Information processing device, information processing method, and information processing program

Abstract

To output an appropriate answer when a generative AI accepts a question regarding an ability of a system or itself under a situation that the generative AI is integrated in the system to be used.SOLUTION: An information processing device 16 acquires interaction data input from a user. The information processing device 16 refers to a system configuration database 162 in which configuration data representing a configuration of an information processing system 10 is stored and outputs answer data according to the configuration data when the interaction data represents a question regarding an ability of the information processing system 10 or a generative AI.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] A technology called RAG (Retrieval-Augmented Generation) has been known in the past (see, for example, Non-Patent Documents 1 and 2). By combining artificial intelligence (AI) and RAG, it is possible to make the data output from the artificial intelligence more appropriate. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Patrick Lewis, et al. "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks", [Retrieved February 29, 2024], Internet<URL:https: / / arxiv.org / abs / 2005.11401> [Non-patent document 2] Yunfan Gao, et al. "Retrieval-Augmented Generation for Large Language Models: A Survey", [Retrieved February 29, 2024], Internet<URL:https: / / arxiv.org / abs / 2312.10997> Summary of the Invention [Problem to be solved by the invention]

[0004] As disclosed in Non-Patent Documents 1 and 2, using RAG allows the generation AI to refer to a knowledge database. This allows, for example, when document data is stored in the knowledge database, the generation AI to refer to the document data and output an appropriate answer to a question.

[0005] However, when considering a scenario in which a user and a generating AI are interacting, the user may ask the generating AI a question about its capabilities. For example, the user may ask the generating AI a question such as, "Is it possible to do X?" In such a case, the generating AI may give an inappropriate answer because it is not aware that it is incorporated into the RAG system.

[0006] Although the above Non-Patent Documents 1 and 2 disclose techniques related to RAG, they do not disclose how to deal with a case where a question about the generating AI's abilities is asked.

[0007] The present disclosure has been made in consideration of the above points, and aims to output an appropriate answer when a generative AI receives a question about the system or its own capabilities in a situation where the generative AI is incorporated into a system and used. [Means for solving the problem]

[0008] In order to achieve the above-mentioned objective, the information processing device disclosed herein is an information processing device used when using a system incorporating a generative AI (Artificial Intelligence), and is equipped with an acquisition unit that acquires dialogue data input by a user, and an answer unit that determines whether the dialogue data represents a question regarding the capabilities of the system or the generative AI, and if the dialogue data represents a question regarding the capabilities of the system or the generative AI, refers to a system configuration database in which configuration data representing the configuration of the system is stored, and outputs answer data corresponding to the configuration data.

[0009] In addition, the information processing method disclosed herein is an information processing method executed by a computer constituting an information processing device used when using a system incorporating a generative AI (artificial intelligence), which acquires dialogue data input by a user, determines whether the dialogue data represents a question regarding the capabilities of the system or the generative AI, and, if the dialogue data represents a question regarding the capabilities of the system or the generative AI, refers to a system configuration database in which configuration data representing the configuration of the system is stored, and outputs answer data corresponding to the configuration data.

[0010] In addition, the information processing program disclosed herein is an information processing program to be executed by a computer constituting an information processing device used when using a system incorporating a generative AI (artificial intelligence), and is an information processing program that acquires dialogue data input by a user, determines whether the dialogue data represents a question regarding the capabilities of the system or the generative AI, and if the dialogue data represents a question regarding the capabilities of the system or the generative AI, refers to a system configuration database in which configuration data representing the configuration of the system is stored, and outputs answer data corresponding to the configuration data. [Effects of the Invention]

[0011] According to the information processing device, information processing method, and information processing program disclosed herein, when a generation AI is incorporated into a system and used, the generation AI can output an appropriate answer when it receives a question about the system or its own capabilities. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an information processing system according to an embodiment. [Figure 2] 1 is a block diagram illustrating a schematic configuration of an information processing system according to an embodiment. [Figure 3]1 is a block diagram showing a hardware configuration of an information processing apparatus according to an embodiment; [Figure 4] FIG. 2 is a diagram illustrating a system configuration database according to the embodiment. [Figure 5] 1 is a flowchart showing a flow of information processing in an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of the present disclosure will be described below with reference to the drawings. In this embodiment, an information processing system including an information processing device according to the present disclosure will be described as an example. Note that the same reference numerals are used in each drawing to designate identical or equivalent components and parts. Furthermore, the dimensions and proportions of the drawings are exaggerated for the sake of explanation and may differ from the actual proportions.

[0014] Fig. 1 is a diagram for explaining an embodiment. Fig. 1 shows an administrative user M, a user U, a generation AI, and a database. The system shown in Fig. 1 is assumed to be implemented with the above-mentioned RAG (Retrieval-Augmented Generation).

[0015] In this case, as shown in FIG. 1, for example, administrative user M stores document data in a database (S1 in FIG. 1). Then, administrative user M works to implement the RAG in the system. For example, administrative user M implements the RAG using a known framework for building applications related to generative AI (S2 in FIG. 1). This enables the generative AI to search for data in the database and to answer questions from users while referring to the text data stored in the database.

[0016] For example, when a question is received from user U (S3 in Figure 1), the generation AI searches the database (S4 in Figure 1) and obtains document data related to the question (S5 in Figure 1).Then, the generation AI outputs answer data corresponding to the obtained document data (S6 in Figure 1).

[0017] Here, consider a case where, for example, when an administrative user M stores document data in a database, the metadata attached to the document data is deleted before the data is stored in the database. In such a case, when a user U asks the generation AI a question such as "Can you handle metadata (in the system)?", the generation AI may output a response such as "(I = the generation AI) can handle metadata," even though the metadata of the document data stored in the database has been deleted.

[0018] In this way, when a generative AI built into a system is asked by a user about its own abilities, it may respond by only mentioning its own abilities without properly understanding the constraints of the components around it within the system.

[0019] Therefore, the information processing device of the embodiment controls the data output from the generation AI by referring to configuration data that represents the system configuration. As a result, when the generation AI is incorporated into a system and used, it can output an appropriate answer when it receives a question about its own capabilities. This will be explained in detail below.

[0020] <Information Processing System 10 of the Embodiment> 2 is a block diagram showing a schematic configuration of an information processing system 10 according to an embodiment. As shown in the figure, the information processing system 10 includes a management terminal 12-1 operated by a management user M, a user terminal 12-2 operated by a user U, a database server 14, and an information processing device 16. The management terminal 12-1, the user terminal 12-2, the database server 14 on which the generation AI 4 runs, and the information processing device 16 are communicatively connected via a network 30 such as the Internet or an in-house LAN.

[0021] The management terminal 12-1 is operated by a management user M. By operating the management terminal 12-1, the management user M configures the information processing system 10, which is a system incorporating a generation AI. For example, the management user M operates the management terminal 12-1 to operate a known system management tool, thereby changing the configuration of the information processing system 10 and making other settings. When the configuration of the information processing system 10 is changed by the management user M, the information is stored in a system configuration database 162, which will be described later. Note that while FIG. 2 illustrates one management user M and one management terminal 12-1 as an example, in reality, there may be more management users and management terminals.

[0022] The user terminal 12-2 is operated by a user U. The user U interacts with the generation AI by operating the user terminal 12-2. The generation AI is stored in a generation AI storage unit 160 of the information processing device 16, which will be described later. While FIG. 2 illustrates one user U and one user terminal 12-2, in reality, there may be more users and user terminals.

[0023] The management terminal 12-1 and the user terminal 12-2 are realized by a computer such as that shown in FIG. 3, which will be described later.

[0024] The database server 14 is a server that is used when a RAG is implemented in the information processing system 10. As shown in FIG.

[0025] The control unit 140 receives a control signal output from the information processing device 16, which will be described later, and outputs data stored in the database 142 in response to the control signal.

[0026] Various types of data used when using RAG are stored in the database 142. For example, the database 142 stores document data.

[0027] When RAG is implemented in the information processing system 10, for example, when the control unit 140 receives a control signal output from the information processing device 16, it searches the database 142 in accordance with the control signal and outputs specified data to the information processing device 16.

[0028] 3 is a block diagram showing the hardware configuration of an information processing device 16 according to an embodiment. As shown in FIG. 3, the information processing device 16 includes a CPU (Central Processing Unit) 42, a memory 44, a storage device 46, an input / output I / F (Interface) 48, a storage medium reader 50, and a communication I / F 52. Each component is communicably connected to one another via a bus 54. As will be described later, the information processing device 16 stores a generated AI in its own storage unit, a generated AI storage unit 160, and the description will be given taking as an example a case where the generated AI is used; however, the information processing device 16 may also use a generated AI provided via a network 30 from an external generated AI system different from the information processing device 16.

[0029] The storage device 46 stores information processing programs for executing the various processes described below. The CPU 42 is a central processing unit that executes various programs and controls the various components. That is, the CPU 42 reads the programs from the storage device 46 and executes the programs using the memory 44 as a work area. The CPU 42 controls the various components and performs various arithmetic processes in accordance with the programs stored in the storage device 46.

[0030] The memory 44 is made up of RAM (Random Access Memory) and serves as a working area to temporarily store programs and data. The storage device 46 is made up of ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), etc., and stores various programs including the operating system and various data.

[0031] The input / output I / F 48 is an interface for inputting data from an external device and outputting data to an external device. Also, input devices for various inputs, such as a keyboard or a mouse, and output devices for various information outputs, such as a display or a printer, may be connected. A touch panel display may be used as the output device, allowing it to function as an input device.

[0032] The storage medium reader 50 reads data stored in various storage media such as CD (Compact Disc)-ROM, DVD (Digital Versatile Disc)-ROM, Blu-ray Disc, and USB (Universal Serial Bus) memory, and writes data to the storage media.

[0033] The communication I / F 52 is an interface for communicating with other devices, and uses standards such as Ethernet (registered trademark), FDDI, and Wi-Fi (registered trademark).

[0034] Next, the functional configuration of the information processing device 16 will be described. As shown in Fig. 2, the information processing device 16 functionally includes an acquisition unit 164 and a response unit 166. A predetermined storage area of ​​the information processing device 16 also includes a generation AI storage unit 160 and a system configuration database 162. Each functional configuration is realized by the CPU 42 reading out each program stored in the storage device 46, expanding it in the memory 44, and executing it.

[0035] The generated AI is stored in the generated AI storage unit 160. The generated AI 4 is an AI realized by known machine learning technology and known artificial intelligence technology, for example, an AI using a large-scale language model.

[0036] The system configuration database 162 stores configuration data that represents the configuration of the information processing system 10. When the administrative user M makes a change to the system configuration of the information processing system 10, the administrative user M stores the configuration data that represents the configuration of the information processing system 10 in the system configuration database 162. For example, the system configuration database 162 stores table data such as those shown in FIGS. 4(A) and (B).

[0037] Fig. 4(A) is a diagram showing an example in which data on the components of the information processing system 10 is stored in the system configuration database 162 as configuration data representing the configuration of the information processing system 10. Note that Fig. 4(A) also shows details when a system component is added, and the generation AI described below also references these details to generate answer data.

[0038] 4(B) is a diagram showing an example in which change history data representing the change history of the configuration of the information processing system 10 is stored in the system configuration database 162 as configuration data representing the configuration of the information processing system 10. Note that FIG. 4(B) also shows details of when the system was changed, and the generation AI described below also references these details to generate answer data.

[0039] Note that the configuration data does not have to be table data such as those shown in Figures 4(A) and (B). For example, a system configuration diagram of the information processing system 10 may be stored in the system configuration database 162 as the configuration data. In this case, the generation AI described below reads the system configuration diagram, which is the configuration data. Alternatively, for example, data such as a snapshot of the system configuration diagram or specifications of the information processing system 10 at each point in time may be stored in the system configuration database 162 as the configuration data. In this case, the generation AI described below reads data such as a snapshot of the system configuration diagram or specifications, which is the configuration data.

[0040] The acquisition unit 164 acquires dialogue data input from a user U who is a dialogue partner of the generation AI. For example, the acquisition unit 164 acquires dialogue data output from the user terminal 12-2 when the user U operates the user terminal 12-2.

[0041] The response unit 166 reads out the generated AI stored in the generated AI storage unit 160 and operates the generated AI, thereby allowing a dialogue to take place between the user U operating the user terminal 12-2 and the generated AI 4.

[0042] The answering unit 166 determines whether the dialogue data acquired by the acquiring unit 164 represents a question about the capabilities of the information processing system 10 or the generation AI. Note that a question about capabilities is, for example, a question about what components (e.g., databases) the information processing system 10 is connected to, a question about the interface between the information processing system 10 and each component, or a question about restrictions on the handling of data, etc. in each component (e.g., metadata has been deleted, or file names cannot be used as search keys, etc.).

[0043] For example, the answering unit 166 determines whether the dialogue data represents a question about the capabilities of the information processing system 10 or the generation AI using a known natural language processing technique or a known artificial intelligence technique. For example, if the dialogue data is "Can you handle file names?", the answering unit 166 determines that the dialogue data is a question about capabilities using a known natural language processing technique or a known artificial intelligence technique. Note that, for example, if the dialogue data is an instruction to "extract Y contained in file X," the instruction implicitly includes a "question about capabilities (intention or trust)" such as "You can handle file names, right?" In this case, the answering unit 166 also determines that the dialogue data is a question about capabilities using a known natural language processing technique or a known artificial intelligence technique.

[0044] If the dialogue data represents a question regarding the capabilities of the information processing system 10 or the generation AI, the answering unit 166 refers to the system configuration database 162 in which configuration data representing the configuration of the information processing system 10 is stored, and outputs answering data corresponding to the configuration data.

[0045] On the other hand, if the dialogue data acquired by the acquisition unit 164 does not represent a question regarding the capabilities of the information processing system 10 and the generation AI, the answering unit 166 inputs the dialogue data into the generation AI, causing the generation AI to output data, and outputs the data output from the generation AI as answer data.

[0046] When the dialogue data represents a question about the capabilities of the information processing system 10 or the generation AI, the following methods can be considered as a method for generating answer data.

[0047] (Method 1: Enter a specific prompt for the generated AI) For example, the answering unit 166 generates answer data according to the configuration data of the system configuration database 162 by inputting a predetermined prompt to the generation AI. Specifically, when the dialogue data represents a question about the capabilities of the information processing system 10 or the generation AI, the answering unit 166 inputs a prompt to the generation AI instructing it to refer to the system configuration database 162. For example, an example of a predetermined prompt is, "The question from the user is about the capabilities of the information processing system 10 or the generation AI. Therefore, please refer to the system configuration database 162 to generate answer data." When a prompt instructing it to refer to the system configuration database 162 is input to the generation AI, the generation AI accesses the system configuration database 162 itself and generates answer data by referring to the configuration data. As a result, for example, when the dialogue data input by the user U represents a question such as "Can you handle metadata?", answer data such as "No, we cannot handle metadata" is output from the generation AI.

[0048] (Method 2: Enter a specific prompt for the generated AI) Alternatively, the following method may be considered as a method for inputting a predetermined prompt to the generation AI. When the dialogue data represents a question regarding the capabilities of the information processing system 10 or the generation AI, the answering unit 166 acquires configuration data by referring to the system configuration database 162. Then, the answering unit 166 inputs the acquired configuration data and a prompt instructing the generation AI to generate an answer based on the configuration data to the generation AI. For example, an example of the predetermined prompt is, "The question from the user is regarding the capabilities of the information processing system 10 or the generation AI. Therefore, please generate answer data based on the following configuration data. Configuration data: XX." Then, the answering unit 166 causes the generation AI to output data and outputs the data output from the generation AI as answer data. As a result, for example, when the dialogue data input by user U represents a question such as "Can you handle metadata?", answer data such as "No, we cannot handle metadata" is output from the generation AI.

[0049] (How to correct data output from a generative AI) Alternatively, for example, the answering unit 166 generates answer data corresponding to the configuration data of the system configuration database 162 by modifying the data output from the generation AI. Specifically, when the dialogue data represents a question regarding the capabilities of the information processing system 10 and the generation AI, the answering unit 166 first inputs the dialogue data to the generation AI, causing the generation AI to output data. Then, the answering unit 166 generates answer data by modifying the data output from the generation AI with reference to the configuration data of the system configuration database 162. For example, suppose that dialogue data input from user U is a question such as "Can you handle metadata?" and when that dialogue data is input to the generation AI, data such as "(I = the generation AI) can handle metadata" is output from the generation AI. In this case, the data "(I = the generation AI) can handle metadata" is modified to "The generation AI cannot handle metadata." Note that, for example, the answering unit 166 modifies the data output from the generation AI based on a rule base. Alternatively, for example, the response unit 166 modifies the data output from the generation AI based on known natural language processing technology or known artificial intelligence technology so that the configuration data of the system configuration database 162 is reflected in the response data.

[0050] The response unit 166 may output more detailed response data rather than simply saying, "Metadata cannot be handled." For example, the response unit 166 may refer to the data in the "Details" section shown in Figures 4(A) and 4(B) and output response data such as, "Metadata cannot be handled. This is because the metadata of the document data stored in the linked database has been deleted."

[0051] Alternatively, the response unit 166 may refer to the change history data shown in Figure 4(B) and output response data such as, "A database was added on November 20, 2023, but the metadata in that database has been deleted, so the metadata cannot be used."

[0052] Also, for example, as described above, if the dialogue data is "Can you handle file names?" or "Please extract Y contained in file X," the answering unit 166 outputs answer data such as "This system does not allow searching by file name."

[0053] Next, the operation of the information processing system 10 according to this embodiment will be described.

[0054] The CPU 42 of the information processing device 16 reads the information processing program from the storage device 46, expands it in the memory 44, and executes it. As a result, the CPU 42 functions as each functional component of the information processing device 16, the information processing shown in Fig. 5 is executed, and a dialogue is started between the user U and the generation AI.

[0055] In step S100, the acquisition unit 164 acquires the dialogue data output from the user terminal 12-2.

[0056] In step S102, the answering unit 166 determines whether the dialogue data acquired in step S100 represents a question about the capabilities of the information processing system 10 or the generation AI. If the dialogue data represents a question about the capabilities of the information processing system 10 or the generation AI, the process proceeds to step S104. On the other hand, if the dialogue data does not represent a question about the capabilities of the information processing system 10 or the generation AI, the process proceeds to step S106.

[0057] In step S104, the response unit 166 refers to the system configuration database 162 in which configuration data representing the configuration of the information processing system 10 is stored, and generates response data according to the configuration data.

[0058] In step S106, the response unit 166 inputs the dialogue data to the generation AI, causing the generation AI to output data, and sets the data as response data.

[0059] In step S108, the response unit 166 outputs the response data generated in step S104 or step S106 to the user terminal 12-2.

[0060] The user terminal 12-2 acquires the answer data output from the information processing device 16 and displays it on a display unit (not shown). A user U who operates the user terminal 12-2 checks the answer data.

[0061] As described above, an information processing device according to an embodiment is used when using a system in which a generation AI is incorporated. The information processing device acquires dialogue data input by a user. When the dialogue data represents a question about the capabilities of the system or the generation AI, the information processing device references a system configuration database in which configuration data representing the system configuration is stored and outputs answer data corresponding to the configuration data. This allows the generation AI to output an appropriate answer when it receives a question about the system or its own capabilities in a situation in which the generation AI is incorporated into a system and used. In particular, the information processing device according to an embodiment provides the generation AI with configuration data of the system in which the generation AI itself is incorporated as prior knowledge, and has the generation AI respond based on this data. As a result, when the system settings and configuration are changed, the configuration data is updated and the generation AI's prior knowledge is also updated.

[0062] The technology of the present disclosure is not limited to the above-described embodiment, and various modifications and applications are possible within the scope of the gist of this disclosure.

[0063] For example, in the above embodiment, the information processing device has each database, but this is not limiting. For example, each database may exist outside the information processing device.

[0064] Furthermore, the information processing device 16 has been described as including a generation AI storage unit 160 and using a generation AI stored in the generation AI storage unit 160, but this is not limiting. For example, a generation AI provided by a generation AI system different from the information processing device 16 may be used.

[0065] Furthermore, in the above embodiment, an example was described in which RAG was implemented in the information processing system 10, but this is not limiting. For example, when another system cooperates with the information processing system 10, the data may be added to the system configuration database 162. For example, as shown in FIGS. 4(A) and 4(B), data on components such as a spreadsheet system and a translation system may be stored as configuration data in the system configuration database 162. In this case, in response to a question from user U such as "Can you translate?", the answering unit 166 may refer to the configuration data and output answer data such as "Yes, we can translate. However, if I translate, a fee based on tokens will be charged, but if you use the linked translation system on December 20, 2023, the translation will be free."

[0066] Furthermore, the processes executed by the CPU after reading the software (program) in the above-described embodiments may be executed by various processors other than the CPU. Examples of such processors include programmable logic devices (PLDs) whose circuit configuration can be changed after fabrication, such as field-programmable gate arrays (FPGAs), and dedicated electrical circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed to execute specific processes. Each process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0067] In the above embodiment, the programs are pre-stored (installed) in a storage device, but the present invention is not limited to this. The programs may be provided in a form stored on a storage medium such as a CD-ROM, DVD-ROM, Blu-ray disc, or USB memory. The programs may also be downloaded from an external device via a network.

[0068] (Addendum) The following additional notes are provided regarding aspects of the present disclosure.

[0069] (Appendix 1) An information processing device used when using a system incorporating generative AI (Artificial Intelligence), an acquisition unit that acquires interaction data input by a user; an answering unit that determines whether the dialogue data represents a question about the capabilities of the system or the generation AI, and if the dialogue data represents a question about the capabilities of the system or the generation AI, refers to a system configuration database in which configuration data representing the configuration of the system is stored, and outputs answer data corresponding to the configuration data; An information processing device comprising: (Appendix 2) The system configuration database further stores change history data representing a change history of the system configuration, the response unit refers to the change history data stored in the system configuration database, and outputs the response data corresponding to the change history data. 2. The information processing device according to claim 1. (Appendix 3) The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generation AI, inputting the dialogue data into the generation AI to cause the generation AI to output data, and outputting the data output from the generation AI; If the dialogue data represents a question about the capabilities of the system or the generation AI, the configuration data is acquired by referring to the system configuration database, and the acquired configuration data and a prompt instructing the generation AI to generate an answer based on the configuration data are input to the generation AI, causing the generation AI to output data, and the data output from the generation AI is output as the answer data. 10. The information processing device according to claim 1 or 2. (Appendix 4) The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generation AI, inputting the dialogue data into the generation AI to cause the generation AI to output data, and outputting the data output from the generation AI; If the dialogue data represents a question about the capabilities of the system or the generation AI, a prompt instructing the generation AI to refer to the system configuration database is input to the generation AI, causing the generation AI to output data, and the data output from the generation AI is output as the answer data. 10. The information processing device according to claim 1 or 2. (Appendix 5) The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generation AI, inputting the dialogue data into the generation AI to cause the generation AI to output data, and outputting the data output from the generation AI; If the dialogue data represents a question about the capabilities of the system or the generation AI, the dialogue data is input to the generation AI to cause the generation AI to output data, the data output from the generation AI is modified to generate the answer data, and the answer data is output. 10. The information processing device according to claim 1 or 2. (Appendix 6) The generating AI is an AI that uses a large-scale language model. An information processing device according to any one of Supplementary notes 1 to 5. (Appendix 7) An information processing method executed by a computer constituting an information processing device used when using a system incorporating generative AI (Artificial Intelligence), Acquire user-input interaction data; determining whether the dialogue data represents a question about the capabilities of the system or the generation AI, and if the dialogue data represents a question about the capabilities of the system or the generation AI, refer to a system configuration database in which configuration data representing the configuration of the system is stored, and output answer data according to the configuration data; Information processing methods. (Appendix 8) An information processing program to be executed by a computer constituting an information processing device used when using a system incorporating a generative AI (Artificial Intelligence), Acquire user-input interaction data; determining whether the dialogue data represents a question about the capabilities of the system or the generation AI, and if the dialogue data represents a question about the capabilities of the system or the generation AI, refer to a system configuration database in which configuration data representing the configuration of the system is stored, and output answer data according to the configuration data; Information processing program. [Explanation of symbols]

[0070] 10 Information Processing Systems 12-1 Management terminal 12-2 User terminal 14 Database Server 16 Information processing equipment 160 Generation AI storage unit 162 System Configuration Database 164 Acquisition Department 166 Answer section

Claims

1. An information processing device used when using a system incorporating artificial intelligence (AI), an acquisition unit that acquires dialogue data input by a user; an answering unit that determines whether the dialogue data represents a question about the capabilities of the system or the generating AI, and when the dialogue data represents a question about the capabilities of the system or the generating AI, refers to a system configuration database in which configuration data representing the configuration of the system is stored, and outputs answer data according to the configuration data; An information processing device comprising:

2. The system configuration database further stores change history data representing a change history of the system configuration, the response unit refers to the change history data stored in the system configuration database, and outputs the response data corresponding to the change history data. The information processing device according to claim 1 .

3. The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generating AI, inputting the dialogue data into the generating AI to output data from the generating AI, and outputting the data output from the generating AI; If the dialogue data represents a question regarding the capabilities of the system or the generating AI, the configuration data is obtained by referring to the system configuration database, and the obtained configuration data and a prompt instructing the generating AI to generate an answer based on the configuration data are input to the generating AI, thereby causing the generating AI to output data, and the data output from the generating AI is output as the answer data.

3. The information processing device according to claim 1.

4. The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generating AI, inputting the dialogue data into the generating AI to output data from the generating AI, and outputting the data output from the generating AI; If the dialogue data represents a question about the capabilities of the system or the generating AI, a prompt is input to the generating AI instructing it to refer to the system configuration database, thereby causing the generating AI to output data, and the data output from the generating AI is output as the answer data.

3. The information processing device according to claim 1.

5. The answering section If the dialogue data does not represent a question regarding the capabilities of the system and the generating AI, inputting the dialogue data into the generating AI to output data from the generating AI, and outputting the data output from the generating AI; If the dialogue data represents a question regarding the capabilities of the system or the generating AI, the dialogue data is input to the generating AI to cause the generating AI to output data, the data output from the generating AI is modified to generate the answer data, and the answer data is output.

3. The information processing device according to claim 1.

6. The generative AI is an AI that uses a large-scale language model.

3. The information processing device according to claim 1.

7. An information processing method executed by a computer constituting an information processing device used when using a system incorporating artificial intelligence (AI), Acquire user-input interaction data; determining whether the dialogue data represents a question about the capabilities of the system or the generating AI, and if the dialogue data represents a question about the capabilities of the system or the generating AI, refer to a system configuration database in which configuration data representing the configuration of the system is stored, and output answer data according to the configuration data; Information processing methods.

8. An information processing program to be executed by a computer constituting an information processing device used when using a system incorporating artificial intelligence (AI), Acquire user-input interaction data; determining whether the dialogue data represents a question about the capabilities of the system or the generating AI, and if the dialogue data represents a question about the capabilities of the system or the generating AI, refer to a system configuration database in which configuration data representing the configuration of the system is stored, and output answer data according to the configuration data; Information processing program.

Images