the registration data acquired in S9, and the AI ​​(S10). In S10, the production-related server 20 transmits the input data to an external system that manages the AI. The production-related server 20 acquires output data including an electronic document generated by the AI ​​from the external system. The production-related server 20 transmits the electronic document generated in S10 to the business support server 30 (S11). The electronic document generated in S10 may be transmitted from the production-related server 20 to the user terminal 40, and then transmitted by the user terminal 40 to the business support server 30.

[0087] The business support server 30 receives the electronic document from the production-related server 20 (S12). The business support server 30 deploys the electronic document in the application environment (S13). The business support server 30 executes processing between the production-related server 20 and the user terminal 40 to provide the electronic document to the user (S14), and this processing ends. The business support server 30 transmits display data of a business support screen SC indicating the electronic document deployed in the application environment to the user terminal 40 via the production-related server 20. Upon receiving the display data of the business support screen SC, the user terminal 40 displays the business support screen SC on the display unit 45. If a voice output of the answer from the AI ​​is required, the voice conversion server 10 acquires data indicating the AI's answer from the production-related server 20 and executes processing to convert the text into voice. The converted voice is output on the user terminal 40.

[0088] [5. Summary of embodiments] The business support system 1 of this embodiment acquires registration data registered in the business support system 1. The business support system 1 acquires user input information based on user input. The business support system 1 executes generation-related processing based on the registration data, the user input information, and AI. The business support system 1 provides an electronic document to the user. This allows the user to generate an electronic document using AI without having to create a program for generating the electronic document, thereby improving user convenience. For example, a user of a no-code or low-code business support system 1 may have little or no knowledge of programming languages. The user can easily generate an electronic document through the electronic document generation process of the business support system 1 without acquiring knowledge of programming languages. Even users with knowledge of programming languages ​​can avoid the hassle of creating a program for generating an electronic document, so the business support system 1 improves convenience for users with knowledge of programming languages. For example, non-AI electronic document creation tools may only be able to generate a limited number of electronic documents and may not be able to meet the diverse needs of users. By utilizing AI, the business support system 1 can respond to a variety of user requests. The business support system 1 can generate electronic documents that can be customized according to specific user requests.

[0089] [6. Modifications] The present disclosure is not limited to the above-described embodiments, and may be modified as appropriate without departing from the spirit of the present disclosure.

[0090] 8 is a diagram showing an example of functions implemented in the business support system 1 of the modified example. As shown in FIG. 8, the modified example described below implements a setting information acquisition unit 205, a template document acquisition unit 206, a generated electronic document acquisition unit 207, a first comment information acquisition unit 208, an electronic document generation unit 209, a correction content information acquisition unit 210, a correction-related process execution unit 211, an electronic document correction unit 212, a verification process execution unit 213, a business process execution unit 214, and a second comment information acquisition unit 215. Each of the setting information acquisition unit 205, the template document acquisition unit 206, the generated electronic document acquisition unit 207, the first comment information acquisition unit 208, the electronic document generation unit 209, the correction content information acquisition unit 210, the correction-related process execution unit 211, the electronic document correction unit 212, the verification process execution unit 213, the business process execution unit 214, and the second comment information acquisition unit 215 is implemented by the control unit 21.

[0091] [6-1. Variation 1] For example, some registration data may have settings specific to the registration data. If, as in the embodiment, an application record corresponds to the registration data, the registration data may include settings such as field names of the record. Recognizing the settings of the registration data by AI may improve the accuracy of the generation-related process. For example, AI may be able to generate an electronic document according to the settings of field names, etc. Therefore, in Modification Example 1, an example is given in which setting information regarding the settings of the registration data is used in the generation-related process.

[0092] The business support system 1 of the first modification includes a setting information acquisition unit 205. The setting information acquisition unit 205 acquires setting information related to the settings of registered data. The setting information may be any information related to the settings of registered data. For example, the setting information may indicate identification information such as the name or ID of the registered data, the type (format), data size, extension, access rights, additional information such as a calculation formula, the layout at the time of display, or other settings. In the first modification, an example is given in which an application record corresponds to registered data, and therefore the setting information is information related to the settings of the record. Furthermore, an example is given in which information related to the settings of a field corresponds to the setting information.

[0093] A field is an individual item that makes up a record. A record is an individual unit of data in an app. A field may also be called a cell or other name. For example, the setting information may indicate a field name, which is the name of the field, a field code, which is the code of the field, a field type, which is the type of the field, a calculation formula associated with the field, the order of the fields, the position of the input form where the user enters the field value, the design of the field on the business support screen SC, the access rights of the field, or other settings. The setting information may indicate multiple of these settings. The setting information may or may not be user-specifiable.

[0094] For example, when a user selects button B with text entered in input form F on the business support screen SC, the setting information acquisition unit 205 acquires the application ID of the application selected by the user from the user terminal 40. The application ID is assumed to be included in the display data (e.g., HTML data) of the business support screen SC. The application ID may be included as part of the URL (e.g., an argument included in the link of button B). The setting information acquisition unit 205 may acquire the application ID of the application for which an electronic document is to be generated in some way. The setting information acquisition unit 205 may acquire the application ID of the application selected by the user from the speech conversion server 10, the business support server 30, or another computer.

[0095] For example, the setting information acquisition unit 205 requests setting information from the business support server 30 based on the application ID of the application selected by the user. The request includes the application ID. Upon receiving the request, the business support server 30 refers to the business support database DB and acquires setting information associated with the application ID. In the data storage example of FIG. 6 , the setting information is included in the application setting data. The application setting data may include information on other settings, such as settings for the application itself, in addition to setting information that is field settings. In Modification 1, it is assumed that setting information that is field settings is acquired from the application setting data. The business support server 30 transmits the setting information to the generation-related server 20. The setting information acquisition unit 205 acquires the setting information from the business support server 30.

[0096] The setting information may indicate the settings of the app itself, rather than the fields of the app. For example, the setting information may be the app name, which is the name of the app, notes for the app administrator, the display format of the list L, the app icon, the app design, workflow settings, notification settings, functions extended by a plug-in, script, CSS, or the like added to the app, access rights, or the hierarchical format of records.

[0097] For example, when an electronic document is generated based on other registered data than the application record, the setting information acquisition unit 205 may acquire the setting information of the other registered data. When the data storage unit 200 stores the setting information, the setting information acquisition unit 205 may acquire the setting information from the data storage unit 200. The setting information acquisition unit 205 may acquire the setting information from a computer other than the generation-related server 20 and the business support server 30 (for example, the user terminal 40), or from an external information storage medium.

[0098] The generation-related process execution unit 203 of Modification 1 executes the generation-related process further based on the setting information. "Further based on the setting information" means that the process is based not only on the registered data, user input information, and AI, but also on the setting information. For example, the generation-related process execution unit 203 inputs input data including the setting information to the AI. The AI ​​calculates an embedded expression based not only on the registered data and user input information, but also on the setting information. The embedded expression reflects not only the registered data and user input information, but also the setting information. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded expression. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded expression corresponding to the setting information, and generates the electronic document.

[0099] The generation-related process of Modification 1 is not limited to the process of generating an electronic document further based on the setting information. As with the embodiment, the generation-related process of Modification 1 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV data further based on the setting information and importing the data into a default electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document further based on the setting information. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document further based on the setting information.

[0100] The business support system 1 of the first modification executes generation-related processing further based on the setting information. This allows the business support system 1 to generate an electronic document specific to the settings of the registered data. For example, if the setting information indicates a field name, the business support system 1 can generate an electronic document that matches the field name, thereby improving the accuracy of the electronic document. If the setting information indicates the purpose of the application, the business support system 1 can generate an electronic document that matches the purpose, thereby improving the accuracy of the electronic document.

[0101] [6-2. Variation 2] For example, when an electronic document template is input to an AI, the AI ​​can output output data that conforms to the template. Therefore, in Modification 2, an example is given of a case in which an electronic document template is used in generation-related processing. Hereinafter, an electronic document template will be referred to as a template document. The business support system 1 of Modification 2 includes a template document acquisition unit 206. The template document acquisition unit 206 acquires a template document related to an electronic document, which is a template document prepared in advance.

[0102] In the second modification, the data storage unit 200 stores a template document. For example, the data storage unit 200 may store a template database in which an index used in searching for the template document is associated with the template document. The index may be a keyword or the like for searching for the template document. The template document may be prepared by any person. For example, the template document may be prepared by the operator of the business support system 1 or a user. An electronic document created by a user in the past may be used as the template document.

[0103] For example, the template document acquisition unit 206 acquires a template document from a template database. The template document acquisition unit 206 may search the template database using user-input information as a query and acquire a template document that is found in the search. When no search is particularly used, the template document acquisition unit 206 may acquire a template document selected by the user from among multiple template documents. When there is only one template document, the template document acquisition unit 206 may acquire the template document without searching, selecting, or the like.

[0104] The template document may be stored in a location other than the template database. For example, the template document acquisition unit 206 may acquire the template document from a database other than the template database, a computer other than the generation-related server 20 (e.g., the business support server 30), or an external information storage medium. The template document acquisition unit 206 may acquire only one template document, or may acquire multiple template documents.

[0105] The generation-related process execution unit 203 in Modification 2 executes the generation-related process further based on the template document. "Further based on the template document" means that the process is based not only on the registered data, user input information, and AI, but also on the template document. For example, the generation-related process execution unit 203 inputs input data including the template document to the AI. The AI ​​calculates an embedded expression based not only on the registered data and user input information, but also on the template document. The embedded expression reflects not only the registered data and user input information, but also the template document. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded expression. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded expression corresponding to the template document, and generates the electronic document.

[0106] The generation-related process of Modification 2 is not limited to the process of generating an electronic document further based on a template document. As with the embodiment, the generation-related process of Modification 2 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV further based on the template document and importing the data into the template document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document further based on the template document. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document further based on the template document.

[0107] The business support system 1 of the second modification executes generation-related processing further based on the template document. This allows the business support system 1 to generate an electronic document specific to the template document. In the examples of Figures 2 and 3, a template invoice is prepared as the template document. The AI ​​outputs output data that references the template invoice. This allows the business support system 1 to generate invoices that conform to the template invoice. Similarly, when electronic documents other than invoices are generated, the business support system 1 can improve the accuracy of the other electronic documents.

[0108] [6-3. Variation 3] For example, when an electronic document is generated based on certain registered data, other registered data may be useful as a reference. In the case of an invoice such as that shown in FIGS. 2 and 3, detailed information about the invoice recipient may not be registered in the invoice management app selected by the user. If detailed information about the invoice recipient is registered in a customer management app other than the invoice management app, it may be more appropriate to use not only the registered data in the invoice management app but also other registered data in the customer management app. Therefore, Variation 3 will take as an example a case where other registered data is used in generating an electronic document.

[0109] The registration data acquisition unit 201 of the third modification acquires selected registration data, which is registration data selected by a user from among a plurality of registration data, and related registration data, which is other registration data related to the selected registration data. The selected registration data is the registration data described in the embodiment. For example, a record of an app selected by the user corresponds to the selected registration data. The related registration data is other registration data associated with the selected registration data. For example, the related registration data may be another record of the same app or a record of another app.

[0110] It is assumed that definition data defining which selected registration data and which related registration data are associated with each other is stored in advance in the data storage unit 200. The registration data acquisition unit 201 acquires related registration data based on the definition data. In the examples of Figures 2 and 3, the definition data defines in advance that the invoice management application and the customer management application are associated with each other. Based on the definition data, the registration data acquisition unit 201 can determine that it is sufficient to acquire records of the customer management application as related registration data. For example, the registration data acquisition unit 201 searches the customer management application using the value of the field "billing destination" included in the registration data as a key, and acquires records of the customer management application found in the search as related registration data. It is assumed that which field will be the key is determined in advance.

[0111] In the fifth modification, it is assumed that the related registration data is stored in the business support database DB. The registration data acquisition unit 201 identifies the related registration data based on the application ID of the application selected by the user and the related registration data. The registration data acquisition unit 201 requests the related registration data from the business support server 30. It is assumed that the request includes the application ID of the application in which the related registration data is registered.

[0112] For example, when the business support server 30 receives a request, it refers to the business support database DB and acquires related registration data associated with the application ID. The business support server 30 transmits the related registration data to the generation-related server 20. The registration data acquisition unit 201 acquires the related registration data from the business support server 30. Note that the related registration data may be identified by the business support server 30, rather than by the generation-related server 20. In this case, the data storage unit 300 stores the related registration data. The business support server 30 acquires the application ID of the application for generating the electronic document from the generation-related server 20, and identifies the related registration data based on the application ID and the related registration data.

[0113] The generation-related process execution unit 203 of Modification 3 executes generation-related processes based on the selected registration data and the related registration data. The generation-related process execution unit 203 inputs input data to the AI ​​as registration data, including not only the selected registration data but also the related registration data. The AI ​​calculates an embedded expression based on not only the selected registration data and user input information but also the related registration data. The embedded expression reflects not only the selected registration data and user input information but also the related registration data. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded expression. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded expression corresponding to the setting information, and generates the electronic document.

[0114] The generation-related process of Modification 3 is not limited to the process of generating an electronic document based on selected registration data and related registration data. As in the embodiment, the generation-related process of Modification 3 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV based on the selected registration data and related registration data and importing the data into a default electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document based on the selected registration data and related registration data. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document based on the selected registration data and related registration data.

[0115] The business support system 1 of the third modification executes the generation-related process based on the selected registration data and the related registration data. This allows the business support system 1 to generate an electronic document specific to the related registration data. In the example of FIGS. 2 and 3, if detailed information about the billing destination is not registered in the invoice management app, the business support system 1 can obtain the detailed information about the billing destination from the related registration data registered in the customer management app and generate a more appropriate electronic document.

[0116] [6-4. Variation 4] For example, a user may wish to generate an electronic document in the same format as a previously generated electronic document. When a user repeatedly issues invoices to the same billing recipient, the user may wish to issue an invoice in the same format as a previously generated invoice issued to this billing recipient. Even if the invoice is not to the same billing recipient, the user may wish to issue an invoice in the same format as a previously generated invoice. Therefore, Variation 3 takes as an example a case in which a previously generated electronic document is used in generating an electronic document. In Variation 3, the user is assumed to be able to repeatedly execute generation-related processes.

[0117] The business support system 1 of the fourth modification includes a generated electronic document acquisition unit 207. The generated electronic document acquisition unit 207 acquires a generated electronic document that was generated by a generation-related process that was executed in the past. For example, the data storage unit 200 stores the generated electronic document. The generated electronic document is stored in the data storage unit 200 in association with the user who instructed the generation of the electronic document. The generated electronic document may be stored in the data storage unit 200 in association with the delivery destination of the electronic document (in the examples of FIGS. 2 and 3, the billing destination). The generated electronic document may be stored in the data storage unit 200 in association with the application that generated the electronic document. When the generation-related process is executed, the production-related server 20 records the generated electronic document in the data storage unit 200.

[0118] For example, the generated electronic document acquisition unit 207 acquires a generated electronic document from the data storage unit 200. The generated electronic document acquisition unit 207 may acquire a generated electronic document associated with a user who instructed the generation of a new electronic document. The generated electronic document acquisition unit 207 may acquire a generated electronic document associated with a destination of the new electronic document. The generated electronic document acquisition unit 207 may acquire a generated electronic document associated with an application that generates the new electronic document. The generated electronic document acquisition unit 207 may acquire a generated electronic document from a computer other than the production-related server 20 (for example, the business support server 30) or an external information storage medium.

[0119] The generation-related process execution unit 203 in Modification 4 executes the generation-related process further based on the generated electronic document. "Further based on the generated electronic document" means that the process is based not only on the registered data, user input information, and AI, but also on the generated electronic document. For example, the generation-related process execution unit 203 inputs input data including the generated electronic document to the AI. The AI ​​calculates an embedded representation based not only on the registered data and user input information, but also on the generated electronic document. The embedded representation reflects not only the registered data and user input information, but also the generated electronic document. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded representation. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded representation corresponding to the generated electronic document, and generates the electronic document.

[0120] The generation-related process of Modification 4 is not limited to the process of generating an electronic document based on an already-generated electronic document. As with the embodiment, the generation-related process of Modification 4 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV based on the already-generated electronic document and importing the data into a default electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document based on the already-generated electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document based on the already-generated electronic document.

[0121] The business support system 1 of the fourth modification executes generation-related processing further based on the generated electronic document. This allows the business support system 1 to generate an electronic document specific to the generated electronic document. In the examples of Figures 2 and 3, the generated electronic document is an invoice that the user issued in the past. The AI ​​outputs output data that references the generated invoice. This allows the business support system 1 to generate an invoice that conforms to the generated invoice. Similarly, when an electronic document other than an invoice is generated, the business support system 1 can improve the accuracy of the other electronic document.

[0122] [6-5. Variation 5] For example, since an application has not only a database function but also a communication function, a user can register any comment in the application's records. By registering a comment, a user can communicate with other users. In the examples of FIGS. 2 and 3, a user communicates with other users by registering a comment about the business content related to the issuance of an invoice. Such comments can be useful in generating electronic documents. Therefore, Variation 3 will be described as an example of a case where a comment is used in a generation-related process.

[0123] The business support system 1 includes a first comment information acquisition unit 208. The first comment information acquisition unit 208 acquires comment information regarding comments associated with registered data. The comment information is text in a natural language indicating the content of the comment. The comment can also be said to be a post by a user. A comment associated with registered data is a comment entered on a business support screen SC indicating the registered data. In other words, a comment that can be searched from registered data corresponds to a comment associated with the registered data.

[0124] In the fifth modification, it is assumed that the comment information is stored in the business support database DB. For example, the first comment information acquisition unit 208 acquires the comment information from the business support database DB. The first comment information acquisition unit 208 may acquire the comment information from the business support database DB in the same manner as the registered data acquisition unit 201 acquires the registered data. The first comment information acquisition unit 208 may acquire the comment information from a database other than the business support database DB, a computer other than the business support server 30, or an external information storage medium.

[0125] The generation-related process execution unit 203 of Modification 5 executes the generation-related process further based on the comment information. "Further based on the comment information" means that the process is based not only on the registered data, user input information, and AI, but also on the comment information. For example, the generation-related process execution unit 203 inputs input data including comment information to the AI. The AI ​​calculates an embedded expression based not only on the registered data and user input information, but also on the comment information. The embedded expression reflects not only the registered data and user input information, but also the comment information. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded expression. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded expression corresponding to the comment information, and generates the electronic document.

[0126] The generation-related process of Modification 5 is not limited to the process of generating an electronic document further based on comment information. As with the embodiment, the generation-related process of Modification 5 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV data further based on the comment information and importing the data into a default electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document further based on the comment information. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document further based on the comment information.

[0127] The business support system 1 of the fifth modification executes generation-related processing further based on the comment information. This allows the business support system 1 to generate an electronic document specific to the comment information. For example, if a user comments on the layout of an electronic document in a record of a certain application, the business support system 1 can generate an electronic document that conforms to the layout desired by the user. If a user comments on items that the user wants to include in the electronic document, the business support system 1 can generate an electronic document that includes the items desired by the user.

[0128] [6-6. Variation 6] For example, as explained somewhat in the embodiment and modified examples 1 to 5, the generation-related process execution unit 203 may execute, as the generation-related process, a code generation process for generating code related to the generation of an electronic document. The code generated by the code generation process may be code in any programming language as long as it is code executable by the business support system 1. For example, a library for generating electronic documents is provided in the Python library, and therefore the code generation process may be a process for generating code that utilizes this library. For other programming languages, such as Javascript (registered trademark) or C language, code for generating electronic documents is also provided, and therefore the code generation process may be a process for generating this code.

[0129] For example, the generation-related process execution unit 203 inputs input data to the AI ​​in the same manner as in the embodiment. The user input information may indicate that the AI ​​should generate code. A default prompt indicating that the AI ​​should generate code may be prepared in advance. The default prompt is assumed to be stored in the data storage unit 200. The default prompt may be prepared by an administrator of the business support system 1 or by a user. The AI ​​can recognize that it should generate code for generating an electronic document based on at least one of the user input information and the default prompt.

[0130] The AI ​​calculates an embedded representation of the input data and outputs output data including code corresponding to the embedded representation. When GPT is used as the AI, a function called a code interpreter provided in GPT may be used to generate the code. The output data of the AI ​​may include information referenced by the code to generate an electronic document (e.g., detailed information in the invoice, in the example of the invoice at the bottom of Figure 3). While the AI ​​generating code for generating an electronic document based on registered data in the business support system 1 is a novel configuration as of the filing of the application, the technology itself for the AI ​​generating code for generating an electronic document may be publicly known as of the filing of the application. Therefore, a person skilled in the art would be able to understand, based on the description of this embodiment and the common general technical knowledge as of the filing of the application, that the AI ​​of this embodiment can perform the process of generating code for generating an electronic document.

[0131] The business support system 1 of the sixth modification includes an electronic document generation unit 209. The electronic document generation unit 209 generates an electronic document based on code generated by a code generation process. For example, the electronic document generation unit 209 executes the code generated by the code generation process to generate an electronic document based on the registration data and user-input information. The code may indicate not only the process for generating the electronic document but also information to be included in the electronic document, or the information may be attached to the code. The electronic document generation unit 209 generates an electronic document by executing such code. The process of generating an electronic document based on the code itself may be a known process. For example, at least one of the aforementioned Python library and code prepared in another programming language may be used.

[0132] The business support system 1 of the sixth modification executes, as a generation-related process, a code generation process for generating code related to the generation of an electronic document. The business support system 1 generates an electronic document based on the code generated by the code generation process. As a result, even if the AI ​​does not have the function of generating the electronic document itself, as long as it has the function of generating code for generating the electronic document, the business support system 1 can provide the electronic document to the user.

[0133] [6-7. Variation 7] For example, as described somewhat in the embodiment, the providing unit 204 may provide the electronic document to the user by executing a process for displaying, on the user terminal 40 of the user, a screen on which the user can modify the electronic document, based on the deployment result of the electronic document. The deployment result is the result of the process for deploying the electronic document in the environment of the business support system 1. In the example at the bottom of FIG. 3, the business support screen SC including the display area A2 corresponds to the screen on which the user can modify the electronic document. This screen may be a screen other than the business support screen SC shown at the bottom of FIG. 3. For example, the electronic document may be displayed on the entire screen, rather than in a window like the display area A2.

[0134] FIG. 9 is a diagram showing an example of how a user modifies an electronic document. As shown in the upper part of FIG. 9, when the user selects button B2, the providing unit 204 places the business support screen SC in an electronic document editing mode. A program used in a known document editor may be used to edit the electronic document. The providing unit 204 executes processing for the user to edit the electronic document based on the program. In the example at the top of FIG. 9, the AI ​​was unable to generate the total amount of the invoice, so the user manually inputs the total amount.

[0135] For example, as shown in the lower part of FIG. 9, when the user inputs the corrections and selects button B4, the providing unit 204 receives data indicating the corrections input by the user from the user terminal 40. The providing unit 204 modifies at least a portion of the electronic document based on the data. The providing unit 204 transmits the modified electronic document to the user terminal 40. The user terminal 40 displays the modified electronic document on the business support screen SC. For example, the user terminal 40 displays the electronic document including the total amount input by the user on the business support screen SC. The providing unit 204 may perform this series of processes using a known document editor.

[0136] The business support system 1 of the seventh modification provides the electronic document to the user by executing a process for displaying a business support screen SC on the user terminal 40, on which the user can modify the electronic document, based on the deployment result of the electronic document. This allows the user to modify the electronic document generated by the business support system 1, and the business support system 1 can further improve user convenience.

[0137] [6-8. Variation 8] For example, AI may not be able to generate an electronic document that meets the user's wishes in one go. For this reason, a user may be able to instruct the AI ​​to correct the electronic document generated. In the examples of Figures 2 and 3, the user may instruct the AI ​​to correct the electronic document generated from the business support screen SC at the bottom of Figure 3. In Variation 8, an example is given in which a user instructs the AI ​​to correct an electronic document by voice input, but the user can instruct the AI ​​to correct an electronic document by any other input method. For example, a user may instruct the AI ​​to correct an electronic document by text input. For example, if the total amount listed on the third line of an invoice is incorrect or missing, the user may input an instruction such as, "Please correct the third line."

[0138] The user may explicitly instruct the business support system 1 to modify the electronic document by voice input, text input, or other operation (for example, selecting the "Modify" button). The business support system 1 can specify, based on the user's explicit instruction, that the generated electronic document should be modified rather than a new electronic document should be generated. The AI ​​may also infer that the electronic document will be modified even without the user's explicit instruction. The AI ​​may specify, based on the input data, that the generated electronic document should be modified rather than a new electronic document should be generated. The AI ​​can make such a specification using the embedded representation of the input data.

[0139] FIG. 10 is a diagram showing an example of processing for correcting an electronic document. The business support system 1 of Modification 8 includes a correction content information acquisition unit 210, a correction-related processing execution unit 211, and an electronic document correction unit 212. The correction content information acquisition unit 210 acquires correction content information regarding the correction content of the electronic document based on a user's input. The correction content information is an instruction indicated by the user's input when correcting the electronic document. The correction content information can also be said to be the user's intention at the time of correction. The correction content information is sometimes called a prompt for the AI. As shown in FIG. 10, when making a correction, input data including the correction content information is input to the AI.

[0140] In Variation 8, an example is given in which the text entered into input form F when the user selects button B1 when correcting an electronic document corresponds to the correction content information. Therefore, the correction content information is text indicating the specific content of the correction the user wishes to make to the electronic document. When the user selects button B1, the user terminal 40 transmits the correction content information, which is the text entered into input form F, to the production-related server 20. The correction content information acquisition unit 210 acquires the correction content information from the user terminal 40. The correction content information acquisition unit 210 may acquire only one piece of correction content information, or may acquire multiple pieces of correction content information.

[0141] The correction content information may not be text in a natural language, but may be the voice input by the user. In this case, the correction content information acquisition unit 210 may acquire the correction content information in the form of voice from the user terminal 40, and then request the voice conversion server 10 to convert the correction content information into text. The correction content information acquisition unit 210 acquires the correction content information converted into text from the voice conversion server 10. The correction content information acquisition unit 210 may not acquire the correction content information directly from the user terminal 40, but may acquire the correction content information indirectly via the voice conversion server 10, the business support server 30, or another computer.

[0142] The correction-related process execution unit 211 generates correction portion information regarding the content of a portion of an electronic document after correction according to the correction content, based on the correction content information and AI. The correction portion according to the correction content is a portion of the electronic document before correction. The amount of the correction portion varies depending on the correction content. For example, the correction portion may be only one item in the electronic document, or two or more items. The correction portion may not be a continuous portion. For example, in an electronic document with 20 lines, the correction portions may be the third and tenth lines. Which portions are corrected is determined by AI. The correction portion may be only some items in a single line.

[0143] For example, the AI ​​outputs, along with the correction portion information, correction portion identification information that can identify the correction portion in the electronic document before correction. The correction portion identification information can also be referred to as the position of the correction portion in the electronic document before correction. For example, the correction portion identification information indicates the line number of the correction portion. A default prompt during correction may be provided, such as, "Please correct only the parts of the electronic document before correction that require correction. Please output the correction portion information after correction of that part and the identification information of that part." This default prompt allows the AI ​​to more accurately understand that it is necessary to output the correction portion information and the correction portion identification information.

[0144] For example, the correction-related process execution unit 211 inputs input data including the pre-correction electronic document and correction content information to the AI. In the example of Figure 10, the correction-related process execution unit 211 inputs input data further including the pre-correction electronic document to the AI. The AI ​​calculates an embedded expression based on not only the correction content information but also the pre-correction electronic document. The embedded expression reflects not only the correction content information but also the pre-correction electronic document. The AI ​​outputs output data including correction portion information and correction portion identification information according to the calculated embedded expression. The correction-related process execution unit 211 acquires the correction portion information and correction portion identification information included in the output data output by the AI. In the example of Figure 10, only the third line of the pre-correction electronic document is output from the AI ​​as correction portion information. The correction portion identification information indicates that it is the third line.

[0145] The electronic document correction unit 212 corrects the electronic document by replacing the corrected portion of the electronic document with the corrected portion information. The replacement can also be referred to as overwriting or changing. In the example of FIG. 10, the third line of the electronic document before correction is replaced with the corrected portion data. For example, the electronic document correction unit 212 replaces the corrected portion of the electronic document before correction, which is indicated by the corrected portion identification information, with the corrected portion data. The user may also specify the corrected portion. For example, the user may input, "Please correct the third line." In this case, the correction content information includes the corrected portion identification information. The AI ​​does not need to output the corrected portion identification information. Even if the AI ​​does not output the corrected portion identification information, the electronic document correction unit 212 can simply replace the corrected portion input by the user with the corrected portion information.

[0146] The business support system 1 of Variation 8 acquires correction content information based on user input. The business support system 1 executes correction-related processing based on the correction content information and AI. The business support system 1 corrects the electronic document by replacing the corrected portion of the electronic document with the correction portion information. This enables the business support system 1 to streamline the user's work of correcting the electronic document, thereby improving user convenience during correction. For example, when AI regenerates the entire electronic document, there is a possibility that the electronic document will be generated with processing that is completely different from the pre-correction version. However, by replacing only the corrected portion of the pre-correction electronic document with the correction portion information, the business support system 1 can prevent this from occurring and improve the accuracy of corrections.

[0147] [6-9. Variation 9] For example, AI may not be able to generate an electronic document that meets the user's wishes. The user may verify the electronic document generated by AI. Variation 9 takes as an example a case where processing is executed to assist the user in verifying the electronic document. The business support system 1 of Variation 9 includes a verification processing execution unit 213. The verification processing execution unit 213 executes verification processing related to the verification of the electronic document when the electronic document is generated. The verification processing is processing to assist the user in verifying the electronic document. Verification of an electronic document is checking whether the electronic document is correct or not.

[0148] For example, the verification process may be a process of identifiably displaying information included in the electronic document from among the registered data. In the example shown at the bottom of Fig. 3, the values ​​of each field in the registered data with record number 00001 are included in the electronic document, so the verification process execution unit 213 may execute the verification process by changing the color of the record with record number 00001 in the list L. For example, the verification process execution unit 213 transmits HTML data including a code indicating the changed color. Instead of changing the color of the record, the verification process execution unit 213 may display only the record on the business support screen SC, thereby making it possible to identify which record's information was used in the electronic document.

[0149] For example, the verification process may be a process of identifiably displaying registered data portions of an electronic document. In the example at the bottom of Figure 3, in an invoice, which is an example of an electronic document, the registered data is used for the name of the billing recipient, the billing amount, and details. The other portions are generated by AI. Therefore, the verification process execution unit 213 may execute the verification process by changing the color of the portions of the electronic document in which registered data is used. Instead of changing the color of the portions, the verification process execution unit 213 may execute the verification process by applying other effects, such as underlining.

[0150] The verification process is not limited to the above example. The verification process may be any process for supporting a user in verifying an electronic document. For example, if an AI generates an electronic document based on registered data and a learned formula, the verification process execution unit 213 may execute the verification process by acquiring information about the formula from the AI ​​and displaying the formula on the business support screen SC. The verification process execution unit 213 may execute the verification process by determining whether any items are missing from the electronic document based on items included in the electronic document generated by the AI ​​and predetermined items, and displaying the result of the determination on the business support screen SC.

[0151] The business support system 1 of the ninth modification executes a verification process for verifying an electronic document when the electronic document is generated. This enables the business support system 1 to support the user in verifying the electronic document, thereby further improving user convenience.

[0152] [6-10. Variation 10] For example, in the embodiment, the provision unit 204 displays the electronic document on the business support screen SC, thereby providing the electronic document to the user. The user uses the electronic document displayed on the business support screen SC in their own business. Variation 10 describes an example of a business that the user performs using the electronic document. Furthermore, an example is given of a case where the business support system 1 executes processing to support the business.

[0153] The business support system 1 of the tenth modification includes a business process execution unit 214. When an electronic document is generated, the business process execution unit 214 executes business process related to a business in which the electronic document is used. The business process is a process for supporting a business related to the electronic document. For example, the business process may be a process for notifying that an electronic document has been generated, a process for changing the status of a business flow, a process for leaving a comment indicating that an electronic document has been generated, a process for registering the electronic document in a specified folder, a process for downloading the electronic document to the user terminal 40, or other process. In the tenth modification, a process for notifying that an electronic document has been generated will be described as an example of business process.

[0154] For example, when an electronic document is generated, the business process execution unit 214 notifies a predetermined notification destination that the electronic document has been generated. The notification may be performed by any means. For example, the notification may be performed by a notification function on the business support system 1 (in the examples of FIGS. 2 and 3, a notification function displayed from a bell-shaped icon), email, SMS, a messaging app, a push notification, a badge, or other means. Data indicating the notification destination is assumed to be stored in advance in the data storage unit 200. For example, the notification destination may be the boss or colleague of the user who generated the electronic document. When an electronic document is generated, the business process execution unit 214 executes business processing by notifying the user that the electronic document has been generated based on the data indicating the notification destination.

[0155] When an electronic document is generated, the business support system 1 of the tenth modification executes business processing related to the business in which the electronic document is used. This allows the business support system 1 to effectively support the user's business. For example, when an electronic document is generated, if a notification is sent to a predetermined notification destination, the user does not need to perform any operation to send the notification to the notification destination himself / herself, and therefore the business support system 1 can reduce the user's workload.

[0156] [6-11. Variation 11] For example, other users, such as the user's superior or colleagues, may leave comments on an electronic document generated by the business support system 1. Such comments may be useful information when a new electronic document is generated the next time or later. Therefore, Variation 11 takes as an example a case where a new electronic document is generated based on comments from other users on an electronic document that has already been generated.

[0157] In Variation 11, the business support system 1 includes a second comment information acquisition unit 215. The second comment information acquisition unit 215 acquires comment information relating to comments on an already generated electronic document generated by a generation-related process executed in the past, which comments are entered by a user other than the user. The comment information is assumed to be associated with the already generated electronic document and stored in the business support database DB. The comment information of Variation 11 differs from the comment information of Variation 5 in that it is a comment left on an electronic document, but is similar to the comment information of Variation 5 in that it indicates comments registered in the business support system 1.

[0158] For example, the second comment information acquisition unit 215 acquires comment information from the business support database DB. The second comment information acquisition unit 215 may acquire comment information from the business support database DB in the same manner as the first comment information acquisition unit 208 acquires comment information. The second comment information acquisition unit 215 may acquire comment information from a database other than the business support database DB, a computer other than the business support server 30, or an external information storage medium.

[0159] The generation-related process execution unit 203 of Modification 11 executes the generation-related process further based on the comment information. "Further based on the comment information" means that the process is based not only on the registered data, user input information, and AI, but also on the comment information. For example, the generation-related process execution unit 203 inputs input data including the comment information to the AI. The AI ​​calculates an embedded expression based not only on the registered data and user input information, but also on the comment information. The embedded expression reflects not only the registered data and user input information, but also the comment information. The AI ​​outputs output data including an electronic document corresponding to the calculated embedded expression. The generation-related process execution unit 203 acquires the electronic document included in the output data output by the AI. For example, the AI ​​identifies what kind of electronic document should be generated based on the embedded expression corresponding to the comment information, and generates the electronic document.

[0160] The generation-related process of Modification 11 is not limited to the process of generating an electronic document further based on comment information. As with the embodiment, the generation-related process of Modification 11 may be other processes. For example, the generation-related process execution unit 203 may execute the generation-related process by generating data such as CSV data further based on the comment information and importing the data into a default electronic document. The generation-related process execution unit 203 may execute the generation-related process by generating an API request for requesting the generation of an electronic document further based on the comment information. The generation-related process execution unit 203 may execute the generation-related process by generating code for generating an electronic document further based on the comment information.

[0161] The business support system 1 of the eleventh modification executes generation-related processing further based on the comment information. This allows the business support system 1 to generate an electronic document specific to the comment information. For example, if another user leaves a comment on an already generated electronic document, the business support system 1 can generate an electronic document in accordance with the comment. If the other user who left the comment is a superior, the business support system 1 can generate an electronic document that reflects the superior's comments on the already generated electronic document.

[0162] [6-12. Other variations] For example, two or more of the modifications 1 to 11 may be combined.

[0163] For example, a function described as being realized by the voice conversion server 10 may be realized by the generation-related server 20, the business support server 30, or the user terminal 40. A function described as being realized by the generation-related server 20 may be realized by the voice conversion server 10, the business support server 30, or the user terminal 40. A function described as being realized by the business support server 30 may be realized by the voice conversion server 10, the generation-related server 20, or the user terminal 40. A function described as being realized by the user terminal 40 may be realized by the voice conversion server 10, the generation-related server 20, or the business support server 30. Each function may be shared by multiple computers or may be realized by a single computer. [Explanation of symbols]

[0164] 1 Business support system, 10 Voice conversion server, 11, 21, 31, 41 Control unit, 12, 22, 32, 42 Memory unit, 13, 23, 33, 43 Communication unit, 20 Generation-related server, 30 Business support server, 40 User terminal, 44 Operation unit, 45 Display unit, 46 Voice input unit, 47 Voice output unit, 100 Data storage unit, 101 Voice conversion unit, 200 Data storage unit, 201 Registration data acquisition unit, 202 User input information acquisition unit, 203 Generation-related process execution unit, 204 Provision unit, 205 Setting information acquisition unit, 206 Template document acquisition unit, 207 Electronic document acquisition unit, 208 First comment information acquisition unit, 209 Electronic document generation unit, 210 Correction content information acquisition unit, 211 Correction-related process execution unit, 212 Electronic document correction unit, 213 Verification processing execution unit, 214 business processing execution unit, 215 second comment information acquisition unit, 300 data storage unit, 301 business support unit, 400 data storage unit, 401 display control unit, 402 operation reception unit, A1, A2 display area, B1, B2, B3, B4 buttons, F input form, I icon, L list, N network, SC business support screen, DB business support database.

Claims

1. a registered data acquisition unit that acquires registered data registered in a business support system that can support a user's business; a user input information acquisition unit that acquires user input information related to an electronic document to be generated based on the user input; a generation-related process execution unit that executes a generation-related process related to the generation of the electronic document based on the registration data, the user input information, and AI; a providing unit that provides the electronic document to the user; Business support system including.

2. the business support system further includes a setting information acquisition unit that acquires setting information related to settings of the registration data; the generation-related process execution unit executes the generation-related process further based on the setting information. The business support system according to claim 1 .

3. the business support system further includes a template document acquisition unit that acquires a template document related to the electronic document, the template document being a prepared template document; the generation-related process execution unit executes the generation-related process further based on the template document. The business support system according to claim 1 or 2.

4. the registration data acquisition unit acquires selected registration data, which is the registration data selected by the user, from the plurality of registration data, and related registration data, which is other registration data related to the selected registration data; the generation-related process execution unit executes the generation-related process based on the selected registration data and the related registration data. The business support system according to claim 1 or 2.

5. the business support system further includes a generated electronic document acquisition unit that acquires the generated electronic document generated by the generation-related process that was executed in the past; the generation-related process execution unit executes the generation-related process further based on the generated electronic document. The business support system according to claim 1 or 2.

6. the business support system further includes a first comment information acquisition unit that acquires comment information regarding a comment associated with the registration data, the generation-related process execution unit executes the generation-related process further based on the comment information. The business support system according to claim 1 or 2.

7. the generation-related process execution unit executes, as the generation-related process, a code generation process for generating code related to generation of the electronic document; the business support system further includes an electronic document generation unit that generates the electronic document based on the code generated by the code generation process. The business support system according to claim 1 or 2.

8. the providing unit provides the electronic document to the user by executing a process for displaying, on the user terminal of the user, a screen on which the user can modify the electronic document based on a deployment result of the electronic document. The business support system according to claim 1 or 2.

9. The business support system includes: a correction information acquisition unit that acquires correction information regarding corrections to the electronic document based on the user's input; a correction-related processing execution unit that executes a correction-related processing related to generation of correction portion information regarding the content after correction of the correction portion of the electronic document according to the correction content, based on the correction content information and the AI; an electronic document correction unit that corrects the electronic document by replacing the corrected portion of the electronic document with the corrected portion information; The business support system according to claim 1 or 2, further comprising:

10. the business support system further includes a verification process execution unit that executes a verification process related to verification of the electronic document when the electronic document is generated; The business support system according to claim 1 or 2.

11. the business support system further includes a business process execution unit that, when the electronic document is generated, executes business process related to a business in which the electronic document is used; The business support system according to claim 1 or 2.

12. the business support system further includes a second comment information acquisition unit that acquires comment information regarding a comment on the electronic document that has been generated by the generation-related process that has been executed in the past and that has been input by a user different from the user; the generation-related process execution unit executes the generation-related process further based on the comment information. The business support system according to claim 1 or 2.

13. Acquires registered data registered in a business support system capable of supporting the user's business, acquiring user input information related to an electronic document to be generated based on the user input; Executing a generation-related process related to generation of the electronic document based on the registration data, the user input information, and AI; providing the electronic document to the user; Business support methods.

14. a registered data acquisition unit that acquires registered data registered in a business support system that can support a user's business; a user input information acquisition unit that acquires user input information related to an electronic document to be generated based on the user input; a generation-related process execution unit that executes a generation-related process related to the generation of the electronic document based on the registration data, the user input information, and AI; a providing unit that provides the electronic document to the user; A program that allows a computer to function as a

Images