Information processing apparatus, application generation system, program, and application generation method

Abstract

To generate an application by using an external generative AI system.SOLUTION: An information processing apparatus includes: an application generation unit which functions in response to execution of a predefined function, and generates an application related to a request on the basis of a parameter included in the request related to generation of the application; and a control unit which transmits, when receiving sample data for generating the application from a terminal device, data based on the received sample data to a generative AI system. When the control unit receives a request transmitted by the generative AI system on the basis of the data transmitted to the generative AI system, setting information and information for calling the function, the application generation unit generates the application related to the request, on the basis of the parameter included in the received request.SELECTED DRAWING: Figure 10

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an application generation system, a program, and an application generation method.

Background Art

[0002] For application development, an operation called programming (coding) is required in which a developer inputs source code from a keyboard or the like. However, a great deal of time and cost are required to master the grammar of programming languages and efficient programming. Therefore, programming support technologies that reduce or eliminate the input of program code are known.

[0003] A programming method using artificial intelligence (AI) has been devised (see, for example, Patent Document 1). Patent Document 1 discloses a program code database in which text data is acquired from a conversation sentence and one or more program codes are stored in association with the extracted context, a program grammar analysis database, and a program automatic generation knowledge database in which an optimized program is associated with a processing operation to be realized, and a technique for generating one or more programs according to the extracted context.

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in order to generate a program such as an application using an AI system, it is necessary to develop, maintain, or operate the AI system separately from the application.

[0005] Therefore, in view of the above problems, an object of the present invention is to generate an application using an external AI system (such as a generation AI system).

Means for Solving the Problems

[0006] In view of the above problems, the present invention is an information processing apparatus capable of communicating with a terminal device and a generation AI (Artificial Intelligence) system via a network, and is an application generation unit that functions by executing a predefined function. An application generation unit that generates the application related to the request based on the parameters included in the request related to the generation of the application, and when sample data for app generation is received from the terminal device, data based on the received sample data is sent to the generation AI system. A control unit for transmitting, wherein the control unit transmits, at least once, setting information for generating the application and information for calling the function to the generation AI system, and the data transmitted to the generation AI system, the setting information transmitted to the generation AI system, and the information for calling the function transmitted to the generation AI system. When the control unit receives the request transmitted by the generation AI system based on the above, the application generation unit generates the application related to the request based on the parameters included in the received request, which is an information processing apparatus.

Effect of the Invention

[0007] An application can be generated using an external AI system (such as a generation AI system).

Brief Description of the Drawings

[0008]

Figure 1

Figure 2A

Figure 2B

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Mode for Carrying Out the Invention

[0009] Hereinafter, as an example of a mode for carrying out the present invention, an information processing system and an application generation method performed by the information processing system will be described with reference to the drawings.

[0010] <Support for Application Development Using a Generation AI System> Generative AI systems such as ChatGPT (registered trademark) are known. Generative AI systems can execute various natural language processing tasks such as text generation, question answering, text classification, sentiment analysis, information extraction, and text summarization. Also known are generative AI systems such as Copilot (registered trademark) that propose the next code to write during program coding. In this embodiment, a technique for generating an application through a conversation (also called a chat) between a user and a generative AI system will be described. Note that the generative AI system or its function may sometimes be simply referred to as AI (Artificial Intelligence). Here, the external generative AI system only needs to be provided as a system different from the system that provides the service related to the application, and the service related to the application and the generative AI system may be provided by the same provider respectively.

[0011] First, when a user with little expertise develops an app, the following two are said to be barriers. 1. Don't know what kind of app to make. 2. Even if there is an app you want to make, don't know how to make it.

[0012] Regarding barrier 1, it can be easily solved because the generative AI system can come up with ideas. Since generative AI systems generally learn based on a large number of articles on the Internet, they have knowledge of various industries and businesses. Therefore, the generative AI system can provide rich ideas regarding the types of apps.

[0013] Regarding barrier 2, generally, AI including generative AI systems cannot generate applications. Therefore, in this embodiment, by using the function of calling a function (a function called function calling, function call, etc.) provided by the generative AI system and having an information processing system intervene between the user and the generative AI system, barrier 2 is solved. This will be described with reference to FIGS. 1 and 2.

[0014] FIG. 1 is a diagram for explaining the processing until the generation AI system 50 requests the information processing system 20 to execute a function and the information processing system 20 generates an application for the sample data input by the user. Although the information processing system 20 will be described later, the information processing system 20 provides a user interface when the user develops an application using the generation AI system 50. Further, the information processing system 20 converts the sample data transmitted from the user terminal 10 into a request message that calls an API (Application Programming Interface) published by the generation AI system 50 and the application service 40, and transmits it to the generation AI system 50 and the application service 40.

[0015] (1) The user terminal 10 transmits the sample data prepared by the user to the information processing system 20. The sample data is data that serves as a sample for application development. For example, when the user develops an application that handles a table format or a database using the generation AI system 50, a file such as a spreadsheet software may be used.

[0016] (2) When the information processing system 20 receives the sample data input by the user, it transmits the data based on the received sample data to the generation AI system 50 by including it in a request message for receiving the request message provided by the generation AI system via an API. Here, the information processing system 20 also includes the specification of the function in the request message and transmits it. A function is a program interface that performs a determined process with specified arguments and returns a return value as a result. This function is for enabling the generation AI system 50 to request the information processing system 20 to generate or update the application used in the application service 40. By the information processing system 20 including the setting of the specification of this function in the request message and transmitting it to the generation AI system 50, the information processing system 20 can generate or update the application in low-code or no-code in response to the request from the generation AI system 50. Note that the generation AI system 50 requesting the information processing system 20 to call this function is called a function call. Also, as supplementary information, the information processing system 20 can include in the request message the system setting for notifying the generation AI system 50 of what kind of application it is. Although the details of the system setting and the setting of the function specification will be described later, the system setting is the general policy regarding the application to be generated, while the setting of the function specification is the information that the information processing system 20 designates to the generation AI system 50 regarding the specification of the function to be called by the generation AI system 50.

[0017] Note that the information processing system 20 does not have to include system settings and function specification settings in the same request message as the data based on the received sample data. For example, the information processing system 20 may generate and send system settings and function specification settings to the AI system 50 in a request message separate from the request message including the data based on the received sample data. Further, the information processing system 20 may also include the system settings and the function specification settings in separate request messages and send them to the AI system 50.

[0018] Note that the information processing system 20 may send the system settings and the function specification settings each time it sends a request message including the data based on the received sample data, or it may send them only once at the beginning.

[0019] (3) The AI system 50 generates a response message including a function call request based on the data (which may include the conversation history before sending the sample data) based on the sample data included in the sent request message, the function specification settings, and the system settings, and sends it to the information processing system 20. Here, note that the AI system 50 only requests the information processing system 20 to make a function call, and it is the information processing system 20 that actually executes the function. However, the AI system 50 includes in the request message field names corresponding to the types of applications requested by the user (an example of a parameter), etc.

[0020] Note that the AI system 50 does not always have to send a response message including a function call request to the information processing system 20 based on the conversation history, the function specification settings, and the system settings. For example, the AI system 50 may send a response message including a question or a response message indicating that it could not understand the content of the sample data to the information processing system 20.

[0021] (4) The information processing system 20 generates an application in response to a function call included in the response message sent from the generative AI system 50. What kind of application to generate is determined in (2) and (3). More specifically, the information processing system 20 generates a request message for calling the API of the application service 40 from the content of the function call, and sends the generated request message to the application service 40. In this embodiment, the process related to the generation of such a request message may be expressed as "execution of a function" or "execute a function". In the case of this embodiment, the information processing system 20 generates or updates the application of the application service 40 in response to the function call.

[0022] In this way, since the user only needs to input sample data on the user terminal 10 and the information processing system 20 can develop an application using the generative AI system 50, the barrier 2 is also eliminated.

[0023] The application generation support screen in FIG. 2A is an example of an application generation page displayed on the user terminal 10. On the application generation page, there are displayed points for attention 301 in application generation, a space 302 where the application is generated (the space is a URL space or the like), and a message 303 indicating that an application is to be generated from sample data. And below the message 303, an add button 304 for adding sample data is displayed. When the user presses the add button 304, a file list screen is displayed, and the sample data to be sent to the generative AI system 50 can be selected.

[0024] FIG. 2B is an example of a quotation management app screen 260 displayed by the quotation management app generated from the sample data of FIG. 2A. The quotation management app screen 260 has input fields corresponding to the item names of client name 261, client address 262, client contact 263, issue date 264, company name 265, company address 266, company contact 267, person in charge 268, estimated amount 269, subtotal 271, consumption tax 272, total 273, remarks 274. The quotation management app screen 260 also has an input field corresponding to the sub-table 276.

[0025] These item names and the sub-table 276 are automatically generated as described later, either included in the sample data or based on the sample data (even if not included in the sample data). The generation AI system 50 and the information processing system 20 can automatically pick up items from the sample data and set them in the items of the application.

[0026] In this way, the app generation system 100 of the present embodiment enables the information processing system 20 to communicate with the generation AI system 50 and develop an application by the user sending sample data such as a quotation file to the information processing system 20. Since the information processing system 20 designates a function to the generation AI system 50, the generation AI system 50 can request the information processing system 20 for function calls together with field names of the application, etc. Then, the information processing system 20 actually generates or updates the application. As a result, from the user's perspective, by inputting sample data such as a quotation, a no-code or low-code platform for actually developing a quotation management app can be realized.

[0027] <Regarding terms> An application is an abbreviation of an application program and is a program generated by a computer according to any task. While the OS (Operating System) is general-purpose software that provides basic functions and systems (file system, communication, display control, etc.) in the operation of a computer, an application provides specific functions on top of the OS. There are web applications and native applications. In this embodiment, either one can be developed.

[0028] Since the API is an interface of an application (software), it is a contact point for connecting systems to share functions and mechanisms. The API defines the specifications of the interface used for applications to exchange information with each other. The API between computers is the specification for one website to communicate with another website via HTTP (HTTPS) communication. Through communication, one website can use the functions of another website. The API between computers is sometimes referred to as a Web-API.

[0029] When an API sends a specific request (such as data acquisition, update, deletion, processing, etc.), it returns the result for the response (such as data, update result, deletion result, processing result, etc.). The request is sometimes called a request message, and the result is sometimes called a response message. To call an API means to send a request according to the API's specifications and obtain the result. Calling an API is sometimes also referred to as executing, operating, hitting, or using it, etc.

[0030] The information for calling a function is information that enables the function provided by the information processing system 20 to be called from outside the information processing system, for example, from the generation AI system 50. The information for calling a function includes information regarding the Web-API for calling the function.

[0031] Information about the Web-API for calling a function is information for enabling the generative AI system 50 to call (utilize) the Web-API. In the present embodiment, it is described using the term "setting of function specifications" (hereinafter referred to as "function specification setting"). The function specification setting is information that the information processing system 20 specifies to the generative AI system 50 regarding the specifications of the function call that the generative AI system 50 calls. Since the generative AI system 50 calls the function to the information processing system 20 based on the setting of the function specifications, the information processing system 20 can analyze the function.

[0032] A function is a program interface that performs a determined process with specified arguments and returns a return value as a result. While developers can design the specifications and functions of a function, APIs are pre-prepared for functions related to functions that are publicly available for the generative AI system 50 and application service 40 to use. A function is one of the specifications of an API and can be set by calling the API when the API defines the method of specifying the function. Also, calling a function or a function call request means requesting the execution of a function.

[0033] Data based on sample data may be either the sample data itself or data obtained by converting the sample data into another format. The generative AI system 50 generates a request related to the generation of an application using the data based on the sample data as a model. The sample data is data that the generative AI system 50 uses as a model, and the sample data may be called template data, case data, original data, item data, etc.

[0034] A chat service is a service in which multiple users send and receive messages in real time. The generative AI system is a service in which a user sends and receives messages with the AI in real time.

[0035] The setting information is the general policy for the generation of an application. The setting information includes, for example, the content description and hints of the application, or content that should not be asked of the user. The setting information is information that facilitates the generation of a desired application when notified to the generation AI system 50.

[0036] System settings refer to information in which all or part of this setting information is converted into a request message for calling an API. That is, system settings are information in which part or all of the setting information is converted into the format of an API.

[0037] The parameters included in the request related to the generation of an application are variables that affect the behavior of the application. The content of the parameters varies depending on the application. For example, in the case of an application that handles tables or databases, there are field names and data formats of fields. In addition, the number of rows, the number of columns, the size of rows and columns, the font and color when displaying data, the position of fields, etc. may also be parameters.

[0038] The user is an end user who uses the application provided by the application service 40. The user can also develop an application. The developer is a person who makes settings for the information processing system 20 for application development by no-code or low-code programming. The developer sets the setting information described later for the information processing system 20.

[0039] <System configuration example> Referring to FIG. 3, the system configuration of the application generation system 100 according to the present embodiment will be described. FIG. 3 is a diagram showing an example of the system configuration of the application generation system 100. The application generation system 100 shown in FIG. 3 includes an information processing system 20, a user terminal 10, and a developer terminal 60. The information processing system 20 and the user terminal 10, and the information processing system 20 and the developer terminal 60 are communicably connected via networks N1 and N2. Further, the information processing system 20 can communicate with the generation AI system 50 and the application service 40 which is an external system via the network N1. Furthermore, the user terminal 10 and the developer terminal 60 can communicate with the generation AI system 50 and the application service 40 which is an external system via the networks N1 and N2.

[0040] The user terminal 10 and the developer terminal 60 are arranged in facilities such as companies or homes and are connected to the network N2. The network N2 may be a LAN, Wi-Fi (registered trademark), wide area Ethernet (registered trademark), a mobile phone network such as 4G, 5G, 6G, etc. The network N1 is a wide area network such as the Internet or WAN. The user terminal 10 and the developer terminal 60 do not necessarily have to be always connected to the network N2, and may be connected when using the information processing system 20, the generation AI system 50, or the application service 40.

[0041] The generation AI system 50 provides a service that enables users to have conversations with artificial intelligence (AI) in a conversational format. As such a generation AI system 50, a system using large language models (LLMs) is known. A large language model is a natural language processing model trained using a large amount of text data. The generation AI system 50 incorporates a vast amount of text in advance and learns knowledge from it through deep learning, reinforcement learning, etc. By utilizing this knowledge, the generation AI system 50 provides response messages for data based on chat messages and sample data. The generation AI system 50 has an interface for receiving chat messages, sample data, etc. input by the user. The chat messages, sample data, etc. received through this interface are called prompts. Prompts include not only chat messages (natural language) such as instructions and questions but also sample data such as files. Chat messages may be conversational sentences and words composed of natural language spoken by humans. Also, an image can be used as a chat message. The generation AI system 50 that generates text for data based on chat messages and sample data is sometimes referred to as generative AI. In this embodiment, the information processing system 20 generates an application that operates in the application service 40 by using the response message that the generation AI system 50 answers for data based on the sample data input by the user. The application that operates in the application service 40 includes a web application that operates in the application service 40 and a native application installed on the user terminal 10. When the native application installed on the user terminal 10 is executed, it connects to the application service 40 and executes the functions of the application service 40.

[0042] The generation AI system 50 has the following features. 1. The generation AI system 50 advances the conversation in a natural flow. 2. The generation AI system 50 can generate and propose ideas even in fields where the user has no knowledge. 3. The generation AI system 50 can output accurate program code. Therefore, the information processing system 20 can carry on a conversation with the user in a natural flow via the generation AI system 50. Also, the user can obtain the ideas necessary for the app just by instructing the app to be created. Moreover, since the functions called by the generation AI system 50 are accurate (high reproducibility), the information processing system 20 can easily generate the application desired by the user.

[0043] As the generation AI system 50, systems using LLMs such as GPT-3, GPT-4, Transformer, and BERT (all trademarks) are known. As an example, ChatGPT using GPT-3 or GPT-4 can be used in the app generation system 100 of the present embodiment, but systems using other LLMs may also be used.

[0044] The application service 40 is one or more information processing devices that provide applications executed by the user. The applications provided by the application service 40 are, for example, database-type web applications that manage data in tabular form. The user can arbitrarily set the fields of the application and customize it so that data related to their business can be saved, read, or processed. Developing an application in this way means setting fields and the like desired by the user in a pre-prepared database. In the present embodiment, the information processing system 20 includes data based on sample data from the user in a request message and sends it to the generation AI system 50. The information processing system 20 uses the response message from the generation AI system 50 to generate or update an application for the application service 40. That is, the user can develop an application for the application service 40 without writing code by inputting sample data.

[0045] When the domains of the application service 40 and the information processing system 20 are different (for example, when the service providers are different), even for the same user, the accounts in the application service 40 and the information processing system 20 are different.

[0046] On the other hand, the application service 40 and the information processing system 20 may be integrated. That is, the functions of the information processing system 20 may be included in the application service 40, or the functions of the application service 40 may be included in the information processing system 20. Also, the application service 40 and the generative AI system 50 may be integrated. Further, the generative AI system 50 and the information processing system 20 may be integrated. Moreover, the information processing system 20, the application service 40, and the generative AI system 50 may be integrated.

[0047] Examples of the application service 40 include, for example, cloud services, ASP (Application Service Provider), SaaS, etc., and may include various services provided via a network. For example, examples of services include the provision of a database and storage services. The application service 40 may exist on the Internet or on-premises.

[0048] The information processing system 20 transmits data based on the sample data transmitted from the user terminal 10 to the generation AI system 50. The information processing system 20 is configured by one or more information processing devices. Also, the information processing system 20 serves as a server that accepts requests as viewed from the user terminal 10. A server is a computer or software that fulfills the function of providing information and processing results in response to requests from clients. The information processing system 20 provides a user interface to the user terminal 10, generates a request message from the received sample data, and transmits the generated request message to the generation AI system 50. Also, when the information processing system 20 receives an application generation request from the generation AI system 50, it requests the application service 40 to generate an application. As a user, there is no need to connect the user terminal 10 to the generation AI system 50 or to the application service 40.

[0049] Note that, as will be described later, the user may develop an application using the application service 40 as a portal. The information processing system 20 receives a connection request from the user terminal 10 connected to the application service 40 to the generation AI system 50 and communicates with the generation AI system 50. Details of such communication will be described with reference to FIGS. 16 to 18.

[0050] In addition, the information processing system 20 receives the setting of the setting information from the developer terminal 60. The setting of the setting information means setting the knowledge (setting information) necessary for the generation of the application of the application service 40 in the information processing system 20. The setting information is information for the generation AI system 50 to generate the parameters of the application. The setting information may include, for example, what kind of application generation is requested. By the developer setting the setting information in the information processing system 20, the user does not have to include the application parameters or the like in the chat message, or attach the application parameters or the like to the sample data (it is also possible to attach). The information processing system 20 can create an appropriate system setting for the generated application based on the setting information and notify the generated AI system 50 of the created system setting. The system setting is generated from the setting information, and the system setting is part or all of the setting information.

[0051] The setting information is set in the information processing system 20 before the user starts developing the application. However, it is also possible for the information processing system 20 to customize for each customer. For example, when the setting information is "You will talk to customers in the $$ industry from now on" according to the customer's industry, the information processing system 20 changes the name of the $$ industry according to the customer's industry and notifies the generation AI system 50.

[0052] The information processing system 20 uses this setting information to create a request message to be sent to the generation AI system 50. In the request message, the setting information is reflected in the system setting described later. Details will be described later. By the developer sending the setting information to the information processing system 20, the user can generate an application by sending sample data even without specialized knowledge of the application.

[0053] Note that the setting of the setting information is not necessarily required, and there may be cases where the setting information is unnecessary depending on the application.

[0054] The information processing system 20 may be implemented by cloud computing or by a single information processing device. Cloud computing refers to a form in which resources on a network are used without awareness of specific hardware resources. The information processing system 20 may exist on the Internet or on-premises.

[0055] Also, the functions of the information processing system 20 may be distributed among a plurality of information processing devices, or there may be a plurality of information processing systems 20 having the same functions, and the information processing system for distributing videos may be increased or decreased according to the processing load.

[0056] The user terminal 10 or the developer terminal 60 is, for example, a terminal device such as a PC (Personal Computer), a smartphone, or a tablet terminal used by a user or a developer. A web browser or a native app operates on the user terminal 10 or the developer terminal 60. The developer operates the developer terminal 60 to create setting information regarding the application. The user operates the user terminal 10 to prepare sample data for developing the application of the application service 40. The sample data may be an existing form file or the like. Details will be described later. The administrator or the user can operate the developer terminal 60 and the user terminal 10 to use various services provided by the information processing system 20, the generation AI system 50, or the application service 40.

[0057] The user terminal 10 may be any information processing device. Examples of such information processing devices include output devices such as electronic blackboards and digital signage, HUD (Head Up Display) devices, industrial machines, imaging devices, sound collection devices, medical devices, network home appliances, mobile phones, smartphones, tablet terminals, game machines, PDAs (Personal Digital Assistants), digital cameras, wearable PCs, and the like.

[0058] <Hardware Configuration Example> Referring to FIG. 4, the hardware configurations of the information processing system 20, the user terminal 10, and the developer terminal 60 included in the application generation system 100 will be described. Regarding the generation AI system 50 and the application service 40, it is assumed that they have the same hardware configuration as that shown in FIG. 4 or a hardware configuration of an information processing apparatus corresponding to cloud computing.

[0059] <<Information Processing System, User Terminal, and Developer Terminal>> FIG. 4 is a diagram showing an example of the hardware configurations of the information processing system 20, the user terminal 10, and the developer terminal 60 according to the present embodiment. As shown in FIG. 4, the information processing system 20, the user terminal 10, and the developer terminal 60 are constructed by a computer 500, and include a CPU 501, a ROM 502, a RAM 503, an HD (Hard Disk) 504, an HDD (Hard Disk Drive) controller 505, a display 506, an external device connection I / F (Interface) 508, a network I / F 509, a bus line 510, a keyboard 511, a pointing device 512, a DVD-RW (Digital Versatile Disk Rewritable) drive 514, and a media I / F 516.

[0060] Among these, the CPU 501 controls the operation of the entire computer 500. The ROM 502 stores programs used for driving the CPU 501 such as the IPL. The RAM 503 is used as a work area for the CPU 501. The HD 504 stores various data such as programs. The HDD controller 505 controls the reading or writing of various data to / from the HD 504 according to the control of the CPU 501. The display 506 displays various information such as a cursor, menu, window, characters, or images. The external device connection I / F 508 is an interface for connecting various external devices. External devices in this case are, for example, a USB (Universal Serial Bus) memory, a printer, and the like. The network I / F 509 is an interface for performing data communication using the network N2. The bus line 510 is an address bus, a data bus, etc. for electrically connecting each component such as the CPU 501 shown in FIG. 4.

[0061] Also, the keyboard 511 is a type of input means having a plurality of keys used for inputting characters, numerical values, or various instructions. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting a processing target, moving a cursor, and the like. The optical drive 514 controls the reading or writing of various data with respect to the DVD-RW 513 as an example of a removable recording medium. Note that the removable recording medium is not limited to the DVD-RW 513 and may be a DVD-R or the like. The media I / F 516 controls the reading or writing (storage) of data with respect to the recording medium 515 such as a flash memory.

[0062] <Regarding functions> Next, with reference to FIG. 5, the functional configuration of the application generation system 100 will be described. FIG. 5 is a diagram showing an example of the functional configuration of the information processing system 20, the user terminal 10, and the developer terminal 60.

[0063] <<User terminal>> The user terminal 10 includes a communication unit 11, a display control unit 12, an operation reception unit 13, and an inter-browser cooperation unit 14. Each of these functional units is a function or means realized by the CPU 501 shown in FIG. 4 executing instructions included in one or more programs installed in the user terminal 10. For example, the communication unit 11, the display control unit 12, the operation reception unit 13, and the inter-browser cooperation unit 14 may be realized by at least one of a web browser and JavaScript (registered trademark, hereinafter omitted). When the developer terminal 60 executes a native app, these may be realized by the native app.

[0064] The communication unit 11 transmits and receives various types of information to and from the information processing system 20. In the present embodiment, the communication unit 11 receives screen information of the portal screen from the application service 40, or receives screen information such as a screen of an app generation page where a chat message is input from the information processing system 20. The communication unit 11 transmits a chat message, operation information for the user terminal 10, and the like to the information processing system 20. Note that the communication unit 11 can also communicate directly with the generation AI system 50.

[0065] The display control unit 12 interprets the screen information of various screens and displays it on the display 506. The operation reception unit 13 receives various operations of the user on various screens displayed on the display 506.

[0066] The browser cooperation unit 14 transmits and receives information between Web browsers. One user terminal 10 can execute a plurality of Web browsers simultaneously. The browser cooperation unit 14 can notify information from one of the plurality of Web browsers to the other Web browser (and vice versa). When only one Web browser holds authentication information about a specific Web site (for example, the application service 40) by the browser cooperation unit 14, the other Web browser can communicate with the specific Web site in cooperation with the one Web browser. Assume that one Web browser communicates with the application service 40 and the other Web browser is a Web browser that communicates with the generation AI system 50 generated via the information processing system 20. The other Web browser can transmit a response message from the generation AI system 50 to the one Web browser. The function of the browser cooperation unit 14 is executed by the Web browser (user terminal 10), but is described in JavaScript that realizes the browser cooperation unit 14 in the screen information transmitted from the application service 40 and the information processing system 20.

[0067] <<Developer Terminal>> The developer terminal 60 includes a communication unit 61, a display control unit 62, and an operation reception unit 63. Each of these functional units is a function or means realized by the CPU 501 shown in FIG. 4 executing instructions included in one or more programs installed in the developer terminal 60. For example, the communication unit 61, the display control unit 62, and the operation reception unit 63 may be realized by at least one of a Web browser or JavaScript. When the developer terminal 60 executes a native application, these may be realized by the native application.

[0068] The communication unit 61 transmits and receives various types of information to and from the information processing system 20. In the present embodiment, the communication unit 61 receives screen information regarding the input of setting information from the information processing system 20. The communication unit 61 transmits setting information, operation information for the developer terminal 60, and the like to the information processing system 20. Note that the communication unit 21 can also communicate with the generation AI system 50 and the application service 40.

[0069] The display control unit 62 interprets the screen information of various screens and displays it on the display 506. The operation reception unit 63 receives various operations of the user on the various screens displayed on the display 506.

[0070] <<Information Processing System>> The information processing system 20 includes a communication unit 21, a screen generation unit 22, a control unit 23, a setting information storage unit 24, a data generation unit 28, and an application generation unit 25. Each functional unit included in the information processing system 20 is a function or means realized by the CPU 501 shown in FIG. 4 executing instructions included in one or more programs installed in the information processing system 20. Further, the setting information storage unit 24 is constructed in the HD 504, RAM 503, etc. shown in FIG. 4. The setting information storage unit 24 may not be included in the information processing system 20, and it may be on a network accessible by the information processing system 20.

[0071] The communication unit 21 transmits and receives various information to and from the user terminal 10. The communication unit 21 transmits the screen information of the application generation page to the user terminal 10. The communication unit 21 receives the chat messages and sample data input by the user for application development from the user terminal 10. Further, the communication unit 21 transmits and receives various information to and from the developer terminal 60. The communication unit 11 transmits the screen information of the setting information input screen to the developer terminal 60. The communication unit 11 receives the setting information input by the developer from the developer terminal 60 and stores it in the setting information storage unit 24.

[0072] The screen generation unit 22 generates screen information of the screens (Web pages) displayed on the user terminal 10 and the developer terminal 60. The Web page is provided as part of a Web application. The screen information is a program described in HTML, JSON, XML, a scripting language, CSS (Cascading Style Sheet), etc. The structure of the Web page is specified mainly by HTML, the operation of the Web page is defined by the scripting language, and the style of the Web page is specified by CSS. The user terminal 10 may also execute a native app. A native app is an application that cannot be executed unless it is installed on the user terminal 10. In the case of a native app, the screen information is held by the user terminal 10, and the information to be displayed is transmitted in JSON, XML, etc.

[0073] The data generation unit 28 generates data (data based on the sample data) obtained by converting the sample data received by the communication unit 21 into a predetermined format. The data generation unit 28 passes the converted data to the control unit 23. Note that when the data based on the sample data received by the communication unit 21 is the same as the sample data (when conversion is not necessary), the data generation unit 28 does not perform the conversion.

[0074] The control unit 23 sends a request message to the generation AI system 50 by calling the first API 26. The request message includes sample data information and function specification settings. The sample data information includes data based on the sample data generated by the data generation unit 28. Further, the control unit 23 can also send a request message including a chat message (including the history of past conversations) input by the user before or after sending the sample data information or together with the sample data information to the generation AI system 50.

[0075] The first API 26 is one or more APIs published by the generative AI system 50. As a result of calling the first API 26, the control unit 23 receives a response message from the generative AI system 50 for the request message. The response message includes a response message for the chat message, a function call request for the information processing system 20, or a URL of the generated or developed application, etc.

[0076] The application generation unit 25 sends a request message to the application service 40 by calling the second API 27. The application generation unit 25 functions by executing predefined functions. The request message includes parameters related to the application (database field names, data formats, etc.). The request message for the application service 40 is for requesting the generation or update of an application. The second API 27 is one or more APIs published by the application service 40. As a result of calling the second API 27, the application generation unit 25 receives a response message from the application service 40 for the request message. The response message includes the result (success or failure) of the request for the generation or update of the application. In the case of success, the URL of the application is notified, and in the case of failure, an error message is notified.

[0077] Note that the application generation unit 25 may generate an application within the information processing system 20 without requesting the application service 40. For example, the application generation unit 25 may generate a macro that operates on spreadsheet software or set fields in database software.

[0078] Here, "generating an application" not only means that the application generation unit 25 actually generates an application, but also includes the case where the application generation unit 25 requests the application service 40 or the like to generate an application, and the application service 40 or the like actually generates an application.

[0079] <Supplement regarding the operation of the generation AI system> In the present embodiment, the information processing system 20 uses the generation AI system 50 by calling the first API 26 published by the generation AI system 50. By the information processing system 20 calling the first API 26, a conversation with the AI, which is one of the functions of the generation AI system 50, becomes possible. Since the generation AI system 50 has characteristic operations or processes, they are supplemented.

[0080] The information processing system 20 communicates with the generation AI system 50 by sending a request message for calling the API to the generation AI system 50. With the request message, the information processing system 20 can obtain a response message from the generation AI system 50.

[0081] The generation AI system 50 returns a response message to the request message to the information processing system 20. The response messages included in the response message of the generation AI system 50 are often different each time even for the same chat message. However, if the information processing system 20 designates a parameter called temperature to 0, the generation AI system 50 returns the same response message for the same chat message.

[0082] When the information processing system 20 wants to continue the conversation with the generation AI system 50, it is necessary to include all the past conversation histories in the request message. This is because the conversation with the generation AI system 50 is stateless. This is the specification of a certain generation AI system 50, and in another generation AI system 50, it may not be necessary to include the past conversation history.

[0083] Thus, the first API 26 has no state regarding past communications (stateless). Therefore, the history of past conversations must be held by the user of the first API 26 (in this embodiment, the information processing system 20) and specified each time the first API 26 is called. The history of past conversations may be held by the user terminal 10. Also, since the first API 26 returns an error if the conversation history becomes too long, it is preferable for the information processing system 20 to devise appropriate measures, such as including only the most recent exchanges in the request message when the conversation has continued for a long time.

[0084] <<function call returned by the generative AI system>> Among the functions provided by the generative AI system 50 is a function called function call. Function call means that the generative AI system 50 requests the information processing system 20 to make a call to a function. Therefore, if the information processing system 20 allows the generative AI system 50 to use this function, the generative AI system 50 can call a "function".

[0085] To enable the generative AI system 50 to call a "function", the request message includes function specification settings configured by the information processing system 20. The function specification settings enable the generative AI system 50 to make a function call (function call request). Thus, the function specification settings are information regarding the first API 26 for calling the application generation unit 25. That is, the function specification settings notify the generative AI system 50 that the information processing system 20 can request the generative AI system 50 to make a function call.

[0086] In this way, by having the information processing system 20 allow the generative AI system 50 to use function call, the generative AI system 50 can call the functions provided by the information processing system 20, and the information processing system 20 can execute the functions. Also, the information processing system 20 can use the execution results of the functions to converse with the user.

[0087] However, since the response message of the generative AI system 50 is different each time, the generative AI system 50 does not necessarily request a function call. Even if the information processing system 20 includes a function specification setting in the request message, the generative AI system 50 may return the same response message as in the case where there is no function specification setting.

[0088] If the process of including all the past conversation histories in the request message is adopted, the information processing system 20 also needs to include the execution result of the executed function in the request message and send it to the generative AI system 50. However, it is not essential for the information processing system 20 to include the execution result of the function in the request message together with the past conversation histories and send it to the generative AI system 50. That is, the information processing system 20 may directly send the execution result of the function to the user terminal 10. However, by the information processing system 20 sending the execution result of the function to the generative AI system 50, the generative AI system 50 can continue the conversation using the past conversation histories, so continuity is generated in the conversation. For example, consistency is generated in the writing style and diction, making it less likely for the user to feel uncomfortable. For example, even if the user's native language is English and they are having a conversation in English, the information processing system 20 does not need to translate the response message into English.

[0089] Also, the information processing system 20 cannot predict whether the generative AI system 50 will request a function call. However, if the information processing system 20 explicitly specifies the "function_call option" in the request message, it can force the generative AI system 50 to make a function call.

[0090] <Support for Application Development of Application Services> In this embodiment, taking the case where the user develops an estimate management application as an example, the request message sent by the information processing system 20 and the response message sent by the generative AI system 50 will be described.

[0091] FIG. 6 is a diagram showing an example of a request message for the information processing system to call the API of the generation AI system when the user operates the user terminal 10 to send sample data to the information processing system. The request message in FIG. 6 first includes a system setting 229 by the system. The system setting 229 is information 229a that says "You will be assisted in app development within a SaaS service called the ○○ application service from now on. You will be asked to interact with the user to determine the 'field' of the application. The definition of the field will be expressed in JSON format. For example, an app with the following three fields can be considered." Also, the system setting 229 includes information 229b indicating fields named "Date", "Business Content", and "Thoughts, Learnings". Each field is also instructed with a data format such as DATE, MULTI_LINE_TEXT, and MULTI_LINE_TEXT. These pieces of information 229a and 229b are based on the setting information previously sent by the developer to the information processing system 20.

[0092] The information 229a includes a role 230a and content 230b. The role 230a indicates the speaker, and there are user (the user), assistant (the AI of the generation AI system 50), and system (indicating the settings of the AI assistant). The content 230b is the content of the speech and may be described in natural language.

[0093] Also, the request message includes sample data information 231 sent from the user terminal 10. The sample data information 231 has a message 231a that says "The following is the data obtained by converting the form file to JSON. Please create an app from this information." The message 231a was generated by the control unit 23 based on a request to generate an application specifying the sample data from the user terminal 10.

[0094] The sample data transmitted from the user terminal 10 to the generation AI system 50 is often in file format. Therefore, when the generation AI system 50 does not support sample data in file format, the data generation unit 28 converts the data included in the file into a format (format) that the generation AI system 50 supports. In FIG. 6, each item of the sample data (for example, a form file) transmitted from the user terminal 10 is converted into data 231b in JSON format. The data 231b corresponds to "data based on the sample data". The data 231b transmitted to the generation AI system 50 may be in XML format, CSV (Comma Separated Values) format, text format, or the like. Also, when the generation AI system 50 supports file format, the data 231b transmitted to the generation AI system 50 may remain in file format. The file format may be Excel (registered trademark), WORD, PowerPoint (registered trademark), PDF, or the like, as long as the generation AI system 50 supports it.

[0095] Note that in this embodiment, for convenience of explanation, the sample data transmitted from the user terminal 10 and the sample data information 231 (the data format may be converted) transmitted to the generation AI system 50 may both be referred to as "sample data" without distinction.

[0096] Also, the request message in FIG. 6 includes a function specification setting 233. functions is the function specification setting 233, and the function specification setting 233 has the following attributes. name234 is the name of the function (create_or_update_app). description235 indicates the specification of the function. The details of the specification are "Creates an app. Returns {\"ok\": true, \"value\": \"URL of the app\"} on success and {\"ok\": false, \"error\":...} on failure." That is, description235 instructs the generation AI system 50 to return a URL or an error message. parameters236 is also part of the function specification. "type": "object" indicates the data format of the return value. "required": ["properties", "name"] indicates the item names required for the return value. "name": { "type": "string"} indicates the data format of name. "type": "array" indicates that it is in tabular form. Below "items" indicates the attributes and data formats required for the fields.

[0097] The information processing system 20 instructed the generation AI system 50 that, based on this function specification setting 233, the generation AI system 50 can request the information processing system 20 to make a call to the function defined as shown in FIG. 6.

[0098] FIG. 7 is an example of a response message of the generation AI system 50 to the request message of FIG. 6. The response message includes a function call request 237 (function call). In this embodiment, when a function call is included in the response message, the information processing system 20 generates an application of the application service 40. The application service 40 is a low-code or no-code platform. The application of the application service 40 is a database that manages user data, and the user can easily customize the UI screen for displaying the data. The application service 40 exposes various APIs, and the information processing system 20 can generate and update an application by calling the second API 27. In this embodiment, by the information processing system 20 calling the second API 27 exposed by the application service 40 and the first API 26 exposed by the generation AI system 50, it is possible for the information processing system 20 to generate or update an application of the application service 40.

[0099] The function call request 237 of the response message corresponds to an application generation request. The function call request 237 includes a name 238 and arguments 239. The name 238 is the name of the function defined in the function specification setting 233. The generation AI system 50 requests the call of the function with this name. The arguments 239 are return values and are defined in the function specification setting 233. In FIG. 7, the application name 239a of "estimate", the field names 239b, 239c included in the estimate management application, and their identification information (Content of the item named code), data format (TEXT or MULTI_LINE_TEXT of the item named type), etc. are included in the return value 239.

[0100] For example, the application name 239a and the field names 239b, 239c may or may not be included in the sample data information 231, which are the application name and field names determined by the generation AI system 50 based on the sample data information 231. When not included, it is presumed that the generation AI system 50 generated them from system settings, function specification settings, and other learned information.

[0101] Through this function call, the generation AI system 50 can request the information processing system 20 to call a function that specifies field names such as business content and generates an application.

[0102] The information processing system 20 analyzes the function call included in the response message and determines to generate and update the application of the application service 40 (execution of the function). For this reason, the information processing system 20 calls the second API 27 published by the application service 40, and uses the field names and data formats (an example of parameters) included in the response message to generate or update the application. When the generation or update of the application is successful, the information processing system 20 obtains the URL of the application from the application service 40. The URL is access information for the user terminal 10 to access the application. The information processing system 20 returns the URL of the application to the generation AI system 50. By doing so, continuity is created in the conversation between the user and the generation AI system 50.

[0103] Specifically, an example of the information processing system 20 using three APIs of the application service 40 is conceivable as follows. 1. API for generating an application published by the application service 40 2. API for adding two fields, "date" and "business content", to the application generated in 1 3. API for publishing the application When the generation or update of the application is successful, the information processing system 20 calls the first API 26 published by the generation AI system 50 again by specifying the result of the function (the URL of the application).

[0104] FIG. 8 is an example of a request message that the information processing system 20 sends to the generation AI system 50 after generating or updating an application for the application service 40. This request message includes the system settings 229, sample data information 231, and function call request 241 as the history of past conversations. In addition, the information processing system 20 adds the function execution result 243 to the history of past conversations. The function execution result 243 in FIG. 8 includes the fact that the function was executed 243a, the name of the executed function 243b (create_or_update_app), and the URL 243c. Note that FIG. 8 includes the function specification settings 233 again, which is also the history of past conversations. Although FIG. 8 includes the function specification settings 233 as the history of past conversations, it may not be included depending on the specifications of the API provided by the generation AI system 50.

[0105] Note that in FIG. 8, in addition to the URL 243c, the history of past conversations (system settings 229, sample data information 231, function call request 241, the fact that the function was executed 243a, the name of the function 243b) is included. However, if the generation AI system 50 has a function to hold the history of past conversations, the information processing system 20 may send only the URL 243c to the generation AI system 50. That is, there may be cases where the content of the history of past conversations may have been sent by the information processing system 20 to the generation AI system 50 at least once in the past.

[0106] FIG. 9 is an example of a response message from the generation AI system 50 to the request message in FIG. 8. Note that in the case of application development, the response message often varies each time. For example, it is expected that a response message like the one in FIG. 9 will be returned. The response message in FIG. 9 includes a response message 245 that says "The application has been created. Please check from \"https: / / sample.com / k / 42 / \"". Since the information processing system 20 sends this URL to the user terminal 10, the user can check the field names of the developed application (database) by pressing the URL.

[0107] Thereafter, until the user is satisfied, the input of chat messages (e.g., modification instructions for the application) and the transmission and reception of request messages and response messages between the information processing system 20 and the generative AI system 50 are repeated. In this way, by the user sending sample data or having conversations, the application of the application service 40 can be developed, and thus the user does not need any programming knowledge at all.

[0108] <Operation or Process> FIG. 10 is an example of a sequence diagram for explaining the process in which the information processing system 20 supports application development. As a major flow, steps S3 to S14 are repeatedly executed, and among them, steps S9 to S14 are repeatedly executed.

[0109] S1: The communication unit 11 of the user terminal 10 connects to the URL of the information processing system 20. This URL may be specified on the user terminal 10 by a method directly input by the user or by executing a shortcut for which the URL is specified. The communication unit 11 of the user terminal 10 generates an HTTP request including the URL of the application generation page and transmits the generated HTTP request to the information processing system 20.

[0110] S2: When the communication unit 21 of the information processing system 20 receives the above HTTP request from the user terminal 10, the screen generation unit 22 creates the screen information of the application generation page. The communication unit 21 transmits an HTTP response including the screen information of the application generation page to the user terminal 10 as a response to the above HTTP request. An example of the application generation page is shown in FIGS. 12(a) and (b).

[0111] S3: The user operates the user terminal 10 to select sample data (such as a document file like an estimate). This sample data (see FIG. 11) may have items to be input into the application to be generated hereafter. The input may be made using a keyboard or voice input. The operation reception unit 13 receives the designation of the sample data. The communication unit 11 of the user terminal 10 generates a request message including the sample data, and transmits the generated request message to the information processing system 20. The communication unit 11 of the user terminal 10 transmits the generated request message as, for example, an HTTP request. Note that the communication unit 11 of the user terminal 10 may generate a request message including the history of past conversations. Also, the information processing system 20 may hold the history of past conversations. When the information processing system 20 holds the history of past conversations, the communication unit 11 of the user terminal 10 does not have to include the history of past conversations in the request message.

[0112] S4: The communication unit 21 of the information processing system 20 receives the sample data. The communication unit 21 of the information processing system 20 passes the sample data information 231 to the data generation unit 28 and the control unit 23. The data generation unit 28 converts the sample data into data 231b based on the sample data and passes it to the control unit 23. The control unit 23 generates a request message including system settings (setting information), sample data information 231 (data 231b based on the sample data in the figure), and function specification settings, and transmits the generated request message to the generation AI system 50 by calling the first API 26 (see FIG. 6). In the present embodiment, the sample data information 231 transmitted in step S4 includes data 231b based on the sample data converted into a format corresponding to the generation AI system 50. However, the sample data information 231 transmitted in step S4 may remain in the file format in some cases.

[0113] S5: The generation AI system 50 returns a response message including a response message or a function call request to the information processing system 20 (see FIG. 7). The control unit 23 receives the response message from the generation AI system 50. This response message may be a response message or a function call request. In the case of a function call request, the process proceeds to step S7, and in the case of a response message, the process proceeds to step S6.

[0114] S6: When the control unit 23 receives a normal response message, the communication unit 21 of the information processing system 20 transmits the response message to the user terminal 10. For example, when the response message is "Please tell me the details".

[0115] S7: When the control unit 23 receives a function call request, it analyzes this function and determines that a request (application generation request) for generation or update of an application of the application service 40 has been made. Since a function for application generation is specified in the function specification setting 233 in step S4, based on the name (name238) of the function included in the function call request, the control unit 23 can easily determine that it is an application generation request. Also, the control unit 23 acquires arguments239 (application name 239a, field names 239b, 239c, data format, etc.) included in the function call request.

[0116] Therefore, the control unit 23 requests the application generation unit 25 of the application service 40 to generate or update an application. The application generation unit 25 calls the second API 27 to send a request message for generating or updating an app to the application service 40. That is, the application generation unit 25 realizes the function of the function called from the generation AI system 50 by sending a request message. In this embodiment, the application generation unit 25 generates or updates an application. The application generation unit 25 calls the above three APIs. 1. API for generating an application published by the application service 40 2. API for adding a plurality of fields such as "date" and "business content" to the application generated in 1 3. API for publishing an application In "2.", the application generation unit 25 includes, in the request message, arguments239 (application name 239a, field names 239b, 239c, data format, etc.), which are parameters included in the response message from the generation AI system 50, and requests the generation of an application. The specific request message may vary depending on the application service 40.

[0117] Note that the information processing system 20 updates the existing application when the second function call request is made. Therefore, not only can an application be generated but also updated.

[0118] S8: The application generation unit 25 receives a response message from the application service 40. The result included in this response message is, for example, the "URL of the application". Also, when the generation of the application fails, an error message is returned from the application service 40. If successful, the process proceeds to step S9, and if failed, the process proceeds to step S13.

[0119] S9: When the application generation is successful, the control unit 23 calls the first API 26 to send a request message including the URL of the application to the generation AI system 50 (see Figure 8). By doing so, continuity is created in the conversation between the user and the generation AI system 50.

[0120] S10: The generation AI system 50 returns a response message including a response message to the information processing system 20. The control unit 23 receives the response message from the generation AI system 50 (see Figure 9). This response message includes the URL of the application.

[0121] S11: If the app generation is successful, the communication unit 21 of the information processing system 20 transmits the response message included in the response message of step S10 to the user terminal 10. The process of FIG. 10 ends once, and after that, the user returns to step S3 as necessary to update the application. In this case, the user specifies different sample data or instructs the modification of the application via a chat message.

[0122] S12: If the app generation fails and fails a certain number of times or more, the communication unit 21 of the information processing system 20 transmits a result such as "The creation / updating of the app has failed" to the user terminal 10. The process of FIG. 10 ends once, and after that, the user returns to step S3 as necessary to generate the application again. In this case, the user specifies different sample data.

[0123] S13: If the response message in step S8 notifies of the failure of app generation, the control unit 23 calls the first API 26 to transmit an error message from the application service 40 to the generation AI system 50. In addition to the error message, the sample data information 231 is also transmitted. By doing so, the generation AI system 50 can create a function call request that does not result in an error message. For example, if the request message sent by the application generation unit 25 to the application service 40 violates the specification of the second API 27 published by the application service 40, the correct specification content may be included in the error message. The generation AI system 50 can understand the specification and approach a function call request that does not result in an error message. For example, if the error message points out character types that cannot be used in the application service 40, the error message includes the unusable character types, so that the generation AI system 50 can create a function call request that does not include the character types. This is the same not only for character types but also for the format of the request message.

[0124] S14: The control unit 23 receives a response message from the generation AI system 50. The response message is a function call request or a response message. However, since the control unit 23 has sent an error message, it is expected that a function call request for successfully generating an application is included in the response message. In the case of a function call request, the process proceeds to step S7, and in the case of a response message, the process proceeds to step S6.

[0125] <Example of the screen displayed on the user terminal, etc.> Figure 11 shows an example of sample data that the user inputs to the generation AI system 50. Note that the user only needs to select sample data in file format, and there is no need to display the content of the file on the user terminal 10. The sample data in Figure 11 is a quotation in the form of a document. This sample data has a client name 281, an address 282, a person in charge name 283, and a quoted amount 289. Also, the sample data has column headings 295 (No, item, quantity, unit, unit price, amount). The number of records is 3. Further, the sample data has a quoting company 285, a quotation issue date 284, a quoting company address 286, a quoting company contact 287, and a quoting company person in charge 288. Also, the sample data has items such as subtotal 291, consumption tax 292, total 293, and remarks 294.

[0126] In this embodiment, a document file is used as an example for explanation, but the sample data only needs to be appropriate for the application generated by the application service 40. For example, if the generated application is a business card management application, the sample data is business card data, and if the generated application is an expense management application, the sample data is a receipt or the like. Also, if the generated application is a personnel management application, the sample data is personal data, and if the generated application is a questionnaire management application, the sample data is questionnaire data.

[0127] Figure 12 shows an example of an app generation page displayed by the user terminal 10. In the description of Figure 12(a), the differences from Figure 2A will mainly be explained. When the user presses the add button 304, a file list screen is displayed, and the user can select sample data to be sent to the generation AI system 50. The user terminal 10 sends the sample data in Figure 11 to the information processing system 20, and the information processing system 20 sends a request message to the generation AI system 50, including the sample data information 231 and the specification of the function. As a result, the generation AI system 50 sends a function call request to the information processing system 20, and the information processing system 20 can generate an application for the application service 40 (execution of the function).

[0128] Figure 12(b) is a screen for app generation support displayed by the user terminal 10 in response to a response message indicating that the information processing system 20 has generated an application. That is, Figure 12(b) is a transition from Figure 12(a). On the app generation support screen in Figure 12(b), a response message 305 saying "The app has been created / updated" and the URL 306 of the app generation destination are displayed.

[0129] When the user presses the URL 306 with a mouse pointer or the like, the generated or updated application can be used. Therefore, the user can develop a quotation management app without knowledge of programming or even knowledge of the quotation management app.

[0130] FIG. 13 is an example of a quotation management app screen 260 displayed when the URL of the app generation destination is pressed. For the sake of explanation, the corresponding description of the quotation in FIG. 11 is shown on the quotation management app screen 260, but this description is not actually displayed. The quotation management app screen 260 has columns for client name 261, client address 262, client contact 263, issue date 264, company name 265, company address 266, company contact 267, person in charge 268, estimated amount 269, subtotal 271, consumption tax 272, total 273, and remarks 274. The quotation management app screen 260 also has a column heading list 275. · It is presumed that the client name 261 is generated based on the client name 281 of the quotation in FIG. 11. · It is presumed that the client address 262 is generated based on the address 282 of the quotation in FIG. 11. · It is presumed that the client contact 263 is independently generated by the generation AI system 50. · It is presumed that the issue date 264 is generated based on the quotation issue date 284 of the quotation in FIG. 11. · It is presumed that the company name 265 is generated based on the quotation issuing company 285 of the quotation in FIG. 11. · It is presumed that the company address 266 is generated based on the quotation issuing company address 286 of the quotation in FIG. 11. · It is presumed that the company contact 267 is generated based on the quotation issuing company contact 287 of the quotation in FIG. 11. · It is presumed that the person in charge 268 is generated based on the quotation issuing company person in charge 288 of the quotation in FIG. 11. · It is presumed that the estimated amount 269 is generated based on the estimated amount 289 of the quotation in FIG. 11. · It is presumed that the subtotal 271 is generated based on the subtotal 291 of the quotation in FIG. 11. · It is presumed that the consumption tax 272 is generated based on the consumption tax 292 of the quotation in FIG. 11. · It is presumed that the total 273 is generated based on the total 293 of the quotation in FIG. 11. · It is presumed that the remarks 274 are generated based on the remarks 294 of the quotation in FIG. 11. ·The column heading list 275 is presumed to be generated based on the column headings 295 of the estimate in FIG. 11.

[0131] These are fields generated by the user terminal 10 sending sample data to the information processing system 20. Therefore, the user was able to develop an estimate management application without listing any field names at all.

[0132] <<Modification of the Generated Application>> Next, it is a diagram for explaining a display example of an application generation page displayed by the user terminal 10 when the user modifies the generated application. For example, a user who has confirmed the estimate management application can add or delete fields by conversing with the generation AI system 50.

[0133] FIG. 14 is a display example of an application generation page in which the user has added a chat message 307 to the application generation page in FIG. 12(b). In FIG. 14, the chat message 307 "Can 'No', items, and quantity be made into a sub-table? Also, I want it placed before 'Estimated Amount'" is input.

[0134] The user terminal 10 sends this chat message 307 to the information processing system 20, and the information processing system 20 generates a request message including the chat message 307, sample data information 231 which is the history of past conversations, and the specification of the function, and sends it to the generation AI system 50. As a result, the generation AI system 50 sends a function call request to the information processing system 20, and the information processing system 20 can generate an application for the application service 40 (execution of the function).

[0135] In FIG. 14, the URL 309 of the updated application is displayed. By the user pressing the URL 309 with a mouse pointer or the like, the updated application can be used.

[0136] FIG. 15 is an example of an estimate management app screen 280 displayed by the estimate management app when the URL 309 of the updated application is pressed. In the description of FIG. 15, the differences from FIG. 13 will mainly be described. Since the user requested the information processing system 20 to modify the estimate management app in the chat message 307, the estimate management app screen 280 in FIG. 15 has a sub-table 276. The sub-table 276 is presumed to be generated from the estimate column headings 295 in FIG. 11, but is generated in a tabular format separately from other items as desired by the user. In this way, after the user creates an estimate management app with sample data, the user can modify the estimate management app in natural language (chat message).

[0137] <Supplement regarding authentication for the information processing system to use the second API published by the application service> In order for the information processing system 20 to call the second API 27, it is necessary for the information processing system 20 to receive authentication from the application service 40. When the information processing system 20 in the sequence diagram of FIG. 10 operates in the same domain as the application service 40, the authentication information of the application service 40 is sent from the web browser operating on the user terminal 10 to the information processing system 20. The authentication information is, for example, included in a cookie in advance. For this reason, it is possible for the information processing system 20 to call the second API 27 published by the application service 40. When the low-code or no-code platform (application service 40) and the information processing system 20 are developed by the same organization, it is considered easy to set them in the same domain, and in this case, there is no problem.

[0138] However, when the information processing system 20 and the application service 40 operate in different domains, problems regarding authentication may occur. This will be described with reference to FIG. 16. FIG. 16 is an example of a portal screen 330 of the application service 40 displayed on the user terminal 10. The user can use or develop an application from the portal screen 330.

[0139] For example, assume that the configuration of the portal screen 330 of the application service 40 is as follows. A "Create AI App" button 331 is displayed on the portal screen 330. When the user presses the "Create AI App" button 331, it is assumed that another web page 332 that communicates with the information processing system 20 is opened in a pop-up. In this case, since the application service 40 and the information processing system 20 are in different domains, the user terminal 10 cannot send the authentication information of the application service 40 to the information processing system 20. Therefore, the information processing system 20 cannot call the second API 27 published by the application service 40. This is because the other web page 332 displayed in the pop-up has a different domain from the portal screen 330, so the other web page 332 displayed in the pop-up cannot access the cookie of the application service 40.

[0140] Therefore, a configuration can be considered in which a request to call the second API 27 published by the application service 40 is made from the other web page 332 displayed in the pop-up to the original portal screen 330.

[0141] FIG. 17 and FIG. 18 are examples of sequence diagrams in which the information processing system 20 generates or updates an application of the application service 40 by utilizing the cooperation of two web browsers in the user terminal 10. In the description of FIGS. 17 and 18, the differences from FIG. 10 may be mainly described. As a major flow, steps S36 to S49 are repeatedly executed.

[0142] S21: The user instructs the user terminal 10 to enter the URL of the application service 40. The web browser for connecting to the application service 40 is set as the original web browser 240 (an example of the first web browser).

[0143] S22: The communication unit 11 of the user terminal 10 connects to the URL of the application service 40. Since the user instructs the user terminal 10 with the URL of the portal screen 330, the web browser of the user terminal 10 sends an HTTP request including the URL of the portal screen 330 to the application service 40.

[0144] S23: When the application service 40 receives the above HTTP request from the user terminal 10, it sends the screen information (HTML, JavaScript, CSS, etc.) of the portal screen 330 to the user terminal 10. This screen information includes a script for launching another web browser 250 (an example of a second web browser), and the URL of another web page 332 (application generation page), etc.

[0145] S24: The communication unit 11 of the user terminal 10 receives the screen information of the portal screen 330, and the display control unit 12 of the original web browser 240 displays the portal screen 330.

[0146] S25: The user presses the "AI App Creation" button 331 on the portal screen 330.

[0147] S26: As a result, the browser cooperation unit 14 launches another web browser 250. Another web browser 250 is displayed as a pop-up. More specifically, the launching of another web browser 250 is performed by the JavaScript included in the screen information of the portal screen 330.

[0148] S27: Another web browser 250 requests another web page 332 (application generation page) from the information processing system 20 using the URL of another web page 332 (application generation page) notified from the original web browser 240.

[0149] S28: The screen generation unit 22 of the information processing system 20 generates screen information (HTML, JavaScript, CSS, etc.) of the app generation page, and the communication unit 21 transmits the screen information of the app generation page to another web browser 250 (user terminal 10).

[0150] S29: The communication unit 11 of the user terminal 10 receives the screen information of the app generation page. The display control unit 12 displays the app generation page based on the screen information.

[0151] S30: The user operates the user terminal 10 to select sample data such as a form file.

[0152] The flow after the user terminal 10 displays the app generation page is the same as that in FIG. 10. Therefore, in FIGS. 17 and 18, mainly the differences from FIG. 10 will be described. First, steps S31 to S34 may be the same as steps S3 to S6 in FIG. 10.

[0153] S35: When another web browser 250 receives a response message (in this case, a response message) from the generation AI system 50 in step S34, the display control unit 12 of another web browser 250 displays the response message (for example, Please provide details).

[0154] S36: When another web browser 250 receives a response message (in this case, a function call request) from the generation AI system 50 in step S34, the inter-browser cooperation unit 14 of another web browser 250 requests the original web browser 240 to generate or update the application of the application service 40. Such inter-browser cooperation (message communication) includes https: / / developer.mozilla.org / ja / docs / web-API / Window / postMessage is known.

[0155] S37: The original web browser 240 performs generation or update of the application of the application service 40 for the application service 40.

[0156] S38: The application service 40 transmits the result (success or failure) regarding the generation or update of the application to the original web browser 240. In the case of success, the URL of the application is notified. In the case of failure, an error message is notified.

[0157] S39: The browser inter - working unit 14 of the original web browser 240 transmits the result regarding the generation or update of the application to another web browser 250. After that, if the result is successful, the process proceeds to step S40, and if the result is a failure, the process proceeds to step S46.

[0158] S40: The browser inter - working unit 14 of another web browser 250 receives the result of success (the URL of the app), and the communication unit 11 of another web browser 250 transmits the result (success) regarding the generation or update of the application to the information processing system 20. Therefore, in the flow of FIG. 18, the information processing system 20 receives the result from the user terminal 10 (another web browser 250) instead of the application service 40. The processing of steps S41 - S43 hereafter is the same as steps S9 - S11 of FIG. 10.

[0159] S44: The communication unit 11 of another web browser 250 receives a response message. The display control unit 12 causes the response message to be displayed on the app generation page. The processing of FIG. 18 ends once at step S44, and after that, the user returns to step S30 as necessary to update the application.

[0160] S45: If another web browser 250 receives the result (success or failure) of step S39, the browser - to - browser cooperation unit 14 determines whether there have been failures continuously for a certain number of times or more. If there have been failures continuously for a certain number of times or more, the display control unit 12 causes another web browser 250 to display a result such as "Failed to create / update the application". The process of FIG. 18 ends once, and after that, since the user needs to generate the application again, the user returns to step S30 as necessary.

[0161] S46: When the browser - to - browser cooperation unit 14 of another web browser 250 receives the result of failure (error message), the communication unit 11 of another web browser 250 transmits the result (failure) regarding the generation or update of the application to the information processing system 20. The processes of subsequent steps S47 and S48 are the same as steps S13 and S14 in FIG. 10.

[0162] S49: The information processing system 20 transmits a function call request or a normal response message to another web browser 250. In the case of a function call request, the process proceeds to step S36, and in the case of a response message, the process proceeds to step S35.

[0163] After that, also during the repeated process, the information processing system 20 generates or updates the application of the application service 40 in the form of requesting the user terminal 10.

[0164] Also, in FIGS. 17 and 18, an example of pop - up displaying another web browser 250 has been described, but a function called an iframe that the web browser supports may also be used. An iframe (inline frame) is defined by an HTML element (tag) and is a function for displaying another web page or content (text, image, video, etc.) within a web page. By embedding another web page within a web page, it is possible to display an application generation page, which is another site, within the portal screen of the application service 40. In this case, postMessage is known for communication between windows. Note that the sequence diagram in this case may be the same as FIG. 10.

[0165] <Main effects> The information processing system 20 of this embodiment can solve two barriers (not knowing what kind of application to create, not knowing how to create the desired application even if there is an application to be created) when a user lacking expertise develops an application.

[0166] The application generation system 100 of this embodiment enables a user to develop an application by operating the user terminal 10 and sending sample data to the generation AI system 50. Since the information processing system 20 designates a function to the generation AI system 50, the generation AI system 50 can request the information processing system 20 to perform a function call together with the field name of the application, etc. Then, the information processing system 20 actually generates or updates the application. As a result, from the user's perspective, by sending sample data such as a form file to the information processing system 20, a no-code or low-code platform that can actually develop an application can be realized.

[0167] <Other application examples> As described above, the best mode for carrying out the present invention has been described using examples. However, the present invention is not limited to such examples, and various modifications and substitutions can be made without departing from the gist of the present invention.

[0168] For example, in this embodiment, an example in which a user uses sample data as an input to the information processing system 20 has been described. However, the user may request the generation of an application by, for example, sending an image (photo, handwritten, snapshot, etc.) representing the screen of the application to the information processing system 20. The information processing system 20 sends the application screen to the generation AI system 50, and the generation AI system 50 analyzes the application screen and sends a function call request to the information processing system 20. The generation AI system 50 can include the field name and data format extracted from the application screen in the function call request.

[0169] Also, the sample data may be an image file. For example, as images, image data obtained by imaging document files, receipts, business cards, etc. can be considered. The information processing system 20 can perform OCR (Optical Character Reader / Recognition) on the image data and extract characters, thereby generating an application in the same manner as in this embodiment.

[0170] Also, in this embodiment, the user causes the user terminal 10 to transmit the sample data, but the sample data may be stored on a predetermined server. In this case, the user inputs information for designating the sample data on the server in natural language (chat message) to the user terminal 10, and the user terminal 10 transmits information for designating the sample data to the information processing system 20 or the generation AI system 50. The information processing system 20 or the generation AI system 50 acquires the sample data from the server and generates an application.

[0171] Also, in this embodiment, the information processing system 20 transmits the URL of the application to the generation AI system 50, but the URL may be any access information for accessing the application. For example, when the application service 40 returns the ID (identification information) of the generated application to the information processing system 20, the information processing system 20 transmits the ID of the application to the generation AI system 50. The information processing system 20 transmits the ID of the application included in the response message returned from the generation AI system 50 to the user terminal 10. When the user terminal 10 requests the execution of the application by instructing the ID of the application, the information processing system 20 converts the ID into the URL of the application based on the ID and returns this URL to the user terminal 10.

[0172] In addition, in this embodiment, the case where the information processing system 20 receives a function call request from the generation AI system 50 has been described as an example. However, the information processing system 20 may receive a call request for the Web-API itself from the generation AI system 50. That is, the function and the API do not have to be strictly distinguished.

[0173] Also, the device group described in the embodiments merely shows one of a plurality of computing environments for implementing the embodiments disclosed in this specification. In one embodiment, the information processing system 20 includes a plurality of computing devices such as a server cluster. The plurality of computing devices are configured to communicate with each other via any type of communication link including a network and a shared memory, and implement the processing disclosed in this specification.

[0174] Furthermore, the information processing system 20 can be configured to share the processing steps disclosed in this embodiment, such as FIG. 10, in various combinations. For example, a process executed by a predetermined unit can be executed by a plurality of information processing devices included in the information processing system 20. Also, the information processing system 20 may be integrated into one server device or divided into a plurality of devices.

[0175] Also, the configuration example such as FIG. 5 is divided according to the main functions in order to facilitate the understanding of the processing by the information processing system 20. The present invention is not limited by the way of dividing the processing units and the names. The processing of the information processing system 20 can be further divided into more processing units according to the processing content. Also, one processing unit can be divided so as to include more processing.

[0176] In addition, each function of the embodiments described above can be realized by one or more processing circuits. Here, the "processing circuit" in this specification refers to a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, an ASIC (Application Specific Integrated Circuit) designed to execute each function described above, a DSP (digital signal processor), an FPGA (field programmable gate array), and devices such as conventional circuit modules.

[0177] A configuration example in the case where the application service 40 and the information processing system 20 are integrated will be described. Hereinafter, an example in which the function of the application service 40 is included in the information processing system 20 will be described, but the function of the information processing system 20 may be included in the application service 40.

[0178] FIG. 19 is a diagram for explaining the processing until the generation AI system 50 requests the information processing system 20 to execute a function for the chat message input by the user, and the information processing system 20 generates an application. The processing of (1) to (3) may be the same as the description in FIG. 1.

[0179] (4) The information processing system 20 generates an application in response to a function call included in the response message transmitted from the generation AI system 50. Which application to generate is determined in (2) and (3). More specifically, the information processing system 20 executes a function for generating an application from the content of the function call. That is, in the case of the configuration of FIG. 19, the information processing system 20 generates or updates an application by itself.

[0180] FIG. 20 is a diagram showing a functional configuration example of the information processing system 20, the user terminal 10, and the developer terminal 60 when the application service 40 and the information processing system 20 are integrated. In the description of FIG. 20, the differences from FIG. 5 will be mainly described. Since the information processing system 20 and the application service 40 are integrated, the application generation unit 25 does not call the second API 27. Also, the functions of the communication unit 21, the screen generation unit 22, the setting information storage unit 24, the data generation unit 28, and the control unit 23 may be the same as those in FIG. 5.

[0181] And the application generation unit 25 in FIG. 20 functions by executing a predefined function. The parameters input to the function to be executed include database field names, data formats, etc.

[0182] Embodiments of the present invention bring about significant improvements in the capabilities and functionality of computers. These improvements enable users to utilize a computer that provides a more efficient and robust interaction with a table, which is a method of storing and presenting information in an information processing device. Furthermore, embodiments of the present invention provide a better user experience through the use of a more efficient, powerful, and robust user interface. Such a user interface provides better interaction between humans and machines.

[0183] <Appendix> [Appendix 1] A terminal device, and an information processing device capable of communicating with a generation AI (Artificial Intelligence) system via a network, An application generation unit that functions by executing a predefined function, the application generation unit generating the application related to the request based on the parameters included in the request related to the generation of the application, A control unit that, when receiving sample data for application generation from the terminal device, transmits data based on the received sample data to the generation AI system, having The control unit transmits, at least once, the setting information for generating the application and the information for calling the function to the generation AI system, When the control unit receives the request sent by the generation AI system based on the data sent to the generation AI system, the setting information sent to the generation AI system, and the information for calling the function sent to the generation AI system, the application generation unit generates the application related to the request based on the parameters included in the received request. An information processing apparatus. [Appendix 2] The information processing apparatus according to Appendix 1, wherein when the control unit receives a response message for the data sent to the generation AI system from the generation AI system, the control unit transmits the response message to the terminal device. [Appendix 3] The information processing apparatus according to Appendix 2, wherein the control unit transmits the access information to the generation AI system in order to enable the generation AI system to include, in the response message, the access information for accessing the generated application. [Appendix 4] The information processing apparatus according to Appendix 3, wherein when the control unit receives, as a response to transmitting the access information to the generation AI system, the response message including the access information from the generation AI system, the control unit transmits the response message including the access information to the terminal device. [Appendix 5] The information for calling the function includes the setting of the specification of the function to be called by the generation AI system. The function call request for the generation AI system to call the function based on the setting of the function specification includes a request related to the generation of the application, and the control unit receives the request related to the generation of the application from the generation AI system. The information processing apparatus according to any one of Appendices 1 to 4. [Appendix 6] When the control unit receives a request related to the generation of the application from the generation AI system, the application generation unit generates the application related to the request based on the parameter, When the control unit receives the response message for the data from the generation AI system, instead of a request related to the generation of the application, the control unit transmits the response message to the terminal device. The information processing apparatus according to Supplementary Note 3. [Supplementary Note 7] When the application generation unit fails to generate the application, the control unit transmits the error message obtained due to the failure of the application generation and the data again to the generation AI system, and receives a request related to the generation of the application as a response to the error message and the data. The information processing apparatus according to any one of Supplementary Notes 1 to 6. [Supplementary Note 8] When the application generation unit fails to generate the application a certain number of times, The control unit transmits a message indicating the failure of the application generation to the terminal device. The information processing apparatus according to any one of Supplementary Notes 1 to 6. [Supplementary Note 9] When the application is an application in which information is registered in a table, The parameter is one or more field names of the table. The information processing apparatus according to any one of Supplementary Notes 1 to 7. [Supplementary Note 10] The information processing apparatus communicates with an application service that executes the application via a network, The application generation unit requests the application service to generate the application by specifying the parameter. The information processing apparatus according to any one of Supplementary Notes 1 to 8. [Supplementary Note 11] In the terminal device, a first Web browser that communicates with the application service and a second Web browser launched by the first Web browser are executed. The information processing apparatus receives data based on the sample data from the second web browser, when the control unit receives a request related to generation of the application transmitted by the generation AI system, the application generation unit transmits a request related to generation of the application to the second web browser, the second web browser transmits a request related to generation of the application to the first web browser, the information processing apparatus according to Supplementary Note 10, wherein the first web browser transmits a request related to generation of the application to the application service. [Supplementary Note 12] further comprising a data generation unit that generates data obtained by converting the received sample data into a predetermined format, the information processing apparatus according to any one of claims 1 to 11, wherein the control unit transmits the generated data to the generation AI system. [Supplementary Note 13] the information processing apparatus according to any one of claims 1 to 12, wherein the data based on the received sample data is the same data as the sample data. [Supplementary Note 14] the information processing apparatus according to any one of Supplementary Notes 1 to 12, wherein the sample data is a file in a format of Excel (registered trademark), WORD, or PDF. [Description of Reference Signs]

[0184] 10 User terminal 20 Information processing system 40 Application service 50 Generation AI system 100 Application generation system [Prior Art Documents] [Patent Documents]

[0185] [Patent Document 1] Japanese Patent Application Laid-Open No. 2023-018851

Claims

1. An information processing device capable of communicating with a terminal device and a generation AI (Artificial Intelligence) system via a network, an application generator that functions by executing predefined functions, the application generator generating an application according to a request for generation of the application based on parameters included in the request; A control unit that, when sample data for application generation is received from the terminal device, transmits data based on the received sample data to the generation AI system; having The control unit transmits setting information for generating the application and information for calling the function to the generation AI system at least once, When the control unit receives the request transmitted by the generating AI system based on the data transmitted to the generating AI system, the setting information transmitted to the generating AI system, and the information for calling the function transmitted to the generating AI system, the application generation unit generates the application related to the request based on the parameters included in the received request. Information processing device.

2. The information processing device according to claim 1 , wherein the control unit, when receiving a response message from the generating AI system in response to the data transmitted to the generating AI system, transmits the response message to the terminal device.

3. The information processing device described in claim 2, wherein the control unit transmits access information for accessing the generated application to the generation AI system to enable the generation AI system to include the access information in the response message.

4. The information processing device described in claim 3, wherein when the control unit receives a response message including the access information from the generation AI system in response to transmitting the access information to the generation AI system, the control unit transmits the response message including the access information to the terminal device.

5. The information for calling the function includes a setting of the specification of the function to be called by the generating AI system, An information processing device according to any one of claims 1 to 4, wherein a function call request for calling the function sent by the generation AI system to the information processing device based on the setting of the function specifications includes a request related to the generation of the application, and the control unit receives the request related to the generation of the application from the generation AI system.

6. When the control unit receives a request for generating the application from the generation AI system, the application generation unit generates the application related to the request based on the parameters, The information processing device according to claim 3 , wherein when the control unit receives a response message for the data from the generation AI system rather than a request for generation of the application, the control unit transmits the response message to the terminal device.

7. The information processing device of claim 1, wherein when the application generation unit fails to generate the application, the control unit transmits an error message obtained due to the failure to generate the application and the data again to the generation AI system, and receives a request for generating the application in response to the error message and the data.

8. When the application generation unit fails to generate the application a certain number of times, The information processing apparatus according to claim 1 , wherein the control unit transmits a notification to the terminal device indicating that the generation of the application has failed.

9. If the application is an application in which information is registered in a table, The information processing apparatus according to claim 1 , wherein the parameter is one or more field names of the table.

10. the information processing device communicates with an application service that executes the application via a network; The information processing apparatus according to claim 1 , wherein the application generation unit specifies the parameters and requests the application service to generate the application.

11. In the terminal device, a first Web browser that communicates with the application service and a second Web browser that is started by the first Web browser are executed; the information processing device receives data based on the sample data from the second web browser; When the control unit receives a request for generating the application transmitted by the generation AI system, the application generation unit transmits a request for generating the application to the second Web browser; the second web browser transmits a request for generating the application to the first web browser; The information processing apparatus according to claim 10 , wherein the first Web browser transmits a request for generating the application to the application service.

12. A data generating unit that generates the data by converting the received sample data into a predetermined format, The information processing device according to claim 1 , wherein the control unit transmits the generated data to the generation AI system.

13. The information processing apparatus according to claim 1 , wherein the data based on the received sample data is the same data as the sample data.

14. The information processing apparatus according to claim 1 , wherein the sample data is a file in Excel (registered trademark), WORD, or PDF format.

15. An application generation system in which a terminal device, a generation AI (Artificial Intelligence) system, and an information processing device communicate with each other via a network, The terminal device Sending sample data for application generation to the generation AI system; The information processing device includes: an application generator that functions by executing predefined functions, the application generator generating an application according to a request for generation of the application based on parameters included in the request; A control unit that, when the sample data is received from the terminal device, transmits data based on the received sample data to the generation AI system; having The control unit transmits setting information for generating the application and information for calling the function to the generation AI system at least once, When the control unit receives the request transmitted by the generating AI system based on the data transmitted to the generating AI system, the setting information transmitted to the generating AI system, and the information for calling the function transmitted to the generating AI system, the application generation unit generates the application related to the request based on the parameters included in the received request. App generation system.

16. A terminal device and an information processing device capable of communicating with a generating AI (Artificial Intelligence) system via a network, an application generator that functions by executing predefined functions, the application generator generating an application according to a request for generation of the application based on parameters included in the request; a control unit that, when sample data for generating an application is received from the terminal device, transmits data based on the received sample data to the generation AI system; Function as a The control unit transmits setting information for generating the application and information for calling the function to the generation AI system at least once, When the control unit receives the request transmitted by the generating AI system based on the data transmitted to the generating AI system, the setting information transmitted to the generating AI system, and the information for calling the function transmitted to the generating AI system, the application generation unit generates the application related to the request based on the parameters included in the received request. program.

17. An application generation method performed by a terminal device and an information processing device capable of communicating with a generation AI (Artificial Intelligence) system via a network, comprising: The information processing device includes an application generation unit that functions by executing a predefined function, and that generates an application related to a request based on a parameter included in the request; A control unit that, when sample data for application generation is received from the terminal device, transmits data based on the received sample data to the generation AI system; having The control unit transmits setting information for generating the application and information for calling the function to the generation AI system at least once, When the control unit receives the request transmitted by the generating AI system based on the data transmitted to the generating AI system, the setting information transmitted to the generating AI system, and the information for calling the function transmitted to the generating AI system, the application generation unit generates the application related to the request based on the parameters included in the received request. How to generate an application.

Images