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

Abstract

The system will allow users to switch from a previously selected or executed conversational AI to a more appropriate one in response to changes in the user's situation or requests. [Solution] The information processing device is an information processing device that provides a plurality of conversational AIs that interact with a user via a user terminal, and comprises: a setting unit that sets a first conversational AI that interacts with the user; a storage unit that stores the user's behavior history when interacting with the first conversational AI; a determination unit that determines whether it is necessary to switch from the first conversational AI to a second conversational AI different from the first conversational AI based on the user's behavior history while interacting with the first conversational AI; and a switching unit that switches to the second conversational AI based on the determination result determined by the determination unit.

Description

Technical Field

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

Background Art

[0002] There is an information processing apparatus that provides a plurality of dialogue AIs (Artificial Intelligence) for interacting with a user via a user terminal. For example, a technique is known in which an appropriate dialogue AI is selected and provided to the user based on analysis of conversations, input information from the user (such as name, auditory, character, visual input, etc.) (see, for example, Patent Document 1).

Summary of the Invention

Problems to be Solved by the Invention

[0003] In the technique disclosed in Patent Document 1, there is a problem that when an appropriate dialogue AI is selected for the user, it cannot flexibly respond to changes in the user's situation or requests.

[0004] One embodiment of the present invention has been made in view of the above problems, and enables the dialogue AI that has already been selected or executed for the user to be switched to a more appropriate dialogue AI according to changes in the user's situation or requests.

Means for Solving the Problems

[0005] To solve the above problems, an information processing apparatus according to one embodiment is an information processing apparatus that provides a plurality of dialogue AIs for interacting with a user via a user terminal, and includes a setting unit that sets a first dialogue AI that interacts with the user, a storage unit that stores the behavior history of the user who interacts with the first dialogue AI, a determination unit that determines whether to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI based on the behavior history of the user during the interaction with the first dialogue AI, and a switching unit that performs the switching to the second dialogue AI based on the determination result determined by the determination unit. [Effects of the Invention]

[0006] According to one embodiment of the present invention, a conversational AI that has already been selected or executed can be switched to a more appropriate conversational AI in response to changes in the user's situation or requests. [Brief explanation of the drawing]

[0007] [Figure 1] This figure shows an example of the system configuration of an information processing system according to one embodiment. [Figure 2] This figure shows another example of the system configuration of an information processing system according to one embodiment. [Figure 3] This figure shows an example of a computer hardware configuration according to one embodiment. [Figure 4] This figure shows an example of the hardware configuration of an information terminal according to one embodiment. [Figure 5] This figure shows an example of the functional configuration of an information processing system according to one embodiment. [Figure 6] This figure shows an example of the functional configuration of a switching control unit according to one embodiment. [Figure 7] This is a sequence diagram showing an example of the switching process of the dialogue AI according to the first embodiment. [Figure 8] This flowchart shows an example of the setup process for the conversational AI according to the first embodiment. [Figure 9] This flowchart shows an example of the process for determining whether a switch is necessary according to the first embodiment. [Figure 10] This is a sequence diagram showing an example of the switching process of the dialogue AI according to the second embodiment. [Figure 11] This flowchart shows an example of the process for determining whether a switch is necessary according to the second embodiment. [Figure 12] This figure shows an example of switching information according to one embodiment. [Figure 13] Figure (1) shows an example of a display screen according to one embodiment. [Figure 14]Figure (2) shows an example of a display screen according to one embodiment. [Figure 15] This is a flowchart showing an example of processing in the information processing apparatus according to the third embodiment. [Modes for carrying out the invention]

[0008] Embodiments of the present invention will be described in detail below with reference to the drawings.

[0009] <System Configuration> Figure 1 shows an example of the system configuration of an information processing system according to one embodiment. In the example in Figure 1, the information processing system 1 includes a user terminal 10, a host server 20, and an information processing device 1000, all connected to a communication network N such as the Internet and a LAN (Local Area Network).

[0010] User terminal 10 is an information terminal used by user 11, such as a PC (Personal Computer), tablet, or smartphone. User terminal 10 can communicate with host server 20 and information processing device 100 via communication network N. User 11 can also interact with the conversational AI provided by information processing device 100 by using the services provided by host server 20.

[0011] The host server 20 is, for example, an information processing device with a computer configuration, or a system composed of multiple computers. The computers comprising the host server 20 may, for example, be virtual machines on the cloud. The host server 20 is a system that provides services such as a metaverse, a virtual space on the internet, or web conferencing. In this embodiment, the host server 20 may have any configuration. For example, the host server 20 may be a general-purpose system that provides services outside the system.

[0012] The information processing apparatus 100 is an information processing apparatus having a computer configuration or a system including a plurality of computers. Note that the computer constituting the information processing apparatus 100 may be, for example, a virtual machine on the cloud or the like. The information processing apparatus 100 provides, for example, a plurality of dialogue AIs that interact with a user via the user terminal 10.

[0013] The dialogue AI is a program or system that responds to inquiries from a user 11 or the like using the user terminal 10. For example, it is a service that automatically responds using AI (Artificial Intelligence), a chatbot, or knowledge including registered information and knowledge, and is also called an AI agent or a dialogue agent. Preferably, the information processing apparatus 100 supports the execution of a predetermined task such as business negotiation or care through a dialogue in which the dialogue AI automatically responds to a voice or message from the user.

[0014] As a use case of the dialogue AI, for example, it is used as a non-human AI avatar in a Web conference, a website, a smartphone app, or a virtual space in the metaverse (hereinafter referred to as the metaverse space). The information processing apparatus 100 can change the dialogue content according to various applications such as business negotiation, care, teaching, or counseling by changing the dialogue scenario.

[0015] FIG. 2 is a diagram showing another example of the system configuration of the information processing system 1 according to an embodiment. In the example of FIG. 2, the information processing system 1 includes a user terminal 10 and an information processing apparatus 1000 connected to a communication network N. Thus, the information processing system 1 may not have the host server 20.

[0016] In this case, the information processing apparatus 100 may have the functions of the host server 20 described in FIG. 1, or may provide a plurality of dialogue AIs that interact with the user to the user terminal 10 without using the functions of the host server 20.

[0017] The information processing device 100 according to this embodiment provides multiple conversational AIs that interact with the user via the user terminal 10, and has the function of selecting or switching to the appropriate conversational AI based on user input information and behavioral history. This improves the user experience and enables more effective conversations by utilizing the expertise of each conversational AI.

[0018] <Hardware Configuration> (Computer hardware configuration) The host server 20 and the information processing device 100 have a hardware configuration of a computer 300 as shown in Figure 3, for example. Note that the host server 20 or the information processing device 100 may be composed of multiple computers 300.

[0019] Furthermore, the user terminal 10 may have a hardware configuration of a computer 300, for example, as shown in Figure 3.

[0020] Figure 3 shows an example of the hardware configuration of a computer according to one embodiment. The computer 300 includes, for example, a CPU (Central Processing Unit) 301, ROM (Read Only Memory) 302, RAM (Random Access Memory) 303, HD (Hard Disk) 304, HDD (Hard Disk Drive) controller 305, display 306, external device connection I / F (Interface) 307, network I / F 308, keyboard 309, pointing device 310, DVD-RW (Digital Versatile Disk Rewritable) drive 312, media I / F 314, and bus line 315, as shown in Figure 3.

[0021] Furthermore, if the computer 300 is the user terminal 10, the computer 300 is further equipped with a microphone 321, a speaker 322, an audio input / output interface 323, a CMOS (Complementary Metal Oxide Semiconductor) sensor 324, and an image sensor interface 325, etc.

[0022] Of these components, the CPU 301 controls the overall operation of the computer 300. The ROM 302 stores programs used to start the computer 300, such as the IPL (Initial Program Loader). The RAM 303 is used, for example, as the work area for the CPU 301. The HD 304 stores programs such as the OS (Operating System), applications, device drivers, and various data. The HDD controller 305 controls the reading or writing of various data to the HD 304, for example, according to the control of the CPU 301. Note that the HD 304 and the HDD controller 305 are examples of storage devices.

[0023] Display 306 displays various information, such as a cursor, menu, window, text, or image. Note that display 306 may be located outside the computer 300. External device connection I / F 307 is an interface for connecting various external devices to the computer 300. Network I / F 308 is an interface for connecting the computer 300 to a communication network N and communicating with other devices.

[0024] The keyboard 309 is a type of input device equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 310 is a type of input device for selecting and executing various instructions, selecting processing targets, moving the cursor, and so on. The keyboard 309 and the pointing device 310 may be located outside the computer 300.

[0025] The DVD-RW drive 312 controls the reading or writing of various data to the DVD-RW 311, which is an example of a removable recording medium. Note that the DVD-RW 311 is not limited to DVD-RW; it may be any other removable recording medium. The media interface 314 controls the reading or writing (storage) of data to the media 313, such as flash memory. The bus line 315 includes an address bus, a data bus, and various control signals for electrically connecting the above components.

[0026] Microphone 321 is a built-in circuit that converts sound into electrical signals. Speaker 322 is a built-in circuit that converts electrical signals into physical vibrations to produce sound such as music and speech. Audio input / output interface 323 is a circuit that processes the input and output of audio signals between microphone 321 and speaker 322 according to the control of CPU 301.

[0027] The CMOS sensor 324 is a type of built-in imaging means that captures an image of a subject (e.g., a self-portrait) and obtains image data according to the control of the CPU 301. The computer 300 may have other imaging means, such as a CCD (Charge Coupled Device) sensor, instead of the CMOS sensor 324. The image sensor interface 325 is a circuit that controls the driving of the CMOS sensor 324.

[0028] (Hardware configuration of information terminals) Figure 4 shows an example of the hardware configuration of an information terminal according to one embodiment. The user terminal 10 has, for example, the hardware configuration of an information terminal 400 as shown in Figure 4. Alternatively, as mentioned above, the user terminal 10 may have the hardware configuration of a computer 300 as shown in Figure 3.

[0029] In the example shown in Figure 4, the information terminal 400 includes a CPU 401, ROM 402, RAM 403, storage device 404, CMOS sensor 405, image sensor I / F 406, acceleration / direction sensor 407, media I / F 409, and GPS (Global Positioning System) receiver 410.

[0030] Of these components, the CPU 401 controls the overall operation of the information terminal 400 by executing a predetermined program. The ROM 402 stores programs used to start the CPU 401, such as an IPL (Initial Program Load). The RAM 403 is used as the work area for the CPU 401. The storage device 404 is a large-capacity storage device that stores programs such as the OS and applications, as well as various types of data, and is implemented by, for example, an SSD (Solid State Drive) or flash ROM.

[0031] The CMOS sensor 405 is a type of built-in imaging means that captures an image of a subject (mainly a self-portrait) and obtains image data according to the control of the CPU 401. The user terminal 10 may have an imaging means such as a CCD sensor instead of the CMOS sensor 405. The image sensor interface 406 is a circuit that controls the driving of the CMOS sensor 405. The acceleration / direction sensor 407 is a type of sensor such as an electronic magnetic compass, gyrocompass, or acceleration sensor that detects the Earth's magnetic field. The media interface 409 controls the reading or writing (storage) of data to or from the media (storage medium) 408, such as flash memory. The GPS receiver 410 receives GPS signals (positioning signals) from GPS satellites.

[0032] Furthermore, the information terminal 400 includes a long-range communication circuit 411, an antenna 411a for the long-range communication circuit 411, a CMOS sensor 412, an image sensor interface 413, a microphone 414, a speaker 415, an audio input / output interface 416, a display 417, an external device connection interface 418, a short-range communication circuit 419, an antenna 419a for the short-range communication circuit 419, and a touch panel 420.

[0033] Of these, the long-distance communication circuit 411 is a circuit that communicates with other devices, for example, via a communication network N. The CMOS sensor 412 is a type of built-in imaging means that captures an image of a subject and obtains image data according to the control of the CPU 401. The image sensor interface 413 is a circuit that controls the driving of the CMOS sensor 412. The microphone 414 is a built-in circuit that converts sound into electrical signals. The speaker 415 is a built-in circuit that converts electrical signals into physical vibrations to produce sounds such as music and speech. The sound input / output interface 416 is a circuit that processes the input and output of sound wave signals between the microphone 414 and the speaker 415 according to the control of the CPU 401.

[0034] The display 417 is a type of display means, such as a liquid crystal or organic EL (electroluminescence), that displays images of the subject and various icons. The external device connection I / F 418 is an interface for connecting various external devices. The short-range communication circuit 419 includes a circuit for performing short-range wireless communication. The touch panel 420 is a type of input means that allows the user to operate the user terminal 10 by pressing the display 417.

[0035] Furthermore, the user terminal 10 is equipped with a bus line 421. The bus line 421 includes an address bus, a data bus, and the like for electrically connecting each component, such as the CPU 401 shown in Figure 6.

[0036] <Functional Configuration> Figure 5 shows an example of the functional configuration of an information processing system according to one embodiment.

[0037] (Functional configuration of information processing equipment) The information processing device 100 realizes various functional configurations, such as those shown in Figure 5, by having the computer 300 equipped with the information processing device 100 execute a predetermined program stored in a storage medium. In the example in Figure 5, the information processing device 100 has various functional configurations such as a communication unit 501, a setting unit 502, a switching control unit 503, a dialogue AI provision unit 504, an action history DB (Database) 505, a 3DCG (3-Dimensional Computer Graphics) DB 506, a scenario DB 507, and a model DB 508. Note that among the above functional configurations, the databases for the action history DB 505, 3DCG DB 506, scenario DB 507, and model DB 508 may be databases external to the information processing device 100.

[0038] The communication unit 501 connects the information processing device 100 to the communication network N using, for example, a network interface 308, and performs communication processing to communicate with the host server 20 or the user terminal 10. For example, the communication unit 501 receives predetermined information from a user 11 using the user terminal 10.

[0039] Preferably, the specified information includes information about the user 11's activity history. Information about the user's activity history is information that records information about a specified action performed by the user. A specified action includes, for example, one or more of the following: conversation history, movement history, browsing history, search history, selection history, and purchase history. Preferably, the information about the activity history includes one or more of the following: location information, device information, form input content, social media activity, and applications used.

[0040] This information may be received from, for example, the host server 20, or from the user terminal 10.

[0041] The configuration unit 502 executes a configuration process to set a first conversational AI that interacts with user 11, based on the user's behavior history stored in the behavior history DB 505 or the like. For example, if the configuration unit 502 has a behavior history of past interactions with user 11, it sets the conversational AI that was previously interacted with (for example, the last conversational AI) as the first conversational AI that interacts with user 11.

[0042] Furthermore, if there is no activity history of user 11, the setting unit 502 sets a first conversational AI that corresponds to the attribute information of user 11, for example, based on user 11's attribute information (e.g., name, age, gender, address, or industry of affiliation).

[0043] The switching control unit 503 executes a switching control process that switches from a first dialogue AI that interacts with user 11 to a second dialogue AI that is different from the first dialogue AI, based on predetermined information of user 11. The switching control unit 503 has, for example, the functional configurations shown in Figure 6. In the example in Figure 6, the switching control unit 503 has functional configurations such as a recognition unit 601, an interpretation unit 602, an extraction unit 603, a judgment unit 604, and a switching unit 605.

[0044] The recognition unit 601 performs recognition processing to recognize the user 11's dialogue data. For example, the recognition unit 601 performs speech recognition processing on the audio included in the dialogue data to convert the user 11's spoken audio into text. Preferably, the recognition unit 601 further acquires non-verbal information of the user 11 from the user's dialogue data (audio and images), such as the volume of the voice, the intonation of the voice, or the timbre of the voice.

[0045] The interpretation unit 602 performs intent interpretation processing to interpret the intent of the user's utterance based on the linguistic information of the user 11 recognized by the recognition unit 601, for example. Preferably, the interpretation unit 602 interprets the intent of the user's utterance by taking into account the non-linguistic information of the user 11 recognized by the recognition unit 601.

[0046] For example, the interpretation unit 602 may input the linguistic and nonverbal information of user 11 into a machine learning model that has been pre-trained to interpret the user's intent using the linguistic and nonverbal information of multiple users as input data, and interpret the intent of user 11's utterance.

[0047] Here, machine learning is a technique for enabling computers to acquire human-like learning abilities. It refers to a technique in which a computer autonomously generates algorithms necessary for data identification and other judgments from pre-inputted training data, and then applies these algorithms to new data to make predictions. The learning method for machine learning can be supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or deep learning, or a combination of these learning methods; the learning method for machine learning is not restricted.

[0048] The extraction unit 603 performs an extraction process to extract information from predetermined information of user 11 received by the communication unit 501 for determining whether or not to switch the conversational AI. For example, the extraction unit 603 extracts (identifies) the types of content that user 11 is interested in from predetermined information of user 11.

[0049] Preferably, the extraction unit 603 extracts information from predetermined information acquired after the setting unit 502 has set up a first dialogue AI that interacts with the user 11, in order to determine whether or not it is necessary to switch the dialogue AI.

[0050] The decision unit 604 performs a decision process to determine whether it is necessary to switch the conversational AI interacting with user 11, based on, for example, the intent of user 11's utterance as interpreted by the interpretation unit 602, or the type of content that user 11 is interested in, as extracted by the extraction unit 603. For example, while user 11 is interacting with the first conversational AI, the decision unit 604 determines, based on user 11's behavior history, whether it is necessary to switch from the first conversational AI set by the setting unit 502 to a second conversational AI that is different from the first conversational AI.

[0051] Preferably, the decision unit 604 implements an algorithm for selecting an appropriate conversational AI by analyzing the user 11's dialogue history and the current context.

[0052] The switching unit 605 executes a switching process to switch the dialogue from the first dialogue AI to the second dialogue AI based on the judgment result of the judgment unit 604. For example, the switching unit 605 is designed so that the user can switch dialogue AIs smoothly without feeling any interruption to the dialogue. The switching unit 605 also has a function to carry over, for example, dialogue history information or the user 11's intentions when switching dialogue AIs. Alternatively, when switching dialogue AIs, the switching unit 605 may present candidate dialogue AIs to the user 11 for selection and switch to the selected dialogue AI.

[0053] Now, let's return to Figure 5 and continue explaining the functional configuration of the information processing device 100. The conversational AI provision unit 504 executes a conversational AI provision process that provides multiple conversational AIs 510.

[0054] As mentioned above, the conversational AI 510 is a service that automatically responds to inquiries from users 11 and others using the user terminal 10, for example, using AI, a chatbot, or knowledge including registered information and knowledge. The conversational AI 510 is implemented, for example, by 3DCG 511, a conversation scenario 512, and a conversation model 513.

[0055] 3DCG511 is a three-dimensional, three-dimensional computer graphics (CG) that displays the conversational AI 510 (for example, a composite image of a person) on the user terminal 10 or the like. Note that the CG used to display the conversational AI 510 is not limited to three-dimensional CG; it may also be two-dimensional CG. Dialogue scenario 512 is pre-set data that outlines the flow or patterns of conversations that the conversational AI 510 will have. Dialogue model 513 is a trained dialogue model (machine learning model) that interacts with the user 11.

[0056] The conversational AI provider unit 504 provides multiple conversational AIs 510 by combining 3DCG 511 registered in 3DCG DB 506, conversational scenarios 512 registered in scenario DB 507, and conversational models 513 registered in model DB 508.

[0057] The Behavior History DB (storage unit) 505 is a database that registers, for example, the behavior history of user 11 (e.g., dialogue history, visit history, etc.). The Behavior History DB 505 is an example of a storage unit that stores the behavior history of a user interacting with the first dialogue AI. The 3DCG DB 506 is a database in which multiple 3DCGs ​​511 are registered. The Scenario DB 507 is a database in which multiple dialogue scenarios 512 are registered. The Model DB 508 is a database in which multiple dialogue models 513 are registered. In the following description, the 3DCG DB 506, Scenario DB 507, and Model DB 508 may be referred to as the Dialogue AI DB.

[0058] (User terminal functionality configuration) Here, the following explanation assumes that user terminal 10 has the hardware configuration of information terminal 400 as shown in Figure 4. However, user terminal 19 may have the hardware configuration of computer 300 as shown in Figure 3, for example.

[0059] The user terminal 10 implements the various functional configurations shown in Figure 5, for example, by having the CPU 401 execute a predetermined program stored in a storage medium such as a storage device 404. In the example in Figure 5, the user terminal 10 has various functional configurations such as a communication unit 521, a display unit 522, an audio input / output unit 523, and an operation reception unit 524. At least some of the above functional configurations may be implemented by hardware.

[0060] The communication unit 521 performs communication processing to connect the user terminal 10 to the communication network N using, for example, a long-distance communication circuit 411, and to communicate with the host server 20 or the information processing device 100. The display unit 522 performs display processing to display the conversational AI provided by the information processing device 100 using, for example, a display 417. The audio input / output unit 523 performs audio input / output processing to input the voice of the user 11 and output the voice of the conversational AI using, for example, a microphone 414, a speaker 415, and an audio input / output interface 416. The operation reception unit 524 performs operation reception processing to receive operations from the user 11.

[0061] (Host server functional configuration) In this embodiment, the host server 20 only needs to be capable of enabling interaction between the conversational AI 510 provided by the information processing device 100 and the user 11 via the user terminal 10. For example, an existing metaverse system or web conferencing system can be applied. Therefore, a description of the functional configuration of the host server 20 is omitted here.

[0062] <Processing flow> Next, the processing flow of the information processing method according to this embodiment will be described.

[0063] [Example 1] (Switching process for conversational AI) Figure 7 is a sequence diagram showing an example of the switching process of the conversational AI according to the first embodiment. Here, as an example, we will explain the case in which user 11 views content exhibited in the metaverse space as an exhibition featuring business improvement solutions.

[0064] In step S701, user 11 uses user terminal 10 to access the entry site for the metaverse exhibition provided by host server 20 and register an account. At this time, user 11 registers user attribute information such as name, age, gender, address, and industry affiliation with host server 20.

[0065] In step S702, the host server 20 issues login information (ID, password) to the user terminal 10 of the registered user 11 for logging into the metaverse exhibition.

[0066] In step S703, user 11 logs in to the metaverse exhibition provided by host server 20 using user terminal 10.

[0067] In step S704, the host server 20 transmits to the information processing device 100 the ID that identifies the logged-in user 11 and the attribute information registered by the user 11.

[0068] In step S705, the setting unit 502 of the information processing device 100 checks the behavior history DB 505 based on the ID received from the host server 20 and checks whether there is a conversational AI 510 that has previously interacted with user 11.

[0069] In step S706, the setting unit 502 performs a setting process for the conversational AI, for example, as shown in Figure 8.

[0070] Figure 8 is a flowchart showing an example of the setting process for a conversational AI according to the first embodiment. This process shows an example of the setting process for a conversational AI executed by the setting unit 502 of the information processing device 100 in step S706 of Figure 7.

[0071] In step S801, the configuration unit 502 determines whether or not there is an action history corresponding to the user 11's ID. For example, the configuration unit 502 checks the action history DB 505 and determines that there is an action history if there is a conversational AI 510 that has previously interacted with user 11. If there is an action history, the configuration unit 502 moves the process to step S802. On the other hand, if there is no action history, the configuration unit 502 moves the process to step S803.

[0072] When the process moves to step S802, the setting unit 502 selects the conversational AI 510 with which the user 11 has previously interacted. For example, the setting unit 502 selects the conversational AI with which the user 11 last interacted.

[0073] On the other hand, when the process moves to step S803, the configuration unit 502 obtains the attribute information of user 11 that was received from the host server 20 in step S704.

[0074] In step S804, the setting unit 502 selects a conversational AI according to the attribute information. For example, if user 11 belongs to the manufacturing industry, the setting unit 502 selects a conversational AI 510 that can introduce production management solution products from among the various conversational AIs pre-registered in the conversational AI DB. If the accuracy of predicting which products the user is interested in is not good based on attribute information (for example, only the industry), the setting unit 502 may select a conversational AI 510 that provides a comprehensive overview of the entire product lineup.

[0075] In step S805, the setting unit 502 sets the selected conversational AI as the first conversational AI corresponding to user 11.

[0076] Now, let's return to Figure 7 and continue the explanation of the sequence diagram. In step S707, the extraction unit 603 of the information processing device 100 obtains movement history and other information corresponding to the user 11's ID from the host server 20. For example, the extraction unit 603 obtains the activity history in the metaverse virtual space corresponding to the user 11's ID after login. This activity history includes, for example, the type of content viewed and the viewing time (for example, viewing content related to parts management software for 15 minutes and content related to production management software for 2 minutes), the type of exhibition booth visited and the number of visits to that type, etc.

[0077] In step S708, the information processing device 100 performs a determination process to determine whether or not to switch the conversational AI, for example, as shown in Figure 9.

[0078] Figure 9 is a flowchart showing an example of the process for determining whether a switch is necessary according to the first embodiment. This process shows an example of the process for determining whether a switch is necessary for the conversational AI, which is executed by the information processing device 100 in step S708 of Figure 7.

[0079] In step S901, the extraction unit 603 extracts decision information from the acquired movement history, etc., to determine whether or not to switch the conversational AI. For example, the extraction unit 603 extracts (identifies) the type of content that user 11 is most interested in, based on the type of content viewed for the longest time, the type of industry of the exhibition booth visited most often, etc., in order to determine whether or not to switch the first conversational AI set by the setting unit 502.

[0080] In step S902, the decision unit 604 determines whether or not to switch the conversational AI based on the decision information extracted by the extraction unit 603. For example, the decision unit 604 extracts a conversational AI 510 from the conversational AI DB (3DCG DB 506, scenario DB 507, model DB 508) that corresponds to the type of content that user 11 is most interested in, as extracted by the extraction unit 603. The decision unit 604 also determines that if the extracted conversational AI (second conversational AI) is not the same as the conversational AI (first conversational AI) set by the setting unit 502, it is necessary to switch from the first conversational AI to the second conversational AI. On the other hand, if the second conversational AI is the same as the first conversational AI, the decision unit 604 determines that it is not necessary to switch from the first conversational AI to the second conversational AI.

[0081] Furthermore, if the decision unit 604 cannot identify the type of viewing content, but can identify the industry type of the exhibition booth, it may select a conversational AI for a specific industry registered in the conversational AIDB, provided that it is not the same as an industry previously registered. Also, if the industry is the same as one previously registered, the decision unit 604 does not need to change the conversational AI.

[0082] If the setting unit 502 sets a general information dialogue AI instead of a dialogue AI for a specific industry, the judgment unit 604 will continue to select the general information dialogue AI regardless of whether the industry is the same or different. However, if the type of content that user 11 is interested in is identified, the judgment unit 604 will change to the dialogue AI corresponding to that type of content.

[0083] For example, as described above, suppose the setting unit 502 has set up a conversational AI suitable for general guidance, and in step S901, the user 11 has been able to identify the type of content they are interested in (for example, parts management software). In this case, the judgment unit 604 selects a conversational AI from among the conversational AIs for specific industries registered in the conversational AIDB that has been further trained or retrained and tuned specifically for a particular specialized field such as parts management software. As a result, the judgment unit 604 can more directly connect the user to the introduction of products of interest than the set general guidance conversational AI, and it becomes easier to avoid the risk of the user ending the conversation before moving on to the step of introducing products of interest.

[0084] Now, let's return to Figure 7 and continue the explanation of the sequence diagram. In step S708, if the decision unit 604 determines that a switch is necessary for the conversational AI, the information processing device 100 executes the process in step S709.

[0085] In step S709, the switching unit 605 switches the first dialogue AI set by the setting unit 502 to a second dialogue AI that is different from the first dialogue AI, according to the determination result of the determination unit 604. For example, the determination unit 604 sends a switching signal to the switching unit 605 and uploads information about the dialogue AI to be updated or overwritten, or information about a new dialogue AI, to the dialogue AI 510. This dialogue AI information includes, for example, at least one of the following: the 3DCG 511 of the dialogue AI 510, the dialogue scenario 512, and the dialogue model 513.

[0086] The switching unit 605 switches the conversational AI that interacts with the user 11 from the first conversational AI set by the setting unit 502 to the second conversational AI set by the judgment unit 604.

[0087] Here, we will explain an example of how to modify part of the conversational AI configuration.

[0088] (If only the dialogue scenario is changed) For example, let's assume that the conversational AI (first conversational AI) that user 11 interacted with during their previous login is a conversational AI that is knowledgeable about logistics solutions. Also, let's assume that user 11's metaverse activity history indicates that they focused on booths and explanations related to products and services related to pallet loss prevention within the logistics field. In this case, the switching control unit 503 extracts a scenario 512 in which conversational scenarios related to pallet loss are prioritized, and replaces the conversational scenario 512 with the first conversational AI. This allows the switching control unit 503 to switch to a second conversational AI in which only the conversational scenario 512 portion of the first conversational AI has been modified.

[0089] For example, upon receiving a determination that a switch is necessary, the switching control unit 503 extracts a dialogue scenario 512 for a product that resolves the pallet loss issue from the scenario DB 507 and performs an overwrite process on the currently set dialogue scenario 512. As a result, the dialogue scenario 512, which was set as the first dialogue AI, is changed, and the system switches to the second dialogue AI.

[0090] (If only 3DCG is being modified) For example, suppose a male 3DCG 511 is set as the first conversational AI to provide general information, and then the user 11 is female and, based on her visit history to other booths, has only visited female staff members, or has visited beauty-related booths. In this case, the switching control unit 503 may determine that the user prefers an explanation from a woman and change only the 3DCG 511 to a female conversational AI.

[0091] Furthermore, the 3DCG511 in this embodiment may include not only the appearance of the conversational AI, but also models that control its voice, reactions, or actions. Reactions or actions may include, for example, the size of gestures or the frequency of nodding.

[0092] Preferably, the dialogue model 513 according to this embodiment includes not only a model for generating dialogue sentences, but also a model for controlling response timing or backcasting such as acknowledgments.

[0093] Now, let's return to Figure 7 and continue explaining the sequence diagram. In step S710, the dialogue AI 510 determined in steps S705 to S710 generates 3DCG to depict the dialogue AI and the audio of the dialogue.

[0094] In steps S711 and S712, the communication unit 501 transmits the generated 3DCG and audio to the user terminal 10 via the host server 20.

[0095] In step S713, the user terminal 10 displays the conversational AI based on the received 3DCG and audio. In step S714, a conversation can be initiated between the user terminal 10 and the information processing device 100.

[0096] [Second Embodiment] In the second embodiment, an example of the process for switching the conversational AI based on the voice of user 11, or the voice of user 11 via their avatar in the metaverse space (hereinafter simply referred to as "user 11's voice") will be described.

[0097] (Switching process for conversational AI) Figure 10 shows an example of the switching process of the dialogue AI according to the second embodiment. This process shows an example of the process in which the information processing device 100 switches from the first dialogue AI to the second dialogue AI based on the voice of the user 11 or the like. It is assumed that the process in Figure 7 has already been executed at the start of the process in Figure 10. Also, a detailed explanation of the process similar to that of the first embodiment is omitted here.

[0098] In step S1001, the user terminal 10 transmits the voice and image of user 11 to the host server 20, and in step S1002, the host server 20 transfers the received voice and image to the information processing device 100.

[0099] In step S1003, the information processing device 100 performs a determination process to determine whether or not to switch the conversational AI, for example, as shown in Figure 11.

[0100] Figure 11 is a flowchart showing an example of the process for determining whether a switch is necessary according to the second embodiment. This process shows an example of the process for determining whether a switch is necessary for the conversational AI, which is executed by the information processing device 100 in step S1003 of Figure 10.

[0101] In step S1101, the communication unit 501 of the information processing device 100 acquires (receives) the voice and image of user 11. Note that the voice and image of user 11 are just another example of the user's predetermined information.

[0102] In step S1102, the recognition unit 601 performs speech recognition processing on the user 11's voice to convert the user 11's voice into text. The recognition unit 601 may also acquire non-verbal information from the user 11.

[0103] In step S1103, the interpretation unit 602 performs intent interpretation processing to interpret the intent of the user's utterance based, for example, on the linguistic information of the user 11 recognized by the recognition unit 601. The interpretation unit 602 may also interpret the intent of the user's utterance by taking into account the non-linguistic information of the user 11 recognized by the recognition unit 601.

[0104] In step S1104, the decision unit 604 determines whether it is necessary to switch from the current conversational AI (first conversational AI) to another conversational AI (a second conversational AI different from the first conversational AI). For example, if the first conversational AI is unable to answer the user 11's technical questions, the decision unit 604 determines that it is necessary to switch to a second conversational AI that has expertise in that technical field. Alternatively, if the decision unit 604 receives a request from the user 11 regarding the first conversational AI, it may determine that it is necessary to switch to a second conversational AI that responds to the user 11's request.

[0105] On the other hand, the decision unit 604 determines that switching the conversational AI is unnecessary if there is no specific reason for switching.

[0106] Now, let's return to Figure 10 and continue the explanation of the sequence diagram. In step S1003, if the determination unit 604 determines that a switch is necessary for the dialogue AI, the switching unit 605 executes the process in step S1004.

[0107] In step S1004, the switching unit 605 switches the current dialogue AI (first dialogue AI) to another dialogue AI (second dialogue AI) determined by the decision unit 604, according to the decision result of the decision unit 604.

[0108] In step S1005, the dialogue AI 510 determined in steps S1003 to S1004 generates 3DCG to depict the dialogue AI and audio for the dialogue.

[0109] In steps S1006 and S1007, the communication unit 501 transmits the generated 3DCG and audio to the user terminal 10 via the host server 20.

[0110] In step S1008, the user terminal 10 can display the conversational AI 510 determined in steps S1003 to S1004 based on the received 3DCG and audio, and continue the conversation.

[0111] (Examples of usage scenarios) For example, let's assume that the information processing device 100, through the processing shown in Figure 7, selects a conversational AI for camera equipment and begins a conversation with user 11. Let's also assume that during the conversation, user 11 makes a request: "Based on our discussion about the unique characteristics of your product (camera products), I would like to know the differences between your company's industrial films and those of other companies for a new business venture."

[0112] In this case, the information processing device 100 changes the dialogue scenario 512 of the dialogue AI 510 from a scenario explaining cameras to a scenario explaining industrial film. The information processing device 100 also changes the 3DCG 511 of the dialogue AI 510 from a character for camera merchandise to one for industrial parts, and changes the dialogue model 513 from (higher tone / larger reaction) to (lower tone / smaller reaction).

[0113] For example, the information processing device 100 may store and manage the switching details of the conversational AI 510 in switching information 1200, as shown in Figure 12.

[0114] Figure 12 shows an example of switching information according to one embodiment. In the example in Figure 12, the switching information 1200 includes information such as "user industry," "user gender," "user voice," "behavioral history," "dialogue AI change," "dialogue model, reaction model," "sales scenario," and "3DCG" as items.

[0115] Here, "user industry," "user gender," "user voice," and "behavioral history" correspond to predetermined information 1201 of user 11. In addition, "dialogue AI change," "dialogue model, reaction model," "sales scenario," and "3DCG" are the switching contents 1202 of the dialogue AI 510 that correspond to predetermined information 1201 of user 11.

[0116] For example, if the user 11's attribute information indicates that the user's industry is "nursing care," the user's gender is "female," and their behavioral history is "viewing other company's content (dementia-related videos)," the decision unit 604 switches the conversational AI in step S708 of Figure 7 according to the switching content 1202 of the switching information 1203 in the second row.

[0117] Furthermore, if, based on the attribute information of user 11, the user's industry is "business planning," the user's gender is "male," and the user's voice includes "I'm also interested in industrial film...", the judgment unit 604 switches the conversational AI in step S1003 of Figure 10 according to 1202 so as not to switch the switching information 1204 on the 8th line.

[0118] Note that the switching information 1200 shown in Figure 12 is just one example. The decision unit 604 may make such decisions, for example, according to a predetermined algorithm, or using a trained machine learning model.

[0119] Furthermore, when switching conversational AIs, the 3DCG511 also changes. Therefore, it is desirable that, for example, the previous conversational AI perform a handover action and engage in conversation to attract the new conversational AI on the screen before switching to the new conversational AI. This allows for a smooth handover. In this case, displaying both the first and second conversational AIs simultaneously on the user terminal 10 will allow for an even more natural handover.

[0120] Furthermore, when the information processing device 100 receives voice data indicating a desire to proceed with the purchase of the explained product, it may take actions such as displaying the purchase site on the user screen or connecting with a real sales representative.

[0121] Furthermore, if the information processing device 100 cannot identify a single conversational AI to switch to, for example, it may switch to multiple (e.g., two) conversational AIs and display multiple conversational AIs on the user screen.

[0122] <Example of display screen> Figures 13 and 14 show examples of display screens according to one embodiment. Figure 13 shows an example of a display screen 1300 that displays the first dialogue AI 1301. Figure 14 shows an example of a display screen 1400 that displays the second dialogue AI 1401. In Figure 13, the first dialogue AI 1301 is a dialogue AI for general information, and in Figure 14, the second dialogue AI 1401 is a dialogue AI specializing in nursing care solutions. The information processing device 100 displays such display screens on a user terminal 10 or the like used by the user 11.

[0123] In the example shown in Figure 13, the display screen 1300 showing the first conversational AI 1301 displays a list 1302 of available conversational AIs. This list 1302 of conversational AIs is displayed so that the user 11 can understand what fields the first conversational AI 1301, with which the user is currently interacting, specializes in, and what other conversational AIs are knowledgeable in. In the example shown in Figure 13, since the first conversational AI is a conversational AI for general information, "General Information" 1303 in the list of conversational AIs 1302 is highlighted.

[0124] In this state, for example, if the first conversational AI 1301 receives a question about the nursing care solution, the information processing device 100 switches to a display screen 1400 that displays the second conversational AI 1401, as shown in Figure 14.

[0125] Preferably, user 11 can switch dialogue AIs by telling the first dialogue AI 1301 of the general guidance system which second dialogue AI 1401 they want to call.

[0126] Furthermore, preferably, user 11 may switch dialogue AIs by selecting a second dialogue AI 1401 that they wish to call from the list of dialogue AIs 1302. In this way, when switching dialogue AIs, the information processing device 100 (switching unit 605) may present a list of candidate dialogue AIs 1302 in a selectable format and switch to the dialogue AI selected by user 11.

[0127] Furthermore, the specialists A through D displayed in the list of conversational AIs (1302) are not limited to the nursing care field, but may represent various other specialized fields, such as logistics or image processing. Additionally, conversational AIs capable of providing detailed explanations of the quality and safety of a particular product may be displayed.

[0128] [Example 3] The information processing device 100 according to this embodiment is not limited to the metaverse space and can be applied to various uses. Here, we will describe an example of processing by the information processing device 100, which is not limited to a specific embodiment.

[0129] Figure 15 is a flowchart showing an example of processing in the information processing apparatus according to the third embodiment.

[0130] In step S1501, the communication unit 501 receives predetermined information of user 11. In addition to the information described in the first and second embodiments, the predetermined information of user 11 may include user 11 behavioral data collected in real time by the user terminal 10. For example, if user 11 is using a web browser, the user terminal 10 collects information such as browsing history or search history. Also, if user 11 is using a smartphone application, the user terminal 10 collects application usage history or location information.

[0131] In step S1502, the setting unit 502 analyzes predetermined information of user 11 received by the communication unit 501, and based on the analysis results, sets the optimal dialogue AI (first dialogue AI) for user 11 from among multiple dialogue AIs.

[0132] Preferably, the analysis of predetermined information is performed considering the user 11's current behavior patterns, past dialogue history, browsing history, search history, or selection history. For example, if user 11 is searching for information about a product, the setting unit 502 may select a dialogue AI that can respond to questions about product details.

[0133] Furthermore, the selection of a conversational AI is performed using pre-configured rules or machine learning algorithms to choose the conversational AI that best suits the user's needs or the current context.

[0134] In step S1503, the decision unit 604 determines whether or not a change to the conversational AI is necessary. For example, the decision unit 604 monitors the performance of the current conversational AI in real time. Also, if the conversational AI is unable to provide an appropriate answer to the user's question, or if the user 11 expresses dissatisfaction with the conversational AI, the decision unit 604 may intervene and determine whether or not a change to the conversational AI is necessary.

[0135] The decision unit 604 determines whether or not to switch conversational AIs based on multiple evaluation criteria. These include, for example, the tone of the current conversation of user 11, the response speed of the conversational AI, or the suitability of the conversational AI for the user's request. For example, if user 11 is asking a technical question and the current conversational AI cannot answer that question, the decision unit 604 will switch to a conversational AI with more specialized knowledge.

[0136] In step S1504, if the determination unit 604 determines that a switch is necessary, it proceeds to step S1505. On the other hand, if the determination unit 604 determines that a switch is not necessary, it proceeds to step S1506.

[0137] When the system moves to step S1505, the switching unit 605 switches the conversational AI based on the judgment result of the judgment unit 604. This switching is performed seamlessly, allowing the user 11 to continue the conversation with the new conversational AI without interruption.

[0138] For example, after the switch, the new conversational AI inherits the conversation history from the previous conversational AI and smoothly continues the conversation with user 11. This allows the user to receive support from the new conversational AI while maintaining the flow of the conversation.

[0139] In step S1506, the newly selected conversational AI takes over and continues the conversation with user 11. For example, the conversational AI provides appropriate information and solves problems according to user 11's needs.

[0140] Preferably, the conversational AI collects user 11 feedback during the conversation to help improve the quality of the conversation. This includes, for example, user 11 satisfaction and feedback on the conversational AI's performance.

[0141] In step S1507, the information processing device 100 determines whether the dialogue has ended. If the dialogue has not ended, the information processing device 100 returns to step S1503. On the other hand, if the dialogue has ended, the information processing device 100 terminates the process shown in Figure 15.

[0142] The process shown in Figure 15 enables the information processing device 100 to switch from an already selected or executed conversational AI to a more appropriate conversational AI in response to changes in the user's situation or requests. For example, after switching from the first conversational AI to the second conversational AI, the information processing device 100 can similarly switch to a third conversational AI, a fourth conversational AI, and so on, to further appropriate conversational AIs.

[0143] <Specific Use Cases> [Use Case 1] Customer support scenarios (Scenario Overview) User 11 accesses the online store's customer support and asks a question about a product. In this process, the first conversational AI responds to User 11's initial question.

[0144] (Decision to switch conversational AI) If the first conversational AI is unable to answer the user 11's technical questions, the switching control unit 503 decides to switch to a second conversational AI (technical support AI) that possesses specialized knowledge.

[0145] (Execute the switch and continue the dialogue) The switching control unit 503 executes a switch to the second conversational AI, which responds to the user's technical questions and provides appropriate support.

[0146] [Use Case 2] Personalized Marketing Scenarios (Scenario Overview) User 11 is using a shopping app, and a conversational AI for marketing purposes is providing personalized product recommendations based on their recent purchase and browsing history.

[0147] (Selection and switching of conversational AI) A conversational AI for marketing analyzes user 11's purchase and browsing history and recommends products suitable for user 11. However, if user 11 requests detailed technical information about a specific product, the switching control unit 503 decides to switch to a conversational AI for technical explanations.

[0148] (Execute the switch and continue the dialogue) The switching control unit 503 performs a switch to a conversational AI for technical explanation, and the switched conversational AI provides detailed technical information according to the user's request.

[0149] As described above, according to each embodiment of the present invention, the user will be able to switch from a previously selected or executed conversational AI to a more appropriate conversational AI in response to changes in the user's situation or requests.

[0150] In this embodiment, the information processing device 100 provides multiple conversational AIs, enabling it to appropriately select or switch between conversational AIs to meet the diverse needs of the user 11. This improves the quality of the user experience and allows for maximum utilization of the expertise of each conversational AI.

[0151] Furthermore, the seamless switching between conversational AIs minimizes interruptions to the user's (11) conversational experience. Additionally, by utilizing user (11) behavioral and conversational history, it becomes possible to provide more personalized services, improving the overall efficiency and effectiveness of the system.

[0152] This embodiment provides advanced conversational AI selection and switching technology based on the user 11's behavioral history, enabling the information processing device 100 to perform at its best. This technology can be applied to various fields such as customer support, personalized marketing, education, or entertainment.

[0153] <Supplement> Each function of the embodiments described above can be realized by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), FPGAs (field programmable gate arrays), and conventional circuit modules designed to execute each function described above.

[0154] Furthermore, the apparatus described in the examples represents only one of several computing environments for carrying out the embodiments disclosed herein. In one embodiment, the information processing apparatus 100 includes multiple computing devices, such as a server cluster. The multiple computing devices are configured to communicate with each other via any type of communication link, including a network or shared memory, and perform the processing disclosed herein.

[0155] Furthermore, each functional configuration of the information processing device 100 may be combined into a single device or divided among multiple devices. In addition, at least some of the functional configurations of the information processing device 100 may be provided by the user terminal 10 or the host server 20.

[0156] <Note> This specification discloses information processing devices, information processing systems, information processing methods, and programs as described below. (Note 1) An information processing device that provides multiple conversational AIs that interact with a user via a user terminal, A settings unit for configuring the first conversational AI that interacts with the user, A storage unit that stores the user's behavioral history when interacting with the first dialogue AI, A determination unit that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching unit that switches to the second dialogue AI based on the judgment result determined by the judgment unit, An information processing device having (Note 2) The information processing device described in Appendix 1, wherein the determination unit determines whether or not it is necessary to switch from the first dialogue AI to the second dialogue AI based on the predetermined information acquired after setting the first dialogue AI. (Note 3) The switching unit presents a second dialogue AI as a candidate for switching, and switches to the second dialogue AI selected by the user, as described in Appendix 1. (Note 4) The information processing device described in Appendix 1, wherein the determination unit determines, after setting the first dialogue AI and before dialogue with the user begins, whether it is necessary to switch from the first dialogue AI to the second dialogue AI based on the user's behavior history. (Note 5) The information processing apparatus according to claim 1, wherein the aforementioned behavioral history includes a dialogue history. (Note 6) The information processing device described in Appendix 1 or Appendix 5, wherein the behavioral history includes one or more pieces of information from among movement history, browsing history, search history, selection history, and purchase history. (Note 7) The aforementioned behavioral history includes one or more pieces of information from among location information, device information, form input content, social media activity, and applications used, as described in any of Appendix 1, Appendix 5, or Appendix 6 of the information processing device. (Note 8) The setting unit sets the first conversational AI based on the user's behavior history, as described in any of the information processing devices described in Appendix 1 to Appendix 7. (Note 9) The information processing device described in Appendix 8, wherein the setting unit sets the first conversational AI based on the user's attribute information if there is no user activity history. (Note 10) The switching unit further switches from the second dialogue AI that interacts with the user to a third dialogue AI that is different from the second dialogue AI, based on the behavior history, as described in Appendix 1 or Appendix 2 of the information processing apparatus. (Note 11) The switching unit switches from the first conversational AI that interacts with the user to a plurality of conversational AIs based on the behavior history, as described in Appendix 1 or Appendix 2. (Note 12) The information processing device described in Appendix 11, wherein the plurality of dialogue AIs include the first dialogue AI. (Note 13) The information processing device described in Appendix 11, wherein the plurality of dialogue AIs include a second dialogue AI and a third dialogue AI, which are different from the first dialogue AI. (Note 14) The information processing device described in Appendix 11, which displays the plurality of conversational AIs on the user terminal. (Note 15) The first dialogue AI is an information processing device described in any of the appendices 1 to 14, which is a dialogue AI that performs general guidance. (Note 16) An information processing system comprising a user terminal and an information processing device that provides multiple conversational AIs that interact with the user via the user terminal, The aforementioned information processing device is A settings unit for configuring the first conversational AI that interacts with the user, A storage unit that stores the user's behavioral history when interacting with the first dialogue AI, A determination unit that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching unit that switches to the second dialogue AI based on the judgment result determined by the judgment unit, It has, The aforementioned user terminal is A communication unit that communicates with the aforementioned information processing device, A display unit that displays the conversational AI provided by the aforementioned information processing device, Having, Information processing system. (Note 17) A computer that provides multiple conversational AIs that interact with users via user terminals, The setup process involves configuring the first conversational AI that interacts with the user, A memory process that stores the user's behavioral history while interacting with the first dialogue AI, A decision process that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching process is performed to switch to the second dialogue AI based on the judgment result determined by the aforementioned judgment process, An information processing method that performs [this action]. (Note 18) A computer that provides multiple conversational AIs that interact with users via user terminals, The setup process involves configuring the first conversational AI that interacts with the user, A memory process that stores the user's behavioral history while interacting with the first dialogue AI, A decision process that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching process is performed to switch to the second dialogue AI based on the judgment result determined by the aforementioned judgment process, A program that executes something.

[0157] Although embodiments of the present invention have been described above, the present invention is not limited to these specific embodiments, and various modifications and applications are possible within the scope of the gist of the present invention as described in the claims. [Explanation of Symbols]

[0158] 1. Information Processing System 10 User terminals 20 Host Servers 100 Information Processing Devices 300 Computers 400 Information terminals (computers) 501 Communications Department 502 Settings Section 503 Switching Control Unit 505 Behavioral History Database (Memory Unit) 510 Conversational AI 604 Judgment Department 605 Switching section 1301 The First Dialogue AI 1401 The Second Dialogue AI [Prior art documents] [Patent Documents]

[0159] [Patent Document 1] Special Publication No. 2023-525173

Claims

1. An information processing device that provides multiple conversational AIs that interact with a user via a user terminal, A settings unit for configuring the first conversational AI that interacts with the user, A storage unit that stores the user's behavioral history when interacting with the first dialogue AI, A determination unit that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching unit that switches to the second dialogue AI based on the judgment result determined by the judgment unit, An information processing device having

2. The information processing apparatus according to claim 1, wherein the determination unit determines whether it is necessary to switch from the first dialogue AI to the second dialogue AI based on the behavior history acquired after setting the first dialogue AI.

3. The information processing apparatus according to claim 1, wherein the switching unit presents a second conversational AI as a candidate for switching, and switches to the second conversational AI selected by the user.

4. The information processing apparatus according to claim 1, wherein the determination unit determines, after setting the first dialogue AI and before dialogue with the user begins, whether or not it is necessary to switch from the first dialogue AI to the second dialogue AI based on the user's behavior history.

5. The information processing apparatus according to claim 1, wherein the aforementioned behavioral history includes a dialogue history.

6. The information processing device according to claim 1 or 5, wherein the behavioral history includes one or more pieces of information from among movement history, browsing history, search history, selection history, and purchase history.

7. The information processing apparatus according to claim 1 or 5, wherein the behavioral history includes one or more pieces of information from among location information, device information, form input content, social media activity, and applications used.

8. The information processing apparatus according to claim 1 or 2, wherein the setting unit sets the first conversational AI based on the user's behavior history.

9. The information processing apparatus according to claim 8, wherein the setting unit sets the first conversational AI based on the user's attribute information if there is no user activity history.

10. The information processing apparatus according to claim 1 or 2, wherein the switching unit further switches from the second conversational AI that interacts with the user to a third conversational AI different from the second conversational AI, based on the behavior history.

11. The information processing apparatus according to claim 1 or 2, wherein the switching unit switches from the first conversational AI that interacts with the user to a plurality of conversational AIs based on the behavior history.

12. The information processing apparatus according to claim 11, wherein the plurality of conversational AIs include the first conversational AI.

13. The information processing apparatus according to claim 11, wherein the plurality of conversational AIs include a second conversational AI and a third conversational AI, which are different from the first conversational AI.

14. The information processing apparatus according to claim 11, which displays the plurality of conversational AIs on the user terminal.

15. The information processing apparatus according to any one of claims 1 to 4, wherein the first conversational AI is a conversational AI that performs general guidance.

16. An information processing system comprising a user terminal and an information processing device that provides a plurality of conversational AIs that interact with the user via the user terminal, The aforementioned information processing device is A settings unit for configuring the first conversational AI that interacts with the user, A storage unit that stores the user's behavioral history when interacting with the first dialogue AI, A determination unit that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching unit that switches to the second dialogue AI based on the judgment result determined by the judgment unit, It has, The aforementioned user terminal is A communication unit that communicates with the aforementioned information processing device, A display unit that displays the conversational AI provided by the information processing device, Having, Information processing system.

17. A computer that provides multiple conversational AIs that interact with users via user terminals, The setup process involves configuring the first conversational AI that interacts with the user, A memory process that stores the user's behavioral history while interacting with the first dialogue AI, A decision process that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching process is performed to switch to the second dialogue AI based on the judgment result determined by the judgment process, An information processing method that performs [this action].

18. A computer that provides multiple conversational AIs that interact with users via user terminals, The setup process involves configuring the first conversational AI that interacts with the user, A memory process that stores the user's behavioral history while interacting with the first dialogue AI, A decision process that determines whether it is necessary to switch from the first dialogue AI to a second dialogue AI different from the first dialogue AI, based on the user's behavior history during a conversation with the first dialogue AI, A switching process is performed to switch to the second dialogue AI based on the judgment result determined by the judgment process, A program that executes something.

Images