Information processing equipment, terminal equipment, information processing system, program

Abstract

To assist in entering text into input fields. [Solution] The present invention relates to an information processing device 40, which is a screen that includes a plurality of input fields, each accepting user input of data to be entered into a plurality of items, and at least one of the plurality of input fields that accepts text input, and a registration unit 43 that registers information entered via a screen that accepts operations to create text to be entered into the specific input field; a request transmission unit 46b that, when an operation from the user is received, transmits a request to a generation AI system that includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and an instruction to create text to be entered into the specific input field of the specific item based on the information indicating the one or more items and the data; and a transmission unit 41b that transmits text created by the generation AI system based on the request to the terminal device.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, a terminal device, an information processing system, and a program.

Background Art

[0002] So-called generative AI that utilizes AI technology to generate text data, image data, voice data, etc. is known. Generative AI can utilize learned patterns and data relationships to generate new text data.

[0003] Techniques for assisting creation using generative AI have been devised (for example, see Patent Document 1). Patent Document 1 discloses a technique for outputting a title for input of a genre and keywords, and generating a summary for input of a title and keywords.

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology has a problem that it cannot generate a sentence to be input into an input field for an item. Therefore, the user has to manually input a sentence suitable for the item.

[0005] In view of the above problems, the present invention provides a technique for assisting the input of sentences into an input field.

Means for Solving the Problems

[0006] In view of the above problems, the present invention provides a terminal device, a generation AI system, and an information processing device connected via a network, the terminal device having a screen that includes a plurality of input fields, each accepting user input of data to be entered into a plurality of items, and each of the plurality of input fields including at least one specific input field that accepts text input, and the screen that accepts an operation to create text to be entered into the specific input field, the registration unit that registers information entered via the screen, the registration unit that registers information entered via the screen, the registration unit that, upon receiving the operation from the user, sends a request to the generation AI system that includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and an instruction to create text to be entered into the specific input field of the specific item based on the information indicating the one or more items and the data, the request transmission unit that, upon receiving the operation from the user, sends a request to the generation AI system that includes information indicating one or more items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and an instruction to create text to be entered into the specific input field of the specific item based on the information indicating the one or more items and the data, the request transmission unit that transmits the text created by the generation AI system based on the request to the terminal device. [Effects of the Invention]

[0007] In view of the above problems, the present invention can assist in inputting text into an input field. [Brief explanation of the drawing]

[0008] [Figure 1] This is an example of an application creation screen displayed on a user's terminal. [Figure 2] This figure shows an example of the input screen for a business trip report application displayed on the user's terminal. [Figure 3] This diagram illustrates the process by which a user enters values ​​into the input fields of a business trip report application. [Figure 4] This diagram illustrates the flow of information setting services performed by an information processing system. [Figure 5] This is a diagram showing the system configuration of an example of an information processing system. [Figure 6]This diagram shows an example hardware configuration for an application service, a user terminal, and a developer terminal. [Figure 7] This diagram shows an example of the functional configuration of an application service and a user terminal. [Figure 8] This figure shows an example of the information set in the application's input fields. [Figure 9] This figure shows an example of information regarding the input fields of an application. [Figure 10] This is an example sequence diagram illustrating the processes performed by an information processing system. [Figure 11] Figure 10 shows an example of parameters included in the request message that the application service sends to the AI ​​generation system in step S4. [Figure 12] This diagram explains the prompt that is set in "Prompt" in Figure 11. [Figure 13] This figure shows the format of the response message sent from the generating AI system to the application service in step S5 of Figure 10. [Figure 14] This diagram shows an example of an input screen for a business trip report application displayed on a user's terminal. [Figure 15] This figure shows an example prompt generated by the request generation unit. [Figure 16] This figure shows an example of a response message from the generation AI system to the request message shown in Figure 15. [Figure 17] This figure shows an example of the input screen of a business trip reporting app, with the generated values ​​already set in the daily report section of the business trip reporting app. [Figure 18] This diagram shows an example of an input screen for a school newsletter creation app displayed on a user's device. [Figure 19A] This diagram shows information about the input fields in an example of a newsletter creation app for kindergartens. [Figure 19B] This diagram shows the information set in the input fields of an example of a newsletter creation app. [Figure 20]This is a diagram showing an example of a prompt generated by the request generation unit. [Figure 21] This is a diagram showing an example of a response message from the generation AI system for the request message in FIG. 20. [Figure 22] This is a diagram showing an input screen of an example of a garden newsletter creation app in a state where the generated value is set in the garden newsletter text field of the garden newsletter creation app. [Figure 23] This is a diagram showing an input screen of an example of a business trip report app displayed on a user terminal. [Figure 24] This is a diagram showing an example of a prompt generated by the request generation unit. [Figure 25] This is a diagram showing an example of a prompt input screen that is pop-up displayed on the input screen of the business trip report app. [Figure 26] This is a diagram showing an example of a prompt in the request message generated by the request generation unit. [Figure 27] This is a diagram showing an example of a confirmation dialog that is pop-up displayed on the input screen of the business trip report app. [Figure 28] This is a diagram showing an example of an input item selection dialog that is pop-up displayed on the input screen of the business trip report app. [Figure 29] This is a diagram showing an example of a prompt generated by the request generation unit. [Figure 30] This is a diagram showing an example of a prompt generated by the request generation unit. [Figure 31] This is a diagram showing an input screen of an example of a garden newsletter creation app displayed on a user terminal. [Figure 32] This is a diagram showing an example of a generation target selection dialog that is pop-up displayed on the input screen of the garden newsletter creation app. [Figure 33] This is a diagram showing an example of a prompt generated by the request generation unit. [Figure 34] This is a diagram showing an example of a response message from the generation AI system for the request message in FIG. 33. [Figure 35]This figure shows an example of the input screen of a school newsletter creation app, with the generated values ​​already set. [Figure 36] This figure shows an example prompt using few-shot prompting. [Figure 37] This is an example sequence diagram illustrating the processing of an information processing system when using few-shot prompting. [Modes for carrying out the invention]

[0009] The following describes an example of a configuration method used by an information processing system to implement this disclosure.

[0010] <About Application Services> Application services are services that assist users in creating applications using low-code or no-code methods. Such services are also known as visual programming. Application services send a web application that assists in application creation to the user's terminal. Users can then create various applications by interacting with the web application running on their terminal.

[0011] Figure 1 shows the application creation screen 200 displayed on the user terminal. The application creation screen 200, as an example, includes a form area 208 and a work area 209. The form area 208 displays a list of forms that can be placed in the application. A form is a display component that makes up a screen, and examples include input forms, selection forms, and file registration forms. Figure 1 shows a text form 201, a numeric form 202, a radio button form 203, a checkbox form 204, and an attachment form 205. These are just examples.

[0012] String form 201 is a form for entering text. Full-width characters, half-width characters, numbers, symbols, etc., can be entered into string form 201.

[0013] Numeric form 202 is a form for entering numerical values. Only numerical values ​​can be entered into Numeric form 202.

[0014] Radio button form 203 is a form for buttons that accept the selection of one option from multiple options. Radio button form 203 has fields for displaying the options.

[0015] Checkbox form 204 is a form for checkboxes that accepts the selection of one or more options from multiple choices. Checkbox form 204 has fields for displaying the options.

[0016] Attachment form 205 is a form that accepts settings for files to be registered in the application. Attachment form 205 may restrict the file formats that can be accepted for registration.

[0017] The workspace 209 is the area where the user places forms. The user can drag and drop forms from the form area 208 into the workspace 209 using the mouse pointer. Alternatively, the user can drag and drop forms into the workspace 209 using their finger or a pen on the touch panel.

[0018] The form placed in work area 209 is referred to as input field 206. Input field 206 has one or more input fields, but for simplicity, it will sometimes simply be referred to as input field below. A label 207 is displayed on input field 206. Label 207 is the name of input field 206. The user enters an appropriate label for input field 206. The user can repeat this process to create any application. For example, the user can create a business trip report application like the one below by placing a text form 201 in work area 209 and entering labels such as "traveler" and "business trip date". Note that the position of an already placed input field 206 can also be changed in work area 209.

[0019] Figure 2 shows the input screen 210 of the business trip report application. This business trip report application has fields for the traveler 211, the date of the trip 212, the destination 213, the purpose 214, the result 215, the daily report 216, and a save button 217. Except for the save button 217, these are input fields. Users can use the application created in this way for work and other purposes. For example, when an employee goes on a business trip, the employee uses the business trip report application. The employee enters the traveler's information into the respective input fields. This allows the business trip report application to digitize information, or to share information with a team. Figure 3(a) shows the application list 220 displayed on the user terminal operated by the user. The application list 220 is a list of applications that the user has created and registered in the application service using the procedure shown in Figure 1. As an example, the application list 220 displays the business trip report application 221 and the nursery newsletter creation application 222. Here, the user has selected the business trip report application 221. The application creation button 223 is a button that displays a screen like the one in Figure 1.

[0020] Figure 3(b) shows the record list 224 displayed by the user terminal. The record list 224 displays a table-like list of travel information registered in the travel report application 221. A record is a single row of data when data in a database is arranged in a two-dimensional table. One record represents one piece of travel information. A record 225 has multiple input fields. These input fields are sometimes called fields. A single column is called a column. In Figure 3(b), no travel information has been registered, so the record list 224 is blank.

[0021] When the user presses the Add Record button 226, the input screen 210 of the business trip report application is displayed. Figure 3(c) shows the input screen 210 of the business trip report application. As described above, the input screen 210 of the business trip report application has input fields created by the user for the business trip report application 221. The user enters values ​​into the input fields and presses the Save button 227. The input content (in this case, business trip information) is saved as a record in the application service.

[0022] Figure 3(d) shows the record list 224 displayed by the user terminal. The travel information entered on the input screen 210 of the travel report application in Figure 3(c) is displayed as one record.

[0023] Thus, since input is usually done using a keyboard, it placed a heavy burden on the user. Furthermore, there was a risk of input errors.

[0024] <Processing flow> In this embodiment, the user terminal sends a list of application input items and values ​​already entered in those input items to the application service, and the application service requests the generative AI system to generate values. The generative AI system can perform various natural language processing tasks, such as text generation, question answering, text classification, sentiment analysis, information extraction, and text summarization. Generative AI systems such as Copilot®, which suggest the next code to write while a program is being coded, are also known. In this embodiment, we describe a technique for generating values ​​for other input items from a list of input items and some already entered values, without the user having to converse (also called chat) with the generative AI system. Note that the generative AI system or its function may sometimes simply be referred to as AI (Artificial Intelligence).

[0025] The generation AI system analyzes a list of input fields and the values ​​already entered in those fields, generates values ​​to be entered into the specified input fields, and sends them to the application service. The application service sends the generated values ​​to the user terminal. The user terminal registers the generated values ​​with the application service.

[0026] Furthermore, users can create any application they use for work or other purposes, not just the business trip reporting application, using the application service. Therefore, the information processing system of this embodiment can generate appropriate values ​​for the input fields of any application using the AI ​​generation system and set them as input fields of the application service.

[0027] Figure 4 illustrates the process by which the information processing system 100 sets values ​​in the application service 40. A web application is running on the user terminal 10. The application for which values ​​are to be set in the input fields is assumed to have already been created in the application service 40. The generation AI system 50 analyzes the list of input fields that the application has and the values ​​that have already been entered into the input fields, and generates the values ​​to be set in the specified input fields.

[0028] (1) The user terminal 10 is displaying the application's input screen. For example, the user is using the business trip report application to create a business trip report and has entered values ​​into several input fields regarding their business trip report. The user wants to automatically set values ​​generated by the generation AI system 50 into specific input fields. By pressing a designated button, the user sends the values ​​already entered into the input fields and the input fields for which values ​​should be generated to the application service 40 (AI input request). Note that the values ​​entered by the user to create the business trip report do not necessarily have to be stored by the user terminal 10, but may be obtained from the application service 40.

[0029] (2) The application service 40 identifies a list of input fields and the name of the application being run on the user terminal 10, in response to a request. The name of the application is optional, or instead of the name of the application, the application description document (the application description, which has been set in advance by the user) may be obtained. The application service 40 sends information about the application (list of input fields, entered values, and the name of the application) and the input fields for which values ​​are to be generated to the generation AI system 50. The "input fields for which values ​​are to be generated" may hereafter be referred to as the "specified input fields". The application service 40 obtains the values ​​to be set for the specified input fields from the generation AI system 50. That is, the generation AI system 50 analyzes the list of input fields, the entered values, and the name of the application, generates the values ​​to be set for the specified input fields, and sends them to the application service 40.

[0030] Note that pre-entered values ​​are not necessarily required. The generating AI system 50 can generate information that has not been provided. For example, the generating AI system 50 can generate values ​​for input fields specified from at least one of the list of input fields or the application name. Furthermore, by utilizing the few-shot prompting described later, the generating AI system 50 can generate appropriate input field values ​​even if no pre-entered values ​​are available.

[0031] (3) The application service 40 sends the values ​​obtained from the generation AI system 50 to the user terminal 10. As a result, the user terminal 10 displays an input screen with values ​​set in the specified input fields, allowing the user to confirm the generated values. When the user presses a button such as register, the user terminal 10 sends the values ​​corresponding to the input fields to the application service 40, and the application service 40 sets the values ​​in the application's record.

[0032] Thus, the information processing system 100 of this embodiment can set values ​​for input items of any application.

[0033] <About Terminology> An application is an application program, a program generated by a computer in response to a specific task. While an OS (Operating System) is general-purpose software that provides basic functions and systems for the computer's operation (file system, communication, display control, etc.), an application provides specific functions on top of the OS. Applications include web applications and native applications. In this embodiment, either type may be developed.

[0034] An API is an application (software) interface, serving as a point of contact for connecting systems and sharing functions and mechanisms. An API defines the specifications for the interface that applications use to exchange information with each other. A computer-to-computer API is a specification for communication between one website and another via HTTP (HTTPS) communication. Through this communication, one website can use the functions of the other website. Computer-to-computer APIs are sometimes referred to as Web APIs.

[0035] An API takes a specific request (e.g., retrieving, updating, deleting, or processing data) and returns a result (e.g., data, update result, deletion result, processing result, etc.) in response. The request is sometimes called a request message, and the result is sometimes called a response message. Calling an API means sending a request according to the API's specifications and obtaining the result. Calling an API may also be described as executing, operating, hitting, or using it.

[0036] A user is an end-user who uses the applications provided by Application Service 40. Users can also develop applications. A developer is a person who configures Application Service 40 for the necessary settings for developing and using applications using no-code or low-code programming.

[0037] An item is a field for entering information. The input field can accept various types of information, including text, numbers, symbols, image data, audio data, video data, files, and selection options. A single screen may have multiple items and multiple input fields.

[0038] The specific input field that accepts text input is the input field into which values ​​to be generated by the generation AI system 50 are entered. The one or more items other than the specific item related to the specific input field are the input fields of the application other than the specific input field. These one or more items may have values ​​entered by the user.

[0039] [First Embodiment] <Example System Configuration> Referring to Figure 5, the system configuration of the information processing system 100 according to this embodiment will be described. Figure 5 is a diagram showing the system configuration of an example of the information processing system 100. The information processing system 100 shown in Figure 5 has a user terminal 10, a developer terminal 60, and an application service 40. The user terminal 10 and the developer terminal 60 are connected to the application service 40 so as to be able to communicate via networks N1 and N2. The information processing system 100 may further have a generation AI system 50. The user terminal 10 and the developer terminal 60 are connected to the generation AI system 50 so as to be able to communicate via networks N1 and N2. The application service 40 may also be able to communicate with the generation AI system 50 via an API (Application Programming Interface).

[0040] The user terminal 10 and developer terminal 60 are located in facilities such as companies or homes and are connected to network N2. Network N2 can be a LAN, Wi-Fi (registered trademark), Wide Area Ethernet (registered trademark), 4G, 5G, 6G, or other mobile phone network. Network N1 is a wide-area network such as the Internet or WAN. The user terminal 10 and developer terminal 60 do not need to be constantly connected to network N2; they only need to be connected when using the generation AI system 50 or application service 40.

[0041] The generative AI system 50 provides a service that allows users to converse with artificial intelligence (AI) in natural language. A well-known example of such a generative AI system 50 is one that utilizes Large Language Models (LLMs). Large Language Models are natural language processing models trained using large amounts of text data. The generative AI system 50 pre-inputs a vast amount of text and learns knowledge from it using deep learning, reinforcement learning, etc. Using this knowledge, the generative AI system 50 provides response messages to chat messages. Chat messages include prompts and image data, which will be described later. A prompt refers primarily to the text data within a chat message.

[0042] The generation AI system 50, which generates text from data based on chat messages, is sometimes referred to as the generation AI. In this embodiment, the response messages provided by the generation AI system 50 are used to generate values ​​for input fields of an application running in the application service 40. The application running in the application service 40 includes a web application that runs on 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 on the user terminal 10, it connects to the application service 40 and executes the functions of the application service 40.

[0043] The generation AI system 50 has the following characteristics: 1. The generating AI system 50 conducts the conversation in a natural flow. 2. The generation AI system 50 can expand on ideas and propose them even in fields where the user lacks expertise. 3. The generation AI system 50 can output accurate program code. Taking advantage of these features, users can specify input fields that generate information and values ​​related to the application, and receive values ​​to set in the specified input fields from the generation AI system 50 via the application service 40.

[0044] As a generation AI system 50, systems using LLMs such as GPT-3, GPT-4, Transformer, and BERT (all registered trademarks) are known. In the information processing system 100 of this embodiment, ChatGPT using GPT-3 or GPT-4 can be used as an example, but other systems using LLMs may also be used.

[0045] Application Service 40 is one or more information processing devices that provide applications for users to run. Application Service 40 is also a server device that provides applications for managing information entered by users into input fields. The applications provided by Application Service 40 are, for example, database-type web applications that manage data in a tabular format. Users can arbitrarily create input fields for the applications and customize them to save, read, or process data related to their work. Application Service 40 has multiple applications, such as a business trip reporting application and a nursery newsletter creation application.

[0046] In this embodiment, the user sets, for example, the date in a business trip report, in the application. The user terminal 10 requests AI input from the application service 40, specifying these entered values ​​and the daily report fields for which it wants to generate values. The application service 40 sends information about the application (list of input items, entered values, application name) and the input items for which it wants to generate values ​​to the generation AI system 50, and receives a response message from the generation AI system 50 (values ​​of the specified input items). The application service 40 sends the values ​​of the specified input items to the user terminal 10. Therefore, the user can automatically set information that would otherwise need to be manually entered in the application.

[0047] Examples of application services 40 include cloud services, ASPs (Application Service Providers), SaaS, etc., and may include various services provided over a network. For example, database provision and storage services are examples of such services. Application services 40 may reside on the internet or on-premises.

[0048] Furthermore, the application service 40 may have its functions distributed across multiple information processing devices, or multiple application services 40 with the same function may exist, and the number of information processing devices that distribute video may increase or decrease depending on the processing load.

[0049] In addition, a separate web server may exist in addition to the application service 40, and this web server may communicate with the user terminal 10. In this case, the web server will communicate with the application service 40 instead of the user terminal 10.

[0050] A server is a computer or software that provides information and processing results in response to requests from clients.

[0051] Furthermore, the application service 40 accepts various settings from the developer terminal 60. These settings include user registration with the application service 40 and registration of a web application for creating chat messages. In other words, the administrator performs the task of setting values ​​for the application's input fields using the generation AI system 50 with the application service 40.

[0052] The user terminal 10 or developer terminal 60 is, for example, a terminal device such as a PC (Personal Computer), smartphone, or tablet used by the user or developer. A web browser or native application runs on the user terminal 10 or developer terminal 60. The developer operates the developer terminal 60 to create configuration information for the application. The administrator or user can operate the developer terminal 60 and the user terminal 10 to use various services provided by the generation AI system 50 or application service 40.

[0053] The user terminal 10 or developer terminal 60 can be any information processing device. Examples of such information processing devices include output devices such as electronic whiteboards and digital signage, HUD (Head Up Display) devices, industrial machinery, imaging devices, sound collection devices, medical equipment, networked home appliances, mobile phones, smartphones, tablet devices, car navigation systems, game consoles, PDAs (Personal Digital Assistants), digital cameras, and wearable PCs.

[0054] <Example Hardware Configuration> Referring to Figure 6, the hardware configurations of the application service 40, user terminal 10, and developer terminal 60 included in the information processing system 100 will be described. The generation AI system 50 is assumed to be the same as in Figure 6, or to be an information processing device hardware configuration compatible with cloud computing.

[0055] <<Application services, user terminals, and developer terminals>> Figure 6 shows an example of the hardware configuration of an application service 40, a user terminal 10, and a developer terminal 60. As shown in Figure 6, the application service 40, user terminal 10, and developer terminal 60 are built by a computer 500, which includes a CPU 501, ROM 502, RAM 503, HD (Hard Disk) 504, HDD (Hard Disk Drive) controller 505, display 506, external device connection I / F (Interface) 508, network I / F 509, bus line 510, keyboard 511, pointing device 512, optical drive 514, and media I / F 516.

[0056] Of these, the CPU 501 controls the operation of the entire computer 500. The ROM 502 stores programs used to drive the CPU 501, such as the IPL. The RAM 503 is used as the 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 the HD 504 according to the control of the CPU 501. The display 506 displays various information such as cursors, menus, windows, characters, or images. The external device connection I / F 508 is an interface for connecting various external devices. In this case, external devices include, for example, USB (Universal Serial Bus) memory and printers. The network I / F 509 is an interface for data communication using the network N2. The bus line 510 is an address bus, data bus, etc., for electrically connecting each component such as the CPU 501 shown in Figure 6.

[0057] The keyboard 511 is a type of input means equipped with multiple keys used for inputting characters, numbers, or various instructions. The pointing device 512 is a type of input means used for selecting and executing various instructions, selecting processing targets, moving the cursor, etc. The optical drive 514 controls the reading or writing of various data to the optical storage medium 513, which is an example of a removable recording medium. The optical storage medium is a DVD, CD, etc. The media interface 516 controls the reading or writing (storage) of data to the recording medium 515, such as flash memory.

[0058] <About the features> Next, with reference to Figure 7, the functional configuration of the information processing system 100 will be described. Figure 7 is a diagram showing an example of the functional configuration of the application service 40 and the user terminal 10.

[0059] <<User Terminal>> The user terminal 10 includes a communication unit 11, a display control unit 12, an operation reception unit 13, and an input processing unit 14. Each of these functional units is a function or means realized by the CPU 501 shown in Figure 6 executing instructions contained in one or more programs installed on the user terminal 10. For example, the communication unit 11, the display control unit 12, the operation reception unit 13, and the input processing unit 14 may be realized by a web browser and a web application. The web application is sent from the application service 40 to the user terminal 10. If the user terminal 10 runs a native application, these may be realized by the native application.

[0060] The communication unit 11 sends and receives various types of information to and from the application service 40. The communication unit 11 has a receiving unit 11a and a transmitting unit 11b. In this embodiment, the receiving unit 11a receives screen information such as the application's input screen from the application service 40. The transmitting unit 11b sends to the application service 40 values ​​that have been entered into input fields and the specifications of the input fields for which values ​​are to be generated. The receiving unit 11a also receives values ​​from the application service 40 to be set in the specified input fields.

[0061] The display control unit 12 interprets screen information from various screens and displays it on the display 506. The operation reception unit 13 receives various user operations on the various screens displayed on the display 506.

[0062] The input processing unit 14 inputs values ​​corresponding to the input items transmitted from the application service 40 into the input fields of the input items. The display control unit 12 displays a screen in which values ​​have been set for the input items. The input processing unit 14 operates by executing the transmission program from the application service 40 in a web browser.

[0063] <<Application Services>> The application service 40 includes a communication unit 41, a screen generation unit 42, a registration unit 43, a specification unit 44, a program transmission unit 45, a message communication unit 46, and an application information storage unit 49. Each functional unit of the application service 40 is a function or means realized by the CPU 501 shown in Figure 6 executing instructions contained in one or more programs installed in the application service 40. The application information storage unit 49 is built on the HD 504 or RAM 503 shown in Figure 6. The application information storage unit 49 does not necessarily have to be present in the application service 40; it only needs to be on a network that the application service 40 can access.

[0064] The communication unit 41 sends and receives various information with the user terminal 10. The communication unit 41 has a receiving unit 41a and a transmitting unit 41b. The receiving unit 41a receives values ​​entered into input fields and specifications for input fields to generate values ​​from the user terminal 10. The transmitting unit 41b transmits the values ​​of the specified input fields to the user terminal 10. The transmitting unit 41b also transmits to the user terminal 10 the web application executed by the user terminal 10 and screen information for display by the web application.

[0065] The screen generation unit 42 generates screen information for the screen displayed by the user terminal 10. The screen information is a program written in HTML, JSON, XML, a scripting language, and CSS (Cascading Style Sheet), and may be called a web application. The structure of the web page is mainly specified by HTML, the operation of the web application is defined by the scripting language, and the style of the web page is specified by CSS. In some cases, the user terminal 10 may run a native application. A native application is an application that cannot be run unless it is installed on the user terminal 10. In the case of a native application, the user terminal 10 holds the screen configuration, and the information to be displayed is sent in JSON, XML, etc.

[0066] The registration unit 43 manages application information for each application in the application information storage unit 49. The registration unit 43 registers values ​​corresponding to input items transmitted from the user terminal 10 (or the generation AI system 50) in the application information storage unit 49. The application information includes information set in the application's input items and information about the input items that the application has. Therefore, the application information storage unit 49 stores information set in the application's input items and information about the input items (see Figures 8 and 9).

[0067] The identification unit 44 includes an item identification unit 44a and an application identification unit 44b. The item identification unit 44a identifies the input items of an application based on information identifying the application received along with the AI ​​input request. The application identification unit 44b identifies the application name of an application based on information identifying the application selected by the user.

[0068] The program transmission unit 45 transmits a program to the user terminal 10 in response to a program request sent from the user terminal 10. This program is a web application, and furthermore, it is a component of the web application, such as JavaScript (registered trademark).

[0069] The message communication unit 46 sends and receives messages with the generation AI system 50. The generation AI system 50 exposes an API, and the message communication unit 46 sends a request message containing a chat message to the generation AI system 50 by calling the API. The message communication unit 46 receives a response message from the generation AI system 50. Thus, the request message is information that includes a chat message, but it is a general term for HTTP communication, and sometimes the chat message is referred to as the request message.

[0070] The message communication unit 46 includes a request generation unit 46a, a request transmission unit 46b, and a response receiving unit 46c. The request generation unit 46a generates a request message that calls an API exposed by the generation AI system 50. The request message requests the generation AI system 50 to generate information. The request message may include a text portion called a prompt and image data (which may be the image data itself or a URL). The request message may also include other data such as audio data.

[0071] The request transmission unit 46b sends a request to the generation AI system 50 that includes a list of input items, entered values, the application name, the input items for which values ​​are to be generated, and instructions to generate values ​​corresponding to the specified input items. This request is included in the request message generated by the request generation unit 46a.

[0072] The response receiving unit 46c receives a response message generated by the generating AI system 50 in response to the instruction sent to the generating AI system 50. This response message contains a value corresponding to the specified input item.

[0073] <App Information Storage Unit> Figure 8 shows an example of information set in the input fields of an application. This information includes both information manually set by the user and information generated by the AI ​​generation system 50. Figure 8 uses a business trip report application as an example to illustrate the information set in the application's input fields. The information set in the input fields is managed on a record basis. Each record is identified by an ID. In the case of the business trip report application, the information set in the input fields is referred to as business trip information. Business trip information has values ​​for traveler, travelDate, destination, purpose, result, and dailyReport. Note that traveler, travelDate, destination, purpose, result, and dailyReport correspond to the input fields and are the same as the name field in Figure 9.

[0074] Figure 9 shows an example of information related to application input fields, which is part of the application information. The information related to input fields defines what kind of information is stored in each input field.

[0075] The `name` field is the identifier for the input field that application service 40 uses to manage and identify the input field.

[0076] The `label` field is the name (so-called label) of the input field displayed on the input screen 210 of the business trip report application.

[0077] The `type` field specifies the data format of the input field.

[0078] The `constraints` field defines conditions for the values ​​of input fields. For example, if the input field for `label` is "Daily Report," the condition is set that the maximum number of characters (`maxLength`) is 200.

[0079] <Action or process> The overall flow of processing performed by the information processing system 100 will be explained with reference to Figure 10. Figure 10 is a sequence diagram illustrating the processing of the information processing system 100. The business trip reporting application has already been registered in the application service 40.

[0080] S1: The user terminal 10 displays the input screen 210 of the business trip report application. If the input screen 210 of the business trip report application is implemented by a web application, the transmission unit 11b sends a request to the application service 40 for one or more programs to be executed on the user terminal 10. The program transmission unit 45 of the application service 40 sends the web application to the user terminal 10. The web application includes a program. The program is a screen that accepts input values ​​from the user into input fields, and displays a screen that can accept instructions to generate information to be entered into specified input fields from a list of input items and entered values. When instructions are received on the screen, the program sends a request to the application service 40 that includes instructions to generate a value corresponding to the specified input field from the list of input items and entered values. The application service 40 receives the value corresponding to the specified input field obtained by sending a request to the generation AI system 50, inputs (displays) the received value into the input field of the specified input field, and sends the value entered into the input field to the application service 40 for management. The above instruction, "to generate information to be entered into the input field from the list of input items and the entered values," can be rephrased as an instruction to automatically enter information into the input field.

[0081] The user is currently entering relatively easy-to-enter information such as the date on the input screen 210 of the business trip report application. For input items where input assistance would be preferable, such as the daily report section 216, the user presses the "AI Input" button 228 to start AI input. The operation reception unit 13 of the user terminal 10 receives this operation. AI input is a series of processes that analyze information about the application to generate values ​​for specified input items and request that these be sent to the user terminal 10.

[0082] S2: In response to this operation, the transmission unit 11b of the user terminal 10 sends the application identification information, the currently displayed record ID (information that identifies the record), the values ​​currently entered in the input fields, and the input fields for which values ​​are to be generated to the application service 40. Along with these transmissions, the transmission unit 11b requests AI input from the application service 40. The values ​​already entered in the input fields are the values ​​of input fields for which values ​​have already been set. In this embodiment, the input fields for which values ​​are to be generated are predetermined, but input fields for which no values ​​have been set may be automatically selected. Note that although the user terminal 10 is shown to hold the values ​​entered by the user in order to create a business trip report, the user terminal 10 may also obtain them from the application service 40. In this case, the user terminal 10 does not need to send the entered values ​​to the application service 40.

[0083] The entered values ​​are not necessarily required. The generating AI system 50 can also generate information that has not been provided. For example, the generating AI system 50 can generate values ​​for input items specified from at least one of the list of input items or the application name. Also, if the transmission unit 11b does not transmit the entered values, the application service 40 can generate more appropriate input item values ​​by using the few-shot prompting described later. Alternatively, if the user does not enter any values ​​in the input items, the application service 40 may switch to using few-shot prompting.

[0084] Currently, the application displayed by user terminal 10 is identified, so the application's identification information is also known. To set a value for an application that user terminal 10 is not displaying, the user selects the application, for example. The displayed record ID is known because it is the identification information for the record currently displayed by user terminal 10. If the displayed record is not registered with application service 40, the record ID is undetermined, so user terminal 10 notifies application service 40 that the record ID is undetermined, and application service 40 assigns a new record ID.

[0085] S3: The receiving unit 41a of the application service 40 receives an AI input request, and the item identification unit 44a uses the application information storage unit 49 to identify information about the input items of the application identified by the application identification information, and obtains a list of input items. More specifically, since the label item is appropriate as an input item to be used by the generating AI system 50, the item identification unit 44a receives a list of label items.

[0086] Furthermore, the application identification unit 44b obtains the application name of the application identified by the application identification information from the application information storage unit 49. The reason for requesting the application name is that the accuracy of the generation AI system 50 in generating appropriate values ​​for the input items is improved by analyzing the application name. Therefore, the application name is not required. Alternatively, the application service 40 may send an application description document to the generation AI system 50 instead of the application name. An application description document might be, for example, "This application is an application that assists in creating business trip reports."

[0087] The request generation unit 46a of the application service 40 generates a request message using information about the application (list of input items, entered values, application name) and input items for which values ​​are to be generated. This request message includes instructions for generating information corresponding to the input items for which values ​​are to be generated. An example of this request message is shown in Figure 11.

[0088] S4: The request transmission unit 46b sends a request message along with a request to generate values ​​for the specified input items to the generation AI system 50.

[0089] S5: The generation AI system 50 analyzes the list of input items, entered values, and application name to generate values ​​for the specified input items. The generation AI system 50 sends a response message (the value of the specified input item) to the application service 40.

[0090] S5-2: The response receiving unit 46c of the application service 40 receives a response message (the value of the specified input item). Upon receipt, the registration unit 43 of the application service 40 may register the generated value in the application information storage unit 49. If the registration unit 43 registers the generated value in the application information storage unit 49, no further processing is required. Even if the user modifies the generated value, it can be overwritten. In this embodiment, the case in step S10, after the user has confirmed the generated value, where the generated value is registered in the input item will be described.

[0091] S6: The transmission unit 41b of the application service 40 sends the value of the specified input item to the user terminal 10. The receiving unit 11a of the user terminal 10 receives the value of the specified input item. Note that the transmission unit 41b of the application service 40 may not only send the value of the specified input item, but also send screen information to the user terminal 10 to update the input screen 210 of the business trip report application.

[0092] S7: The input processing unit 14 of the user terminal 10 inputs the received value into the input field of the specified input item. The display control unit 12 displays the input screen 210 of the business trip report application with the values ​​set in the specified input item.

[0093] S8: The user views the input screen 210 of the business trip report application and checks the values ​​of the input items generated by the generation AI system 50. If there are any deficiencies in the text (generated values) or if otherwise necessary, the user edits the text on the input screen 210. To save the values ​​of each input item on the input screen 210 of the business trip report application, the user performs a save operation (presses a button 229 such as a registration button) on the user terminal 10. The operation reception unit 13 accepts the operation.

[0094] S9: The user terminal 10's transmission unit 11b sends a save request to the application service 40, specifying the application's identification information and record ID, along with the values ​​of the input items (the entered values ​​and the generated values). If the entered values ​​have already been sent, resending is not necessary.

[0095] S10: The receiving unit 41a of the application service 40 receives these, and the registration unit 43 identifies the application using the application identification information and identifies the record using the record ID. The registration unit 43 associates the values ​​with the input fields of the identified record and saves them (registers) in the application information storage unit 49. The transmitting unit 41b of the application service 40 sends an input OK (value registration is complete) message to the user terminal 10. The receiving unit 11a of the user terminal 10 receives the input OK message.

[0096] <Example of a request message from an application service to a generation AI system> Figure 11 shows the parameters included in the request message that the application service 40 sends to the generation AI system 50 in step S4 of Figure 10.

[0097] • messages241 is the API for the generation AI system 50, and the following indicates that it is a chat message.

[0098] Role242 is an API for the Generating AI System 50 and is a classification of the requester of a request message. It includes user, assistant (AI of the Generating AI System 50), and system (instruction for configuration by the AI ​​assistant).

[0099] • content243 is the API for the generation AI system 50, and it contains the dialogue text. Since content is an array, it can also specify a prompt and multiple image data. In Figure 11, three parameters 244-246 are described in JSON format. Two of these are files.

[0100] Parameters 244-246 are the format of the information to be sent to the generating AI system 50. "type" defines the data type. If "type" is "text", the value of "text" is "prompt" 249. A prompt is set in "prompt" 249. An example of a template prompt set in "prompt" 249 is shown in Figure 12. If "type" is "file_url", the value of "file_url" is "file"247,248, where "file"247,248 contains either the URL where the image data is stored or the Base64 encoded image. Note that if the application has only one input field for image data, then only one value each of parameters 244 and 245 is needed.

[0101] As shown in Figure 11, a request message combining the prompt and file is sent to the generation AI system 50. Note that the file is not required in this embodiment.

[0102] Figure 12 is a diagram illustrating the prompt set in "Prompt" 249 in Figure 11. The string in Figure 12 is a template for the request generation unit 46a to generate the prompt. The string has five ${...}. When a request message is sent, ${appName}251, ${labels.join()}252, ${labels.length}253, ${currentValue}254, and ${targetLabel}255 are set as input fields that generate information and values ​​related to the application. That is, the five ${...} are replaced with input fields that generate information and values ​​related to the application. The other strings are boilerplate text and are held in advance by the request generation unit 46a.

[0103] • ${appName}251 will be set to the app name. The app name is optional, or it can be a description of the application (that explains what the app is about).

[0104] The variable ${labels.join()}252 will contain a list of input fields.

[0105] The value ${labels.length}253 is set to the number of input fields.

[0106] The value entered in the input field will be set to ${currentValue}254.

[0107] The variable ${targetLabel}255 is set to the input field from which you want to generate a value (for example, one of the name fields). A specific example of this setting is explained in Figure 15.

[0108] <Example of a response message from a generating AI system to an application service> Figure 13 shows the format of the response message sent from the generating AI system 50 to the application service 40 in step S5 of Figure 10. In other words, Figure 13 is the format, not the response message itself.

[0109] Messages256 indicates that the following is the response message.

[0110] • Role 257 is the classification of the sender that sends the response message, and in this case it is assistant (AI of Generating AI System 50).

[0111] • content258 is the content of the response message. Here, content258 is response 259 (input items and values) from the generating AI system 50. Details of the response message from the generating AI system 50 are explained in Figure 16.

[0112] <Example of setting values ​​for input fields> The following sections will explain how to set values ​​for input fields, using a business trip reporting app and a nursery newsletter creation app as examples.

[0113] <<Example of daily report settings for the business trip reporting app>> Referring to Figure 14, etc., we will explain an example of setting values ​​for the input fields of the business trip report application. Figure 14 is the input screen 210 of the business trip report application as displayed on the user terminal 10. The explanation of Figure 14 will mainly focus on the differences from Figure 2. In the input screen 210 of the business trip report application, the daily report field 216 is a specific input field that accepts text input.

[0114] In Figure 14, the user entered values ​​in the Traveler field 211, Travel Date field 212, Destination field 213, Purpose field 214, and Result field 215. At this point, the goal was to have the AI ​​system 50 generate the values ​​for the Daily Report field 216. Therefore, the user pressed the "AI Input" button 228. The Daily Report field 216 is an input field that the user can manually enter even without input from the AI ​​system 50. The "AI Input" button 228 may become active (pressable) when a value is entered in one or more of the predetermined input fields in the business trip report application. The "AI Input" button 228 is a display component that accepts instructions to create text.

[0115] This section describes information regarding the business trip reporting application. First, the application name for the business trip reporting application is "Business Trip Reporting Application". Next, according to the information regarding input items in Figure 9, the list of input items (label items) is: Traveler, Business Trip Date, Destination, Purpose, Result, and Daily Report. Of these, values ​​have already been entered for Traveler, Business Trip Date, Destination, Purpose, and Result. Therefore, the input item for which we want to generate a value is "Daily Report". In this embodiment, it is assumed that it has been decided in advance to generate a value for "Daily Report". The request generation unit 46a uses this information to set the application name, the list of input items, the values ​​already entered for the input items, and the input item for which to generate a value as prompts in Figure 12.

[0116] Figure 15 shows the prompt generated by the request generation unit 46a. The following information is set in ${appName}251, ${labels.join()}252, ${labels.length}253, ${currentValue}254, and ${targetLabel}255 shown in Figure 12.

[0117] • ${appName}251 is set to "Business Trip Report App" 261.

[0118] • ${labels.join()}252 is set to "Traveler, Travel Date, Destination, Purpose, Result, Daily Report"262. In other words, the label field is set for information related to the input items. The name field is not set because the name field is usually identification information, and often contains information unrelated to the label.

[0119] • ${labels.length}253 is set to "6"263.

[0120] The entry ${currentValue}254 contains "{"Traveler":"Taro Patent","Travel Date":"2024 / 07 / 22","Destination":"〇× Dairy △ Factory","Purpose":"Meeting to discuss a factory tour.","Result":"The factory tour date was set for 10 / 13.","Daily Report":""}"264. In other words, input fields with values ​​entered are associated with those values. Input fields that do not have values ​​entered, such as "Daily Report," are associated with a blank "" field.

[0121] • ${targetLabel}255 is set to "Daily Report" 265. The input fields to be set in ${targetLabel}255 are predetermined. Alternatively, the request generation unit 46a may determine which input fields do not have values ​​entered and set those input fields in ${targetLabel}255. If there are two or more existing input fields that do not have values ​​entered, two or more input fields may be set in ${targetLabel}255.

[0122] The generating AI system 50 recognizes that the target is the business trip report app from the prompt's opening phrase, "business trip report app" 261. Next, the generating AI system 50 recognizes the input fields of the business trip report app from "traveler, business trip date, destination, purpose, result, daily report" 262. Next, the generating AI system 50 recognizes the values ​​already entered in the input fields. Next, the generating AI system 50 recognizes the request to "generate text to be entered into the daily report" and generates text to be entered into the "daily report" using the values ​​already entered in the input fields.

[0123] Figure 16 shows the response message from the generation AI system 50 to the request message in Figure 15. The generation AI system 50 analyzes the request message in Figure 15 and generates values ​​to be set in the "daily report". As an example, the generation AI system 50 generated the message: "Today, we had a meeting at the ○× Dairy △ Factory to discuss a factory tour. As a result of the discussion, the date for the factory tour was decided to be October 13th." Comparing this with the input values, it can be seen that the destination, purpose, and result are included in the response message.

[0124] The application service 40 uses the response message shown in Figure 16 to send the values ​​to be displayed in the business trip report application to the user terminal 10.

[0125] Although not shown in Figure 16, the response message may include information identifying the application that received the user's selection. This application identification information may be, for example, the application name. The application identification unit 44b identifies the application based on the application identification information. The item identification unit 44a then identifies the input item corresponding to this identified application (see Figure 9).

[0126] Figure 17 shows the input screen 210 of the business trip report application with the generated value set in the daily report section 216 of the business trip report application. The input processing unit 16 inputs the value corresponding to the input item into the input field of the corresponding input item. In other words, the text generated by the generation AI system 50, as shown in Figure 16, is set in the daily report section 216.

[0127] Furthermore, the values ​​created by the generation AI system 50, which are entered into the input fields by the input processing unit 16, can be edited manually by the user. In addition, the user can register the values ​​(text) set in the input fields into the application by pressing the registration button 229 on the input screen 210 of the business trip report application.

[0128] In this way, by entering relatively easy-to-enter values ​​for the standardized input fields of the business trip report app, users can automatically set values ​​for predetermined input fields that would otherwise take more time to input. The user terminal 10 can set appropriate values ​​for input fields of any application, not just the business trip report app.

[0129] Alternatively, the user may request the application service 40 to generate values ​​for the Traveler field 211, Travel Date field 212, Destination field 213, Purpose field 214, and Result field 215, even if only the user has entered a value in the Daily Report field 216. In this case, if the Daily Report field 216 contains this information, it can be expected that appropriate values ​​will be generated for each input field. Furthermore, in this case, the Traveler field 211, Travel Date field 212, Destination field 213, Purpose field 214, and Result field 215 are specific input fields that accept text input.

[0130] <<Example of newsletter text settings in the newsletter creation app>> Next, referring to Figure 18, etc., we will explain an example of setting values ​​for the input fields of the newsletter creation app. Figure 18 is the input screen 270 of the newsletter creation app displayed on the user terminal 10. This newsletter creation app has a date field 271, an event field 272, a short memo field 273, a newsletter text field 274, a photo attachment field 275, and an "AI Input" button 276. Except for the "AI Input" button 276, these are input fields. In the input screen 270 of the newsletter creation app, the newsletter text field 274 is a specific input field that accepts text input.

[0131] Users can use the nursery newsletter creation app for both work and personal purposes. For example, a nursery school staff member can use the app to create a newsletter to send to parents. This makes it easier to create newsletters for parents.

[0132] To set a value in the newsletter text field 274 using the generation AI system 50, for example, the user entered information in the date field 271, event field 272, short memo field 273, and photo attachment field 275. The photo attachment field 275 displays a thumbnail of image data of the children taken as photos. In this state, we wanted the generation AI system 50 to generate the value that the user would enter in the newsletter text field 274. Therefore, the user presses the "AI Input" button 276. The "AI Input" button 276 may become active (pressable) only when a value has been entered in one or more of the predetermined input fields of the newsletter creation application.

[0133] Figure 19A shows information regarding the input fields of the newsletter creation app. Similar to the information regarding the input fields of the business trip report app (Figure 9), the information regarding the input fields of the newsletter creation app includes the fields name, label, type, and constraints. These can be the same as in Figure 9.

[0134] Figure 19B shows the information set in the input fields of the nursery newsletter creation application. Figure 19B shows the information for one record. In the case of the nursery newsletter creation application, the information for one record set in the input fields is called the nursery newsletter information. The nursery newsletter information is represented by associating a name field with a value field. The name field (date, event, memo, photo, newsletter) is the identifier information for the input field, and the value field is its value.

[0135] This section describes information about the application for the nursery newsletter creation app. The name of the nursery newsletter creation app is "Nursery Newsletter Creation App". Next, according to the information about the input items in Figure 19A, the labels of the input items are Date, Event, Short Memo, Photo Attachment Field, and Nursery Newsletter Text. Therefore, there are 5 input items. Of these, values ​​have already been entered for Date, Event, Short Memo, and Photo Attachment Field. The input item for which we want to generate a value is "Nursery Newsletter Text". The request generation unit 46a uses this information to set the application name, a list of input items, the input items and their values, and the input item for which to generate a value as prompts in Figure 12. Also, since the image data set in the photo attachment field is a file, the image data set in the photo attachment field is set in parameter 244 in Figure 11.

[0136] Figure 20 shows the prompt generated by the request generation unit 46a. The following information is set in ${appName}251, ${labels.join()}252, ${labels.length}253, ${currentValue}254, and ${targetLabel}255 shown in Figure 12.

[0137] • ${appName}251 is set to "School Newsletter Creation App" 281.

[0138] • ${labels.join()}252 is set to "Date, Event, Short Memo, Photo Attachment Field, Newsletter Text"282. In other words, the label field is set for information related to the input field. The name field is not set because the name field is usually for identification information, and often contains information unrelated to the label.

[0139] • ${labels.length}253 is set to "5" (283).

[0140] The value ${currentValue}254 is set to "{"Date":"2024 / 07 / 05","Event":"Mud Play","Short Memo":"The children had fun getting their clothes covered in mud","Photo Attachment":"001.jpeg","Newsletter Text":""}"284. In other words, input fields with values ​​already entered are associated with those values. Input fields that do not already have values ​​entered, such as "Newsletter Text," are associated with a blank "".

[0141] Regarding the photo attachment field, a file name is set, but this alone may not be enough for the generating AI system 50 to analyze the image data in the photo attachment field and generate the "newsletter text". Therefore, it would be good if the prompt in Figure 20 included a sentence such as, "Please recognize the image named 001.jpeg and generate the text to be entered into the 'newsletter text'." Since the generating AI system 50 can generate text data from the objects contained in the image data, it can reliably reflect the image data in the "newsletter text".

[0142] • ${targetLabel}255 is set to "Newsletter Text" 285. The input items to be set in ${targetLabel}255 are predetermined. Alternatively, the request generation unit 46a may determine which input items do not have values ​​entered and set those input items in ${targetLabel}255. If there are two or more existing input items that do not have values ​​entered, two or more input items may be set in ${targetLabel}255.

[0143] The generating AI system 50 understands that the target is a nursery school newsletter creation app from the prompt beginning with "nursery school newsletter creation app" 281. Next, the generating AI system 50 understands the input fields that the nursery school newsletter creation app has from "date, event, short memo, photo attachment field, nursery school newsletter text" 282. Next, the generating AI system 50 understands the values ​​that have already been entered into the input fields. Next, the generating AI system 50 understands the request to "generate text to be entered into the nursery school newsletter text" and generates text to be entered into "nursery school newsletter text" using the values ​​that have already been entered into the input fields.

[0144] Figure 21 shows the response message from the generating AI system 50 to the request message in Figure 20. The generating AI system 50 analyzes the request message in Figure 20 and generates values ​​to be set in the "Nursery School Newsletter Text". As an example, the generating AI system 50 generated the following: "At the mud play on July 5th, the children were covered in mud but had a great time with big smiles on their faces. They poured water on the mud piles with watering cans and enjoyed playing in the mud in their own ways. Every child's eyes lit up as they were engrossed in playing in the mud, and they felt the joy of interacting with nature through this valuable experience that was different from their usual routine." Comparing this with the input values, it can be seen that the date, event, and a short memo have been incorporated.

[0145] The application service 40 uses the response message shown in Figure 20 to send the value (text) to be set in the newsletter text field 274 of the newsletter creation app to the user terminal 10.

[0146] Figure 22 shows the input screen 270 of the newsletter creation app with the generated value set in the newsletter text field 274. The input processing unit 16 inputs the value corresponding to the input item into the corresponding input field. That is, the text generated by the generation AI system 50, as shown in Figure 21, is set in the newsletter text field 274.

[0147] Furthermore, the values ​​created by the generation AI system 50, which are entered into the input fields by the input processing unit 16, can be edited manually by the user. In addition, the user can register the contents set in the input fields to the application by pressing the registration button 229 on the input screen 270 of the nursery newsletter creation application.

[0148] In this way, users can automatically set values ​​for time-consuming input fields in the newsletter creation app by entering values ​​into the relatively easy-to-use, standardized input fields. Users can set appropriate values ​​for input fields in any application, not just the newsletter creation app.

[0149] Furthermore, the user may request the generation AI system 50 to generate values ​​to be entered in the date field 271, event field 272, and short memo field 273, after entering values ​​in the newsletter text field 274 and the photo attachment field 275. In this case, if the newsletter text field 274 or the photo attachment field 275 contains this information, it can be expected that appropriate values ​​will be generated for each input field. Also, in this case, the date field 271, event field 272, and short memo field 273 are specific input fields that accept text input.

[0150] <Main effects> According to the information processing system 100 of this embodiment, when a user enters a value into one or more input fields, the AI ​​system 50 generates values ​​for input fields that do not have values ​​entered and automatically sets them in the input fields. The user can set appropriate values ​​for input fields of any application, not just one application.

[0151] [Second Embodiment] This embodiment describes a modified version applicable to the first embodiment. In this embodiment, the hardware configuration diagram shown in Figure 6 and the functional block diagram shown in Figure 7, as described in the first embodiment, can be used as references.

[0152] <If the input field that generates the value already has a value> In the first embodiment, it was explained that either the input field for generating a value is predetermined, or an input field that does not have an existing value is automatically determined. In the former case, where the input field for generating a value is predetermined, there may be cases where a value has already been set in that input field. In this case, when the user terminal 10 sends the existing value as a draft to the application service 40, and the application service 40 sends it to the generation AI system 50, the text generated by the generation AI system 50 can be made closer to the text intended by the user.

[0153] The following explains, using a business trip reporting app as an example, how the generation AI system 50 generates text for the daily report field 216 when text has already been entered into the daily report field 216.

[0154] Figure 23 shows the input screen 210 of the business trip report application displayed on the user terminal 10. The explanation of Figure 23 mainly focuses on the differences from Figure 14. In Figure 23, the user has entered values ​​in the Traveler field 211, Business Trip Date field 212, Destination field 213, Purpose field 214, Result field 215, and Daily Report field 216. At this point, the user wanted to further enhance the text to be set in the Daily Report field 216. Therefore, the user presses the "AI Input" button 228.

[0155] In this embodiment, it is predetermined that the request generation unit 46a will generate the value for the daily report column 216. Similar to the first embodiment, the request generation unit 46a generates a prompt that specifies information about the application and the input items for which to generate a value.

[0156] Figure 24 shows the prompt generated by the request generation unit 46a. Figure 24 mainly explains the differences from Figure 15. In Figure 24, the information set in ${currentValue}254 is different from that in Figure 15.

[0157] · ${currentValue}254 has the following entry set: "{"Traveler":"Taro Patent","Travel Date":"2024 / 07 / 22","Destination":"〇× Dairy △ Factory","Purpose":"Meeting to discuss a factory tour.","Result":"The date for the factory tour has been set to 10 / 13.","Daily Report":"I had a meeting with Mr. Yamada from 〇× Dairy to discuss a factory tour. The date for the factory tour has been set to 10 / 13."}"266. In other words, a draft entry 268, "I had a meeting with Mr. Yamada from 〇× Dairy to discuss a factory tour. The date for the factory tour has been set to 10 / 13." has been added to correspond to the "Daily Report".

[0158] Additionally, the prompt in Figure 24 has the text data 267 added, which reads, "The value currently entered in the 'Daily Report' is a draft." The request generation unit 46a determines that the daily report field 216 is not blank, and adds the text entered in the daily report field 216 as text data 267 to the prompt.

[0159] The generation AI system 50 determines from the text data 267 that the draft 268 can serve as a reference for the value to be generated for the daily report field 216, and uses the above draft 268 to generate the value, making it easier to generate the text intended by the user. In this case, the draft initially entered in the daily report field 216 is overwritten by the input processing unit 16, and the text generated by the generation AI system 50 is entered into the daily report field 216. <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, the application service 40 notifies the generation AI system 50 of a draft for the input items that generate values, making it easier to generate text that the user intended.

[0160] <Additional instructions for generating values> In this embodiment, the information processing system 100 allows the generation AI system 50 to generate values ​​for input items without the user having to input a prompt. However, the user can also input a prompt. This allows the values ​​of the input items generated by the generation AI system 50 to more closely resemble the user's intended text.

[0161] Figure 25 shows the prompt input screen 280 that pops up on the input screen 210 of the business trip report app. The input screen 210 of the business trip report app is displayed when the user presses the "AI Input" button 228.

[0162] The prompt input screen 280 has a message 286 that reads, "Executing AI input. Please enter any additional instructions," and a prompt input field 287. If the user has instructions for the generation AI system 50 via the application service 40 regarding the values ​​to be entered in the daily report field 216, the user can enter the instructions in the prompt input field 287. In Figure 25, the instruction "Please generate using child-friendly language" has been entered. This instruction becomes part of the prompt included in the request message. When the user presses the OK button 288, the request message is generated.

[0163] Figure 26 shows the prompt in the request message generated by the request generation unit 46a. Figure 26 mainly explains the differences from Figure 15. The request message in Figure 26 has the text data 285 "Please generate it using child-friendly language" added to it. When the content of an instruction is entered in the prompt input field 282, the request generation unit 46a adds the content of the instruction as text data 285 to the prompt.

[0164] The AI ​​generation system 50 generates values ​​to be set in the daily report section 216 by referring to the text data 285, making it easier to generate sentences that the user intends.

[0165] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, the user can input instructions for the generation AI system 50 when generating values, making it easier to generate sentences that the user intends.

[0166] <Confirmation dialog and regeneration> As a user, there may be times when you are not satisfied with the text generated by the generation AI system 50 and want to restart the generation process. To address this situation, it is effective to display a confirmation dialog before the user terminal 10 sets the values ​​generated by the generation AI system 50 to the application service 40, allowing the user to confirm the text generated by the generation AI system 50. This allows the generation process to be repeated until the text the user desires is produced.

[0167] Figure 27 shows a confirmation dialog 290 that pops up on the input screen 210 of the business trip report application. The confirmation dialog 290 appears immediately after step S9 in the sequence diagram of Figure 10 (before the input field is set).

[0168] The confirmation dialog 290 includes a message 291 that reads, "The daily report text has been generated. Do you want to enter this content?", a generated text display field 292, a regenerate button 293, and an input permission button 294. The generated text display field 292 displays the text generated by the generation AI system 50. If the user is not satisfied with the text generated by the generation AI system 50, they press the regenerate button 293.

[0169] As a result, in the sequence diagram of Figure 10, steps S2 onwards are executed again, allowing the generation AI system 50 to regenerate the text to be entered into the daily report field 216. The user can repeat the generation process until the desired text is generated.

[0170] Furthermore, if steps S2 and beyond are executed again, the request generation unit 46a may prompt the system to generate a different sentence along with the sentences generated immediately before and in the past. This ensures that the generation AI system 50 generates a different sentence each time it generates one. Additionally, when the user presses the regenerate button 293, the user terminal 10 should display the prompt input screen 280 shown in Figure 25. This allows the user to specify how they want to improve the sentence generated by the generation AI system 50 each time.

[0171] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, regeneration is possible, so the user can repeat the generation process until the desired text is generated.

[0172] <Instructions for the reference form> In the first embodiment, the request generation unit 46a includes the values ​​of all input items for which values ​​have been entered in the prompt. However, the user may be able to select the values ​​of the input items that the request generation unit 46a sends to the generation AI system 50. This is because the values ​​of input items already entered by the user may contain information that is noisy for the input items for which a value is to be generated. Therefore, by allowing the user to select the values ​​of the input items that the request generation unit 46a sends to the generation AI system 50, it is possible to eliminate noisy information when generating a value from the prompt sent to the generation AI system 50. This makes it easier for the generation AI system 50 to generate the text intended by the user.

[0173] Figure 28 shows the input item selection dialog 300 that pops up on the input screen 210 of the business trip report application. The input item selection dialog 300 appears when the "AI input button" 228 is pressed.

[0174] The input item selection dialog 300 has a message 301 that reads, "Please select the form to be used as input for generating the daily report text," a list of options 302, and an input button 303. The list of options 302 displays labels for the input items on the input screen 210 of the business trip report application. Each label has a checkbox, and the user selects the input items for which they want to send the entered values ​​to the generation AI system 50. When the user presses the input button 303, the request generation unit 46a generates a request message using only the values ​​of the checked input items.

[0175] Figure 29 shows the prompt generated by the request generation unit 46a. Figure 29 mainly explains the differences from Figure 15. In the request message of Figure 29, the following information is set in ${appName}251, ${labels.join()}252, ${labels.length}253, ${currentValue}254, and ${targetLabel}255, as shown in Figure 12.

[0176] • ${appName}251 is set to "Business Trip Report App" 261.

[0177] • ${labels.join()}252 has "Business Trip Date, Destination, Purpose, Results, Daily Report"262 set. In other words, "Business Traveler" is missing. This is because "Business Traveler" is not selected in the selection list 302. The reason why "Daily Report," which is also not selected in the selection list 302, exists is that it is an input item for which a value is to be generated, and therefore the existence of this input item needs to be notified to the generation AI system 50.

[0178] • ${labels.length}253 is set to "5"263. In other words, it's one less because "Business Traveler" is missing.

[0179] • ${currentValue}254 contains "{"Date of trip":"2024 / 07 / 22","Destination":"〇× Dairy △ Factory","Purpose":"Meeting to discuss a factory tour." ","Result":"The date for the factory tour was set for 10 / 13." "}"264. In other words, "Traveler" and its value, and "Daily Report" and its value (blank) do not exist. This is because they were not selected in the selection list 302. The reason why "Daily Report" and its value (blank) are not included in ${currentValue}254 is because the existence of the input item "Daily Report" has already been notified in "Date of trip, Destination, Purpose, Result, Daily Report"262.

[0180] ${targetLabel}255 can be the same as in Figure 15.

[0181] Although the prompt does not include the traveler's name, the traveler's name is rarely included in the "daily report," so this could become noise when generating the "daily report" value. In this embodiment, the user chooses not to send the "traveler" value to the generation AI system 50 via the application service 40, thus eliminating the "traveler" value that would be noise when generating the value from the prompt sent to the generation AI system 50. Therefore, the generation AI system 50 is able to more easily generate the text intended by the user.

[0182] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, the user can select pre-entered values ​​to send to the generation AI system 50, making it easier to generate text intended by the user.

[0183] <Request message specifying the range of values ​​to be entered> Some application input fields may have input ranges. For example, input fields that use strings as data may have a maximum and minimum number of characters. Input fields that use numbers may have a maximum and minimum value.

[0184] In Figure 9, the information about the input fields shows that the `constraints` field defines conditions for the values ​​of the input fields. For example, for the input field `label`, which is "Daily Report," a condition (input range) is set where the maximum number of characters (`maxLength`) is 200.

[0185] When generating a prompt, the request generation unit 46a also sends information about the input range to the generation AI system 50. This prevents the value generated by the generation AI system 50 from being outside the application's input range.

[0186] Figure 30 shows the prompt generated by the request generation unit 46a. Figure 30 mainly explains the differences from Figure 15. The prompt in Figure 30 has the text data 311 "Please generate within 200 characters." added to it. The "200" in this text is changed by the constraints item in the information about the input items in Figure 9.

[0187] In other words, as shown below, ${……} is set in the string in Figure 12 to correspond to the maximum number of characters. "Please generate it within ${maxLength} characters." The request generation unit 46a replaces ${maxLength} with "200". Therefore, all text data in 311 except for "200" is standard text.

[0188] The generation AI system 50 analyzes the above text data 311 of the request message and generates values ​​so that the values ​​to be generated for the "daily report" do not fall outside the input range.

[0189] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, by specifying an input range, the generation AI system 50 can generate values ​​that do not fall outside the input range.

[0190] <Generating values ​​from multiple forms> The request generation unit 46a can request the generation AI system 50 to generate values ​​for multiple input items with a single request message. This speeds up processing compared to generating multiple request messages and requesting the generation AI system 50 to generate values ​​for each input item each time. In addition, the number of calls to the generation AI system 50 is reduced, which also reduces the usage fees for the generation AI system 50.

[0191] Figure 31 shows the input screen 320 of the newsletter creation application displayed on the user terminal 10. The explanation of Figure 31 mainly describes the differences from Figure 18. The date field 271, event field 272, short memo field 273, photo attachment field 275, and the "AI Input" button 276 are the same as in Figure 18. The input screen 320 of the newsletter creation application in Figure 31 further has input fields for newsletters for parents 321 and newsletters for children 322. When the user presses the "AI Input" button 276, a target selection dialog 330 is displayed.

[0192] Figure 32 shows the generation target selection dialog 330 that pops up on the input screen 320 of the nursery newsletter creation application. The generation target selection dialog 330 has a message 331 that says, "Please select the input items for which you want to generate text," a list of options 332, and an OK button 333. The list of options 332 displays labels for the input items on the input screen 320 of the nursery newsletter creation application. Each label has a checkbox, and the user selects the input items for which they want the generation AI system 50 to generate a value. When the user presses the OK button 333, the request generation unit 46a generates a request message.

[0193] Note that in Figure 32, the input items that generate values ​​when the "AI Input" button 276 is pressed are selected, but the input items that generate values ​​may be predetermined. Alternatively, the user may select them in advance on the settings screen.

[0194] Figure 33 shows the prompt generated by the request generation unit 46a. The explanation of Figure 33 mainly describes the differences from Figure 20. In the prompt of Figure 33, the following information is set in ${appName}251, ${labels.join()}252, ${labels.length}253, ${currentValue}254, and ${targetLabel}255, as shown in Figure 12.

[0195] The same applies to ${appName}251 as shown in Figure 20.

[0196] The labels ${labels.join()}252 has "Date, Event, Short Memo, Photo Attachment Field, Parent-Oriented Newsletter Text, and Child-Oriented Newsletter Text" 282 set. Of these, "Parent-Oriented Newsletter Text and Child-Oriented Newsletter Text" 341 notifies the generating AI system 50 that the newsletter creation app has input fields 321 for parent-oriented newsletters and 322 for child-oriented newsletters.

[0197] • ${labels.length}253 is set to "6" (283).

[0198] · ${currentValue}254 is set to "{"Date":"2024 / 07 / 05","Event":"Mud Play","One-line Memo":"The children had fun getting their clothes covered in mud","Photo Attachment":"001.jpeg","Message for Parents":"","Message for Children":""}" 284. Of these, ""Message for Parents":"","Message for Children":"" 342 notifies the generating AI system 50 of the value (blank) of the input field 321 for the parent newsletter and the value (blank) of the input field 322 for the child newsletter.

[0199] The labels ${targetLabel}255 are set to "Text for the nursery newsletter for parents" and "Text for the nursery newsletter for children" 343. In other words, ${targetLabel}255 instructs the generation AI system 50 to generate text to be set in the nursery newsletter input field 321 for parents and the nursery newsletter input field 322 for children.

[0200] The prompt in Figure 33 has a format specification 344. Since the generation AI system 50 generates multiple sentences in response to the prompt in Figure 33, there may be multiple response messages. For this reason, the format specification 344 instructs the generation AI system 50 to generate values ​​in JSON format. This is expected to result in a response message that clearly shows the correspondence between the input items and the generated sentences.

[0201] Figure 34 shows the response message from the generating AI system 50 to the request message in Figure 33. The response message contains "text of the nursery school newsletter for parents" 351 and "text of the nursery school newsletter for children" 352 in JSON format. In other words, the generating AI system 50 analyzed the request message in Figure 33 and generated "text of the nursery school newsletter for parents" 351 and "text of the nursery school newsletter for children" 352.

[0202] Comparing the "Newsletter for Parents" (351) and the "Newsletter for Children" (352) with the values ​​already entered for "Date," "Event," and "Short Memo," it can be seen that the date, event, and short memo are included. Furthermore, it can be seen that even though the input values ​​referenced by the generation AI system 50 are the same, the two sentences are different. This is thought to be the effect of "Newsletter for Parents" and "Newsletter for Children" (343).

[0203] The application service 40 uses the response message shown in Figure 34 to send the values ​​to be displayed in the newsletter creation app to the user terminal 10.

[0204] Figure 35 shows the input screen 320 of the newsletter creation app, with the generated values ​​displayed. The input processing unit 16 inputs the values ​​corresponding to the input items into the corresponding input fields. That is, the "newsletter text for parents" 351 and the "newsletter text for children" 352, generated by the generation AI system 50 as shown in Figure 34, are displayed in the parent newsletter input field 321 and the child newsletter input field 322, respectively.

[0205] In this way, by entering values ​​into some of the input fields in the newsletter creation app, users can automatically set values ​​for the remaining selected input fields that have not yet been filled in.

[0206] Furthermore, before the two sentences generated by the generation AI system 50 are displayed on the input screen 320 of the newsletter creation app, the confirmation dialog 290 shown in Figure 27 may be displayed. In this case, it would be good to allow the user to select which sentence to regenerate. Also, when the user presses the regenerate button 293, it would be good to display the prompt input screen 280 shown in Figure 25. This would allow the user to specify how they want to improve each sentence generated by the generation AI system 50.

[0207] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, it is possible to request the generation AI system 50 to generate values ​​for multiple input items with a single request message, thereby speeding up processing and reducing the usage fees for the generation AI system 50.

[0208] <Few-shotプロンプティング> The generation AI system 50 employs a technique called few-shot prompting, which improves the accuracy of value generation by providing several output examples in the prompt. In this embodiment as well, the accuracy of generating values ​​for the input items can be improved by performing few-shot prompting.

[0209] Figure 36 shows a prompt using few-shot prompting. Since few-shot prompting is a technique that includes one or more example outputs in the prompt, the request generation unit 46a includes the information already registered in the application service 40 (Figure 8) in the prompt. Note that Figure 36 mainly explains the differences from Figure 15.

[0210] Message 351 states, "We are providing two past input details in JSON format for reference," and indicates that the following is the information registered in the application.

[0211] Sample 362 is the first input. Sample 362 contains the values ​​for one record of information already registered in the application, linked to the label field, which is information about the input item.

[0212] Sample 363 is the second input. Sample 363 contains the values ​​for one record of information already registered in the application, linked to the label field, which is information about the input field.

[0213] Figure 37 is a sequence diagram illustrating the processing of the information processing system 100 when using few-shot prompting. Figure 37 illustrates the differences from Figure 10. In Figure 31, the processing in steps S3 and S5 differs from that in Figure 10.

[0214] S3: The receiving unit 41a of the application service 40 receives the AI ​​input request. The method for identifying the list of input items and the application name can be the same as in Figure 10. Furthermore, the application identification unit 44b identifies one or more records registered in the application being run by the user terminal 10 (for example, the business trip report application) from the application information identified by the application identification information.

[0215] The request generation unit 46a of the application service 40 generates a request message using information about the application (list of input items, entered values, application name), input items for which values ​​are to be generated, and registered records. This request message includes instructions to extract information corresponding to the specified input items.

[0216] S4: The request transmission unit 46b sends this request message along with a request to generate values ​​for the input items to the generation AI system 50.

[0217] S5: The generation AI system 50 analyzes the list of input items, entered values, application name, and registered records to generate values ​​for the specified input items. The generation AI system 50 sends a response message (the value of the specified input item) to the application service 40.

[0218] The subsequent steps can be the same as in Figure 10.

[0219] By using few-shot prompting, the generation AI system 50 can more easily generate appropriate values ​​for the specified input fields, and it can be expected that it will generate sentences that the user intended.

[0220] <<Main Effects>> According to this embodiment, in addition to the effects of the first embodiment, the generation AI system 50 can more easily generate appropriate values ​​for the specified input items, and it can be expected that the user's intended text will be generated.

[0221] [Other application examples] Although the best mode for carrying out the present invention has been described above using examples, the present invention is not limited in any way to these examples, and various modifications and substitutions can be made without departing from the spirit of the present invention.

[0222] For example, in this embodiment, the application service 40 transmits information about the application to the generation AI system 50, but the information about the application may be stored on a predetermined server. In this case, the application service 40 transmits information to the generation AI system 50 that specifies the information about the application on the server. The generation AI system 50 obtains image data from the server and generates values ​​for the input items.

[0223] Furthermore, in this embodiment, the values ​​of the input items generated by the generation AI system 50 are in JSON format, but the values ​​of the input items may be in other formats such as XML or CSV.

[0224] Furthermore, in this embodiment, the user terminal 10 sets the generated value in the input field of the application managed by the application service 40. However, the user terminal 10 may also set the generated value in the input field of a native application running on its own device. For example, if the user terminal 10 is running a spreadsheet application, it may set the generated value in a cell of the spreadsheet application.

[0225] Furthermore, in this embodiment, the application service 40 requests the generation AI system 50 to generate text, but it may also request the generation of image data. For example, in a nursery newsletter creation application, after the application service 40 has the generation AI system 50 generate the text for the nursery newsletter, it further requests the generation AI system 50 to generate illustrations based on the text for the nursery newsletter. For example, if there is no suitable photo to set in the photo attachment field 275, the user terminal 10 can set an alternative illustration in the photo attachment field 275. In addition, the application service 40 may request the generation AI system 50 to generate music data or video data using pre-entered values.

[0226] Furthermore, the apparatus described in the examples represents only one of several computing environments for carrying out the embodiments disclosed herein. In one embodiment, the application service 40 includes multiple computing devices, such as a server cluster. The multiple computing devices are configured to communicate with each other via any type of communication link, including a network or shared memory, and perform the processing disclosed herein.

[0227] Furthermore, the application service 40 can be configured to share the processing steps disclosed in this embodiment, such as those shown in Figure 10, in various combinations. For example, a process executed by a predetermined unit may be executed by multiple information processing devices of the application service 40. Also, the application service 40 may be consolidated into a single server device or divided among multiple devices.

[0228] Furthermore, the configuration examples in Figure 7 and other figures are divided according to their main functions to facilitate understanding of the processing performed by the application service 40. The present invention is not limited by the way the processing units are divided or their names. The processing of the application service 40 can be further divided into many more processing units depending on the processing content. It can also be divided so that one processing unit contains even more processing.

[0229] Furthermore, each function of the embodiments described above can be realized by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), FPGAs (field programmable gate arrays), and conventional circuit modules designed to execute each of the functions described above.

[0230] Embodiments of the present invention bring about significant improvements in the capabilities and functionality of computers. These improvements enable users to utilize computers that provide more efficient and robust interaction with tables, which are methods for storing and presenting information in information processing devices. 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.

[0231] [Pattern] [Aspect 1] A terminal device, a generation AI system, and an information processing device connected via a network, A screen containing multiple input fields, each accepting user input of data to be entered into multiple items, which are displayed on the terminal device, and which includes at least one specific input field for accepting text input, and a registration unit that registers information entered via the screen, which is capable of accepting operations to create text to be entered into the specific input field. When the aforementioned operation is received from the user, the request transmission unit transmits a request to the generation AI system, which includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and instructions to create a sentence to be entered in the specific input field of the specific item based on the information indicating the one or more items and the data. A response receiving unit that receives the text to be entered into the specific input field from the generating AI system as a response to the aforementioned request, A transmission unit that transmits the text created by the generation AI system based on the above request to the terminal device, An information processing device having [Aspect 2] The system further includes a request generation unit that generates the aforementioned request. The information processing apparatus according to Embodiment 1. [Aspect 3] The transmission unit transmits to the terminal device the text to be entered into the specific input field, which has been generated by the generation AI system, so that the terminal device can display it in the specific input field. The information processing apparatus according to embodiment 1 or 2. [Aspect 4] A receiving unit that receives information identifying the application selected by the user from the aforementioned terminal device, Based on the information identifying the aforementioned application, an application identification unit identifies the application, An item identification unit that identifies items corresponding to the application, An information processing apparatus according to any one of embodiments 1 to 3, further comprising the above. [Aspect 5] The above instruction is an instruction to create a sentence that satisfies the conditions of the above-mentioned input field of the above-mentioned item. An information processing device according to any one of embodiments 1 to 4. [Aspect 6] The above instruction includes the name of the application, The information processing apparatus according to Embodiment 4. [Aspect 7] The aforementioned application is an application created by accepting settings for the aforementioned items from the user. The information processing apparatus according to Embodiment 4. [Aspect 8] The transmitting unit transmits one or more programs to be executed on the terminal device to the terminal device. The aforementioned terminal device can run a web browser. The input processing unit that inputs text to be entered into a specific input field received by the terminal device into the input field operates by executing the program transmitted from the information processing device in the web browser. An information processing device according to any one of embodiments 1 to 7. [Aspect 9] The request transmission unit, Furthermore, the request includes one or more records already registered with the application and is sent to the generating AI system. The information processing apparatus according to Embodiment 4. [Aspect 10] The request transmission unit, When the aforementioned operation is received from the user, the system includes information indicating one or more items among the multiple items other than the specific item relating to the specific input field, and instructions to create text to be entered into the specific input field of the specific item based on the information indicating the one or more items, The AI ​​generation system receives the request, which does not include data entered by the user in the input fields corresponding to one or more of the items. The information processing apparatus according to Embodiment 1. [Explanation of symbols]

[0232] 10 user terminals 40 Application Services 50 Generative AI Systems 100 Information Processing Systems [Prior art documents] [Patent Documents]

[0233] [Patent Document 1] Japanese Patent Publication No. 2022-174244

Claims

1. A terminal device, a generation AI system, and an information processing device connected via a network, A screen containing multiple input fields, each accepting user input of data to be entered into multiple items, which are displayed on the terminal device, and which includes at least one specific input field for accepting text input, and a registration unit that registers information entered via the screen, which is capable of accepting operations to create text to be entered into the specific input field. When the aforementioned operation is received from the user, the request transmission unit transmits a request to the generation AI system, which includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and instructions to create a sentence to be entered in the specific input field of the specific item based on the information indicating the one or more items and the data. A response receiving unit that receives the text to be entered into the specific input field from the generating AI system as a response to the aforementioned request, A transmission unit that transmits the text created by the AI ​​generation system based on the above request to the terminal device, An information processing device having

2. The system further includes a request generation unit that generates the aforementioned request. The information processing apparatus according to claim 1.

3. The transmission unit transmits to the terminal device the text to be entered into the specific input field, which has been generated by the generation AI system, so that the terminal device can display it in the specific input field. The information processing apparatus according to claim 1 or 2.

4. A receiving unit that receives information identifying the application selected by the user from the aforementioned terminal device, Based on the information identifying the aforementioned application, an application identification unit identifies the application, An item identification unit that identifies items corresponding to the application, The information processing apparatus according to claim 1, further comprising the above.

5. The above instruction is an instruction to create a sentence that satisfies the conditions of the above-mentioned input field of the above-mentioned item. The information processing apparatus according to claim 1.

6. The above instruction includes the name of the application, The information processing apparatus according to claim 4.

7. The aforementioned application is an application created by accepting settings for the aforementioned items from the user. The information processing apparatus according to claim 4.

8. The transmitting unit transmits one or more programs to be executed on the terminal device to the terminal device. The aforementioned terminal device can run a web browser, The input processing unit that inputs text to be entered into the specific input field received by the terminal device into the input field operates by executing the program transmitted from the information processing device in the web browser. The information processing apparatus according to claim 1.

9. The request transmission unit, Furthermore, the request includes one or more records already registered with the application and is sent to the generating AI system. The information processing apparatus according to claim 4.

10. The request transmission unit, When the aforementioned operation is received from the user, the system includes information indicating one or more items among the multiple items other than the specific item relating to the specific input field, and instructions to create text to be entered into the specific input field of the specific item based on the information indicating the one or more items, The AI ​​generating system receives the request, which does not include data entered by the user in the input fields corresponding to one or more of the items. The information processing apparatus according to claim 1.

11. An information processing device capable of communicating with a generative AI (Artificial Intelligence) system, and a terminal device capable of communicating via a network, A screen containing multiple input fields, each accepting user input of data to be entered into multiple fields, and including at least one specific input field that accepts text input, and a display control unit that displays a screen capable of accepting operations to create text to be entered into the specific input field, When the aforementioned operation is received on the aforementioned screen, a transmission unit transmits a request to an information processing device that includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and instructions to create a sentence to be entered in the specific input field of the specific item based on the information indicating the one or more items and the data. The system includes an input processing unit that receives text to be entered into a specific input field, which is obtained by the information processing unit when it transmits the request to the generation AI system, and inputs the received text into the specific input field. The transmission unit transmits the text entered into the specific input field to the information processing device in order to manage it in the information processing device. Terminal device.

12. An information processing system that manages information entered by a user into an input field, and that can communicate with a terminal device and a generating AI (Artificial Intelligence) system via a network, The aforementioned information processing device is A screen containing multiple input fields, each accepting user input of data to be entered into multiple items, which are displayed on the terminal device, and which includes at least one specific input field for accepting text input, and a registration unit that registers information entered via the screen, which is capable of accepting operations to create text to be entered into the specific input field. When the aforementioned operation is received from the user, the request transmission unit transmits a request to the generation AI system, which includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and instructions to create a sentence to be entered in the specific input field of the specific item based on the information indicating the one or more items and the data. A response receiving unit that receives the text to be entered into the specific input field from the generating AI system as a response to the aforementioned request, A transmission unit that transmits the text created by the AI ​​generation system based on the above request to the terminal device, An information processing system having

13. A terminal device, a generation AI system, and an information processing device connected via a network, A screen containing multiple input fields, each accepting user input of data to be entered into multiple items, which are displayed on the terminal device, and which includes at least one specific input field for accepting text input, and a registration unit that registers information entered via the screen, which is capable of accepting operations to create text to be entered into the specific input field. When the aforementioned operation is received from the user, the request transmission unit transmits a request to the generation AI system, which includes information indicating one or more items among the plurality of items other than the specific item relating to the specific input field, data entered by the user in the input field corresponding to the one or more items, and instructions to create a sentence to be entered in the specific input field of the specific item based on the information indicating the one or more items and the data. A response receiving unit that receives the text to be entered into the specific input field from the generating AI system as a response to the aforementioned request, A transmission unit transmits the text created by the AI ​​generation system based on the aforementioned request to the terminal device. A program designed to function as such.

Images