Information processing device, report creation system, program, and information processing method

Abstract

To provide an information processing device capable of supporting report creation using an external AI system, a report creation system, a program, and an information processing method.SOLUTION: An information processing system is configured to: receive a screen information acquisition request of an analysis screen for data managed by an application provided by an information processing device or an application service from a user terminal; transmit screen information including an analysis program which acquires application data from the application service to create analysis data and upload the created data to a generative AI system to the user terminal; when receiving the analysis data and a chat message related to analysis input to the analysis screen displayed on the user terminal from the user terminal, transmit a request message requesting the analysis of the analysis data according to the message to the generative AI system; receive a response message including the analysis results of the analysis data from the generative AI system; and transmit a report including the analysis results to the user terminal.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a report creation system, a program, and an information processing method. [Background technology]

[0002] In recent years, programming support technologies have become known that reduce or even eliminate the need to input program code. One example of such technologies is the automatic generation of program code using artificial intelligence (AI). Summary of the Invention [Problem to be solved by the invention]

[0003] A variety of data is managed in a program. In order to analyze the data managed by the program and create a report, it is necessary to understand the content of the data managed by the program and how to analyze it, which can be quite difficult. For this reason, it is desirable to have support that reduces or even completely eliminates the need to enter program code when creating reports on data managed by a program.

[0004] The disclosed technology was developed in consideration of the above circumstances, and aims to support the creation of reports using external AI systems (such as generative AI systems). [Means for solving the problem]

[0005] The disclosed technology is an information processing device that communicates with a terminal device and a generation AI system via a network, and includes a communication unit that receives from the terminal device a request to acquire screen information of an analysis screen of data managed by the application, including application identification information, and transmits to the terminal device the screen information including an analysis program that causes the terminal device to acquire the data managed by the application, create analysis data, and upload it to the generation AI system; and when the communication unit receives from the terminal device a chat message requesting analysis of data entered on the analysis screen displayed on the terminal device, the communication unit transmits the chat message, information about the application identified by the identification information, and a message to the information processing device or application that provides the application. and a chat control unit that sends a request message to the generation AI system including information for calling a function that specifies data to be obtained from an online service, and receives a response message from the generation AI system including the call of the function, wherein the communication unit further sends the response message including the call of the function received by the chat control unit to the terminal device and receives from the terminal device the analysis data created from the data obtained based on the function, the chat control unit further sends a request message to the generation AI system requesting analysis of the analysis data and receives a response message from the generation AI system including the analysis results, and the communication unit further sends a report including the analysis results to the terminal device. [Effects of the Invention]

[0006] We can assist in creating reports using external AI systems (generative AI systems, etc.). [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an example of a system configuration of a report creation system according to a first embodiment. [Figure 2] FIG. 1 is a diagram illustrating an outline of the operation of a report creation system. [Figure 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing system, a user terminal, and a developer terminal. [Figure 4] FIG. 2 is a diagram illustrating the functions of each device included in the report creation system of the first embodiment. [Figure 5A] FIG. 2 is a first sequence diagram illustrating the operation of the report creation system according to the first embodiment. [Figure 5B] FIG. 10 is a second sequence diagram illustrating the operation of the report creation system according to the first embodiment. [Figure 6] FIG. 10 is a diagram illustrating the functions of each device included in the report creation system of the second embodiment. [Figure 7A] FIG. 10 is a first sequence diagram illustrating the operation of the report creation system according to the second embodiment. [Figure 7B] FIG. 10 is a second sequence diagram illustrating the operation of the report creation system according to the second embodiment. [Figure 8] FIG. 10 is a first diagram showing an example of a display on a user terminal. [Figure 9] FIG. 10 is a second diagram showing an example of a display on a user terminal. [Figure 10] FIG. 10 is a diagram illustrating an example of a request message requesting creation of a thread. [Figure 11] FIG. 10 is a diagram showing an example of a request message requesting uploading of a file for analysis B. [Figure 12] FIG. 10 is a third diagram showing an example of a display on a user terminal. [Figure 13] FIG. 10 is a diagram illustrating an example of a request message for requesting addition of a chat message to a thread. [Figure 14] FIG. 10 is a diagram showing an example of a request message requesting execution of an assistant in response to a chat message. [Figure 15] FIG. 10 is a diagram illustrating an example of a request message for requesting acquisition of the execution status of a process identified by an execution ID. [Figure 16] FIG. 10 is a diagram illustrating an example of a response message including an execution status. [Figure 17] FIG. 10 is a first diagram showing a request message requesting acquisition of analysis results. [Figure 18] FIG. 10 is a diagram showing a response message including text data. [Figure 19] FIG. 10 is a second diagram showing a request message requesting acquisition of analysis results. [Figure 20] FIG. 4 is a fourth diagram showing an example of a display on a user terminal. [Figure 21] FIG. 5 is a fifth diagram showing an example of a display on a user terminal. DETAILED DESCRIPTION OF THE INVENTION

[0008] (First embodiment) The present embodiment will be described below with reference to the drawings: Fig. 1 is a diagram illustrating an example of the system configuration of a report creation system according to a first embodiment.

[0009] The report creation system 100 of this embodiment includes an information processing system 20, a user terminal 10, and a developer terminal 60.

[0010] In the report creation system 100, the information processing system 20 and the user terminal 10, and the information processing system 20 and the developer terminal 60 are communicatively connected via networks N1 and N2. The information processing system 20 can also communicate with a generation AI system 50 via the network N1. Furthermore, the user terminal 10 and the developer terminal 60 can communicate with the generation AI (Artificial Intelligence) system 50 and an external system, an application service 40, via the networks N1 and N2. The information processing system 20 may also communicate with the application service 40 via the network N1.

[0011] In this embodiment, the network N1 is a wide area network such as the Internet or a WAN, and the network N2 may be a LAN, Wi-Fi (registered trademark), wide area Ethernet (registered trademark), or a mobile phone network such as 4G, 5G, or 6G.

[0012] The user terminal 10 is a terminal device such as a PC (Personal Computer), a smartphone, or a tablet terminal that is mainly used by a user who uses the services provided by the application service 40. The developer terminal 60 is a terminal device that is mainly used by a developer of the information processing system 20.

[0013] The user terminal 10 and the developer terminal 60 are located in facilities such as a company or a home, and are connected to the network N2. Note that the user terminal 10 and the developer terminal 60 do not need to be connected to the network N2 at all times; they only need to be connected when using the information processing system 20, the generation AI system 50, or the application service 40. A web browser or a native application runs on the user terminal 10 or the developer terminal 60. Furthermore, the user terminal 10 or the developer terminal 60 can use various services provided by the information processing system 20, the generation AI system 50, or the application service 40.

[0014] The application service 40 is one or more information processing devices that provide applications executed by users. The applications provided by the application service 40 are, for example, database-type web applications that manage data in a tabular format. Users can arbitrarily set application fields and customize the application so that they can save, read, or process data related to their own business. In this embodiment, data analysis refers to aggregating values ​​for each item contained in the data, visualizing fluctuations in the values ​​of items contained in the data, processing the data, and the like, for data stored in a database prepared in advance. In the following description, an application may be simply referred to as an app.

[0015] The application service 40 may be, for example, a cloud service, an ASP (Application Service Provider), or SaaS, and may include various services provided via a network. For example, a database or storage service is provided as an example of the service. The application service 40 may exist on the Internet or on-premise.

[0016] The generative AI system 50 provides a service that allows users to converse with artificial intelligence (AI) in a conversational format. A known example of such a generative AI system 50 is a system that uses large language models (LLMs). A large language model is a natural language processing model trained using a large amount of text data.

[0017] The generative AI system 50 takes in a huge amount of text in advance and learns knowledge from it using deep learning, reinforcement learning, etc. The generative AI system 50 uses this knowledge to provide a response message to a chat message.

[0018] The interface through which a user inputs chat messages to the generative AI system 50 is called a prompt. Chat messages such as instructions and questions are input into the prompt. Chat messages may be conversational sentences or words written in natural language spoken by humans. Images may also be used as chat messages. The generative AI system 50 that generates sentences in response to chat messages may be called generative AI.

[0019] Other features of the generative AI system 50 include the ability to conduct conversations in a natural flow, the ability to expand and propose ideas even in areas in which the user has no knowledge, and the ability to output accurate program code.

[0020] In this embodiment, by using the generative AI system 50 having such characteristics, the information processing system 20 can advance a conversation with the user in a natural flow.

[0021] In this embodiment, systems using LLMs such as GPT-3, GPT-4, Transformer, and BERT (all of which are registered trademarks) are known as the generative AI system 50. As an example, ChatCPT using GPT-3 or GPT-4 can be used in the report creation system 100 of this embodiment, but systems using other LLMs may also be used.

[0022] The generation AI system 50 of this embodiment may also have a conversation history retention function (Persistent Threads) that creates a thread to retain the history of a conversation between the user of the user terminal 10 and the generation AI system 50 and retains the conversation history, and a file reception function (Data Retrieval) that accepts file uploads from outside.The generation AI system 50 of this embodiment may also have, for example, a program generation and execution function (Code Interpreter) that automatically generates and executes program code as needed, and a function calling function (Function Calling) that calls a specified function in response to a prompt.

[0023] Furthermore, the above-mentioned conversation history retention function (Persistent Threads), file reception function (Data Retrieval), program generation and execution function (Code Interpreter), and function calling function (Function Calling) may be realized by an API (Application Programming Interface) provided by the generation AI system 50 to the information processing system 20. More specifically, the API provided by the generation AI system 50 of this embodiment may be, for example, an Assistants API made public by the generation AI system 50.

[0024] In the following description, for example, calling an API provided by the generative AI system 50 and executing these functions may be expressed as executing the assistant.

[0025] When the information processing system 20 of this embodiment receives an operation from the user terminal 10 to select an application to be used for data analysis, it outputs a program to the user terminal 10 to create a file to be used for data analysis and send it to the generation AI system 50.

[0026] More specifically, when an application to be analyzed is selected on the user terminal 10, the information processing system 20 outputs to the user terminal 10 a program that creates an analysis file from the data managed by the application and transmits the analysis file to the generation AI system 50. In the following description, the program output from the information processing system 20 to the user terminal 10 may be referred to as an analysis program. The analysis file is an example of analysis data.

[0027] Furthermore, the application that is the subject of data analysis is one of the applications managed by the application service 40. In the following description, the application that is the subject of data analysis is referred to as the analysis target application, and the data managed by the application that is the subject of data analysis is referred to as analysis target data.

[0028] Furthermore, when the information processing system 20 receives a chat message regarding data analysis from the user terminal 10, it includes the chat message in a request message and sends it to the generation AI system 50. Furthermore, when the information processing system 20 receives data analysis results from the generation AI system 50, it sends them to the user terminal 10. At this time, the information processing system 20 creates a report including the analysis results obtained from the generation AI system 50 and sends the report including the analysis results to the user terminal 10.

[0029] As described above, in this embodiment, the user can obtain the analysis results of the data to be analyzed simply by selecting the application to be analyzed and entering a chat message regarding the analysis of the data on the user terminal 10. In other words, the user can receive a report including the analysis results simply by selecting the application to be analyzed on the user terminal 10 and entering a chat message instructing the analysis.

[0030] In the example of Figure 1, the application service 40 and the information processing system 20 are provided separately, but this is not limited to this, and the information processing system 20 and the application service 40 may be integrated. That is, the application service 40 may include the functions of the information processing system 20, or the information processing system 20 may include the functions of the application service 40. Furthermore, the application service 40 and the generation AI system 50 may be integrated. Furthermore, the generation AI system 50 and the information processing system 20 may be integrated. Furthermore, the information processing system 20, the application service 40, and the information processing system 20 may be integrated.

[0031] The information processing system 20 may be realized by cloud computing or by a single information processing device. Cloud computing refers to a form in which resources on a network are used without being aware of specific hardware resources. The information processing system 20 may exist on the Internet or on-premise.

[0032] Furthermore, the functions of the information processing system 20 may be distributed among multiple information processing devices, or there may be multiple information processing systems 20 with the same functions, and the number of information processing systems that perform processing may be increased or decreased depending on the processing load.

[0033] The user terminal 10 is, for example, a terminal device such as a PC (Personal Computer), a smartphone, or a tablet terminal that is used by a user to whom a service is provided by the application service 40.

[0034] The user terminal 10 may be any information processing device, such as an electronic whiteboard, an output device such as digital signage, a head-up display (HUD), industrial machinery, an imaging device, a sound collection device, a medical device, a network appliance, a mobile phone, a smartphone, a tablet terminal, a game console, a personal digital assistant (PDA), a digital camera, or a wearable PC.

[0035] An outline of the operation of the report creation system 100 of this embodiment will be described below with reference to Fig. 2. Fig. 2 is a diagram for explaining an outline of the operation of the report creation system.

[0036] In the report creation system 100, when the user terminal 10 selects an application to be analyzed (step S1), the user terminal 10 requests the generation AI system 50 to create a thread via the information processing system 20 (steps S2 and S3). Subsequently, the user terminal 10 transmits a chat message regarding the analysis input by the user to the information processing system 20 (step S4).

[0037] In this embodiment, the chat message may be a message regarding data analysis, such as "Make a graph," etc. The chat message may include not only a message indicating a specific analysis method, but also a message expressing a desire, such as "Please do a proper analysis."

[0038] When the information processing system 20 receives the chat message input by the user, it includes the received chat message in a request message and transmits it to the generation AI system 50 (step S5). At this time, the information processing system 20 transmits the request message to the generation AI system 50 via an API (Application Programming Interface) for receiving the request message, which is provided by the generation AI system 50. The information processing system 20 also transmits the request message together with a specification of the function.

[0039] A function is a program interface that performs a specific process based on specified arguments and returns a return value as a result. This function enables the generation AI system 50 to request data managed by an application provided by the application service 40 from the information processing system 20. The information processing system 20 includes the specification settings of this function in a request message and sends it to the generation AI system 50. In other words, the data managed by the application provided by the application service 40 is the analysis target data that will be analyzed by the generation AI system 50.

[0040] The request from the generation AI system 50 to the information processing system 20 to call this function is called a function call. The information processing system 20 can include information about the application to be analyzed in the request message.

[0041] The information about the application to be analyzed is information indicating parameters managed by the application for which the user requested data analysis, such as the field names, number of fields, and number of characters representing the field names managed by the application.

[0042] Note that the information processing system 20 does not have to include information about the application to be analyzed and function specification settings in the same request message as the received chat message. For example, the information processing system 20 may include information about the application to be analyzed and function specification settings in a request message separate from the request message containing the received chat message and transmit the request message to the generative AI system 50.

[0043] In addition, the information processing system 20 may also include information about the application to be analyzed and function specification settings in separate request messages and transmit them to the generation AI system 50.

[0044] Furthermore, the information processing system 20 may transmit information about the application to be analyzed and function specification settings each time a received chat message is included in a request message and transmitted, or may transmit the information only once at the beginning.

[0045] The generation AI system 50 sends a response message including a function call request to the information processing system 20 based on the conversation history, function specification settings, and information about the application to be analyzed stored in the created thread (step S6).

[0046] Here, the generation AI system 50 simply requests the information processing system 20 to call a function. In the following description, a response message from the generation AI system 50 may be expressed as a response from the generation AI system 50.

[0047] The information processing system 20 transmits the response message received from the generation AI system 50 to the user terminal 10 (step S7).

[0048] When the user terminal 10 receives the response message, it executes the function call included in the response message using the analysis program received from the information processing system 20, and obtains the analysis target data managed by the analysis target application from the application service 40 (step S8).

[0049] Next, the user terminal 10 uses the analysis program to create an analysis file from the acquired data to be analyzed and transmits it to the information processing system 20 (step S9). The information processing system 20 requests the generation AI system 50 to add the analysis file to a thread and analyze it (step S10), and obtains the analysis results from the generation AI system 50 (step S11). Upon obtaining the analysis results, the information processing system 20 creates a report including the analysis results and transmits it to the user terminal 10 (step S12).

[0050] In this manner, in this embodiment, a report including the results of the data analysis can be obtained simply by selecting an application to be analyzed from among the applications provided by the application service 40 and entering a chat message regarding the data analysis.

[0051] Next, the hardware configuration of each device included in the report creation system 100 of this embodiment will be described with reference to FIG.

[0052] Fig. 3 is a diagram showing an example of the hardware configuration of an information processing system, a user terminal, and a developer terminal. As shown in Fig. 3, the information processing system 20, the user terminal 10, and the developer terminal 60 are constructed by a computer 500, and include a CPU 501, a ROM 502, a RAM 503, a HD (Hard Disk) 504, an HDD (Hard Disk Drive) controller 505, a display 506, an external device connection I / F (Interface) 508, a network I / F 509, a bus line 510, a keyboard 511, a pointing device 512, a DVD-RW (Digital Versatile Disk Rewritable) drive 514, and a media I / F 516.

[0053] Of these, the CPU 501 controls the overall operation of the computer 500. The ROM 502 stores programs, such as an IPL, used to drive the CPU 501. The RAM 503 is used as a work area for the CPU 501. The HD 504 stores various data, such as programs. The HDD controller 505 controls the reading and writing of various data from and to the HD 504 under the control of the CPU 501. The display 506 displays various information, such as a cursor, 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) memories 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, a data bus, or the like, for electrically connecting the components, such as the CPU 501, shown in FIG. 3.

[0054] The keyboard 511 is a type of input means having multiple keys used to input characters, numbers, various instructions, etc. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting a processing target, moving a cursor, etc. The DVD-RW drive 514 controls reading and writing of various data from a DVD-RW 513, which is an example of a removable recording medium. The DVD-RW drive 514 is not limited to a DVD-RW, and may be a DVD-R or the like. The media I / F 516 controls reading and writing (storing) of data from a recording medium 515, such as a flash memory.

[0055] Next, the functions of each device included in the report creation system 100 of this embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram illustrating the functions of each device included in the report creation system of the first embodiment.

[0056] First, we will explain the functions of the information processing system 20. The information processing system 20 of this embodiment has a communication unit 21, a screen generation unit 22, a chat control unit 23, a setting information storage unit 24, a program output unit 25, and a report creation unit 28. Each functional unit of the information processing system 20 is a function or means realized by the CPU 501 shown in FIG. 3 executing instructions contained in one or more programs installed in the information processing system 20.

[0057] 3. The setting information storage unit 24 does not have to be included in the information processing system 20, but may be located on a network that the information processing system 20 can access.

[0058] The communication unit 21 transmits and receives various types of information to the user terminal 10. The communication unit 21 transmits screen information of the analysis screen of the application to be analyzed to the user terminal 10. The communication unit 21 also receives chat messages entered by the user for data analysis from the user terminal 10. The communication unit 21 also transmits and receives various types of information to the developer terminal 60. The communication unit 21 transmits screen information of the setting information input screen to the developer terminal 60. The communication unit 21 receives setting information entered by the developer from the developer terminal 60 and stores it in the setting information storage unit 24. The communication unit 21 also transmits a response message (response) received by the chat control unit 23 from the generation AI system 50 to the user terminal 10. The communication unit 21 is an example of a first communication unit.

[0059] The screen generation unit 22 generates screen information for the screen (web page) to be displayed on the user terminal 10 and the developer terminal 60.

[0060] More specifically, the screen generator 22 generates screen information for an analysis screen of the application to be analyzed, which is displayed on the user terminal 10. The screen information for the analysis screen includes an analysis program for realizing the data analyzer 14, which will be described later, on the user terminal 10.

[0061] Web pages are provided as part of web applications. Screen information is a program written in HTML, JSON, XML, scripting languages, and CSS (Cascading Style Sheets), etc. HTML primarily determines the structure of a web page, scripting languages ​​define the behavior of the web page, and CSS determines the style of the web page.

[0062] The chat control unit 23 calls the first API 26 to send a request message to the generation AI system 50.

[0063] The first API 26 is one or more APIs published by the generative AI system 50. The first API 26 of this embodiment may include an assistant API, and the first API 26 may hold an assistant ID as identification information for identifying itself.

[0064] As a result of calling the first API 26, the chat control unit 23 receives a response message to the request message from the generation AI system 50. The response message includes a reply message to the chat message, an analysis result of the data to be analyzed, and the like.

[0065] The setting information storage unit 24 stores the setting information. Here, the setting information will be explained.

[0066] In this embodiment, the setting information is information necessary for analyzing the analysis file. In other words, the setting information is information necessary for the generation AI system 50 to analyze the analysis target data, and includes a function that defines the data to be obtained from the application service 40.

[0067] Specifically, the function that defines the data to be acquired is a function that enables the generation AI system 50 to request the information processing system 20 to acquire the data to be analyzed.

[0068] In the following description, the function that enables the generation AI system 50 to request the information processing system 20 to acquire data to be analyzed may be referred to as a data acquisition function. In this embodiment, the setting information is stored in the setting information storage unit 24 by the developer before the user selects the application to be analyzed. Note that setting the setting information is not necessarily required, and setting information may not be necessary depending on the application.

[0069] When the communication unit 21 receives a request message from the user terminal 10 requesting the acquisition of screen information for the analysis screen of the application to be analyzed, the program output unit 25 outputs an analysis program to the screen generation unit 22 to cause the generation AI system 50 to analyze the data to be analyzed.

[0070] The analysis program is written in JavaScript (registered trademark, omitted below), and when executed on the user terminal 10, causes the user terminal 10 to create an analysis file from the data to be analyzed and send (upload) the analysis file to the generation AI system 50 via the information processing system 20.

[0071] The report creation unit 28 creates a report using the analysis results of the analysis file output from the generation AI system 50. The report in this embodiment may be image data or the like in which the analysis results obtained from the generation AI system 50 are arranged.

[0072] Specifically, the report may be, for example, PDF data or the like, or may be image data in which images, graphs, text data, etc. obtained as analysis results from the generation AI system 50 are arranged on a page. Note that the report is not limited to image data and may be document data or the like, and may be data in any format as long as it contains the analysis results.

[0073] Next, we will explain the functions of the user terminal 10. The user terminal 10 of this embodiment has a web browser 5, which has a communication unit 11, a display control unit 12, and an operation reception unit 13. Each of these functional units is a function or means realized by the CPU 501 shown in FIG. 3 executing instructions contained in one or more programs installed in the user terminal 10.

[0074] The communication unit 11, the display control unit 12, and the operation reception unit 13 may be realized by JavaScript (registered trademark, omitted below).

[0075] The communication unit 11 transmits and receives various types of information to and from the information processing system 20. In this embodiment, the communication unit 11 receives screen information of a portal screen from the application service 40, and receives screen information of an analysis screen, etc., on which chat messages related to analysis are entered, from the information processing system 20. The communication unit 11 transmits chat messages, operation information for the user terminal 10, etc. to the information processing system 20. Note that the communication unit 11 can also communicate directly with the generation AI system 50. The communication unit 11 is an example of a second communication unit.

[0076] The display control unit 12 interprets screen information of various screens and displays it on the display 506. The operation accepting unit 13 accepts various operations on the various screens displayed on the display 506 by the user.

[0077] Furthermore, the user terminal 10 of this embodiment receives screen information of an analysis screen including an analysis program from the information processing system 20.

[0078] The user terminal 10 receives the screen information of the analysis screen and executes the analysis program included in the screen information, thereby realizing the functions of the data analysis unit 14. In other words, the web browser 5 of the user terminal 10 has the data analysis unit 14 by executing the JavaScript included in the screen information of the analysis screen obtained from the information processing system 20.

[0079] The data analysis unit 14 calls the second API 27 to send a request message to the application service 40. The request message requests editing of the application, and includes parameters related to the application (such as the database field name and data format), the content of the editing, and the like.

[0080] The second API 27 is one or more APIs made public by the application service 40. As a result of calling the second API 27, the data analysis unit 14 receives a response message in response to the request message from the application service 40. The response message includes the data to be analyzed.

[0081] Note that the user terminal 10 may also execute a native app. A native app is an application that cannot be executed unless it is installed on the user terminal 10. In the case of a native app, the screen information of the analysis screen is stored in the user terminal 10, and the information to be displayed is transmitted in JSON, XML, or the like.

[0082] Next, the functions of the developer terminal 60 will be described. The developer terminal 60 has a communication unit 61, a display control unit 62, and an operation reception unit 63. Each of these functional units is a function or means realized by the CPU 501 shown in FIG. 3 executing instructions contained in one or more programs installed on the developer terminal 60. For example, the communication unit 61, the display control unit 62, and the operation reception unit 63 may be realized by at least one of a web browser and JavaScript. When the developer terminal 60 executes a native app, these may be realized by the native app.

[0083] The communication unit 61 transmits and receives various information to and from the information processing system 20. In this embodiment, the communication unit 61 receives screen information related to input of setting information from the information processing system 20. The communication unit 61 transmits setting information, operation information for the developer terminal 60, etc. to the information processing system 20. The communication unit 21 can also communicate with the generation AI system 50 and the application service 40.

[0084] The display control unit 62 interprets screen information of various screens and displays it on the display 506. The operation accepting unit 63 accepts various operations on the various screens displayed on the display 506 by the user.

[0085] Next, the operation of the report creation system 100 of this embodiment will be described with reference to Figures 5A and 5B. Figure 5A is a first sequence diagram illustrating the operation of the report creation system of the first embodiment, and Figure 5B is a second sequence diagram illustrating the operation of the report creation system of the first embodiment.

[0086] In the report creation system 100, the Web browser 5 of the user terminal 10 displays a list screen of applications managed by the application service 40 (step S501).

[0087] The application list screen in this embodiment may be displayed on the web browser 5, for example, when an operation to display a list of applications is performed on the portal screen of the application service 40 displayed on the web browser 5 of the user terminal 10.

[0088] Next, the Web browser 5 accepts an operation to select an application to be analyzed on the application list screen (step S502).

[0089] Next, the Web browser 5 requests the application service 40 to start the selected application (step S503).

[0090] Specifically, the web browser 5 connects to the URL of the application service 40 via the communication unit 11. Here, since an application to be analyzed has been selected on the user terminal 10, the communication unit 11 generates an HTTP request including the URL of the application screen of the application to be analyzed, and transmits the generated HTTP request to the application service 40. The application screen is a screen that accepts various operations for the application, and may be the home screen of the application. In the following description, the application screen will be referred to as an app screen.

[0091] When the application service 40 receives the above HTTP request from the user terminal 10, it transmits screen information of the application screen to the Web browser 5 (step S504). Specifically, the application service 40 transmits screen information (HTML, JavaScript, CSS, etc.) of the application screen to the Web browser 5.

[0092] The web browser 5 receives the screen information of the application screen via the communication unit 11, and causes the display control unit 12 to display the application screen based on the screen information (step S505).

[0093] Next, when the operation receiving unit 13 of the Web browser 5 receives an operation to start analyzing the data to be analyzed from the application screen (step S506), the communication unit 11 sends a request message to the information processing system 20 requesting acquisition of screen information of the analysis screen (step S507). Note that the request message sent to the information processing system 20 here may include an application ID, which is identification information that specifies the application to be analyzed selected in step S502.

[0094] The information processing system 20 generates screen information (HTML, JavaScript, CSS, etc.) for the analysis screen (step S508).

[0095] Here, we will explain how the information processing system 20 generates screen information for an analysis screen. When the information processing system 20 of this embodiment receives a request message requesting acquisition of an analysis screen, the program output unit 25 acquires the data to be analyzed, creates an analysis file, and passes the analysis program to the screen generation unit 22 to be sent to the generation AI system 50. The screen generation unit 22 includes the analysis program written in JavaScript in the screen information for the analysis screen.

[0096] Next, the information processing system 20 transmits screen information of the analysis screen to the web browser 5 via the communication unit 21 (step S509). The Web browser 5 receives the screen information of the analysis screen via the communication unit 11, and causes the display control unit 12 to display the analysis screen based on the screen information (step S510). Next, the Web browser 5 causes the operation accepting unit 13 to accept an operation to start analysis of the data to be analyzed on the analysis screen (step S511).

[0097] When the web browser 5 receives an operation to start analyzing the data to be analyzed, it executes the analysis program to realize the data analysis unit 14. Then, the web browser 5 causes the data analysis unit 14 to generate a request message requesting the creation of a thread, and causes the communication unit 11 to transmit the generated request message to the information processing system 20 (step S512). The information processing system 20 receives this request message, and causes the chat control unit 23 to transmit a request message requesting the creation of a thread to the generation AI system 50 (step S513).

[0098] Next, the information processing system 20 acquires the thread ID of the created thread from the generation AI system 50 (step S514), and transmits the acquired thread ID to the Web browser 5 via the communication unit 21 (step S515). The thread ID is identification information for identifying a thread.

[0099] Next, when the Web browser 5 receives an input of a chat message related to the analysis from the user (step S516), the data analysis unit 14 generates a request message requesting that the chat message related to the analysis be added to the thread, and the communication unit 11 transmits the generated request message to the information processing system 20 (step S517). The chat message may be input using a keyboard or by voice input. The request message transmitted to the information processing system 20 here includes a thread ID.

[0100] The information processing system 20 transmits the request message received from the web browser 5 via the communication unit 21 to the generation AI system 50 via the chat control unit 23 (step S518). When the generation AI system 50 adds a chat message to the thread identified by the thread ID, it transmits a response message indicating this to the information processing system 20 (step S519).

[0101] When the chat control unit 23 of the information processing system 20 receives the response message, the chat control unit 23 then transmits a request message to the generation AI system 50 requesting execution of an assistant according to the chat message (step S520).

[0102] In this case, the chat message added to the thread is a chat message regarding the analysis of the analysis file, and therefore the request message sent to the generation AI system 50 in step S519 is a request message including the chat message regarding the analysis, and is a request message requesting the analysis of the analysis file.

[0103] The generation AI system 50 receives this request message, starts the execution of the assistant, and transmits a response message including an execution ID for identifying the process being executed to the information processing system 20 (step S521).

[0104] Specifically, the generation AI system 50, for example, uses a program generation and execution function called by a request message requesting analysis to generate program code for analyzing the analysis file, start executing the generated program code, and send an execution ID to the information processing system 20. In other words, the request message requesting analysis is a request message for calling the program generation and execution function provided by the generation AI system 50.

[0105] When the chat control unit 23 receives the response message including the execution ID, the information processing system 20 transmits the execution ID to the Web browser 5 via the communication unit 21 (step S522).

[0106] Next, the Web browser 5 generates a request message requesting acquisition of the execution status of the process identified by the execution ID using the data analysis unit 14, and transmits the request message to the information processing system 20 using the communication unit 11 (step S523). This request message includes the thread ID and the execution ID.

[0107] In this embodiment, the execution status indicates the processing status of the process identified by the execution ID. The execution status may also include various data obtained by the process identified by the execution ID. The execution status may also include a function call request.

[0108] The information processing system 20 transmits the request message received from the web browser 5 to the generation AI system 50 (step S524). The generation AI system 50 transmits a response message including the execution status of the process identified by the execution ID included in the request message to the information processing system 20 (step S525).

[0109] The information processing system 20 receives the response message including the execution status through the chat control unit 23, and transmits the received response message to the Web browser 5 through the communication unit 21 (step S526).

[0110] In this embodiment, when the execution status becomes information indicating the completion of processing (a value other than a function call request), the Web browser 5 generates a request message requesting acquisition of the analysis results using the data analysis unit 14, and transmits the generated request message using the communication unit 11 to the information processing system 20 (step S527). The information processing system 20 transmits the request message received from the Web browser 5 using the communication unit 11 to the generation AI system 50 using the chat control unit 23 (step S528). In response to the request message, the generation AI system 50 transmits the analysis results to the information processing system 20 (step S529).

[0111] In this embodiment, the operations from step S527 to step S529 are repeated for each piece of data output as an analysis result by the generation AI system 50. Specifically, for example, assume that text data and image data are obtained as analysis results by the generation AI system 50. In this case, in this embodiment, the operations from step S527 to step S529 are repeated to obtain each of the text data and image data.

[0112] When the information processing system 20 acquires all the analysis results from the generation AI system 50, the report creation unit 28 creates a report using the acquired analysis results (step S530).

[0113] In this embodiment, multiple types of report templates may be stored in advance, or a report template may be selected by the user of the user terminal 10. In this embodiment, information indicating the report template may be stored in the setting information storage unit 24, and in that case, the generation AI system 50 may specify the template that the report creation unit 28 should acquire.

[0114] Next, the information processing system 20 transmits the created report via the communication unit 21 to the user terminal 10 (step S531). When the Web browser 5 receives the report via the communication unit 11, it causes the display control unit 12 to display the report (step S532).

[0115] Also, in this embodiment, if the execution status is a function call request, the web browser 5 generates a request message including a chat message regarding the analysis, and transmits the generated request message to the information processing system 20 via the communication unit 11 (step S533).

[0116] Here, the request message sent from the web browser 5 may include the application ID of the application to be analyzed, information about the application, and a thread ID in addition to the chat message.

[0117] When the information processing system 20 receives a request message from the web browser 5, it generates a request message to be sent to the generation AI system 50, and sends the generated request message to the generation AI system 50 by calling the first API 26 (step S534).

[0118] Here, the processing of the information processing system 20 will be described.

[0119] When the information processing system 20 receives a request message from the web browser 5, it passes the chat message included in the request message and information about the application to the chat control unit 23. At this time, since the past conversation history is held in the thread identified by the thread ID, it is not necessary to include the past conversation history in the request message.

[0120] The chat control unit 23 also references the setting information storage unit 24 to identify a function according to the content of the analysis indicated by the chat message. In this case, the chat message is a chat message requesting data analysis. Therefore, the chat control unit 23 references the setting information storage unit 24 to identify a data acquisition function that enables the generation AI system 50 to request the information processing system 20 to acquire the data to be analyzed.

[0121] Then, the chat control unit 23 generates a request message including a chat message requesting analysis of the data, information about the application, and information for calling a data acquisition function, and sends it to the generation AI system 50 by calling the first API 26.

[0122] Next, the generation AI system 50 transmits a response message to the information processing system 20 in response to the request message transmitted from the information processing system 20 (step S535). This response message includes a function call request.

[0123] When the chat control unit 23 of the information processing system 20 receives the response message including the function call request, the communication unit 21 transmits the response message to the Web browser 5 of the user terminal 10 (step S536).

[0124] The web browser 5 of the user terminal 10 receives the response message, executes the analysis program that realizes the data analysis unit 14, and sends a request message to the application service 40 via the communication unit 11, requesting the acquisition of the data to be analyzed (step S537).

[0125] Specifically, the web browser 5 calls the second API 27 to send a request message for acquiring the data to be analyzed to the application service 40. This request message includes the application ID of the application to be analyzed.

[0126] The data to be analyzed is information written in JSON format and is data stored in a database managed by the application in tabular format.

[0127] The application service 40 accepts this request message and transmits the data managed by the application identified by the application ID as data to be analyzed (in JSON format) to the Web browser 5 (step S538).

[0128] When the web browser 5 receives the data to be analyzed, the data analysis unit 14 generates data in CSV format from the acquired data to be analyzed in JSON format, and uses the data in CSV format as a file for analysis (step S539).

[0129] Next, the Web browser 5 causes the data analysis unit 14 to generate a request message requesting the generation AI system 50 to upload the analysis file, and causes the communication unit 11 to transmit the generated request message to the information processing system 20 (step S540). This request message includes the analysis file.

[0130] The information processing system 20 transmits the request message received from the web browser 5 via the communication unit 21 to the generation AI system 50 via the chat control unit 23 (step S541). Specifically, the information processing system 20 transmits a request message requesting the upload of an analysis file to the generation AI system 50 by calling the first API 26. In other words, the information processing system 20 uploads the analysis file to the generation AI system 50 by calling the file reception function of the generation AI system 50 via the first API 26.

[0131] The applied analysis file is added to the thread created in step S513.

[0132] When the analysis file is added to the thread, the generation AI system 50 transmits a file ID for identifying the added analysis file to the information processing system 20 (step S542). The information processing system 20 transmits the file ID received by the chat control unit 23 to the web browser 5 via the communication unit 21 (step S543).

[0133] When the Web browser 5 receives the file ID, the data analysis unit 14 generates a request message requesting the specification of the analysis file referenced in the thread, and the communication unit 11 transmits the generated request message to the information processing system 20 (step S544). In other words, the Web browser 5 transmits a request message including the result of calling the data acquisition function by the function call request to the information processing system 20. The request message is transmitted from the Web browser 5 to the information processing system 20.

[0134] The information processing system 20 transmits the request message received from the web browser 5 via the communication unit 21 to the generation AI system 50 via the chat control unit 23 (step S545).

[0135] The request message sent to the generation AI system 50 includes a thread ID and a file ID. In this embodiment, by specifying the analysis file referenced in the thread in this manner, the generation AI system 50 can be made to recognize that the analysis file added to the thread is the file to be analyzed.

[0136] When the analysis file to be referenced in the thread is specified, the generation AI system 50 transmits a response message indicating this to the information processing system 20 (step S546).

[0137] When the chat control unit 23 of the information processing system 20 receives the response message, the chat control unit 23 then transmits a request message requesting execution of an assistant to the generation AI system 50 (step S547).

[0138] The generation AI system 50 receives this request message, starts execution of the assistant, and transmits a response message including an execution ID for identifying the process being executed to the information processing system 20 (step S548).

[0139] The request message sent to the generation AI system 50 here is a request message requesting analysis of the analysis file added to the thread.

[0140] Specifically, the generation AI system 50, for example, uses a program generation and execution function called by a request message requesting analysis of the analysis file to generate program code for analyzing the analysis file, start executing the generated program code, and send an execution ID to the information processing system 20. In other words, the request message requesting analysis of the analysis file is a request message for calling the program generation and execution function provided by the generation AI system 50.

[0141] When the chat control unit 23 receives the response message including the execution ID, the information processing system 20 transmits the execution ID to the Web browser 5 via the communication unit 21 (step S549).

[0142] In this embodiment, the processes from step S523 to step S549 are repeated until the execution status value becomes a value other than the function call request value.

[0143] If the user of the user terminal 10 desires a different type of report, for example, the user can input a chat message to that effect. In this case, the report creation system 100 can simply repeat the operations from step S517 onwards.

[0144] In this embodiment, by doing so, the user of the user terminal 10 can obtain a report including the analysis results of data managed by the desired application simply by selecting the application to be analyzed and entering a chat message regarding the analysis. Therefore, this embodiment can support the creation of reports using the generation AI system.

[0145] In addition, in this embodiment, by using a function call, the generative AI system 50 can actively obtain analysis files from the application to be analyzed.

[0146] (Second embodiment) The second embodiment will be described below with reference to the drawings. The second embodiment differs from the first embodiment in that the administrator of the application service 40 is different from the administrator of the information processing system 20, and two web browsers are linked in the user terminal 10. Therefore, in the second embodiment below, differences from the first embodiment will be described, and components having the same functional configuration as those in the first embodiment will be assigned the same reference numerals as those used in the description of the first embodiment, and their description will be omitted.

[0147] FIG. 6 is a diagram illustrating the functions of each device included in the report creation system of the second embodiment.

[0148] The report creation system 100A of this embodiment includes a user terminal 10A, an information processing system 20, an application service 40, a generation AI system 50, and a developer terminal 60.

[0149] The user terminal 10A of this embodiment has a web browser 5A and a web browser 5B. The web browser 5A of this embodiment is provided by a provider of an application service 40. The web browser 5B is provided by a provider of an information processing system 20. The web browser 5A is an example of a first web browser, and the web browser 5B is an example of a second web browser.

[0150] The web browser 5A includes a communication unit 11A, a display control unit 12, an operation reception unit 13, and an inter-browser cooperation unit 15.

[0151] The communication unit 11A transmits and receives information to and from the application service 40. The communication unit 11A receives from the application service 40 screen information of the application list screen, information on the application to be analyzed, data to be analyzed, and the like.

[0152] The inter-browser cooperation unit 15 transmits and receives information to and from the web browser 5B. For example, the inter-browser cooperation unit 15 passes information about the application received by the communication unit 11A from the application service 40, data to be analyzed, and the like to the web browser 5B.

[0153] The web browser 5B is a web browser that communicates with the generation AI system 50 via the information processing system 20.

[0154] The web browser 5B includes a communication unit 16, a display control unit 17, an operation reception unit 18, an inter-browser cooperation unit 19, and a data analysis unit 14.

[0155] The communication unit 16 transmits and receives information to and from the information processing system 20. For example, the communication unit 16 transmits a chat message input in the web browser 5B to the information processing system 20. The communication unit 16 also receives from the information processing system 20 a response message that the information processing system 20 received from the generation AI system 50.

[0156] The inter-browser cooperation unit 19 transmits and receives information to and from the web browser 5 A. For example, the inter-browser cooperation unit 19 passes a response message from the generation AI system 50 that the communication unit 16 receives from the information processing system 20 to the web browser 5 A.

[0157] In this embodiment, multiple web browsers can be simultaneously executed on one user terminal 10. The inter-browser cooperation unit 15 can transmit information from the web browser 5A to the other web browser 5B. The inter-browser cooperation unit 19 can transmit information from the web browser 5B to the other web browser 5A.

[0158] Furthermore, in this embodiment, by linking multiple web browsers in this manner, if only one web browser holds authentication information for a specific website (e.g., application service 40), the other web browser can link with the first web browser and communicate with the specific website.

[0159] In other words, in this embodiment, when the Web browser 5A and the Web browser 5B communicate with each other, the Web browser 5B can communicate with the application service 40 in cooperation with the Web browser 5A that holds the authentication information of the application service 40.

[0160] Next, the operation of the report creation system 100A of this embodiment will be described with reference to Fig. 7A. Fig. 7A is a first sequence diagram illustrating the operation of the report creation system of the second embodiment, and Fig. 7B is a second sequence diagram illustrating the operation of the report creation system of the second embodiment. The processing from step S701 to step S706 in FIG. 7A is the same as the processing from step S501 to step S506 in FIG. 5A, except that the processing is performed by the Web browser 5A instead of the Web browser 5, and therefore description thereof will be omitted.

[0161] When the Web browser 5A of the user terminal 10 receives an operation to start analysis of the data to be analyzed from the application screen in step S706, the inter-browser cooperation unit 15 starts up the Web browser 5B (step S707).

[0162] As a result of this processing by the inter-browser cooperation unit 15, the web browser 5B is popped up and displayed on the user terminal 10. At this time, the inter-browser cooperation unit 15 also notifies the web browser 5B of the application ID of the application selected as the analysis target in step S706, by means of a URL or the like. The web browser 5B is launched by JavaScript included in the screen information of the application screen.

[0163] The Web browser 5B of the user terminal 10 uses the application ID notified from the Web browser 5A to send a request message to the information processing system 20, requesting acquisition of screen information of the analysis screen, via the communication unit 16 (step S708). The request message sent to the information processing system 20 here includes the application ID of the application to be analyzed.

[0164] When the information processing system 20 receives the request message from the Web browser 5B, the screen generation unit 22 generates screen information (HTML, JavaScript, CSS, etc.) for the analysis screen (step S709) and transmits the screen information for the analysis screen to the Web browser 5B (step S710). The Web browser 5B receives the screen information for the analysis screen from the information processing system 20 via the communication unit 16. The screen information for the analysis screen includes an analysis program written in JavaScript.

[0165] The Web browser 5B causes the display control unit 17 to display the analysis screen (step S711).

[0166] Next, the operation accepting unit 18 of the Web browser 5B accepts an operation to start analysis of the data to be analyzed on the analysis screen (step S712).

[0167] The operations from step S713 in FIG. 7A to step S737 in FIG. 7B are the same as the operations from step S512 in FIG. 5A to step S536 in FIG. 5B, except that the Web browser 5 becomes the Web browser 5B, and therefore description thereof will be omitted.

[0168] In step S737, when the Web browser 5B receives the response message from the information processing system 20, the data analysis unit 14 of the Web browser 5B passes a request message to the Web browser 5A via the inter-browser cooperation unit 19, requesting acquisition of the analysis target data managed by the analysis target application identified by the application ID (step S738). This request message includes the application ID of the analysis target application.

[0169] The Web browser 5A receives this request message via the inter-browser cooperation unit 15, and transmits a request message requesting acquisition of analysis target data to the application service 40 via the communication unit 11A (step S739).

[0170] The application service 40 accepts this request message and transmits the data managed by the application to be analyzed, which is identified by the application ID, to the web browser 5A as data to be analyzed (in JSON format) (step S740).

[0171] Next, the web browser 5A passes the analysis target data acquired from the application service 40 to the web browser 5B via the inter-browser cooperation unit 15 (step S741).

[0172] When the Web browser 5B acquires the data to be analyzed, the data analysis unit 14 generates a request message requesting the creation of a thread, and the communication unit 16 transmits the generated request message to the information processing system 20 (step S742).

[0173] The operations from step S743 to step S752 in FIG. 7B are the same as the operations from step S540 to step S549 in FIG. 5B, except that the Web browser 5 becomes the Web browser 5B, and therefore description thereof will be omitted.

[0174] In this embodiment, the Web browser 5A and the Web browser 5B provided by different providers are linked in one user terminal 10.

[0175] In this way, even if the web browser 5B does not have authentication information for accessing the application service 40, it can communicate with the application service 40 via the web browser 5A that has authentication information for accessing the application service 40.

[0176] Therefore, even if the provider of application service 40 is different from the provider of information processing system 20 and the domains of web browser 5A and web browser 5B are different, the application provided by application service 40 can be linked to the functions provided by information processing system 20.

[0177] The operation of the report creation system 100A of this embodiment will be described in more detail below.

[0178] Fig. 8 is a first diagram showing an example of a display on a user terminal. Screen 81 shown in Fig. 8 is an example of an application list screen that web browser 5A displays on the display in step S701 of Fig. 7A, for example.

[0179] The screen 81 includes a display area 82, in which a list of applications that are provided by the application service 40 and that are permitted for use by the user of the user terminal 10 is displayed.

[0180] When an application to be analyzed is selected in the display area 82, the Web browser 5A of this embodiment acquires screen information of the application screen of the selected application from the application service 40, and displays the application screen on the display.

[0181] Fig. 9 is a second diagram showing an example of a display on a user terminal. Screen 91 shown in Fig. 9 is an example of an application screen that is displayed on the display by web browser 5A, for example, in step S705 of Fig. 7A. Screen 91 shown in Fig. 9 shows the application screen when "product management application" is selected as the application to be analyzed on screen 81 shown in Fig. 8.

[0182] The screen 91 includes an operation button 92 and a display area 93. The operation button 92 is an operation button for starting analysis of the data to be analyzed. The display area 93 displays data managed in the "product management application." In other words, the display area 93 displays a list of records included in the data managed by the application to be analyzed.

[0183] When the operation button 92 is operated, the web browser 5A of this embodiment assumes that analysis of the data to be analyzed has started, and starts up the web browser 5B.

[0184] When the web browser 5B is started, the data analysis unit 14 obtains the data to be analyzed from the application service 40 via the web browser 5A, and sends a request message to the generation AI system 50 via the information processing system 20 requesting the creation of a thread.

[0185] Fig. 10 is a diagram showing an example of a request message for requesting the creation of a thread. Description 101A shown in Fig. 10 indicates a request message for requesting the creation of a thread.

[0186] When the generation AI system 50 receives the request message indicated by the description 101A from the information processing system 20, it transmits a response message including the thread ID to the information processing system 20. The information processing system 20 transmits the response message including the thread ID to the web browser 5B (see steps S715 and 716 in FIG. 7A).

[0187] 10 is an example of a response message including a thread ID. The description 101B includes the thread ID “abc123” of the thread generated by the conversation history storage function of the generation AI system 50 or the first API 26.

[0188] Furthermore, when the web browser 5B acquires the thread ID "abc123," it creates an analysis file from the data to be analyzed and then transmits a request message to the generation AI system 50 via the information processing system 20, requesting that the analysis file be uploaded to the thread identified by the thread ID "abc123."

[0189] Fig. 11 is a diagram showing an example of a request message for requesting uploading of an analysis file. Description 110A shown in Fig. 11 indicates a request message for requesting uploading of an analysis file.

[0190] The request message indicated by the description 110A indicates that an analysis file with the file name "madata.csv" is being requested to be uploaded.

[0191] When the generation AI system 50 receives the request message indicated by the description 110A from the information processing system 20, it transmits a response message including the file ID "file-abc123" that identifies the uploaded analysis file to the information processing system 20. The information processing system 20 transmits the response message including the file ID "file-abc123" to the Web browser 5B (see steps S724 and 725 in FIG. 7B).

[0192] Furthermore, upon acquiring the file ID "file-abc123," the web browser 5B transmits a request message to the generation AI system 50 via the information processing system 20 requesting the specification of the analysis file referenced in the thread (see steps S743 and 744 in FIG. 7B). Here, the analysis file is an analysis file with the file name "madata.csv" identified by the file ID "file-abc123."

[0193] In this embodiment, when an operation button 92 is operated on the screen 91 shown in FIG.

[0194] Fig. 12 is a third diagram showing an example of a display on a user terminal. Screen 91A shown in Fig. 12 is an example of a screen when a chat message is entered on the analysis screen displayed on the user terminal 10 in step S711 of Fig. 7A. Specifically, screen 91A shows an example of a screen on which the chat message entered in step S717 is displayed on the analysis screen popped up by the web browser 5B.

[0195] The screen 91A includes a pop-up window 94 displayed by the web browser 5B. The pop-up window 94 includes an input field 95 and a display area 96. The input field 95 The operation button 95 a is included, and when a chat message is input from the user and the operation button 95 a is selected, the input chat message is transmitted to the information processing system 20 .

[0196] The display area 96 includes a display area 96a. In the example of Fig. 12, the display area 96a displays chat messages entered in the input field 95. The display area 96 also displays a conversation history between the user and the generation AI system 50.

[0197] The example of FIG. 12 shows a state in which the user has input a chat message "Try analyzing it as you like."

[0198] In the example of FIG. 12, the pop-up window 94 is displayed superimposed on the screen 91A, but the pop-up window 94 may be displayed in an area on the display of the user terminal 10 that is separate from the area in which the screen 91A is displayed.

[0199] In this embodiment, when the operation button 95a is selected on the screen 91B shown in Fig. 12, the web browser 5B generates a request message requesting that the chat message entered in the input field 95 be added to the thread, and transmits the request message to the information processing system 20. The information processing system 20 transmits this request message to the generation AI system 50 (see steps S718 and 719 in Fig. 7A).

[0200] Fig. 13 is a diagram showing an example of a request message for requesting addition of a chat message to a thread. Description 130 shown in Fig. 13 indicates a request message for requesting addition of a chat message to a thread.

[0201] The request message indicated by description 130 includes the thread ID "abc123" of the thread to which the chat message should be added, the chat message "Try analyzing it as you like," and the file ID "file-abc123" of the analysis file to be analyzed.

[0202] Upon receiving this request message, the generation AI system 50 transmits a response message indicating that the chat message has been added to the thread to the information processing system 20 (step S720 in FIG. 7A).

[0203] The information processing system 20 receives this response message and sends a request message to the generation AI system 50 requesting execution of an assistant corresponding to the chat message (step S721 in FIG. 7A). Upon receiving this request message, the generation AI system 50 starts execution of the assistant and sends a response message including an execution ID for identifying the processing currently being executed to the web browser 5B via the information processing system 20 (steps S722, 723 in FIG. 7A).

[0204] 14 is a diagram showing an example of a request message requesting execution of an assistant in response to a chat message. Description 140A shown in FIG. 14 indicates a request message requesting execution of an assistant in response to a chat message.

[0205] The request message indicated by the description 140A includes the thread ID "abc123" of the thread to which the chat message was added and the assistant ID "asst_abc123" of the first API 26 that executes the process.

[0206] Description 140B shown in FIG. 14 indicates a response message to the request message indicated by description 140A.

[0207] The response message indicated by the description 140B includes the execution ID "run_abc123" that identifies the process being executed.

[0208] When the execution of the process begins, the web browser 5B generates a request message requesting to obtain the execution status of the process identified by the execution ID, and sends the generated request message to the generation AI system 50 via the information processing system 20 (steps S724, 725 in Figure 7B).

[0209] 15 is a diagram showing an example of a request message for requesting acquisition of the execution status of a process identified by an execution ID. Description 150 shown in FIG. 15 indicates a request message for requesting acquisition of the execution status of a process identified by an execution ID.

[0210] The request message indicated by description 150 includes the thread ID "abc123" and the execution ID "run_abc123" that identifies the process currently being executed. Furthermore, the web browser 5B sends the request message indicated by description 150 to the generation AI system 50 for each step of the process identified by the execution ID that is being executed in the thread identified by the thread ID. In other words, the generation AI system 50 obtains the execution status of each step of the process identified by the execution ID by polling.

[0211] Each time the generation AI system 50 receives a request message indicated by the description 150, it sends a response message including an execution status indicating the execution status of the processing to the web browser 5B via the information processing system 20 (steps S726, 727 in Figure 7B).

[0212] Fig. 16 is a diagram showing an example of a response message including an execution status. The description 160 shown in Fig. 16 indicates that text data identified by the message ID "msg_abc123" was acquired in the step identified by the step ID "step_abc123" in the process identified by the execution ID "run_abc123."

[0213] Furthermore, description 160 shows that in the process identified by the execution ID "run_abc123," in the step identified by the step ID "step_abc456," the automatically generated program code was executed, and the image data identified by the file ID "image-xyz789" was obtained.

[0214] In this manner, the Web browser 5B of this embodiment acquires the execution status for each step of the process identified by the execution ID until the execution of the process identified by the execution ID is completed. Then, when the execution of the process identified by the execution ID is completed, the Web browser 5 generates a request message to the generation AI system 50 via the information processing system 20, requesting acquisition of the analysis results, and transmits the generated request message by the communication unit 11 (steps S728 and 729 in FIG. 7B).

[0215] The analysis results here are the processing results included in the execution status. Therefore, in this case, the analysis results are the text data identified by the message ID "msg_abc123" and the image data identified by the file ID "image-xyz789."

[0216] In this embodiment, the web browser 5B transmits a request message requesting acquisition of an analysis result to the generation AI system 50 via the information processing system 20 for each processing result included in the execution status.

[0217] 17 is a first diagram showing a request message requesting acquisition of analysis results. The request message indicated by description 170 in FIG. 17 requests acquisition of text data acquired as a processing result. More specifically, the request message indicated by description 170 includes the thread ID "abc123" and the message ID "msg_abc123," and it can be seen that the request message is the result of processing executed in the thread identified by the thread ID "abc123," and requests acquisition of the text data identified by the message ID "msg_abc123."

[0218] When the generation AI system 50 receives the request message indicated by the description 170 from the web browser 5B, it outputs a response message including the text data identified by the message ID "msg_abc123" to the information processing system 20 (step S730 in FIG. 7B).

[0219] 18 shows a response message including text data. Description 180 shown in FIG. 18 shows a response message output from generation AI system 50 in response to the request message shown in description 170.

[0220] Description 180 includes text data "The analysis results are shown below" identified by the message ID "msg_abc123." In this manner, the information processing system 20 of this embodiment obtains the analysis results of the analysis file in the generation AI system 50.

[0221] Furthermore, the web browser 5B transmits a request message requesting acquisition of analysis results to the generation AI system 50 via the information processing system 20 until all data acquired as processing results has been acquired.

[0222] 19 is a second diagram showing a request message requesting acquisition of analysis results. The request message indicated by description 190 in FIG. 19 requests acquisition of image data acquired as a processing result. More specifically, the request message indicated by description 190 includes the file ID "image-xyz789," and it can be seen that the request message requests acquisition of text data identified by the file ID "image-xyz789."

[0223] In this embodiment, when the analysis results are obtained from the generation AI system 50 in this manner, the report creation unit 28 may generate a report using the analysis results and display it on the web browser 5B. The information processing system 20 may also store the report created using the analysis results and display the storage location of the report on the web browser 5B.

[0224] Fig. 20 is a fourth diagram showing an example of a display on the user terminal 10. A screen 91B shown in Fig. 20 is an example of a screen displayed on the user terminal 10 in step S733 of Fig. 7B, for example.

[0225] 17 includes display areas 96a, 96b, and 96c. Display area 96b may display text data created by report creation unit 28. Report creation unit 28 may, for example, edit text data included in the analysis results obtained from generation AI system 50 to generate text data to be displayed in display area 96b.

[0226] The display area 96c may display a storage destination (link) of the report created by the report creation unit 28. In the present embodiment, when a storage destination (link) displayed in the display area 96c is selected, the report stored in the corresponding storage destination may be displayed on the screen 91B.

[0227] The text data displayed in the display area 96b may be the message itself obtained from the generation AI system 50. Furthermore, the display area 96 does not have to include the display area 96b.

[0228] 20, the storage destination of the report is displayed in the display area 96. However, the present invention is not limited to this. The report created by the report creation unit 28 may be displayed in the display area 96.

[0229] Fig. 21 is a fifth diagram showing an example of a display on a user terminal. Screen 91C shown in Fig. 21 shows an example of a screen when, for example, the storage destination displayed in display area 96c of screen 91B shown in Fig. 20 is selected.

[0230] 21 displays a report 97. The report 97 includes display areas 97a and 97b. The display area 97a displays image data obtained as an analysis result by the generation AI system 50, and the display area 97b displays text data obtained as an analysis result by the generation AI system 50.

[0231] As described above, in this embodiment, the information processing system 20 can display the data acquired as the analysis result by the generation AI system 50 on the user terminal 10 as a report in a format that is easy for the user to view.

[0232] In this embodiment, for example, if the user wishes to change the graph shown by the image data of the report 97 to a different type of graph, the user can simply enter a chat message to that effect in the input field 95.

[0233] In the above-described embodiments, the report creation unit 28 is included in the information processing system 20, but this is not limiting. The report creation unit 28 may be provided in, for example, the Web browser 5A. In this case, a program that realizes the report creation unit 28 may be included in the screen information of the analysis screen.

[0234] Each function of the above-described embodiments can be realized by one or more processing circuits. Here, the term "processing circuit" in this specification includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, as well as devices such as an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and conventional circuit modules designed to execute each of the above-described functions.

[0235] Additionally, the devices described in each embodiment represent only one of multiple computing environments for implementing the embodiments disclosed herein.

[0236] In one embodiment, the information processing apparatus that makes up information processing system 20 may include multiple computing devices, such as a server cluster, configured to communicate with each other over any type of communication link, including a network, shared memory, etc., to perform the processes disclosed herein. Similarly, the information processing apparatus that makes up information processing system 20 may include multiple computing devices configured to communicate with each other.

[0237] Furthermore, the information processing devices that make up the information processing system 20 can be configured to share the disclosed processing steps in various combinations. For example, a process executed by a predetermined unit can be executed by an information processing device that makes up the information processing system 20. Similarly, the function of a predetermined unit can be executed by an information processing device that makes up the information processing system 20. Furthermore, in the information processing devices that make up the information processing system 20, each element possessed by each device may be integrated into a single server device or may be separated into multiple devices.

[0238] The information processing devices constituting the information processing system 20 may be any devices equipped with a communication function. The information processing system 20 may be, for example, a PJ (Projector), an IWB (Interactive White Board: a white board with an electronic blackboard function that allows mutual communication), an output device such as digital signage, a HUD (Head Up Display) device, industrial machinery, an imaging device, a sound collection device, medical equipment, a network home appliance, an automobile (Connected Car), a notebook PC (Personal Computer), a mobile phone, a smartphone, a tablet terminal, a game console, a PDA (Personal Digital Assistant), a digital camera, a wearable PC, a desktop PC, or the like.

[0239] For example, aspects of the present invention are as follows. <1> An information processing device that communicates with a terminal device and a generation AI system via a network, a communication unit that receives from the terminal device a request for acquiring screen information of an analysis screen for data managed by the application, including application identification information, and transmits to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; a chat control unit that, when the communication unit receives from the terminal device a chat message requesting analysis input into the analysis screen displayed on the terminal device, sends to the generation AI system a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application, and receives from the generation AI system a response message including the call of the function, The communication unit further sending a response message including the call of the function received by the chat control unit to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further An information processing device that transmits a report including the analysis results to the terminal device. <2> the terminal device has a first web browser that communicates with the application service and a second web browser that communicates with the first web browser; The communication unit receiving, from the second Web browser, a request to acquire the screen information transmitted from the first Web browser to the second Web browser in response to an operation on the first Web browser, and transmitting the screen information to the second Web browser; The chat control unit a chat control unit that, when the communication unit receives from the second web browser the chat message entered on the analysis screen displayed on the second web browser, sends a request message to the generation AI system that includes the chat message, information about the application, and information for calling the function, and receives a response message from the generation AI system that includes a call to the function, The communication unit further a response message including the call of the function received by the chat control unit is sent to the second Web browser, and the second Web browser receives the analysis data created by acquiring data from the application service based on the function via the first Web browser from the second Web browser; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further sending a report containing the analysis results to the web browser; <1> The information processing device described. <3> The chat control unit When the communication unit receives a request message requesting creation of a thread from the second web browser, the communication unit transmits the request message to the generation AI system and obtains a thread ID identifying the thread from the generation AI system; The chat control unit the communication unit transmits the thread ID to the second web browser, and upon receiving a request message from the second web browser requesting uploading of the analysis data to the generation AI system, transmits the request message to the generation AI system, and obtains a file ID from the generation AI system that identifies the uploaded analysis data; The chat control unit the communication unit transmits the file ID to the second web browser, and upon receiving a request message from the second web browser in response to the transmission of the file ID, requesting designation of the analysis data referenced in the thread, transmits the request message to the generation AI system; <2> The information processing device described. <4> The data managed by the application is JSON format data, and the analysis data is a CSV format file. <1> ~ <3> 10. The information processing device according to claim 9, wherein: <5> a report creation unit that creates the report using the analysis result included in the response message; The communication unit transmitting the report created by the report creation unit to the terminal device; <1> ~ <4> 10. The information processing device according to claim 9, wherein: <6> A report creation system in which a terminal device, a generation AI system, an application service, and an information processing device communicate with each other via a network, The information processing device includes: a communication unit that receives from the terminal device a request for acquiring screen information of an analysis screen for data managed by the application, including application identification information, and transmits to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; a chat control unit that, when the communication unit receives from the terminal device a chat message requesting analysis input into the analysis screen displayed on the terminal device, sends to the generation AI system a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application, and receives from the generation AI system a response message including the call of the function, The communication unit further sending a response message including the call of the function received by the chat control unit to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further sending a report including the analysis results to the terminal device; the terminal device has a web browser, The web browser an operation receiving unit that receives an operation to start analysis of the data on the analysis screen displayed on the display device of the terminal device; a second communication unit that receives a response message including a call to the function, acquires data managed by the application from the information processing device or application service that provides the application, creates the analysis data, and transmits a request message to the information processing device requesting uploading of the analysis data to the generation AI system; a display control unit that displays the report received from the information processing device on the display device. <7> An information processing device that communicates with the terminal device and the generation AI system via a network, receive from the terminal device a request for acquiring screen information of an analysis screen for data managed by the application, including application identification information, and transmit to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; When a chat message requesting analysis entered on the analysis screen displayed on the terminal device is received from the terminal device, a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application is sent to the generation AI system, and a response message including the call of the function is received from the generation AI system; sending a response message including a call to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; A program that executes a process of sending a report including the analysis results to the terminal device. <8> An information processing device that communicates with a terminal device and a generation AI system via a network, receive from the terminal device a request for acquiring screen information of an analysis screen for data managed by the application, including application identification information, and transmit to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; When a chat message requesting analysis entered on the analysis screen displayed on the terminal device is received from the terminal device, a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application is sent to the generation AI system, and a response message including the call of the function is received from the generation AI system; sending a response message including a call to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; and transmitting a report including the analysis results to the terminal device.

[0240] Although the present invention has been described above based on the embodiments, the present invention is not limited to the requirements shown in the above embodiments. These requirements can be changed without departing from the spirit of the present invention, and can be appropriately determined depending on the application form. [Explanation of symbols]

[0241] 5, 5A, 5B Web Browser 10 User terminal 14 Data Analysis Department 15, 19 Inter-browser communication section 20 Information Processing Systems 22 Screen generation section 23 Chat control section 24 Setting information storage unit 25 Program output section 40 Application Services 50 Generative AI System 100 Reporting System [Prior art documents] [Patent documents]

[0242] [Patent Document 1] Japanese Patent Application Publication No. 2023-018851

Claims

1. An information processing device that communicates with a terminal device and a generation AI system via a network, a communication unit that receives from the terminal device a request to acquire screen information of an analysis screen for data managed by the application, including application identification information, and transmits to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; a chat control unit that, when the communication unit receives from the terminal device a chat message requesting analysis input into the analysis screen displayed on the terminal device, sends to the generation AI system a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application, and receives from the generation AI system a response message including the call of the function; The communication unit further sending a response message including the call of the function received by the chat control unit to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further An information processing device that transmits a report including the analysis results to the terminal device.

2. the terminal device has a first web browser that communicates with the application service and a second web browser that communicates with the first web browser; The communication unit receiving, from the second Web browser, a request for acquiring the screen information transmitted from the first Web browser to the second Web browser in response to an operation on the first Web browser, and transmitting the screen information to the second Web browser; The chat control unit a chat control unit that, when the communication unit receives from the second web browser the chat message input on the analysis screen displayed on the second web browser, sends a request message to the generation AI system that includes the chat message, information about the application, and information for calling the function, and receives a response message from the generation AI system that includes a call to the function; The communication unit further a response message including the call of the function received by the chat control unit is sent to the second web browser, and the second web browser receives the analysis data created by acquiring data from the application service based on the function via the first web browser from the second web browser; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further The information processing apparatus according to claim 1 , further comprising: a report including the analysis results transmitted to the web browser.

3. The chat control unit When the communication unit receives a request message requesting creation of a thread from the second web browser, the communication unit transmits the request message to the generation AI system and obtains a thread ID identifying the thread from the generation AI system; The chat control unit the communication unit transmits the thread ID to the second web browser, and upon receiving a request message from the second web browser requesting uploading of the analysis data to the generation AI system, transmits the request message to the generation AI system, and obtains a file ID from the generation AI system that identifies the uploaded analysis data; The chat control unit The information processing device of claim 2, wherein the communication unit transmits the file ID to the second web browser, and when it receives a request message from the second web browser requesting the specification of the analysis data referenced in the thread in response to the transmission of the file ID, it transmits the request message to the generation AI system.

4. 3. The information processing apparatus according to claim 1, wherein the data managed by the application is data in JSON format, and the analysis data is a file in CSV format.

5. a report creation unit that creates the report using the analysis result included in the response message; The communication unit The information processing apparatus according to claim 1 , wherein the report created by the report creating unit is transmitted to the terminal device.

6. A report creation system in which a terminal device, a generating AI system, an application service, and an information processing device communicate with each other via a network, The information processing device includes: a communication unit that receives from the terminal device a request to acquire screen information of an analysis screen for data managed by the application, including application identification information, and transmits to the terminal device the screen information, including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; a chat control unit that, when the communication unit receives from the terminal device a chat message requesting analysis input into the analysis screen displayed on the terminal device, sends to the generation AI system a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application, and receives from the generation AI system a response message including the call of the function; The communication unit further sending a response message including the call of the function received by the chat control unit to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; The chat control unit further Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; The communication unit further sending a report including the analysis results to the terminal device; the terminal device has a web browser, The web browser an operation receiving unit that receives an operation to start analysis of the data on the analysis screen displayed on the display device of the terminal device; a second communication unit that receives a response message including a call to the function, acquires data managed by the application from an application service that provides the application, creates the analysis data, and transmits a request message to the information processing device that requests uploading of the analysis data to the generation AI system; a display control unit that causes the display device to display the report received from the information processing device.

7. An information processing device that communicates with the terminal device and the generation AI system via a network, receive from the terminal device a request to acquire screen information of an analysis screen for data managed by the application, including application identification information, and transmit to the terminal device the screen information including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; When a chat message requesting analysis entered on the analysis screen displayed on the terminal device is received from the terminal device, a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application is sent to the generation AI system, and a response message including the call of the function is received from the generation AI system; sending a response message including a call to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; A program that executes a process of sending a report including the analysis results to the terminal device.

8. An information processing device that communicates with a terminal device and a generation AI system via a network, receive from the terminal device a request to acquire screen information of an analysis screen for data managed by the application, including application identification information, and transmit to the terminal device the screen information including an analysis program that causes the terminal device to acquire the data managed by the application, create analytical data, and upload the data to the generation AI system; When a chat message requesting analysis entered on the analysis screen displayed on the terminal device is received from the terminal device, a request message including the chat message, information about the application identified by the identification information, and information for calling a function that specifies data to be obtained from the information processing device or application service that provides the application is sent to the generation AI system, and a response message including the call of the function is received from the generation AI system; sending a response message including a call to the terminal device, and receiving the analysis data created from the data acquired based on the function from the terminal device; Sending a request message to the generation AI system requesting analysis of the analysis data, and receiving a response message including an analysis result from the generation AI system; and transmitting a report including the analysis results to the terminal device.

Images