Business support systems, business support methods, and programs

Abstract

To improve user convenience. [Solution] The function information acquisition unit (102) of the business support system (1) acquires function information related to business support functions that support business operations. The explanation information generation unit (103) causes AI (Artificial Intelligence) to generate explanation information related to the explanation of business support functions based on the function information. The explanation information provision unit (104) provides the explanation information.

Description

Technical Field

[0004] , , , , , , ,

[0005] , , ,

[0003] , , , ,

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

Background Art

[0002] Conventionally, business support functions generated or created to suit the business of users are known. For example, in Patent Document 1, there are described a regular node corresponding to data of each screen that can constitute a screen flow and a display program, and a group node corresponding to a program that performs a series of processes by combining screens, and an application creation support device that receives an arrangement operation of group nodes for each procedure of a procedural business and an arrangement operation of regular nodes within a group node, and generates a definition file describing a screen flow in a procedural business.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technology of Patent Document 1, as the number of applications increases, it becomes difficult to manage for what intention each application was created. For example, as the number of applications increases, it also becomes difficult to manage the relevance between applications. Since the technology of Patent Document 1 cannot generate explanatory information regarding the explanation of an application, it was not possible to sufficiently enhance the convenience of the user. This is not limited to applications such as Patent Document 1, but can be said generally for business support functions.

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

[0006] A business support system relating to one aspect of this disclosure includes a function information acquisition unit that acquires function information relating to business support functions that support business operations, an explanation information generation unit that causes AI (Artificial Intelligence) to generate explanation information relating to the business support functions based on the function information, and an explanation information provision unit that provides the explanation information. [Effects of the Invention]

[0007] This disclosure can improve user convenience. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the hardware configuration of a business support system. [Figure 2] This figure shows an example of a screen displayed on a user's terminal. [Figure 3] This figure shows an example of a screen displayed on a user's terminal. [Figure 4] This figure shows an example of a screen displayed on a user's terminal. [Figure 5] This figure shows an example of a screen displayed on a user's terminal. [Figure 6] This figure shows an example of a screen displayed on a user's terminal. [Figure 7] This figure shows an example of the functions implemented in the business support system. [Figure 8] This figure shows an example of a business support database. [Figure 9] This figure shows an example of AI input and output during application generation. [Figure 10] This figure shows an example of AI input and output when generating explanatory information. [Figure 11] This figure shows an example of a process performed by a business support system. [Figure 12]This figure shows an example of a process performed by a business support system. [Figure 13] This figure shows an example of the functions implemented in the modified operation support system. [Modes for carrying out the invention]

[0009] [1. Hardware Configuration] This document describes an example of an embodiment of the business support system, business support method, and program related to this disclosure. Figure 1 is a diagram showing an example of the hardware configuration of the business support system. For example, business support system 1 includes a server 10 and a user terminal 20. Each of the server 10 and user terminal 20 is connected to a network N such as the Internet or a LAN. In Figure 1, one server 10 and one user terminal 20 are shown, but at least one of them may be present in multiple units.

[0010] Server 10 is a server computer. For example, 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 volatile memory such as RAM and non-volatile memory such as 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 user terminal 20 is the user's computer. For example, the user terminal 20 is a personal computer, tablet, smartphone, or wearable device. The user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25. The hardware configuration of the control unit 21, storage unit 22, and communication unit 23 may be the same as that of the control unit 11, storage unit 12, and communication unit 13, respectively. The operation unit 24 includes an input device such as a mouse or touch panel. The display unit 25 includes a liquid crystal or organic EL display.

[0012] Incidentally, the programs stored in the storage units 12 and 22 may be supplied via the network N. The hardware configurations of each of the server 10 and the user terminal 20 are not limited to the example of FIG. 1. For example, at least one of the server 10 and the user terminal 20 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 directly connecting to an external device. The program stored in the information storage medium may be supplied to at least one of the server 10 and the user terminal 20 via at least one of the reading unit and the input / output unit.

[0013] Also, the business support system 1 may include at least one computer. The computer included in the business support system 1 is not limited to the example of FIG. 1. For example, the business support system 1 may include only the server 10. In this case, the user terminal 20 exists outside the business support system 1. The business support system 1 may include the server 10 and another computer.

[0014] [2. Overview of Business Support System] In the present embodiment, the business support system 1 provides a business support service to a user. The business support service is a service that supports business through information processing. The business support service may support business in an organization such as a company or an administrative agency, or may support an individual's business. A service called groupware is a type of business support service. The business support service may be cloud-based or on-premises. The business support service may be a service that can support business with no-code or low-code.

[0015] For example, the business support system 1 has a business support function related to business support. The business support function is a function realized by a program developed for business support. The business support function can also be regarded as a collection of programs and data for business support. The types of business support functions may be known types. For example, the business support function may be a database function for managing business-related data in a database, a communication function for users to communicate with each other, a file management function for managing files, a schedule management function for managing schedules, a mail management function for managing mails, or other functions.

[0016] In this embodiment, an example is given where a user belonging to an organization uses a business support service by operating the user terminal 20 to access the server 10. For example, the user uses the business support function by displaying the website of the business support service on the browser installed on the user terminal 20. The user may use the business support service from a program dedicated to the business support service instead of the browser.

[0017] FIGS. 2 to 6 are diagrams showing an example of a screen displayed on the user terminal 20. For example, when the user logs in to the business support service, as shown in the upper part of FIG. 2, the user terminal 20 displays a portal screen SC1 corresponding to the entrance in the business support service on the display unit 25. The user can use any business support function among a plurality of business support functions from the portal screen SC1. In the example in the upper part of FIG. 2, the portal screen SC1 displays a notice I10 to the user, a notification N11 to the user, a list L12 of spaces where users perform business with each other, and a list L13 of applications available to the user.

[0018] The term "app" is sometimes used as an abbreviation for "application," a type of program, but in this embodiment, the term "app" is used to refer to an example of a business support function. Therefore, wherever "app" is written, it can be read as "business support function." For example, an app includes a database in which various business-related data is stored. An app may be a complex business support function that includes not only a database function, which is an example of a business support function, but also other business support functions. For example, an app may have at least one of the following: a communication function for users to communicate with each other, and a file management function for managing files using records, which are units of data in the database.

[0019] For example, when a user selects an app from list L13, the user terminal 20 displays the app content screen SC2, which shows the contents of the app selected by the user, on the display unit 25, as shown in the lower part of Figure 2. In the example at the bottom of Figure 2, the app content screen SC2 for the invoice management app is shown. The app content screen SC2 displays a list L20 of records, which are the units of data registered in the app. The first row of list L20 displays the field names, which are the names of the fields. Fields are sometimes called columns. The rows from the second row onward of list L20 display the values ​​of each field in each individual record.

[0020] For example, when a user selects a record from list L20, the app content screen SC2 displays the details of the selected record. The app content screen SC2, which shows the record details, displays field names, input forms for entering values ​​for each field, an input form for entering comments in the communication function, a comment field for entering entered comments, a button for uploading files in the file management function, or other information. From the app content screen SC2, which displays the record details, the user can edit existing records or create new records.

[0021] In this embodiment, users can generate or create new applications to suit their own work. For example, when a user selects button B14 on the portal screen SC1, the user terminal 20 displays the app store screen SC3, which shows the app store for managing applications in the business support service, on the display unit 25, as shown in the upper part of Figure 3. Users can use sample applications provided as examples from the app store as new applications, or they can generate or create new applications themselves.

[0022] For example, if a user selects button B30, they can create a new app by specifying the app's settings themselves. If a user selects button B31, they can generate a new app by utilizing AI (Artificial Intelligence). If a user selects button B32, they can create a new app by importing CSV data. If a user selects button B33, they can create a new app by importing an app template. Users may also generate or create new apps by other means.

[0023] In this embodiment, we take the example of a case where a user generates an application using AI. AI is a program that possesses artificial intelligence. There are various definitions of AI, but the AI ​​in this embodiment may be an AI defined by various known definitions. AI may be an AI called generative AI or conversational AI. For example, AI may be a large-scale language model, a machine learning model that is not classified as a large-scale language model, a program called a bot, or other program. There are also various definitions of machine learning, but the machine learning in this embodiment may be a machine learning that is defined by various known definitions. Machine learning may be supervised learning, semi-supervised learning, or unsupervised learning.

[0024] In this embodiment, we take the example where a large-scale language model corresponds to the AI. For example, when the user selects button B31, the user terminal 20 displays the AI ​​screen SC4 for interaction with the AI ​​on the display unit 25, as shown in the lower part of Figure 3. The user enters a prompt, which is an instruction to the AI, from the input form F40. Hereafter, the prompt entered by the user will be called the user input prompt. The user can enter any content related to the application they wish to use as the user input prompt. The user may also include other data such as images or CSV files in the user input prompt.

[0025] For example, if a user wants to create an app to manage meeting minutes, as shown in the upper part of Figure 4, the user enters a user input prompt in input form F40 indicating the content of the app they want, such as "I want to create an app to manage meeting minutes." This user input prompt is sent to an external system, which is an external system that manages the AI. The external system inputs the user input prompt into the AI. As will be explained in more detail later, other prompts besides the user input prompt may also be entered into the AI. The AI ​​generates an answer consisting of the app settings corresponding to the user input prompt and a message to the user.

[0026] For example, when the AI ​​generates an answer, the user terminal 20 displays message M41A, indicating the AI's answer, on the AI ​​screen SC4, as shown in the lower part of Figure 4. In the example at the bottom of Figure 4, message M41A shows the AI's answer to the user and the field name generated by the AI ​​as an application setting. The AI ​​generates a field name that corresponds to the user's preference indicated by the user input prompt. If the user requests an application to manage meeting minutes, message M41A will show a field name that is estimated to be appropriate as a field name for the application to manage meeting minutes.

[0027] For example, if the user agrees with the content indicated by message M41A, they can create an app with that content by selecting button B410A. In this case, the app will include the fields indicated by the field names in message M41A. The user may also change the settings of the app generated by the AI. If the user does not like the settings of the app generated by the AI, they can also instruct the AI ​​to make changes.

[0028] For example, if a user wants to add a field, as shown in the upper part of Figure 5, the user enters a user input prompt into input form F40 indicating the content of the field they want, such as "Can I also add attendees? It's an important meeting to know who is attending." The AI ​​generates a response in response to the user input prompt. As shown in the lower part of Figure 5, the user terminal 20 displays message M41B on the AI ​​screen SC4, indicating that the attendees field has been added. The user can repeatedly make modifications to the AI ​​until they are satisfied with the settings generated by the AI. Hereafter, when messages M41A and M41B are not distinguished, they will simply be referred to as message M41. Similarly, when buttons B410A and B410B are not distinguished, they will simply be referred to as button B410.

[0029] For example, if the user agrees with the content indicated by message M41B, they can create an application with that content by selecting button B410B. When the user selects button B410B, server 10 creates a meeting minutes management application based on the settings generated by the AI. Once the meeting minutes management application is created, it is added to list L13 on portal screen SC1. When the user selects the meeting minutes management application from list L13, the user terminal 20 displays the application content screen SC2, which shows the contents of the meeting minutes management application, on display unit 25, as shown in the upper part of Figure 6.

[0030] In the upper example of Figure 6, the field names indicated by message M41B are displayed in list L20. The meeting minutes management application may include fields with field names other than those indicated by message M41B. That is, the AI ​​may generate field names not shown in message M41B, as well as field names not shown in message M41B. Message M41B may only show the field names of representative fields from among the field names generated by the AI. The AI ​​may generate other settings, such as application names, in addition to field names. For example, the AI ​​may generate an application name such as "Meeting Minutes Management Application" in response to a user input prompt.

[0031] In this embodiment, the user can have the AI ​​generate explanatory information about the meeting minutes management application. For example, when the user selects button B21 for generating explanatory information, the AI ​​generates explanatory information based on the user input prompts entered by the user when creating the meeting minutes management application. Since the user input prompts reflect the intentions of the user who created the meeting minutes management application, the AI ​​generates explanatory information that aligns with the user's intentions. Once the explanatory information is generated, the user terminal 20 displays a message M22 on the application content screen SC2, indicating that explanatory information has been generated, as shown in the lower part of Figure 6.

[0032] For example, a user can modify the explanatory information by selecting button B220 in message M22. The modification of the explanatory information may be performed by AI or manually by the user. The explanatory information is associated with the meeting minutes management application and stored on server 10. Users can access the explanatory information at any time. The explanatory information may also be provided to users other than the user who created the meeting minutes management application.

[0033] Furthermore, the AI ​​may generate descriptive information for applications other than the meeting minutes management application. For example, the AI ​​may generate descriptive information for applications created by users without using the AI. The business support system 1 of this embodiment prevents situations where it becomes unclear what the intention behind an application was, even if the number of applications in an organization increases or if the user who created or generated the application leaves the company, by providing descriptive information for the applications. The details of the business support system 1 will be described below.

[0034] [3. Functions provided by the business support system] Figure 7 shows an example of the functions implemented by business support system 1.

[0035] [3-1. Functions implemented by the server] For example, server 10 includes a data storage unit 100, a business support function generation unit 101, a function information acquisition unit 102, an explanatory information generation unit 103, and an explanatory information provision unit 104. The data storage unit 100 is implemented by a storage unit 12. The business support function generation unit 101, the function information acquisition unit 102, the explanatory information generation unit 103, and the explanatory information provision unit 104 are implemented by a control unit 11. Each of the functions of the business support function generation unit 101, the function information acquisition unit 102, the explanatory information generation unit 103, and the explanatory information provision unit 104 may be a default function of the business support service or a function added as a plug-in.

[0036] [Data Storage Unit] The data storage unit 100 stores various types of data related to the business support service. For example, the data storage unit 100 stores a business support database DB containing various types of data related to business support functions. In this embodiment, we take the example of a case where the data of multiple tenants (for example, organizations such as companies) using the business support service is managed in the business support database DB, but the data of each tenant does not have to be managed in a single database called the business support database DB. The storage area of ​​the data storage unit 100 may be divided for each tenant, and the data of each tenant may be managed in the storage area corresponding to that tenant. For example, if a tenant adds a plugin, the data of the plugin will be stored in that storage area.

[0037] Figure 8 shows an example of a business support database DB. In this embodiment, an application is described as an example of a business support function, so the business support function database is shown as an example where various data related to the application is stored. The business support database DB may also store data related to other business support functions other than the application. Separate business support database DBs may be prepared for each of the multiple business support functions.

[0038] For example, the business support database DB stores an application ID that identifies the application, an organization ID that identifies the organization using the application, a user ID that identifies the user who created the application, user input prompts, application configuration information, record information which is the actual data of the application's records, and descriptive information. Whenever a new application is created, the data for that new application is stored in the business support database DB. Whenever the descriptive information generation unit 103 (described later) generates descriptive information, that descriptive information is stored in the business support database DB.

[0039] The data stored by the data storage unit 100 is not limited to the business support database DB. The data storage unit 100 can store any data. For example, the data storage unit 100 may store basic data for business support functions, such as an application. By applying user-specified settings or settings generated by the AI ​​to the basic data, it becomes possible to provide business support functions that are configured to suit the user's work. The data storage unit 100 may also store data necessary for displaying the portal screen SC1, application content screen SC2, application store screen SC3, and AI screen SC4, etc. (for example, HTML data). The data storage unit 100 may also store other prompts input to the AI ​​in addition to user input prompts. If other data is input to the AI ​​along with the prompts, the data storage unit 100 may store the other data.

[0040] In this embodiment, we take the example of a case where the server 10 uses the AI ​​of an external system that is linked with the business support system 1, so the data storage unit 100 does not store the actual AI data. However, the data storage unit 100 may store the actual AI data. That is, in this embodiment, we take the example of a case where the actual AI data is stored in an external system, but the server 10 may execute the various processes of this embodiment based on the actual AI data stored in the data storage unit 100.

[0041] For example, an AI includes a program that performs processes such as calculating embedding representations, and parameters referenced by the program. Embedding representations are information that allows the AI ​​to understand the meaning of the data. For example, embedding representations are represented by multidimensional vectors. Embedding representations are sometimes called features that describe the characteristics of the data. Embedding representations may also be represented in forms other than multidimensional vectors. The AI ​​may include other data besides parameters (for example, data equivalent to a dictionary of terms). This other data is referenced by the program. This other data may be separate from the AI. Based on the parameters, the AI ​​calculates embedding representations of the input data it receives and produces output corresponding to those embedding representations. For example, parameters could be weights and biases.

[0042] Furthermore, the AI ​​program and parameters may be publicly known programs and parameters. For example, the AI ​​program 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 GAN (Generative Adversarial Networks), programs and parameters used in generative AI or conversational AI not classified as such, or other programs and parameters. The AI ​​program and parameters may be various programs and parameters that can be understood by a person skilled in the field of computer software based on common technical knowledge at the time of filing.

[0043] In this embodiment, a large-scale language model (e.g., GPT) is described as an example of AI, so the AI ​​program shows the process of analyzing input data (e.g., user input prompts) input to the AI. The AI ​​parameters are parameters such as weights and biases that the AI ​​refers to in order to analyze the meaning as natural language. Based on parameters adjusted through learning, the AI ​​analyzes the input data it receives and produces output according to the analysis results. For example, the AI ​​divides the natural language text represented by the input data into multiple tokens. Based on the parameters, the AI ​​calculates embedding representations that show the meaning of each token. The AI ​​understands the meaning as natural language based on the order of the embedding representations for each token. The AI ​​may, if necessary, make predictions according to the order of the embedding representations for each token. The AI ​​outputs output data according to the order of the embedding representations.

[0044] [Business support function generation department] The business support function generation unit 101 causes an AI (an AI that generates explanatory information) or another AI to generate a business support function based on a user input prompt entered by the user, which concerns the specific content of the business support function. In this embodiment, the case in which the AI ​​that generates explanatory information and the AI ​​that generates the business support function are the same is given as an example, but these AIs may be different from each other. The other AI mentioned above is an AI different from the AI ​​that generates explanatory information. Where AI is written in the description of the business support function generation unit 101, it can be read as AI or another AI.

[0045] The business support function generation unit 101 causing the AI ​​to generate business support functions means that the business support function generation unit 101 causes the AI ​​to generate data related to business support functions. For example, the business support function generation unit 101 causes the AI ​​to generate business support functions by causing the AI ​​to generate settings for business support functions. The settings for business support functions themselves may be the same as those used in publicly known business support services. The business support function generation unit 101 may also cause the AI ​​to generate business support functions by causing the AI ​​to generate a program for the business support functions. For example, if business support functions are provided to the user by a script executed on a browser, the business support function generation unit 101 may cause the AI ​​to generate business support functions by causing the AI ​​to generate a script.

[0046] Figure 9 shows an example of AI input and output during application generation. For example, the business support function generation unit 101 inputs a default prompt, which is a pre-prepared prompt, and a user input prompt to the AI. The default prompt is assumed to be stored in the data storage unit 100 in advance. The default prompt may be prepared by the administrator of the business support service or by the user. The default prompt indicates the specific content of the output that the AI ​​should generate. In other words, the default prompt indicates the task that the AI ​​should perform.

[0047] In this embodiment, an application is described as an example of a business support function, so the default prompt indicates that the application settings should be generated. For example, the default prompt may show a message such as, "You are the AI ​​that generates the application. Based on the user input prompts you have entered, please generate the appropriate settings for the application." If there are multiple items for the application settings, the default prompt may indicate the specific items that the AI ​​should generate. For example, the default prompt may show a message such as, "Please generate the application name and field names for the application." The content of the default prompt is not limited to the example in Figure 9.

[0048] Note that the default prompt may display other information related to the app's settings. For example, The default prompt may include text indicating that the AI ​​should generate basic app specifications (e.g., basic settings in the app, help pages in business support services, or the app's specifications), the number of fields, the types of fields, the layout of the app content screen SC2, access rights settings, or other settings. A default prompt may also be provided for when the user instructs the AI ​​to make corrections. For example, the default prompt for corrections might say, "Please correct the app settings you generated based on the user input prompts."

[0049] For example, the business support function generation unit 101 inputs a default prompt and a user input prompt to the AI. In this embodiment, since the AI ​​is managed by an external system, the business support function generation unit 101 inputs the default prompt and the user input prompt to the AI ​​by sending them to the external system. When the external system receives the default prompt and the user input prompt, it inputs them to the AI. The external system may also have additional default prompts available.

[0050] For example, the AI ​​calculates embedded representations of default prompts and user input prompts based on parameters adjusted through prior training. The AI ​​outputs the app settings corresponding to the embedded representations. The AI ​​may also divide the default prompts and user input prompts into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs the app settings.

[0051] In the example shown in Figure 9, the AI ​​recognizes that the user wants an app to manage meeting minutes based on the embedded expression of the user input prompt, "I want to create an app to manage meeting minutes," and outputs settings that match the user's request. The AI ​​recognizes the settings it should output based on the embedded expression of the default prompt. The AI ​​may output not only app settings but also a response message to the user. It may be indicated in the default prompt that the AI ​​should output a response message.

[0052] For example, the external system sends the AI ​​output to the server 10. The business support function generation unit 101 obtains the AI ​​output from the external system. The business support function generation unit 101 sends the AI ​​output to the user terminal 20. In this embodiment, since the application settings are generated by the AI, the business support function generation unit 101 sends the settings generated by the AI ​​to the user terminal 20. If the user instructs a modification, the business support function generation unit 101 inputs a default prompt for modification and a user input prompt indicating the modification details to the AI.

[0053] For example, the business support function generation unit 101 inputs these prompts to the AI ​​by sending a default prompt for modification and a user input prompt indicating the modification content to an external system. The external system inputs the default prompt for modification and the user input prompt indicating the modification content to the AI. The external system may also input the AI's output up to that point. The AI ​​calculates the embedded representation of the prompts and other information input to itself and produces output corresponding to the embedded representation. The processing performed by the AI ​​during modification may be the same as when the first output is generated. The business support function generation unit 101 obtains the modification content from the external system. The business support function generation unit 101 sends the modification content from the AI ​​to the user terminal 20. Thereafter, the user may repeatedly give instructions for modification.

[0054] For example, when a user instructs the business support function generation unit 101 to generate an application, it generates the application based on the application settings generated by the AI. The business support function generation unit 101 generates the application by issuing an application ID and storing the organization ID of the organization to which the user belongs, the user's user ID, user input prompts, and setting information indicating the application settings generated by the AI ​​in the application database. The database containing the organization ID and user ID is assumed to be stored in the data storage unit 100 in advance. The business support function generation unit 101 only needs to save the data of the generated application in a storage area corresponding to the organization to which the user belongs (an example of a tenant), and this storage area may be a storage area other than the business support database DB storage area.

[0055] In the example shown in Figure 9, the AI ​​generates field names as application settings. The business support function generation unit 101 generates the application by applying the field names generated by the AI ​​as the field names of the application to be generated. Similarly, if the AI ​​generates settings other than field names (for example, application name or field type), the business support function generation unit 101 can generate the application by applying the other settings generated by the AI ​​as the other settings of the application to be generated. The business support function generation unit 101 can generate other business support functions in the same way, by having the AI ​​generate settings and recording those settings in the data storage unit 100.

[0056] [Function Information Acquisition Unit] The function information acquisition unit 102 acquires function information related to business support functions that support business operations. Function information is information input to the AI ​​when generating explanatory information. Function information can be any information that is related to business support functions in some way. For example, function information may be settings for business support functions, data registered in business support functions, programs that show information processing for business support functions, information in the manual (help) for business support functions, user posts (e.g., comments) registered in business support functions or threads, or other information.

[0057] In this embodiment, it is assumed that functional information for various business support functions is stored in the data storage unit 100. Therefore, the functional information acquisition unit 102 acquires functional information for business support functions to be used for generating explanatory information from the data storage unit 100. Functional information may be stored in a computer other than the server 10, or in an information storage medium. The functional information acquisition unit 102 may acquire functional information for business support functions to be used for generating explanatory information from a computer or information storage medium.

[0058] In this embodiment, since the user's intent is reflected in the user input prompts entered by the user when generating the app, the function information acquisition unit 102 acquires the user input prompts as function information. For example, since the user input prompts are stored in the business support database DB, the function information acquisition unit 102 acquires the user input prompts entered by the user when generating the app for which explanatory information is to be generated from the business support database DB. For example, when the user selects button B21 on the app content screen SC2, the function information acquisition unit 102 acquires the user input prompt associated with the app ID of the app currently displayed on the app content screen SC2.

[0059] Furthermore, if a user instructs the AI ​​to make corrections, multiple user input prompts, including the user input prompt initially entered by the user and the user input prompt entered by the user during the correction, are stored in the business support database DB. Therefore, the function information acquisition unit 102 may acquire multiple user input prompts as function information. The function information acquisition unit 102 may acquire only a portion of the multiple user input prompts as function information. Function information is not limited to user input prompts and may include other information. Other examples of function information will be explained in the modified examples below.

[0060] [Explanatory Information Generation Unit] The explanatory information generation unit 103 causes the AI ​​(Artificial Intelligence) to generate explanatory information about the business support function based on the functional information. The explanatory information is text that describes the business support function. The explanatory information may include not only text but also other information such as diagrams or tables. For example, the explanatory information may be a relationship diagram showing the relationships between applications. The explanatory information may also describe the intention, background, purpose, data structure, setting details, or other content of the business support function that was generated or created. The explanatory information generation unit 103 causes the AI ​​to generate the explanatory information by inputting the functional information into the AI.

[0061] Figure 10 shows an example of AI input and output during the generation of explanatory information. For example, the explanatory information generation unit 103 inputs a default prompt for generating explanatory information and function information to the AI. The default prompt is assumed to be stored in the data storage unit 100 in advance. The default prompt may be prepared by the administrator of the business support service or by the user. The default prompt indicates that the AI ​​will generate explanatory information based on the function information. In other words, the default prompt indicates that generating explanatory information is a task that the AI ​​should perform.

[0062] In this embodiment, an application is described as an example of a business support function, so the default prompt indicates that descriptive information for the application should be generated. For example, the default prompt may say, "You are the AI ​​that generates descriptive information for the application. Based on the function information you have entered, please generate appropriate descriptive information for the application." The content of the default prompt is not limited to the example in Figure 10. The default prompt may also indicate the basic specifications of the application (e.g., basic settings in the application, a help page in the business support service, or the application's specifications), the format and volume of the descriptive information, or other information.

[0063] For example, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the user input prompt. The explanatory information generation unit 103 inputs a default prompt and a user input prompt to the AI. In this embodiment, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and the user input prompt to the AI ​​by sending them to the external system. When the external system receives the default prompt and the user input prompt, it inputs them to the AI. The external system may have additional default prompts available.

[0064] For example, the AI ​​calculates embedded representations of default prompts and user input prompts based on parameters adjusted through prior training. The AI ​​outputs descriptive information about the app corresponding to the embedded representations. The AI ​​may also divide the default prompts and user input prompts into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs descriptive information about the app.

[0065] In the example shown in Figure 10, the AI ​​recognizes the user's intention to manage meeting minutes and the important content for the app based on the embedded expressions of the user's initial user input prompt, "I want to create an app to manage meeting minutes," and the user input prompt the user entered when making revisions, "Can I also add attendees? It's an important meeting to know who attended." The AI ​​recognizes the explanatory information it should output based on the embedded expression of the default prompt. The AI ​​may output not only explanatory information about the app but also a response message to the user. The default prompt may indicate that the AI ​​should output a response message.

[0066] For example, an external system sends the output of the AI ​​to the server 10. The explanation information generation unit 103 obtains explanation information by acquiring the output of the AI ​​from the external system. The explanation information generation unit 103 stores the explanation information in the business support database DB. If a user instructs the AI ​​to modify the explanation information, the explanation information generation unit 103 inputs a default prompt for modification and a user input prompt indicating the content of the modification to the AI. The explanation information generation unit 103 inputs these prompts to the AI ​​by sending the default prompt for modification and the user input prompt indicating the content of the modification to the external system. The external system inputs the default prompt for modification and the user input prompt indicating the content of the modification to the AI. The AU modifies the explanation information based on these prompts.

[0067] The external system may input the AI's output up to that point. The AI ​​calculates the embedded expressions, such as prompts, that have been input to it and outputs according to those embedded expressions. The processing performed by the AI ​​during correction may be the same as when the initial output is generated. The explanation information generation unit 103 obtains the corrections made by the AI ​​from the external system. The explanation information generation unit 103 sends the corrections made by the AI ​​to the user terminal 20. Thereafter, the user may repeatedly give instructions for correction. In this embodiment, the case where explanation information is generated after the application is generated is given as an example, but the explanation information may also be generated at the same time as the application is generated. The processing of the business support function generation unit 101 and the processing of the explanation information generation unit 103 may not be executed separately but at the same time.

[0068] [Explanatory Information Provision Department] The explanatory information provision unit 104 provides explanatory information. Providing explanatory information means that the explanatory information provision unit 104 outputs explanatory information to the user terminal 20. For example, the explanatory information generation unit 103 provides explanatory information by sending data of message M22 indicating explanatory information to the user terminal 20. The explanatory information provision unit 104 can provide explanatory information on any screen in the business support service. The explanatory information provision unit 104 may also provide explanatory information using other means such as email or file output.

[0069] [3-2. Functions implemented on the user terminal] For example, the user terminal 20 includes a data storage unit 200, a display control unit 201, and an operation reception unit 202. The data storage unit 200 is implemented by a storage unit 22. The display control unit 201 and the operation reception unit 202 are each implemented by a control unit 21.

[0070] [Data Storage Unit] The data storage unit 200 stores data for users to use business support services. For example, the data storage unit 200 stores a browser for displaying various screens of the business support system 1. For example, the data storage unit 200 stores applications specific to the business support system 1.

[0071] [Display Control Unit] The display control unit 201 displays various screens in the business support system 1 on the display unit 25. For example, based on data received from the server 10, the display control unit 201 displays the portal screen SC1, the application content screen SC2, the application store screen SC3, and the AI ​​screen SC4 on the display unit 25.

[0072] [Operation Reception Section] The operation reception unit 202 receives various operations in the business support system 1. For example, the operation reception unit 202 receives operations on the portal screen SC1, the application content screen SC2, the application store screen SC3, and the AI ​​screen SC4. The data indicating the operation received by the operation reception unit 202 is transmitted to the server 10 as appropriate.

[0073] [4. Processes executed by the business support system] Figures 11 and 12 show examples of processes executed by the business support system 1. The processes in Figures 11 and 12 are executed by the control units 11 and 21 executing programs stored in the memory units 12 and 22, respectively. Each process in Figures 11 and 12 is an example of a process included in the business support method.

[0074] As shown in Figure 11, the user terminal 20 performs a login process with the server 10 to allow the user to log in to the business support service (S1). When the user selects button B14, the user terminal 20 performs a process with the server 10 to display the app store screen SC3 (S2). When the user selects button B31, the user terminal 20 performs a process with the server 10 to display the AI ​​screen SC4 (S3).

[0075] The user terminal 20 accepts input from the user input prompt for input form F40 (S4). The user terminal 20 sends the user input prompt to the server 10 (S5). The server 10 receives the user input prompt from the user terminal 20 (S6). Based on the user input prompt received in S6, the server 10 requests the external system to generate the application settings (S7). The server 10 obtains the AI-generated response from the external system (S8).

[0076] Server 10 performs a process to display message M41 on AI screen SC4 in communication with user terminal 20 (S9). User terminal 20 accepts user input (S10). In S10, input from the user input prompt for input form F40 or selection of button B410 is accepted. User terminal 20 sends operation content data indicating the user's operation to server 10 (S11). Server 10 receives operation content data from user terminal 20 (S12).

[0077] Server 10 refers to the operation content indicated by the operation content data (S13). If a user input prompt for correction is entered in S13 (S13:F40), Server 10 requests the external system to correct the application settings based on the user input prompt (S14). Server 10 obtains the AI ​​response from the external system (S15) and returns to processing S9. From there, the user's instruction to correct is repeated until button B410 is selected in S13.

[0078] In S13, if button B410 is selected (S13:B410), the process moves to Figure 12, and the server 10 executes the process of generating a new application based on the application settings generated by the AI ​​(S16). When the user selects a new application, the server 10 executes the process of displaying the application content screen SC2, which shows the contents of the new application, with the user terminal 20 (S17). When the user selects button B21, the user terminal 20 requests the server 10 to generate explanatory information (S18). The server 10 receives the request from the user terminal 20 to generate explanatory information (S19).

[0079] Server 10 acquires user input prompts entered by the user during application generation as functional information based on the business support database DB (S20). Based on the functional information, Server 10 requests an external system to generate explanatory information using AI (S21). Server 10 acquires the explanatory information generated by the AI ​​from the external system (S22). Server 10 performs processing to provide the explanatory information to the user terminal 20 (S23), and this process ends. In S23, message M22 is displayed. If the user instructs to modify the explanatory information, the explanatory information is modified based on the user input prompt indicating the modification content.

[0080] [5. Summary of Embodiments] The business support system 1 of this embodiment acquires functional information related to business support functions. Based on the functional information, the business support system 1 causes the AI ​​to generate explanatory information about the business support functions. The business support system 1 provides the explanatory information. As a result, even if the number of apps in an organization increases or if the user who created an app leaves the company, the user can understand the intention behind the creation of the app through the explanatory information, thus improving user convenience. For example, the explanatory information makes it easier for users to manage apps.

[0081] Furthermore, the business support system 1 causes an AI or another AI to generate business support functions based on user input prompts. The business support system 1 acquires the user input prompts as function information. The business support system 1 causes the AI ​​to generate explanatory information based on the user input prompts. As a result, the business support system 1 can have the AI ​​generate explanatory information based on user input prompts that directly reflect the intentions of the user who generated the business support function, such as an application, thus improving the accuracy of the explanatory information.

[0082] [6. Variant] This disclosure is not limited to the embodiments described above. This disclosure may be modified as appropriate without departing from the spirit of this disclosure.

[0083] Figure 13 shows an example of the functions implemented in the modified business support system 1. As shown in Figure 13, in the modified version described later, the server 10 includes a data format receiving unit 105. The data format receiving unit 105 is implemented by the control unit 11.

[0084] [6-1. Variation 1] For example, in the embodiment, a user input prompt was described as an example of functional information. Functional information may be any information relating to a business support function for which explanatory information is to be generated, and is not limited to a user input prompt. Modifications 1 to 6 describe other examples of functional information. Functional information is a concept that encompasses the example described in the embodiment and modifications 1 to 6. In the modifications, the application for which explanatory information is to be generated may not be an application generated by AI, but an application whose settings are specified by the user (an application created by the user). Examples of functional information described in the embodiment and modifications 1 to 6 may be combined. For example, two or more examples of functional information from the embodiment and modifications 1 to 6 may be input to the AI.

[0085] The function information acquisition unit 102 in Modification 1 acquires setting information related to the settings of business support functions as function information. The settings of the business support functions themselves may be various settings adopted in publicly known business support services. The settings of the business support functions may be the specific content of the information processing of the business support functions, the layout of the screen of the business support functions, access rights to the data of the business support functions, or other settings. If the AI ​​is a large-scale language model, the setting information shall be presented in natural language text so that the AI ​​can recognize the setting information. If the AI ​​is capable of recognizing information other than text (e.g., images, etc.), the setting information may be other information other than text.

[0086] In Modification 1, similar to the embodiment, we take the example where the application corresponds to a business support function. For example, the application settings information may include the application name, a memo describing the application, the display format of the list L20 on the application content screen SC2, the layout of the input form on the application content screen SC2, the display format of the graph on the application content screen SC2, the design of the application content screen SC2, field names, field types (data types of fields), calculation formulas (functions) set in the fields, settings for notifications to the user, access rights, language, or other settings. The function information acquisition unit 102 only needs to acquire setting information that shows all or part of the application settings. In other words, the setting information does not necessarily have to show all of the application settings.

[0087] In Modification 1, we take the example of a case where the application configuration information is stored in the business support database DB, similar to the embodiment. The function information acquisition unit 102 acquires the application configuration information for which explanatory information is to be generated from the business support database DB. The application configuration information may be stored in a database other than the business support database DB, a computer other than the server 10, or an information storage medium. In this case, the function information acquisition unit 102 only needs to acquire the application configuration information for which explanatory information is to be generated from the other database, a computer other than the server 10, or an information storage medium.

[0088] The function information acquisition unit 102 may also acquire setting information for other applications related to the application for which explanatory information is to be generated. These other applications are those whose records are referenced by the application for which explanatory information is to be generated, or those whose records are referenced by the application for which explanatory information is to be generated. The reference to the record can be specified by a calculation formula such as a lookup. The function information acquisition unit 102 may also identify the relationships between applications from the calculation formula information set in the application and acquire setting information for other applications related to the application for which explanatory information is to be generated.

[0089] Furthermore, if descriptive information for business support functions other than the application is generated, the function information acquisition unit 102 only needs to acquire the setting information for those other business support functions. The setting information acquired by the function information acquisition unit 102 is not limited to the above example. For example, if descriptive information for the communication function is generated, the function information acquisition unit 102 may acquire the name of the place where posts are made using the communication function (e.g., thread name), information of users who can use the communication function, the screen design in the communication function, or setting information indicating other settings.

[0090] For example, when descriptive information for the file management function is generated, the function information acquisition unit 102 may acquire the types of files that can be managed by the file management function, the data size of the files, the number of files, the name of the file management function, information of users who can use the file management function, the screen design of the file management function, or other setting information. When descriptive information for the schedule management function is generated, the function information acquisition unit 102 may acquire the schedule registration rules for the schedule management function, the name of the schedule management function, information of users who can use the schedule management function, the screen design of the schedule management function, or other setting information.

[0091] In Modification 1, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the configuration information. For example, the explanatory information generation unit 103 inputs a default prompt and configuration information to the AI. The default prompt in Modification 1 indicates that the AI ​​will generate explanatory information based on the settings indicated by the configuration information. For example, the default prompt may show a sentence such as, "You are the AI ​​that generates explanatory information for the app. Based on the settings indicated by the configuration information you have entered, please generate appropriate explanatory information as an explanation of the app."

[0092] For example, in Modification 1, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and configuration information to the AI ​​by sending the default prompt and configuration information to the external system. When the external system receives the default prompt and configuration information, it inputs the default prompt and configuration information to the AI. The external system may also have additional default prompts available.

[0093] For example, the AI ​​calculates embedded representations of default prompts and configuration information based on parameters adjusted through prior training. The AI ​​outputs descriptive information about the app corresponding to these embedded representations. The AI ​​may also divide the default prompts and configuration information into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs descriptive information about the app.

[0094] For example, suppose the configuration information indicates the field names of the application. Based on the embedded representation of the application's field names, the AI ​​recognizes the application's purpose—managing meeting minutes—and outputs explanatory information appropriate to the application's purpose. The AI ​​recognizes the explanatory information it should output based on the embedded representation of the default prompt. The AI ​​may output not only explanatory information about the application but also a response message to the user. The default prompt may indicate that the AI ​​should output a response message.

[0095] Furthermore, the flow in which the explanatory information generation unit 103 acquires AI output from an external system and the explanatory information provision unit 104 provides explanatory information may be the same as in the embodiment. Also, since the AI ​​may be able to recognize that it should generate explanatory information even if only configuration information is input, the explanatory information generation unit 103 may input only configuration information to the AI ​​without inputting a default prompt in particular. In addition, if the AI ​​is not a general-purpose large-scale language model but an AI specialized in generating explanatory information (for example, an AI that has learned training explanatory information), the AI ​​can identify its own task, such as generating explanatory information, even if no default prompt is input. For this reason, the AI ​​does not necessarily need to be input a default prompt in particular.

[0096] In the modified example 1, the business support system 1 acquires configuration information regarding the settings of business support functions as function information. Based on the configuration information, the business support system 1 has the AI ​​generate explanatory information. Since the configuration information of business support functions sometimes reflects the purpose of the business support functions, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate explanatory information based on the configuration information that reflects the purpose of the business support functions.

[0097] [6-2. Variation 2] For example, users may be able to configure program code for extending business support functions as configuration information. In the second modification, we take the example of a script executed on a browser that corresponds to program code, but the program code may be code generated or created in any programming language. The program code may be created manually by the user or generated by AI. Program code for extending business support functions can be said to be program code other than the program code indicated by the default program provided by the business support service.

[0098] For example, in business support services, default programs for business support functions are pre-configured so that users can utilize business support functions without coding or using low-code. Users can generate or create program code to extend the functionality of business support functions beyond the default programs. For example, a user might generate or create program code to highlight a specific record on the application content screen SC2, program code for data aggregation, program code to perform calculations other than those provided by the business support service, or program code for other processing.

[0099] In the modified example 2, the function information acquisition unit 102 acquires program code for extending business support functions as configuration information. For example, when a user inputs program code to extend the business support functions of a certain application, the program code is associated with the application ID of that application and stored in the business support database DB. The function information acquisition unit 102 acquires the program code of the application for which explanatory information is to be generated from the business support database DB as configuration information. Similar to the modified example 1, the function information acquisition unit 102 may acquire program code of other applications related to the application for which explanatory information is to be generated, or it may acquire the program code of an application from another database, another computer, or an information storage medium.

[0100] In the modified example 2, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the program code. For example, the explanatory information generation unit 103 inputs a default prompt and a program code, which is an example of setting information, to the AI. The AI ​​calculates the embedded representations of the default prompt and the program code based on parameters adjusted through prior training. The AI ​​outputs explanatory information for the application corresponding to the embedded representations. The AI ​​may also divide the default prompt and the program code into units called tokens and then calculate the embedded representation of each token. Based on the sequence of the token embedded representations, the AI ​​predicts the next sentence as needed and outputs explanatory information for the application.

[0101] The process in which the explanatory information generation unit 103 acquires AI output from an external system and the explanatory information provision unit 104 provides explanatory information may be the same as in Modification 1. In particular, the fact that a default prompt does not need to be input to the AI ​​may also be the same as in Modification 1.

[0102] In the modified version 2, the business support system 1 acquires program code for extending business support functions as configuration information. Based on the program code, the business support system 1 has the AI ​​generate explanatory information. Since the program code generated for extending business support functions may more clearly express the purpose of the business support functions, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate explanatory information based on program code that more clearly expresses the purpose of the business support functions.

[0103] [6-3. Modification 3] For example, as described in the embodiment, the business support function may be a database function that supports business operations using a database. In Modification 3, as in the embodiment, an application is described as an example of a database function, but the database function may be a business support function that is not called an application. For example, the database function may not be a complex business support function such as a communication function, but rather a function for providing spreadsheet software to users on the cloud.

[0104] The functional information acquisition unit 102 in Modification 3 acquires record information about database records as functional information. Record information is information that shows the specific content of a record. For example, record information may be the specific values ​​of each field in the record, comments registered in the record, reactions to comments, files uploaded to the record, or other content.

[0105] For example, the function information acquisition unit 102 may acquire record information for all records in the application, or it may acquire record information for some of the records in the application. In the third modification example, the function information acquisition unit 102 acquires record information for any of the multiple records in the application. The individual record information may show only the values ​​of some of the fields, rather than the values ​​of all fields.

[0106] In Modification 3, similar to the embodiment, we take the example of a case where record information is stored in the business support database DB. The function information acquisition unit 102 acquires record information of the application for which explanatory information is to be generated from the business support database DB. The record information may be stored in a database other than the business support database DB, a computer other than the server 10, or an information storage medium. In this case, the function information acquisition unit 102 only needs to acquire the record information of the application for which explanatory information is to be generated from the other database, a computer other than the server 10, or an information storage medium. Also, similar to Modification 1, the function information acquisition unit 102 may acquire record information of other applications related to the application for which explanatory information is to be generated.

[0107] In the modified example 3, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the record information. For example, the explanatory information generation unit 103 inputs a default prompt and record information to the AI. The default prompt in modified example 3 indicates that the AI ​​will generate explanatory information based on the content of the record indicated by the record information. For example, the default prompt may show a sentence such as, "You are the AI ​​that generates explanatory information for the app. Based on the content of the record indicated by the record information you have entered, please generate appropriate explanatory information as an explanation of the app."

[0108] For example, in Modification 3, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and record information to the AI ​​by sending the default prompt and record information to the external system. When the external system receives the default prompt and record information, it inputs the default prompt and record information to the AI. The external system may also have additional default prompts available.

[0109] For example, the AI ​​calculates embedded representations of default prompts and record information based on parameters adjusted through prior training. The AI ​​outputs descriptive information about the app corresponding to the embedded representations. The AI ​​may also divide the default prompts and record information into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs descriptive information about the app.

[0110] For example, record information indicates the values ​​of each field in the record. Based on the embedded representation of the values ​​of each field, the AI ​​recognizes the application's purpose, which is to manage meeting minutes, and outputs explanatory information appropriate to the application's purpose. The flow in which the explanatory information generation unit 103 obtains the AI's output from an external system and the explanatory information provision unit 104 provides the explanatory information may be the same as in the embodiment and modifications 1 and 2. In particular, the fact that a default prompt does not need to be input to the AI ​​may also be the same as in modifications 1 and 2.

[0111] In variation 3, the business support function is a database function that supports business operations through a database. Business support system 1 acquires record information about database records as functional information. Business support system 1 has AI generate explanatory information based on the record information. Since the record information of the database function may contain specific details of the data managed by the database function, business support system 1 can improve the accuracy of the explanatory information by having AI generate explanatory information based on record information that contains specific details of the data.

[0112] The functional information acquisition unit 102 may acquire multiple record information corresponding to multiple records. The explanatory information generation unit 103 may cause the AI ​​to generate explanatory information based on multiple record information arranged according to the order of multiple records in the database. For example, the order of records is identified by record numbers assigned to each record in a sequential manner. The order of records can be identified by information that can identify individual records in a known database. For example, if information called an index or row number is assigned to each record, the order of records can be identified by the index or row number. The explanatory information generation unit 103 inputs the record information of each of the multiple records in ascending or descending order to the AI.

[0113] For example, the explanatory information generation unit 103 inputs each of the multiple record pieces of information to the AI ​​in the same order as the records in the application. The AI ​​calculates the embedded representation for each of the multiple record pieces of information and generates explanatory information based on the order of the embedded representations. That is, the AI ​​may recognize the order of the multiple record pieces of information as a context and generate explanatory information according to the order of each of the multiple record pieces of information. Since the AI ​​recognizes the order of each of the multiple record pieces of information as a context and generates explanatory information, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate explanatory information according to the order of each of the multiple record pieces of information.

[0114] [6-4. Modification 4] For example, information about who generated or created a business support function can be useful as a description of that function. If a user responsible for taking meeting minutes generates or creates a business support function, that function may be related to meeting minutes. If a user responsible for accounting generates or creates a business support function, that function may be related to accounting. If a user responsible for legal affairs generates or creates a business support function, that function may be related to legal affairs. For this reason, user information about users may be used as function information.

[0115] In the modified example 4, the function information acquisition unit 102 acquires user information as function information regarding the user who generated or created the business support function (for example, a user who had an app generated by AI, or a user who created an app themselves). User information can be any information about the user. User information may also be information about the user's attributes. For example, user information may be the number of times an app has been created, the username, the type of work the user is in charge of, the organization the user belongs to, the group within the organization (for example, a team or department), profile information, year of joining the company, years of service, position, career history, or other information.

[0116] In the modified example 4, the data storage unit 100 stores a user database containing user information. For example, the user database associates a user ID (e.g., login account) that can identify a user with user information. The function information acquisition unit 102 acquires user information from the user database that is associated with the user ID of the user who generated or created the business support function. User information may also be stored in a database other than the user database, a computer other than the server 10, or an information storage medium. In this case, the function information acquisition unit 102 can acquire user information from the other database, a computer other than the server 10, or an information storage medium. Note that the user ID may be used as user information.

[0117] In Modification 4, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on user information. The default prompt in Modification 4 indicates that the AI ​​will generate explanatory information based on the settings indicated by the user information. For example, the default prompt may display a message such as, "You are the AI ​​that generates the app's explanatory information. The user information you have entered is the information of the user who generated or created the app. Based on the user information, please generate appropriate explanatory information as the app's description."

[0118] For example, in Modification 4, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and user information to the AI ​​by sending the default prompt and user information to the external system. When the external system receives the default prompt and user information, it inputs the default prompt and user information to the AI. The external system may also provide additional default prompts.

[0119] For example, the AI ​​calculates embedded representations of default prompts and user information based on parameters adjusted through prior training. The AI ​​outputs app description information corresponding to the embedded representations. The AI ​​may also divide the default prompts and user information into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs app description information.

[0120] For example, user information indicates the tasks the user is responsible for. Based on the tasks the user is responsible for, the AI ​​recognizes the application's purpose from the user's task of taking meeting minutes and outputs explanatory information appropriate to the application's purpose. The AI ​​recognizes the explanatory information it should output through an embedded representation of the default prompt. The AI ​​may output not only explanatory information about the application but also a response message to the user. The default prompt may indicate that the AI ​​should output a response message. The flow in which the explanatory information generation unit 103 acquires the AI's output from an external system and the explanatory information provision unit 104 provides the explanatory information may be the same as in the embodiment and modifications 1 to 3. In particular, the fact that the default prompt does not need to be input to the AI ​​may also be the same as in modifications 1 to 3.

[0121] In the modified example 4, the business support system 1 acquires user information about the user who generated or created the business support function as function information. Based on the user information, the business support system 1 has the AI ​​generate explanatory information. Since information about who generated or created the business support function can be useful as an explanation of the business support function, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate explanatory information based on the user information.

[0122] [6-5. Variation 5] For example, a business support function may have links to other business support functions. If an app corresponds to a business support function, and a comment in that app contains links to other apps, then these apps may be related. App relationships can be useful as a description of an app. Therefore, in Modification 5, we will take the example of when links are obtained as functional information.

[0123] In the modified example 5, the function information acquisition unit 102 acquires link information as function information, relating to links to other business support functions associated with the business support function. The link information indicates a link to access a specific screen of another business support function (for example, the application content screen SC2 that shows a specific record of another application). For example, the link information may indicate the URL of the other business support function, or it may be other information besides a URL. The link information may also be included as actual data of the business support function.

[0124] For example, if an application corresponds to a business support function, the function information acquisition unit 102 acquires link information indicating a link attached to the application's comment. The link information may be included as a field value rather than in the application's comment. In this case, the function information acquisition unit 102 may acquire the link information by referring to the field value. The link information may be stored in a database other than the business support database DB, a computer other than the server 10, or an information storage medium. In this case, the function information acquisition unit 102 can acquire the link information from the other database, a computer other than the server 10, or an information storage medium.

[0125] In Modification 5, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the link information. The default prompt in Modification 5 indicates that the AI ​​will generate explanatory information based on the link information. For example, the default prompt may display a message such as, "You are the AI ​​that generates explanatory information for apps. The link information you have entered indicates links from this app to other apps. These apps are related, so please generate appropriate explanatory information for the app based on their relationship." The default prompt may also have information about the other apps linked to by the link information (for example, setting information such as the app name of the other app) embedded in it. By embedding such information in the default prompt, the AI ​​can recognize the relationships between apps in more detail.

[0126] For example, in Modification 5, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and link information to the AI ​​by sending the default prompt and link information to the external system. When the external system receives the default prompt and link information, it inputs the default prompt and link information to the AI. The external system may also have additional default prompts available.

[0127] For example, the AI ​​calculates embedded representations of default prompts and link information based on parameters adjusted through prior training. The AI ​​outputs app description information corresponding to the embedded representations. The AI ​​may also divide the default prompts and link information into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs app description information.

[0128] For example, link information indicates links to other apps related to the app for which descriptive information is to be generated. The AI ​​recognizes the relationships between these apps and outputs descriptive information according to the relationships between the apps. The AI ​​recognizes the descriptive information it should output through an embedded representation in the default prompt. The AI ​​may output not only descriptive information for the app but also a response message to the user. The default prompt may indicate that the AI ​​should output a response message. The flow in which the descriptive information generation unit 103 obtains the AI's output from an external system and the descriptive information provision unit 104 provides the descriptive information may be the same as in the embodiment and modifications 1 to 4. In particular, the fact that the default prompt does not need to be input to the AI ​​may also be the same as in modifications 1 to 4.

[0129] In the modified example 5, the business support system 1 acquires link information as function information, which concerns links to other business support functions associated with a particular business support function. Based on this link information, the business support system 1 has the AI ​​generate explanatory information. Since link information can be useful for estimating the relationships between business support functions, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate it based on the link information.

[0130] [6-6. Variation 6] For example, a user may post content related to a specific business support function to the business support system 1. In the case of the meeting minutes management app described in the embodiment, a user may mention other users and post something like, "I have registered the meeting minutes in the meeting minutes management app. Please check the minutes." The content of such posts can be useful as a reference for explaining business support functions, with the app being an example. Therefore, in Modification 6, we will give an example of a case where posted information is acquired as function information.

[0131] In the modified example 6, the function information acquisition unit 102 acquires post information as function information, which pertains to posts made in the business support system 1 and which include content related to business support functions. The post information is included as actual data for the business support function. For example, if an application corresponds to a business support function, the function information acquisition unit 102 acquires post information indicating comments on the application. The post information may indicate posts made in other places, such as threads, rather than comments on the application. Data of posts made in other places is stored in the data storage unit 100.

[0132] The posted information may also be stored in a database other than the business support database DB, a computer other than server 10, or an information storage medium. In this case, the function information acquisition unit 102 can acquire the posted information from the other database, a computer other than server 10, or an information storage medium. The function information acquisition unit 102 may also acquire posted information of posts that include links to apps or app names that are the target of generating explanatory information. That is, the function information acquisition unit 102 may acquire posted information of posts that include strings that can identify apps, such as app names, as posted information that includes content related to apps. The function information acquisition unit 102 may also acquire posted information of posts that include links to apps that are the target of generating explanatory information, as posted information that includes content related to apps.

[0133] In Modification 6, the explanatory information generation unit 103 causes the AI ​​to generate explanatory information based on the posted information. The default prompt in Modification 6 indicates that the AI ​​will generate explanatory information based on the posted information. For example, the default prompt may say, "You are the AI ​​that generates explanatory information for the app. The posted information you have entered contains content about this app, so please generate appropriate explanatory information as an explanation of the app based on the posted information."

[0134] For example, in Modification 6, since the AI ​​is managed by an external system, the explanatory information generation unit 103 inputs the default prompt and posting information to the AI ​​by sending the default prompt and posting information to the external system. When the external system receives the default prompt and posting information, it inputs the default prompt and posting information to the AI. The external system may also have additional default prompts available.

[0135] For example, the AI ​​calculates embedded representations of the default prompt and post information based on parameters adjusted through prior training. The AI ​​outputs app description information corresponding to the embedded representations. The AI ​​may also divide the default prompt and post information into units called tokens and then calculate the embedded representation of each token. Based on the sequence of token embedded representations, the AI ​​predicts the next sentence as needed and outputs app description information.

[0136] For example, the posted information indicates content related to the app. The AI ​​recognizes the app's purpose, etc., based on the content of the posted information and outputs explanatory information corresponding to the recognition result. The AI ​​recognizes the explanatory information it should output through an embedded expression in the default prompt. The AI ​​may output not only explanatory information about the app but also a response message to the user. The fact that the AI ​​should output a response message may be indicated in the default prompt. The flow in which the explanatory information generation unit 103 acquires the AI's output from an external system and the explanatory information provision unit 104 provides the explanatory information may be the same as in the embodiment and modifications 1 to 5. In particular, the fact that the default prompt does not need to be input to the AI ​​may also be the same as in modifications 1 to 5.

[0137] In the modified example 6, the business support system 1 acquires posting information as functional information, which pertains to posts made by the business support system 1 that contain content related to business support functions. Based on the posting information, the business support system 1 has the AI ​​generate explanatory information. Since the posting information may contain content useful for explaining business support functions, the business support system 1 can improve the accuracy of the explanatory information by having the AI ​​generate explanatory information based on the posting information.

[0138] [6-7. Variation 7] For example, the user may be able to specify the data format of the explanatory information. In Modification 7, the user can specify the data format of the explanatory information when instructing the generation of explanatory information from the app content screen SC2. On the app content screen SC2, the user can specify any data format from among several data formats. The multiple data formats are assumed to be predetermined. Data indicating the multiple data formats is stored in the data storage unit 100. A program that converts the explanatory information generated by the AI ​​into each of the multiple data formats is also assumed to be stored in the data storage unit 100.

[0139] The business support system 1 of Modification 7 includes a data format receiving unit 105. The data format receiving unit 105 accepts the specification of a data format for explanatory information. The data format that the user can specify may be any data format. For example, the data format may be text format, rich text format, document file format, markup language format such as HTML, image format, or other format. For example, when a user specifies a data format, the user terminal 20 sends data indicating the data format specified by the user to the server 10. The data format receiving unit 105 accepts the specification of the data format by receiving this data.

[0140] In the modified example 7, the explanatory information provision unit 104 converts the explanatory information based on the data format received by the data format receiving unit 105 and provides the converted explanatory information. Based on a program for converting explanatory information, the explanatory information provision unit 104 converts the explanatory information generated by the AI ​​into a data format specified by the user. The explanatory information provision unit 104 stores the converted explanatory information in the business support database DB. Although the explanatory information provision unit 104 performs the data format conversion, the processing for providing explanatory information may be the same as in the embodiment.

[0141] The business support system 1 in the modified example 7 accepts the specification of the data format for the explanatory information. Based on the data format, the business support system 1 converts the explanatory information and provides the converted explanatory information. As a result, the user can obtain explanatory information in the desired data format, and the business support system 1 can improve user convenience.

[0142] [6-8. Variation 8] For example, the explanatory information generation unit 103 may cause the AI ​​to generate explanatory information containing multiple explanations, and the priority of each of those explanations. Priority can also be called the accuracy of the AI's estimation. The AI ​​may be able to calculate a score indicating the accuracy of the estimation for each generated product. Such a score may be called confidence or probability. The AI ​​may calculate such a score as priority. The method for calculating the score may be any of the known calculation methods. For example, when the AI ​​calculates how confidently it selected the next word when predicting that word, the degree of confidence may be used as priority.

[0143] The default prompt in Modification 8 indicates that if the explanatory information contains multiple explanations, each explanation should be given priority. For example, the default prompt includes the wording described in the embodiment, plus the phrase, "If there are multiple explanations, please give each explanation priority." Based on the default prompt, the AI ​​calculates and outputs the priority of each explanation included in the explanatory information. The explanatory information generation unit 103 stores the priority of each of the multiple explanations in the business support database DB.

[0144] The explanatory information providing unit 104 in the modified example 8 provides explanatory information based on the priority of each of the multiple explanatory information. For example, the explanatory information providing unit 104 provides only the explanatory information whose priority is above a threshold from among the multiple explanatory information. The explanatory information providing unit 104 provides only a predetermined number of explanatory information from among the multiple explanatory information in order of priority. The explanatory information providing unit 104 differs from the embodiment in that it uses priority to determine whether or not to provide the multiple explanatory information indicated by the explanatory information, but the processing for providing each explanatory information itself may be the same as in the embodiment.

[0145] In the modified example 8, the business support system 1 causes the AI ​​to generate explanatory information containing multiple explanations, along with the priority of each of those explanations. The business support system 1 provides the explanatory information based on the priority of each of the multiple explanations. This allows the user to know which explanations have higher priority, thus improving user convenience.

[0146] [6-9. Other variations] For example, you may combine two or more of the variations 1-8.

[0147] For example, the functions described as being implemented by server 10 may be implemented by other computers. The functions described as being implemented by server 10 may be shared among multiple computers. [Explanation of symbols]

[0148] 1 Business support system, 10 Server, 11,21 Control unit, 12,22 Storage unit, 13,23 Communication unit, 20 User terminal, 24 Operation unit, 25 Display unit, 100 Data storage unit, 101 Business support function generation unit, 102 Function information acquisition unit, 103 Explanation information generation unit, 104 Explanation information provision unit, 105 Data format reception unit, 200 Data storage unit, 201 Display control unit, 202 Operation reception unit, B14,B21,B30,B31,B32,B33,B220,B410,B410A,B410B Buttons, F40 Input form, L12,L13,L20 List, M22,M41A,M41B Message, N11 Notification, SC1 Portal screen, SC2 App content screen, SC3 App store screen, SC4 AI screen, N Network, DB Business support database.

Claims

1. A function information acquisition unit that acquires function information related to business support functions that support business operations, Based on the aforementioned functional information, an explanatory information generation unit causes AI (Artificial Intelligence) to generate explanatory information regarding the explanation of the aforementioned business support function, An explanatory information providing unit that provides the aforementioned explanatory information, Business support systems including this.

2. The business support system further includes a business support function generation unit that causes the AI ​​or another AI to generate the business support function based on a user input prompt entered by the user, the user input prompt relating to the specific content of the business support function, The function information acquisition unit acquires the user input prompt as the function information, The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the user input prompt. The business support system according to claim 1.

3. The function information acquisition unit acquires setting information related to the setting of the business support function as the function information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the setting information. The business support system according to claim 1 or 2.

4. The function information acquisition unit acquires program code for extending the business support function as the setting information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the program code. The business support system according to claim 3.

5. The aforementioned business support function is a database function that supports the aforementioned business using a database. The function information acquisition unit acquires record information relating to the records in the database as the function information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the record information. The business support system according to claim 1 or 2.

6. The function information acquisition unit acquires user information relating to the user who generated or created the business support function as the function information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the user information. The business support system according to claim 1 or 2.

7. The function information acquisition unit acquires link information relating to links to other business support functions associated with the business support function as the function information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the link information. The business support system according to claim 1 or 2.

8. The function information acquisition unit acquires posting information relating to posts made in the business support system that include content related to the business support function as the function information. The explanatory information generation unit causes the AI ​​to generate the explanatory information based on the posted information. The business support system according to claim 1 or 2.

9. The aforementioned business support system further includes a data format receiving unit that accepts the specification of the data format for the explanatory information, The explanatory information providing unit converts the explanatory information based on the data format and provides the converted explanatory information. The business support system according to claim 1 or 2.

10. The explanatory information generation unit causes the AI ​​to generate explanatory information including multiple explanations and the priority of each of the multiple explanations. The explanatory information providing unit provides the explanatory information based on the priority of each of the plurality of explanations. The business support system according to claim 1 or 2.

11. We obtain functional information regarding business support functions that assist in business operations. Based on the aforementioned functional information, the AI ​​(Artificial Intelligence) is made to generate explanatory information regarding the description of the aforementioned business support function. The above explanatory information is provided, Business support methods.

12. Function information acquisition unit that acquires function information related to business support functions that support business operations. Based on the aforementioned functional information, an explanatory information generation unit causes AI (Artificial Intelligence) to generate explanatory information regarding the explanation of the aforementioned business support function. An explanatory information providing unit that provides the aforementioned explanatory information, A program that makes a computer function.

Images