Interaction support apparatus, interaction support method, and interaction support program

Abstract

To facilitate smooth interaction between a human user and a generative AI regarding data common between them.SOLUTION: An interaction support apparatus 16 acquires data stored in a database 18. The interaction support apparatus 16 acquires identification data for identifying a person to which the acquired data is to be presented. When the acquired identification data represents a user, the interaction support apparatus 16 converts the acquired data into a first presentation format in accordance with a logical structure of the data stored in the database. When the acquired identification data represents a generative AI, the interaction support apparatus 16 converts the acquired data into a second presentation format in accordance with the logical structure of the data stored in the database. The interaction support apparatus 16 presents the data in the converted presentation format.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a dialogue support device, a dialogue support method, and a dialogue support program. [Background technology]

[0002] BACKGROUND ART A mentoring system is known that generates information for input to an artificial intelligence (AI) suitable for mentoring without user intervention and provides mentoring to a user (see, for example, Patent Document 1).

[0003] Also, an information processing device is known that analyzes image data and easily generates a layout for a test using a terminal device (see, for example, Patent Document 2). The new layout generation AI used in this information processing device generates a layout of content that combines elements according to the performance and size of the display of the output terminal device that displays the layout (see, for example, paragraph

[0034] of Patent Document 2).

[0004] Also known is a patent claim creation support device that reduces the variation in quality when creating patent claims or reduces the time required to create claims (see, for example, Patent Document 3). This creation support device graphically displays claims included in claims of past patent applications on a display, accepts changes to the displayed graphic, and generates new claims in text format based on the accepted changes. The creation server corresponding to this creation support device is equipped with a claim generation AI engine that generates and updates claims by having AI learn information from past patent applications. The creation server processes input information with this claim generation AI engine, automatically generating patent claims corresponding to the input keywords (see, for example, paragraph

[0017] ). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7416390 [Patent Document 2] Japanese Patent Publication No. 2023-87805 [Patent Document 3] Japanese Patent Application Publication No. 2023-112150 Summary of the Invention [Problem to be solved by the invention]

[0006] Incidentally, when considering a scenario in which a human and a generative AI are engaged in a dialogue, the data format that is easy for humans to recognize is often different from the data format that is easy for generative AI to recognize. For example, humans may find it easier to recognize data that is presented in graphical or written form than data that is presented in the form of a list of symbols. On the other hand, generative AI may find it easier to recognize data that is presented in the form of a list of symbols than data that is presented in the form of a list of symbols.

[0007] Therefore, when a user and a generating AI have a dialogue related to common data, if the common data is presented to the user and the generating AI in the same presentation format, the presentation formats that are easily recognized by the user and the generating AI will differ, which may result in a problem in which the dialogue between the user and the generating AI is not carried out smoothly.

[0008] The technologies disclosed in the above Patent Documents 1 to 3 generate some information using a generation AI, but do not take into consideration the data format that is easy for users to recognize and the data format that is easy for the generation AI to recognize.

[0009] The present disclosure has been made in consideration of the above points, and aims to facilitate smooth dialogue between a human user and a generation AI when the dialogue relates to common data between the user and the generation AI. [Means for solving the problem]

[0010] In order to achieve the above-mentioned object, the dialogue support device of the present disclosure is a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), and includes: a first acquisition unit that acquires data stored in a database; a second acquisition unit that acquires identification data for identifying a party to whom the data acquired by the first acquisition unit is to be presented; a conversion unit that converts the data acquired by the first acquisition unit into a first presentation format in accordance with the logical structure of the data stored in the database if the identification data acquired by the second acquisition unit represents the user, and converts the data acquired by the first acquisition unit into a second presentation format in accordance with the logical structure of the data stored in the database if the identification data acquired by the second acquisition unit represents the generating AI; and a presentation unit that presents the data whose presentation format has been converted by the conversion unit.

[0011] In addition, the dialogue support device of the present disclosure is a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), and includes: a first acquisition unit that acquires data output by the user operating a device or data output from the generating AI; a second acquisition unit that acquires identification data for identifying the party that output the data acquired by the first acquisition unit; a conversion unit that, if the identification data acquired by the second acquisition unit represents the user, converts the data acquired by the first acquisition unit into data corresponding to the logical structure of data to be stored in a database using a first conversion method, and, if the identification data acquired by the second acquisition unit represents the generating AI, converts the data acquired by the first acquisition unit into data corresponding to the logical structure of data to be stored in the database using a second conversion method; and a reflection unit that reflects the data converted by the conversion unit into the database.

[0012] In addition, the dialogue support method disclosed herein is a dialogue support method executed by a computer constituting a dialogue support device that supports dialogue between a user and a generating AI (Artificial Intelligence), and is a dialogue support method in which the computer executes the following processes: acquire data stored in a database; acquire identification data for identifying the party to whom the acquired data will be presented; and, if the acquired identification data represents the user, convert the acquired data into a first presentation format in accordance with the logical structure of the data stored in the database; and, if the acquired identification data represents the generating AI, convert the acquired data into a second presentation format in accordance with the logical structure of the data stored in the database, and present the data in the converted presentation format.

[0013] In addition, the dialogue support method disclosed herein is a dialogue support method executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), and is a dialogue support method executed by a computer to acquire data output by the user operating a device or data output from the generating AI, acquire identification data for identifying the party that output the acquired data, and, if the acquired identification data represents the user, convert the acquired data using a first conversion method into data corresponding to the logical structure of data stored in a database, and, if the acquired identification data represents the generating AI, convert the acquired data using a second conversion method into data corresponding to the logical structure of data stored in the database, and reflect the converted data in the database.

[0014] In addition, the dialogue support program disclosed herein is a dialogue support program to be executed by a computer constituting a dialogue support device that supports dialogue between a user and a generating AI (Artificial Intelligence), and is a dialogue support program for causing a computer to execute the following processes: acquire data stored in a database; acquire identification data for identifying the party to whom the acquired data will be presented; if the acquired identification data represents the user, convert the acquired data into a first presentation format according to the logical structure of the data stored in the database; and if the acquired identification data represents the generating AI, convert the acquired data into a second presentation format according to the logical structure of the data stored in the database, and present the data with the converted presentation format.

[0015] In addition, the dialogue support program disclosed herein is a dialogue support program to be executed by a computer constituting a dialogue support device that supports dialogue between a user and a generating AI (Artificial Intelligence), and is a dialogue support program that causes a computer to execute the following process: acquire data output by the user operating a device or data output from the generating AI, acquire identification data for identifying the party that output the acquired data, and, if the acquired identification data represents the user, convert the acquired data using a first conversion method into data corresponding to the logical structure of data stored in a database, and, if the acquired identification data represents the generating AI, convert the acquired data using a second conversion method into data corresponding to the logical structure of data stored in the database, and reflect the converted data in the database. [Effects of the Invention]

[0016] According to the dialogue support device, dialogue support method, and dialogue support program disclosed herein, when a dialogue related to common data is held between a human user and a generation AI, the dialogue between the user and the generation AI can be facilitated. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram illustrating a dialogue support system according to an embodiment. [Figure 2] 10A and 10B are diagrams illustrating the data presentation operation of the dialogue support device according to the embodiment. [Figure 3] FIG. 10 is a diagram illustrating a data correction operation of the dialogue support device according to the embodiment. [Figure 4] FIG. 10 is a diagram illustrating a data correction operation of the dialogue support device according to the embodiment. [Figure 5] 1 is a block diagram illustrating a schematic configuration of a dialogue support system according to an embodiment. [Figure 6] FIG. 2 is a block diagram showing a hardware configuration of a control device according to the embodiment. [Figure 7] 10 is a flowchart showing the flow of a dialogue assistance process in the embodiment. [Figure 8] 10 is a flowchart showing the flow of a dialogue assistance process in the embodiment. [Figure 9] FIG. 10 is a diagram for explaining a data presentation process according to the second embodiment. [Figure 10] FIG. 11 is a diagram for explaining a data presentation process according to the third embodiment. [Figure 11] FIG. 10 is a diagram for explaining rules for generating a predetermined presentation format. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of the present disclosure will be described below with reference to the drawings. In this embodiment, a dialogue support system including a dialogue support device according to the present disclosure will be described as an example. Note that the same reference numerals are used in the drawings 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.

[0019] FIG. 1 is a diagram for explaining an embodiment. FIG. 1 shows presentation formats P1 and P2 for information representing the organization of the X division. The presentation format P1 in FIG. 1 represents the X division's organization in a graphical form. On the other hand, the presentation format P2 in FIG. 1 represents the X division's organization using a character string separated by a comma and a semicolon. The presentation format P1 is a presentation format that is easy for human users to recognize. On the other hand, the presentation format P1 is a presentation format that is difficult for a generation AI to recognize. Specifically, the generation AI cannot understand the meaning of the ruled lines and spacing between paragraphs that constitute the structural representation in the presentation format P1, making the presentation format P1 difficult for the generation AI to recognize. Therefore, even if data in the presentation format P1 is presented to the generation AI, recognizing the data in the presentation format P1 requires a lot of time, incurs additional computational costs, and increases the likelihood of recognition errors. In contrast, the presentation format P2 is a presentation format that is easy for a generation AI to recognize. On the other hand, presentation format P2 is a presentation format that is difficult for users to recognize.

[0020] As shown in Figure 1, the user and the generating AI have different formats of information that are easily recognized, which creates the problem that when a dialogue related to common data is held between the user and the generating AI, the dialogue cannot be carried out smoothly.

[0021] Therefore, the dialogue support device of the embodiment makes the dialogue between the user and the generation AI smooth by differentiating the presentation format of the data presented to the user from the presentation format of the data presented to the generation AI.

[0022] FIG. 2 is a diagram illustrating the data presentation operation of the dialogue support device according to the embodiment. In the example of FIG. 2, data representing the organizational structure of the X division is stored in a database. In the database of FIG. 2, the organizational structure of the X division is expressed as a hierarchical structure (or a tree structure). In this case, when the data is presented to a human user 2, the dialogue support device converts the hierarchically structured data stored in the database into a first presentation format P1 and presents it to the user 2. For example, the first presentation format P1 is a format that expresses the logical structure of the data using graphics or text. This is because a human user can more easily understand a structure represented by symbols presented in a graphic or text format than a mere list of symbols. On the other hand, when the data is presented to a generation AI 4, the dialogue support device converts the hierarchically structured data stored in the database into a second presentation format P2 and presents it to the generation AI 4. For example, the second presentation format P1 is a format that expresses the logical structure of the data using a list of symbols. This is because the Generative AI finds it easier to understand a list of symbols presented according to a certain rule than data in the form of diagrams or text. This makes it possible to facilitate a dialogue between User 2 and Generative AI 4 regarding the organizational data of Division X, which is common data.

[0023] 3 and 4 are diagrams for explaining the data correction operation of the dialogue support device of the embodiment. Specifically, Fig. 3 and Fig. 4 are diagrams for explaining a scene in which data output from the user 2 or the generated AI 4 is reflected in data in the database.

[0024] As shown in Figure 3, consider the case where, when data in presentation format P1 is presented to user 2, user 2 corrects "Ito" in the data in presentation format P1 to "Saito." In this case, "Ito" in the database is corrected to "Saito" in accordance with the correction of the data in presentation format P1, and the correction by user 2 is reflected in the database. Also, as shown in Figure 3, when data in presentation format P2 is presented to generation AI4 after the data in the database has been corrected, the data presented is the data in which "Ito" has been corrected to "Saito."

[0025] Also, as shown in Figure 4, consider the case where, when data in presentation format P2 is presented to generation AI4, generation AI4 corrects "Ito" in the data in presentation format P2 to "Saito." In this case, "Ito" in the database is corrected to "Saito" according to the correction of the data in presentation format P2, and the correction by generation AI4 is reflected in the database. Then, as shown in Figure 4, when data in presentation format P1 is presented to user 2 after the data in the database has been corrected, the data presented is the data in which "Ito" has been corrected to "Saito."

[0026] In this way, the dialogue support device of the embodiment facilitates dialogue between the user and the generation AI by differentiating the presentation format of data presented to the user and the generation AI. This will be described in detail below.

[0027] <Dialogue Support System 10 of First Embodiment> Fig. 5 is a block diagram showing a schematic configuration of a dialogue support system 10 according to the first embodiment. As shown in Fig. 5, the dialogue support system 10 includes a user terminal 12 operated by a human user 2, a server 14 on which a generation AI 4 runs, and a dialogue support device 16. The user terminal 12, the server 14 on which the generation AI 4 runs, and the dialogue support device 16 are communicatively connected via a network 30 such as the Internet.

[0028] The user terminal 12 is operated by the user 2. The user 2 interacts with the generated AI 4 by operating the user terminal 12. The user terminal 12 is realized by a computer such as that shown in FIG. 6, which will be described later.

[0029] The server 14 operates the generation AI 4. This allows a dialogue between the user 2 operating the user terminal 12 and the generation AI 4. Specifically, the generation AI 4 is stored in a memory unit (not shown) of the server 14, and the generation AI 4 operates in accordance with control processing by a control unit (not shown) of the server 14. The generation 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. Note that although a large-scale language model is a learning model that primarily generates language, it is also capable of image recognition. Even if the generation AI 4 is capable of image recognition, there are data formats that are difficult for the generation AI 4 to recognize. Therefore, by using the dialogue support device 16 of this embodiment, a dialogue between the user 2 and the generation AI 4 becomes smooth. The server 14 is realized by a computer such as that shown in FIG. 6, which will be described later.

[0030] Note that when a dialogue takes place between the user 2 and the generated AI 4, the dialogue takes place via the dialogue support device 16. As described above, the dialogue support device 16 supports the dialogue between the user 2 and the generated AI 4.

[0031] FIG. 6 is a block diagram showing the hardware configuration of a dialogue support device 16 according to an embodiment. As shown in FIG. 6, the dialogue support 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 reading device 50, and a communication I / F 52. Each component is communicably connected to one another via a bus 54. Note that, in this embodiment, a case is described in which a generated AI provided via a network 30 from a server 14, which is an external generated AI system different from the dialogue support device 16, is used, but this is not limited to this. For example, the dialogue support device 16 may store a generated AI in its own storage device 46 and use the generated AI.

[0032] The storage device 46 stores a dialogue support program for executing each process described below. The CPU 42 is a central processing unit that executes various programs and controls each component. That is, the CPU 42 reads the program from the storage device 46 and executes the program using the memory 44 as a work area. The CPU 42 controls each component and performs various arithmetic processes in accordance with the program stored in the storage device 46.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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).

[0037] Next, the functional configuration of the dialogue support device 16 will be described. As shown in Fig. 5, the dialogue support device 16 functionally includes a first acquisition unit 20, a second acquisition unit 22, a conversion unit 24, a presentation unit 26, and a reflection unit 28. A database 18 is also provided in a predetermined storage area of ​​the dialogue support device 16. 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.

[0038] Data having a predetermined logical structure is stored in the database 18. For example, the database 18 stores data having a logical structure that represents a hierarchical structure between events, as shown in Figures 1 to 4.

[0039] The dialogue support device 16 executes a data presentation process for presenting data stored in the database 18 to the user 2 and the generated AI 4, and a data reflection process for reflecting data input from the user 2 and the generated AI 4 in the database 18. Each process will be described below.

[0040] (Data presentation processing) When presenting data stored in the database 18 to the user 2 and the generated AI 4, each unit of the dialogue support device 16 executes the following process.

[0041] The first acquisition unit 20 acquires data stored in the database 18 .

[0042] The second acquisition unit 22 acquires identification data for identifying the party to whom the data acquired by the first acquisition unit 20 will be presented. For example, the second acquisition unit 22 acquires identification data for identifying whether the party to whom the data will be presented is the user 2 or the generated AI 4, using a known technology for identifying whether the party accessing the dialogue support device 16 is a human or a bot (or AI) (for example, a technology for identifying the IP address of the terminal of the accessing party). Alternatively, for example, if an ID is assigned to each party using the dialogue support device 16, the second acquisition unit 22 acquires identification data for identifying whether the party to whom the data will be presented is the user 2 or the generated AI 4, based on the ID data.

[0043] When the identification data acquired by the second acquisition unit 22 represents the user 2, the conversion unit 24 converts the data acquired by the first acquisition unit 20 into a first presentation format in accordance with the logical structure of the data stored in the database 18. For example, the conversion unit 24 converts the data acquired by the first acquisition unit 20 into a presentation format P1 as shown in FIG.

[0044] On the other hand, when the identification data acquired by the second acquisition unit 22 represents the generated AI4, the conversion unit 24 converts the data acquired by the first acquisition unit 20 into a second presentation format in accordance with the logical structure of the data stored in the database 18. For example, the conversion unit 24 converts the data acquired by the first acquisition unit 20 into a presentation format P2 as shown in FIG.

[0045] The conversion unit 24 converts the data based on predetermined rules according to the logical structure of the data stored in the database 18. For example, if the logical structure of the data stored in the database 18 is a hierarchical structure between events as shown in Fig. 2, there is a one-to-one correspondence between the data in each cell of the presentation format P1 in Fig. 2 and the data of each node in the database 18. Similarly, there is a one-to-one correspondence between the data of character strings separated by a semicolon and a comma in the presentation format P2 in Fig. 2 and the data of each node in the database 18.

[0046] Therefore, when the logical structure of data is a hierarchical structure between events, when presenting data in presentation format P1, the logical structure of the data is presented in a format that expresses it using spatial arrangement. Specifically, the logical structure is presented using columns of cells and spaces within the cells (corresponding to the first presentation format in this embodiment). In this case, data conversion is performed based on the rule that the data of each node in the hierarchical structure is displayed in each cell of presentation format P1. On the other hand, when presenting data in presentation format P2, the logical structure of the data is presented in a format that expresses it using punctuation marks such as semicolons or commas and / or line breaks (corresponding to the second presentation format in this embodiment). Specifically, data conversion is performed based on the rule that the data of each node in the hierarchical structure is displayed in the spaces separated by semicolons and commas in presentation format P2.

[0047] The presentation unit 26 presents the data in the presentation format converted by the conversion unit 24. Specifically, when the recipient of the data is the user 2, the presentation unit 26 outputs the data converted into the first presentation format to the user terminal 12. On the other hand, when the recipient of the data is the generation AI 4, the presentation unit 26 outputs the data converted into the second presentation format to the server 14.

[0048] (Data reflection processing) When the data input by the user 2 and the generated AI 4 is reflected in the database 18, each unit of the dialogue support device 16 executes the following process.

[0049] The first acquisition unit 20 acquires data output by the user 2 operating the user terminal 12 or data output from the server 14 on which the generation AI 4 operates. The user terminal 12 is an example of a device operated by the user 2. The data output from the user terminal 12 or the server 14 is, for example, data that changes the data in the database 18, as shown in Figures 3 and 4. The data output from the user terminal 12 or the server 14 may be, for example, data to be newly added to the database 18.

[0050] The second acquisition unit 22 acquires identification data for identifying the party that output the data acquired by the first acquisition unit 20. For example, the second acquisition unit 22 acquires identification data similar to the identification data described in the data presentation process above.

[0051] When the identification data acquired by the second acquisition unit 22 represents user 2, the conversion unit 24 uses the first conversion method to convert the data acquired by the second acquisition unit 22 into data corresponding to the logical structure of the data stored in the database 18.

[0052] On the other hand, when the identification data acquired by the second acquisition unit 22 represents generated AI4, the conversion unit 24 uses the second conversion method to convert the data acquired by the second acquisition unit 22 into data corresponding to the logical structure of the data stored in the database 18.

[0053] For example, the conversion unit 24 converts data based on the same rules as those used in the conversion process described above in the data presentation process. For example, the first conversion method converts the data of the changed cells in the presentation format P1 into the data of each node in the hierarchical structure of the database 18. On the other hand, for example, the second conversion method converts the data of the changed parts in the presentation format P2, which are separated by commas, into the data of each node in the hierarchical structure of the database 18.

[0054] The reflecting unit 28 reflects the data converted by the converting unit 24 in the database 18. For example, as shown in Figures 3 and 4, when the user 2 or the generating AI 4 changes "Ito" to "Saito", the change is reflected in the database 18.

[0055] Next, the operation of the dialogue support system 10 according to this embodiment will be described.

[0056] First, the data presentation process will be described. After a dialogue between the user 2 and the generation AI 4 is initiated, the dialogue support device 16 receives a request signal requesting that data stored in the database 18 be presented to the user 2 or the generation AI 4. The CPU 42 of the dialogue support device 16 reads out a dialogue support program from the storage device 46, loads it into the memory 44, and executes it. Note that this request signal is output, for example, from either the user terminal 12 or the server 14. As a result, the CPU 42 functions as each functional component of the dialogue support device 16, and the dialogue support process shown in FIG. 7 is executed.

[0057] In step S100, the first acquisition unit 20 acquires data stored in the database 18.

[0058] In step S102, the second acquisition unit 22 acquires identification data for identifying the party to whom the data acquired in step S100 is to be presented.

[0059] In step S104, if the identification data acquired in step S102 represents user 2, the conversion unit 24 converts the data acquired in step S100 into a first presentation format in accordance with the logical structure of the data stored in database 18. On the other hand, in step S104, if the identification data acquired in step S102 represents generated AI4, the conversion unit 24 converts the data acquired in step S100 into a second presentation format in accordance with the logical structure of the data stored in database 18.

[0060] In step S106, the presentation unit 26 presents the data in the presentation format converted in step S104. Specifically, when the recipient of the data is the user 2, the presentation unit 26 outputs the data converted into the first presentation format to the user terminal 12. On the other hand, when the recipient of the data is the generated AI 4, the presentation unit 26 outputs the data converted into the second presentation format to the server 14.

[0061] Next, the data reflection process will be described. After a dialogue between the user 2 and the generation AI 4 is started, when the dialogue support device 16 receives a request signal requesting that data be stored in the database 18 or that the data in the database 18 be changed, the CPU 42 of the dialogue support device 16 reads out the dialogue support program from the storage device 46, loads it into the memory 44, and executes it. Note that this request signal is output, for example, from either the user terminal 12 or the server 14. As a result, the CPU 42 functions as each functional component of the dialogue support device 16, and the dialogue support process shown in FIG. 8 is executed.

[0062] In step S200, the first acquisition unit 20 acquires data output by the user 2 operating the user terminal 12 or data output from the server 14 on which the generation AI 4 operates.

[0063] In step S202, the second acquisition unit 22 acquires identification data for identifying the party that output the data acquired in step S200.

[0064] In step S204, if the identification data acquired in step S202 represents user 2, the conversion unit 24 uses the first conversion method to convert the data acquired in step S200 into data corresponding to the logical structure of the data stored in database 18. On the other hand, in step S204, if the identification data acquired in step S202 represents generated AI4, the conversion unit 24 uses the second conversion method to convert the data acquired in step S200 into data corresponding to the logical structure of the data stored in database 18.

[0065] In step S206, the reflecting unit 28 reflects the data converted in step S204 in the database 18.

[0066] As described above, the dialogue support device according to the first embodiment supports a dialogue between a user and a generation AI. The dialogue support device acquires data stored in a database. The dialogue support device acquires identification data for identifying a party to whom the acquired data is to be presented. If the acquired identification data represents a user, the dialogue support device converts the acquired data into a first presentation format in accordance with the logical structure of the data stored in the database. If the acquired identification data represents a generation AI, the dialogue support device converts the acquired data into a second presentation format in accordance with the logical structure of the data stored in the database. The dialogue support device then presents the data in the converted presentation format. This facilitates dialogue between a human user and a generation AI when the dialogue relates to common data. In particular, by presenting data in a presentation format that is easily recognized by the user and the generation AI, misunderstandings and discrepancies are reduced in the dialogue between the user and the generation AI, thereby achieving a smooth dialogue.

[0067] Furthermore, the dialogue support device according to the first embodiment acquires data output by a user operating a device or data output from a generation AI. The dialogue support device acquires identification data for identifying the party that output the acquired data. If the acquired identification data represents a user, the dialogue support device converts the acquired data into data corresponding to the logical structure of data stored in a database using a first conversion method. If the acquired identification data represents a generation AI, the dialogue support device converts the acquired data into data corresponding to the logical structure of data stored in the database using a second conversion method. The dialogue support device then reflects the converted data in the database. This facilitates dialogue between a human user and a generation AI when the dialogue relates to common data. In particular, by enabling the user and the generation AI to modify data presented in a format that is easily recognizable, misunderstandings and inconsistencies are reduced in the dialogue between the user and the generation AI, thereby realizing a smooth dialogue.

[0068] Furthermore, according to the dialogue support device of the embodiment, the dialogue between the user and the generated AI can be made smooth by taking into consideration the human data interface (HDI) and the generated AI data interface (GDI).

[0069] <Dialogue Support System 10 of Second Embodiment> Next, a second embodiment will be described. The dialogue support system of the second embodiment differs from the first embodiment in that the logical structure of the data stored in the database is a logical structure representing a mathematical formula. Note that the configuration of the dialogue support system 10 of the second embodiment is the same as that of the first embodiment, and therefore a detailed description thereof will be omitted.

[0070] Fig. 9 is a diagram for explaining data stored in the database of the second embodiment. Fig. 9 is also a diagram for explaining the data presentation process of the second embodiment. As shown in Fig. 9, data of a logical structure representing a mathematical formula is stored in the database 18 of the second embodiment.

[0071] As shown in Fig. 9, when the data presentation process is executed, the conversion unit 24 of the second embodiment converts the data stored in the database 18 into data such as presentation format P3 when the recipient of the data is user 2. That is, data of a logical structure representing a mathematical formula is presented in a format expressed using a spatial arrangement called a graph (corresponding to the first presentation format in this embodiment). Then, the presentation unit 26 of the second embodiment presents data such as presentation format P3 to user 2. The presentation format P3 shown in Fig. 9 is a presentation format in which mathematical formulas are graphed, making it easy for humans to understand.

[0072] On the other hand, as shown in Figure 9, when executing the data presentation process, if the data is to be presented to the generated AI4, the conversion unit 24 of the second embodiment converts the data stored in the database 18 into data such as presentation format P4. That is, data of a logical structure representing mathematical formulas is presented in a format in which punctuation marks such as semicolons or commas and / or line breaks are used for each formula (corresponding to the second presentation format in this embodiment). Then, the presentation unit 26 of the second embodiment presents data such as presentation format P4 to the generated AI4. The presentation format P4 shown in Figure 9 is a presentation format in which the mathematical formulas are program-coded and are easily recognizable by the generated AI4.

[0073] The data reflection process of the second embodiment is executed in the same manner as in the first embodiment.

[0074] As described above, the dialogue support device according to the second embodiment converts logically structured data representing mathematical formulas stored in a database depending on whether the data is being presented to a user or a generation AI, and presents the converted data to the user or the generation AI. Furthermore, the dialogue support device according to the second embodiment converts the data depending on whether the data is being output to a user or a generation AI, and reflects the converted data in the database. This facilitates dialogue between a human user and a generation AI when the dialogue involves mathematical formulas.

[0075] <Dialogue Support System 10 of Third Embodiment> Next, a third embodiment will be described. The dialogue support system of the third embodiment differs from the first and second embodiments in that the logical structure of the data stored in the database is a logical structure that represents a combination of an event and the time at which the event occurred. Note that the configuration of the dialogue support system 10 of the third embodiment is the same as that of the first embodiment, so a detailed description will be omitted.

[0076] Fig. 10 is a diagram for explaining data stored in the database of the third embodiment. Fig. 10 is also a diagram for explaining the data presentation process of the third embodiment. As shown in Fig. 10, the database 18 of the third embodiment stores data of a logical structure that represents a combination of an event and the time when the event occurred. In the example of Fig. 10, a logical structure that represents a combination of success or failure of logging in to an information system, which is an example of an event, and the time when the event occurred is stored in the database.

[0077] 10, when the data presentation process is executed, the conversion unit 24 of the third embodiment converts the data stored in the database 18 into data such as in presentation format P5 when the recipient of the data is user 2. Then, the presentation unit 26 of the third embodiment presents data such as in presentation format P5 to user 2. The presentation format P5 shown in FIG. 10 is a presentation format in which the login information is written in a document, making it easy for humans to understand.

[0078] Fig. 11 is a diagram for explaining rules for generating data such as the presentation format P5. As shown in Fig. 11, the conversion unit 24 executes extraction by pattern matching and conversion based on a rule base.

[0079] As shown in FIG. 11, first, the conversion unit 24 generates data D2 by applying data D1 stored in the database 18 to predetermined patterns (represented as pattern example 1 and pattern example 2 in FIG. 11).

[0080] Specifically, the conversion unit 24 applies the data stored in the database 18, "2023-12-04-09-10-28 JST yamada login success;", to the input of pattern example 1, "YYYY-MM-DD-hh-mm-ss TZN $USER login success;", and generates the data "2023 / 12 / 04 09:10 yamada succeeded in logging in.", which corresponds to the output of pattern example 1, "YYYY / MM / DD hh:mm, $USER succeeded in logging in."

[0081] In addition, the conversion unit 24 applies the data stored in the database 18, "2023-12-04-13-20-36 JST tanaka login fail - password error;" to the input of pattern example 2, "YYYY-MM-DD-hh-mm-ss TZN $USER login fail - password error;", and generates the data "2023 / 12 / 04 13:20 tanaka failed to log in. Incorrect password.", which corresponds to the output of pattern example 2, "YYYY / MM / DD hh:mm, $USER failed to log in. Incorrect password."

[0082] Next, as shown in FIG. 11, the conversion unit 24 applies the data D2 to predetermined rules (denoted as rule example 1 and rule example 2 in FIG. 11) to generate a data presentation format P5.

[0083] Specifically, the conversion unit 24 applies rule example 1 and rule example 2 to "2023 / 12 / 04 09:10 yamada succeeded in logging in." to generate data "Yamada succeeded in logging in at around 9:10 today." Furthermore, the conversion unit 24 applies rule example 1 and rule example 2 to "2023 / 12 / 04 13:20 tanaka failed to log in. Wrong password." to generate data "Tanaka failed to log in at around 13:20 today. Wrong password." In this way, data presentation format P5 is generated and presented to user 2.

[0084] On the other hand, as shown in FIG. 10, when the data presentation process is executed and the recipient of the data is the generated AI4, the conversion unit 24 of the second embodiment converts the data stored in the database 18 into data such as the presentation format P6. Then, the presentation unit 26 of the second embodiment presents data such as the presentation format P6 to the generated AI4. The presentation format P6 shown in FIG. 6 compresses the login information and is a presentation format that is easy for the generated AI4 to recognize. When generating data such as the presentation format P6 of FIG. 10, the conversion unit 24 generates the data presentation format P6 in the same manner as described above, for example, based on pattern matching and a rule base for the generated AI4.

[0085] The conversion unit 24 may convert the data stored in the database 18 using a generation AI different from the generation AI 4 with which the user 2 is conversing. In this case, the generation AI 4 with which the user 2 is conversing is the first generation AI, and the generation AI different from the generation AI 4 with which the user 2 is conversing is the second generation AI.

[0086] For example, the conversion unit 24 inputs the data stored in the database 18, "2022-12-04-09-10-28 JST yamada login success;" and "2023-12-04-13-20-36 JST tanaka login fail - password error;", into the second generation AI, and also inputs a predetermined prompt to the second generation AI.

[0087] For example, when generating a presentation format P5 for user 2, the conversion unit 24 inputs a prompt such as, "Please summarize the contents of the log data provided as input so that the administrator can easily understand it. The structure of the log data is... The result of an easy-to-understand summary is..." to the second generation AI, and thereby obtains the presentation format P5 for user 2 output from the second generation AI.

[0088] Also, for example, when generating a presentation format P6 for the first generation AI4, the conversion unit 24 obtains the presentation format P6 for the first generation AI4 output from the second generation AI by inputting a prompt to the second generation AI such as, "Please perform a compression process on the log data provided as input to save the amount of tokens consumed, and display the results."

[0089] The data reflection process of the third embodiment is executed in the same manner as in the first embodiment.

[0090] As described above, the dialogue support device according to the third embodiment converts logically structured data representing a combination of an event and the time at which the event occurred, stored in a database, depending on whether the data is being presented to a user or a generation AI, and presents the converted data to the user or the generation AI. Furthermore, the dialogue support device according to the second embodiment converts data output by a user or a generation AI and reflects the converted data in the database. This facilitates dialogue between a human user and a generation AI, even when the dialogue between the user and the generation AI is related to the occurrence of an event.

[0091] In the above embodiment, the logical structure of the data stored in the database is a logical structure that represents a hierarchical structure between events, a logical structure that represents a mathematical expression, or a logical structure that represents a combination of an event and the time at which the event occurred, but the present invention is not limited to this. The data stored in the database may be any data as long as it has some kind of logical structure.

[0092] 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.

[0093] In the above embodiment, the conversation support device has a database, but the present invention is not limited to this. For example, the database may be located outside the conversation support device.

[0094] 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.

[0095] 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.

[0096] (Addendum) The following additional notes are provided regarding aspects of the present disclosure.

[0097] (Appendix 1) A dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), a first acquisition unit that acquires data stored in a database; a second acquisition unit that acquires identification data for identifying a party to whom the data acquired by the first acquisition unit is to be presented; When the identification data acquired by the second acquisition unit represents the user, converting the data acquired by the first acquisition unit into a first presentation format according to a logical structure of the data stored in the database; a conversion unit that converts the data acquired by the first acquisition unit into a second presentation format in accordance with a logical structure of the data stored in the database when the identification data acquired by the second acquisition unit represents the generated AI; a presentation unit that presents the data whose presentation format has been converted by the conversion unit; A dialogue support device comprising: (Appendix 2) A dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), A first acquisition unit that acquires data output by the user operating a device or data output from the generation AI; a second acquisition unit that acquires identification data for identifying a party that has output the data acquired by the first acquisition unit; When the identification data acquired by the second acquisition unit represents the user, converting the data acquired by the first acquisition unit into data corresponding to a logical structure of data to be stored in a database using a first conversion method; a conversion unit that converts the data acquired by the first acquisition unit into data corresponding to the logical structure of data stored in the database using a second conversion method when the identification data acquired by the second acquisition unit represents the generated AI; a reflecting unit that reflects the data converted by the converting unit in the database; A dialogue support device comprising: (Appendix 3) the logical structure of the data stored in the database is at least one of a logical structure representing a hierarchical structure between events, a logical structure representing a mathematical expression, and a logical structure representing a combination of an event and an occurrence time of the event; 3. A dialogue support device according to claim 1 or 2. (Appendix 4) the conversion unit converts the data based on a predetermined rule according to a logical structure of the data stored in the database; 4. A dialogue support device according to any one of Supplementary notes 1 to 3. (Appendix 5) the generated AI is a first generated AI, The conversion unit converts the data using a second generation AI that is different from the first generation AI. 5. A dialogue support device according to any one of Supplementary notes 1 to 4. (Appendix 6) The generating AI is a large-scale language model. 6. A dialogue support device according to any one of Supplementary notes 1 to 5. (Appendix 7) A dialogue support method executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Retrieve data stored in the database acquiring identification data for identifying a party to whom the acquired data is to be presented; If the obtained identification data represents the user, converting the obtained data into a first presentation format according to a logical structure of the data stored in the database; If the obtained identification data represents the generated AI, converting the obtained data into a second presentation format according to a logical structure of the data stored in the database; The presentation format presents the transformed data, A dialogue support method in which processing is executed by a computer. (Appendix 8) A dialogue support method executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Acquire data output by the user operating a device or data output from the generation AI, acquiring identification data for identifying the party that output the acquired data; If the acquired identification data represents the user, converting the acquired data into data corresponding to a logical structure of data to be stored in a database using a first conversion method; If the acquired identification data represents the generated AI, converting the acquired data into data corresponding to the logical structure of data stored in the database using a second conversion method; Reflecting the converted data in the database; A dialogue support method in which processing is executed by a computer. (Appendix 9) A dialogue support program to be executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Retrieve data stored in the database acquiring identification data for identifying a party to whom the acquired data is to be presented; If the obtained identification data represents the user, converting the obtained data into a first presentation format according to a logical structure of the data stored in the database; If the obtained identification data represents the generated AI, converting the obtained data into a second presentation format according to a logical structure of the data stored in the database; The presentation format presents the transformed data, A dialogue support program that causes a computer to execute processing. (Appendix 10) A dialogue support program to be executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Acquire data output by the user operating a device or data output from the generation AI, acquiring identification data for identifying the party that output the acquired data; If the acquired identification data represents the user, converting the acquired data into data corresponding to a logical structure of data to be stored in a database using a first conversion method; If the acquired identification data represents the generated AI, converting the acquired data into data corresponding to the logical structure of data stored in the database using a second conversion method; Reflecting the converted data in the database; A dialogue support program that causes a computer to execute processing. [Explanation of symbols]

[0098] 10 Dialogue Support System 12 User terminal 14 Servers 16 Dialogue support device 18 Databases 20 First acquisition part 22 Second acquisition part 24 Conversion unit 26 Presentation section 28 Reflection section

Claims

1. A dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), a first acquisition unit that acquires data stored in a database; a second acquisition unit that acquires identification data for identifying a party to whom the data acquired by the first acquisition unit is to be presented; When the identification data acquired by the second acquisition unit represents the user, converting the data acquired by the first acquisition unit into a first presentation format according to a logical structure of the data stored in the database; a conversion unit that converts the data acquired by the first acquisition unit into a second presentation format according to a logical structure of the data stored in the database when the identification data acquired by the second acquisition unit represents the generated AI; a presentation unit that presents the data whose presentation format has been converted by the conversion unit; A dialogue support device comprising:

2. A dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), A first acquisition unit that acquires data output by the user operating a device or data output from the generated AI; a second acquisition unit that acquires identification data for identifying a party that has output the data acquired by the first acquisition unit; When the identification data acquired by the second acquisition unit represents the user, converting the data acquired by the first acquisition unit into data corresponding to a logical structure of data to be stored in a database using a first conversion method; a conversion unit that converts the data acquired by the first acquisition unit into data corresponding to a logical structure of data stored in the database using a second conversion method when the identification data acquired by the second acquisition unit represents the generated AI; a reflecting unit that reflects the data converted by the converting unit in the database; A dialogue support device comprising:

3. the logical structure of the data stored in the database is at least one of a logical structure representing a hierarchical structure between events, a logical structure representing a mathematical expression, and a logical structure representing a combination of an event and an occurrence time of the event; The dialogue support device according to claim 1 or 2.

4. the conversion unit converts the data based on a predetermined rule according to a logical structure of the data stored in the database; The dialogue support device according to claim 1 or 2.

5. The generated AI is a first generated AI, The conversion unit converts the data using a second generated AI different from the first generated AI. The dialogue support device according to claim 1 or 2.

6. The generative AI is an AI that uses a large-scale language model. The dialogue support device according to claim 1 or 2.

7. A dialogue support method executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), comprising: Retrieve data stored in the database acquiring identification data for identifying a party to whom the acquired data is to be presented; If the obtained identification data represents the user, converting the obtained data into a first presentation format according to a logical structure of the data stored in the database; If the obtained identification data represents the generated AI, converting the obtained data into a second presentation format according to a logical structure of the data stored in the database; The presentation format presents the transformed data, A dialogue support method in which processing is executed by a computer.

8. A dialogue support method executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), comprising: Acquire data output by the user operating a device or data output from the generated AI; acquiring identification data for identifying the party that output the acquired data; If the acquired identification data represents the user, converting the acquired data into data corresponding to a logical structure of data to be stored in a database using a first conversion method; If the acquired identification data represents the generated AI, converting the acquired data into data corresponding to the logical structure of data stored in the database using a second conversion method; Reflecting the converted data in the database; A dialogue support method in which processing is executed by a computer.

9. A dialogue support program to be executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Retrieve data stored in the database acquiring identification data for identifying a party to whom the acquired data is to be presented; If the obtained identification data represents the user, converting the obtained data into a first presentation format according to a logical structure of the data stored in the database; If the obtained identification data represents the generated AI, converting the obtained data into a second presentation format according to a logical structure of the data stored in the database; The presentation format presents the transformed data, A dialogue support program that causes a computer to execute processing.

10. A dialogue support program to be executed by a computer constituting a dialogue support device that supports a dialogue between a user and a generating AI (Artificial Intelligence), Acquire data output by the user operating a device or data output from the generated AI; acquiring identification data for identifying the party that output the acquired data; If the acquired identification data represents the user, converting the acquired data into data corresponding to a logical structure of data to be stored in a database using a first conversion method; If the acquired identification data represents the generated AI, converting the acquired data into data corresponding to the logical structure of data stored in the database using a second conversion method; Reflecting the converted data in the database; A dialogue support program that causes a computer to execute processing.

Images