Information processing system and information processing device

Abstract

To provide an information processing system and an information processing device that can transfer a conversation between a user and one virtual agent to another virtual agent without causing discomfort to the user. SOLUTION: A virtual agent conversation system 10 converses with a user using one of a plurality of virtual agents 22. The virtual agent conversation system 10 includes a conversation unit 140A that instructs an artificial intelligence system 12 to generate conversation content for the virtual agent 22 with the user, acquires the conversation content generated by the artificial intelligence system 12, and presents it to the user, and a performance control unit 144A that, when the conversation is handed over from one virtual agent 22 to another virtual agent 22, performs a performance to make the user aware that the conversation has been handed over.

Description

[Technical Field]

[0001] The present invention relates to an information processing system and an information processing device. [Background technology]

[0002] In recent years, virtual agent systems have been developed that use conversation models trained through machine learning to conduct conversations with users in natural language.

[0003] In such a virtual agent system, a device such as a smartphone used by a user displays an image of a character corresponding to a virtual agent and accepts input such as questions from the user. The virtual agent is, for example, a two-dimensional or three-dimensional animated character set as a conversation partner for the user. The user may also use multiple virtual agents with different types of expertise to have a conversation.

[0004] Patent document 1 describes a vehicle that supports communication between the user and the vehicle through an interactive user interface using biometric characters, and describes how, when switching from an old vehicle to a new one, the data used to support communication is transferred. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2023-067594 Summary of the Invention [Problem to be solved by the invention]

[0006] Here, if the conversation content is handed over from the virtual agent with which the user is having a conversation to another virtual agent, the user, who is unaware that the conversation content has been handed over, may feel uncomfortable.

[0007] In this regard, Patent Document 1 describes a technique for making a character move when data is transferred from an old vehicle to a new vehicle. As such, the technique described in Patent Document 1 is not applicable to virtual agent systems, as it is not applicable to cases where the content of a conversation is transferred from one virtual agent with which a user is conversing to another virtual agent.

[0008] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing system and an information processing device that are capable of handing over a conversation between a user and one virtual agent to another virtual agent without causing discomfort to the user. [Means for solving the problem]

[0009] The information processing system of the present invention comprises a conversation unit that instructs a task processing device, which processes tasks using artificial intelligence in accordance with task processing instructions, to generate conversation content for the virtual agent with a user, and acquires the conversation content generated by the task processing device and presents it to the user; and a performance control unit that, when a dialogue is being conducted by one of a plurality of virtual agents and the conversation is being handed over from one virtual agent to another virtual agent, performs a performance to make the user aware that the conversation has been handed over.

[0010] The information processing device of the present invention comprises a conversation unit that instructs a task processing device, which processes a task using artificial intelligence in accordance with a task processing instruction, to generate conversation content for a virtual agent for a user, and acquires the conversation content generated by the task processing device and presents it to the user; and a performance control unit that, when a dialogue is being conducted by one of a plurality of virtual agents and the conversation is being handed over from one virtual agent to another virtual agent, performs a performance to make the user aware that the conversation has been handed over. [Effects of the Invention]

[0011] According to the present invention, a conversation with a user can be handed over from one virtual agent to another virtual agent without causing discomfort to the user. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing the configuration of a virtual agent conversation system according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the hardware configuration of the user terminal of this embodiment. [Figure 3] FIG. 3 is a diagram showing the hardware configuration of the server of this embodiment. [Figure 4] FIG. 4 is a functional block diagram relating to the takeover effect of this embodiment. [Figure 5] FIG. 5 is a flowchart showing the flow of conversation processing when a conversation is handed over from a main agent to a specialized agent in the embodiment. [Figure 6] FIG. 6 is a flowchart showing the flow of conversation processing when a conversation is handed over from a specialized agent to another virtual agent according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment described below shows an example of how the present invention can be implemented, and the present invention is not limited to the specific configuration described below. When implementing the present invention, a specific configuration corresponding to the embodiment may be appropriately adopted.

[0014] Fig. 1 is a diagram showing an example of the configuration of a virtual agent conversation system 10 of this embodiment. As shown in Fig. 1, the virtual agent conversation system 10 of this embodiment is an information processing system that uses an artificial intelligence system (generative artificial intelligence model) 12 to generate conversation content for a virtual agent (AI agent) to have with a user.

[0015] The virtual agent conversation system 10 of this embodiment comprises an artificial intelligence system 12, a user terminal 14, and a distribution server 16. The user terminal 14 is owned by a user who uses the virtual agent conversation system 10. There may be multiple distribution servers 16 and multiple artificial intelligence systems 12, as will be described in detail below.

[0016] The virtual agent conversation system 10 may also include other devices such as servers and terminals. The user terminal 14 and the distribution server 16 are communicatively connected to each other via a network NW. The distribution server 16 and the artificial intelligence system 12 are communicatively connected to each other via the network NW. The network NW is composed of the Internet, a local area network (LAN), various mobile communication systems constructed using wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a network that is directly connected using a USB (Universal Serial Bus) cable, etc.

[0017] The user terminal 14 is an information processing device equipped with a touch panel display 20 and used by a user. The user terminal 14 accepts user operations. The user terminal 14 launches an application of this embodiment (hereinafter, may simply be referred to as an "app") in response to a user operation. The app of this embodiment is a virtual agent app that provides a conversation service with a virtual agent 22 displayed on the touch panel display 20 of the user terminal 14. In response to a user operation, the user terminal 14 requests content to be displayed or played by the app from the distribution server 16. Note that the user terminal 14 may display content using any app as long as it can display or play content distributed by the distribution server 16. For example, the user terminal 14 may display or play content using a dedicated application such as the virtual agent app of this embodiment, or may display or play content including the virtual agent 22 using a browser app (hereinafter, may simply be referred to as a "browser").

[0018] The user terminal 14 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In this embodiment, the user terminal 14 is a smartphone having a touch panel function.

[0019] In this embodiment, as an example, the user terminal 14 has a function of a voice response system (voice recognition), detects voice information (hereinafter also referred to as "utterance") uttered by a user, and accepts the detected utterance as input information. For example, the user terminal 14 is a terminal device that performs processing on the user's utterance. When the user terminal 14 detects the user's utterance, it transmits input information based on the user's utterance to the distribution server 16, receives content corresponding to the user's utterance, and presents it to the user.

[0020] The distribution server 16 receives a distribution request from the user terminal 14 of the user, and distributes content related to the virtual agent 22 that interacts with the user in a virtual agent app launched on the user terminal 14. The distribution server 16 uses the artificial intelligence system 12 to generate conversation content for the virtual agent 22 to the user, and distributes the generated conversation content to the user terminal 14. The distribution server 16 is configured by a computer having at least a communication function and a program execution function. The distribution server 16 may be realized by one information processing device or by multiple information processing devices.

[0021] The distribution server 16 may also have a voice recognition function. The distribution server 16 may also be able to acquire information from a voice recognition server that provides a voice recognition service. In this case, the voice recognition server may be included in the virtual agent conversation system 10. Note that in this embodiment, the user terminal 14, the distribution server 16, and the voice recognition server recognize the user's utterance and identify the user who made the utterance by appropriately using various conventional technologies, and therefore, description thereof will be omitted.

[0022] The artificial intelligence system 12 is an information processing device that has an internal LLM (Large Language Model) and is capable of outputting an output sentence (a response to a prompt) in response to an input sentence called a prompt. Examples of the artificial intelligence system 12 include ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, and BERT. The artificial intelligence system 12 may be operated by a business that provides the virtual agent app of this embodiment, or may be used via an API (Application Programming Interface) provided by an external artificial intelligence system 12 operated by another business.

[0023] The artificial intelligence system 12 has a dialogue (chat) function. The distribution server 16 can provide any inquiry or command in text form to the artificial intelligence system 12, thereby obtaining a response to the inquiry or command. In this way, the artificial intelligence system 12 of this embodiment is a task processing device that uses artificial intelligence to process tasks in response to task processing instructions such as any inquiry or command.

[0024] In this embodiment, the distribution server 16 sends a prompt to the artificial intelligence system 12 to cause the artificial intelligence system 12 to generate the conversation content of the virtual agent 22 with the user, or the conversation content for the virtual agent to speak to the user, so that the conversation content can be obtained as an answer.

[0025] Furthermore, in this embodiment, the artificial intelligence system 12 is not limited to text-based dialogue responses. For example, the artificial intelligence system 30 may be capable of voice-based dialogue responses. In this case, the artificial intelligence system 30 may receive voice data of an utterance from a user (for example, the voice data of the utterance itself, or voice data of the utterance with noise, etc., canceled out) along with the user's identification information, etc., and generate the content of the conversation for the virtual agent. Furthermore, the artificial intelligence system 30 may be an image generation AI system, such as Midjourney or Stable Diffusion, that is capable of generating image data.

[0026] 2 is a diagram showing an example of the hardware configuration of the user terminal 14 of this embodiment. The user terminal 14 is a computer (information processing device) such as a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, or a PDA (Personal Digital Assistant).

[0027] The user terminal 14 is physically configured as a computer including a processor 100, memory 102, storage 104, communication device 106, input device 108, output device 110, and a bus connecting these. Each of these devices operates using power supplied from a battery (not shown). In the following description, the term "device" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the user terminal 14 may be configured to include one or more of the devices shown in FIG. 2, or may be configured with some of the devices omitted. Furthermore, the user terminal 14 may be configured by communicating with multiple devices each having a different housing.

[0028] Each function of the user terminal 14 is realized by loading predetermined software (programs) onto hardware such as the processor 100 and memory 102, causing the processor 100 to perform calculations, control communication via the communication device 106, and control at least one of reading and writing data in the memory 102 and storage 104.

[0029] The processor 100 controls the entire computer by running, for example, an operating system. The processor 100 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Furthermore, for example, a baseband signal processing unit, a call processing unit, etc. may be realized by the processor 100.

[0030] The processor 100 reads programs (program codes), software modules, data, etc. from at least one of the storage 104 and the communication device 106 into the memory 102 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described below. Functional blocks of the user terminal 14 may be implemented by a control program stored in the memory 102 and running on the processor 100. Various processes may be executed by one processor 100, or may be executed simultaneously or sequentially by two or more processors 100. The processor 100 may be implemented by one or more chips. The programs may be transmitted to the user terminal 14 via a telecommunications line.

[0031] The memory 102 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 102 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 102 can store executable programs (program codes), software modules, etc. for implementing the method of this embodiment.

[0032] Storage 104 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 104 may also be referred to as an auxiliary storage device.

[0033] The communication device 106 enables communication with the distribution server 16. The communication device 106 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize at least one of Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, a transmitting / receiving antenna, an amplifier unit, a transmitting / receiving unit, a transmission path interface, etc. may be realized by the communication device 106. The transmitting / receiving unit may be implemented as a transmitting unit and a receiving unit that are physically or logically separated.

[0034] The input device 108 is an input device that accepts input from the outside (for example, keys, microphones, cameras, switches, buttons, various sensors such as position information sensors and motion sensors, etc.). The output device 110 is an output device that outputs to the outside (for example, a display, speakers, LED lamps, etc.). The user terminal 14 of this embodiment is equipped with a touch panel display 20 that is an integrated configuration of the input device 108 and the output device 110.

[0035] Each device, such as the processor 100 and the memory 102, is connected by a bus for communicating information. The bus may be configured using a single bus, or different buses may be used between each device.

[0036] The user terminal 14 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 100 may be implemented using at least one of these pieces of hardware.

[0037] 3 is a diagram showing an example of the hardware configuration of the distribution server 16 of this embodiment. The distribution server 16 is an information processing device realized by, for example, a computer, a server device, a cloud system, or the like. The distribution server 16 is physically configured as a computer device including a processor 120, a memory 122, a storage 124, a communication device 126, an input device 128, an output device 130, and a bus connecting these. The processor 120, the memory 122, the storage 124, the input device 128, and the output device 130 are similar in hardware to the processor 100, the memory 102, the storage 104, the input device 108, and the output device 110 of the user terminal 14, and therefore a description thereof will be omitted.

[0038] The communication device 126 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 126 enables communication with the user terminal 14.

[0039] The hardware configuration of the artificial intelligence system 12 of this embodiment is similar to that of the distribution server 16, and therefore a description thereof will be omitted.

[0040] In the virtual agent conversation system 10, as described above, the user converses with the virtual agent 22 using a virtual agent application installed on the user terminal 14.

[0041] The virtual agent app of this embodiment enables a user to converse with multiple different types of virtual agents 22. For this reason, the user uses the virtual agent app to select one virtual agent 22 from the multiple different types of virtual agents 22 and converse with it. The virtual agent app displays different 2D or 3D characters on the touch panel display 20 of the user terminal 14 depending on the virtual agent 22 selected by the user.

[0042] The virtual agents 22 include, for example, a main agent and a subagent. A main agent is a virtual agent 22 that has low expertise but has general conversations with the user. For example, the user has everyday conversations with the main agent. A subagent is a virtual agent 22 that has more specialized conversations than the main agent, and will be referred to as a specialized agent in the following explanation. The specialized agents are divided into categories such as law, home appliances, cooking, and childcare. The user asks specialized questions to the specialized agent.

[0043] In the virtual agent conversation system 10 of this embodiment, as an example, a different artificial intelligence system 12 (LLM) is constructed for each main agent and specialist agent. In particular, the LLM of the artificial intelligence system 12 corresponding to the specialist agent undergoes learning specialized for the specialized content of that specialist agent. Furthermore, the main agent and each specialist agent of the virtual agent conversation system 10 of this embodiment are processed by different distribution servers 16, and respond to the user via the user terminal 14.

[0044] In addition, the main agent and the specialized agent may be operated by different businesses. In this case, the distribution server 16 that operates the main agent and the distribution server 16 that operates the specialized agent are operated by different businesses.

[0045] The virtual agent conversation system 10 of this embodiment is capable of having a specialized agent take over the conversation while the user is having a conversation with the main agent. For example, when the user asks the main agent a question, the handover occurs when the question is specialized and it is appropriate for the specialized agent to have a conversation with the user. The handover of the conversation may occur even when the user's question is not specialized, or when it is more appropriate for the virtual agent 22 to take over the conversation for other reasons. In other words, handover means that the virtual agent 22 with which the user is having a conversation is switched, and the continuity of the conversation with the user is maintained even when the virtual agent 22 is switched.

[0046] The necessity of taking over the conversation is determined, for example, by the artificial intelligence system 12 corresponding to the virtual agent 22 having a conversation with the user, based on whether or not the user's utterance satisfies a preset condition. Then, an appropriate other virtual agent 22 to take over the conversation is selected based on the content of the conversation between the user and the virtual agent 22. The selection of the other virtual agent 22 to take over the conversation is performed, for example, by a control LLM. The control LLM may be provided in the distribution server 16 or may be a function of the artificial intelligence system 12.

[0047] Furthermore, the handover of a conversation includes not only a case where one virtual agent 22 that was having a conversation with a user actively passes the conversation on to another virtual agent 22, but also a case where the user himself wishes to pass the conversation on from one virtual agent 22 to another virtual agent 22.

[0048] As an example, the virtual agent conversation system 10 of this embodiment is configured so that another virtual agent 22 that has taken over a conversation can converse with the user by referring to the content of the conversation with the virtual agent 22 that had been conversing with the user up until that point. For this reason, it is expected that the user will feel uncomfortable if the other virtual agent 22 that has taken over the conversation knows the content of the conversation between the first virtual agent 22 and the user.

[0049] Therefore, in this embodiment, when a conversation is handed over from one virtual agent 22 to another virtual agent 22, the virtual agent conversation system 10 performs a performance (hereinafter referred to as a "handover performance") to make the user aware that the conversation has been handed over.

[0050] Figure 4 is a functional block diagram related to handover performance in the virtual agent conversation system 10. In the example of Figure 4, the business operator who operates the main agent 22A and the business operator who operates the specialist agent 22B are different businesses. In the following explanation, the business operator who operates the main agent 22A will be referred to as business operator A, and the business operator who operates the specialist agent 22B will be referred to as business operator B. In Figure 4, the artificial intelligence system 12, distribution server 16, and their functions corresponding to the main agent 22A will be designated with the suffix "A," and the artificial intelligence system 12, distribution server 16, and their functions corresponding to the specialist agent 22B will be designated with the suffix "B" to distinguish them from one another.

[0051] The artificial intelligence system 12A may be operated by business operator A, or may be operated by a business operator other than business operator A or business operator B. The LLM of the artificial intelligence system 12A is constructed as a trained model that is not specialized but has high versatility.

[0052] Distribution server 16A is distribution server 16 operated by provider A, and includes conversation unit 140A, memory control unit 142A, performance control unit 144A, and storage 124A. Conversation unit 140A, memory control unit 142A, and performance control unit 144A are functions provided in processor 120 of distribution server 16A.

[0053] The conversation unit 140A instructs the artificial intelligence system 12A to generate a conversation content for the main agent 22A to have with the user, and acquires the conversation content generated by the artificial intelligence system 12A and presents it to the user. The above instruction by the conversation unit 140A is a prompt. The prompt is generated based on a question or the like from the user input via the user terminal 14. The conversation content is presented to the user as an utterance or the like of the main agent 22A displayed on the touch panel display 20 of the user terminal 14.

[0054] The storage control unit 142A stores information about the content of a conversation between each virtual agent 22 and the user in a database (hereinafter referred to as a "conversation DB"). For this purpose, the artificial intelligence system 12A transmits the content of a conversation between the main agent 22A and the user to the storage control unit 142A, and stores the content of the conversation in the conversation DB. The conversation DB is held in the storage 124A. The conversation unit 140A instructs the artificial intelligence system 12A to generate the conversation content by referring to the conversation DB.

[0055] When a conversation is being conducted by one of the plurality of virtual agents 22 and the conversation is being handed over from one virtual agent 22 to another virtual agent 22, the performance control unit 144 performs a handover performance, which is a performance to make the user aware that the conversation has been handed over.

[0056] The LLM of the artificial intelligence system 12B corresponding to the specialist agent 22B is constructed as a specialized trained model corresponding to, for example, any of law, home appliances, childcare, cooking, etc. The artificial intelligence system 12B may be operated by business operator B, or may be operated by a business operator different from business operator A or business operator B. The artificial intelligence system 12B of this embodiment transmits the content of the conversation between the specialist agent 22B and the user to the storage control unit 142A, and stores the content of the conversation in a conversation DB.

[0057] The distribution server 16B is a distribution server 16 operated by the business operator B, and includes a conversation unit 140B. The distribution server 16B is provided for each specialized field corresponding to the specialized agent 22B, and may be operated by a business operator specializing in each specialized field.

[0058] The conversation unit 140B has the same functions as the conversation unit 140A, and instructs the artificial intelligence system 12B to generate conversation content for the specialized agent 22B to the user, and acquires the conversation content generated by the artificial intelligence system 12B and presents it to the user. The conversation unit 140B of this embodiment is capable of instructing the artificial intelligence system 12B to generate conversation content by referring to the conversation DB held in the storage 124A.

[0059] The performance control unit 144B has the same functions as the performance control unit 144A. In the following description, when the performance control units 144A and 144B are not to be distinguished from each other, the "A" or "B" added to the end of the reference numeral will be omitted.

[0060] The following describes the transition effect performed by the effect control unit 144. The transition effect is at least one of an image display and an audio output on the touch panel display 20 of the user terminal 14 operated by the user.

[0061] For example, a moving image of the source virtual agent 22 and the destination virtual agent 22 shaking hands or having a conversation is displayed on the user terminal 14. The destination virtual agent 22 may start the conversation with the user by saying something like "I'm listening to you from XX," where XX is the name of the source virtual agent 22. A sound indicating that the conversation is being taken over may also be output from the user terminal 14. This kind of handover effect allows the user to easily recognize that the conversation has been taken over by another virtual agent 22.

[0062] Furthermore, the performance control unit 144A performs a performance when a handover occurs from one virtual agent 22 to another virtual agent 22, but does not perform a handover performance when a handover occurs from another virtual agent 22 to the one virtual agent 22. As an example, the one virtual agent 22 here is the main agent 22A, and the other virtual agent 22 is the specialized agent 22B.

[0063] That is, in the virtual agent conversation system 10 of this embodiment, it is unlikely that the user will feel uncomfortable with the handover from the specialist agent 22B to the main agent 22A, so there is no need to perform unnecessary effects. Note that the virtual agent 22 for which no handover effects are performed is not limited to the main agent 22A, and may be another virtual agent 22 that has been set in advance.

[0064] Furthermore, the handover effect may not be performed depending on the intimacy between the virtual agent 22 and the user. That is, the virtual agent conversation system 10 of this embodiment identifies the intimacy with the user for each virtual agent 22, and does not perform the handover effect when handover is performed from one virtual agent 22 with a low intimacy degree to another virtual agent 22 with a high intimacy degree.

[0065] The intimacy level is, for example, the total time during which the virtual agent 22 and the user have a conversation (hereinafter referred to as "total conversation time"). The total conversation time is specified for each virtual agent 22. That is, when a conversation is handed over from a virtual agent 22 with a relatively short total conversation time to a virtual agent 22 with a relatively long conversation time, no handover effect is performed. The intimacy level may also be set in advance by the user, etc. For example, the main agent 22A is considered to have a high intimacy level regardless of the length of the total conversation time, and when a conversation is handed over from another virtual agent 22 to the main agent 22A, no handover effect is performed.

[0066] The intimacy level for each virtual agent 22 is stored, for example, in the storage 124 provided in the distribution server 16 corresponding to the virtual agent 22, and is updated every time the user and the virtual agent 22 have a conversation.

[0067] A threshold value (hereinafter referred to as "first threshold value") may be set for the total conversation time at which no handover effect is performed. That is, even when a conversation is handed over from a virtual agent 22 with a relatively short total conversation time to a virtual agent 22 with a relatively long conversation time, the handover effect is performed if the conversation time of the virtual agent 22 as the handover destination is shorter than the first threshold value.

[0068] Furthermore, when a conversation is handed over to a virtual agent 22 whose total conversation time exceeds a second threshold, the handover effect may not be performed even if the total conversation time is shorter than that of the original virtual agent 22. The second threshold is a value greater than the first threshold.

[0069] The intimacy level may be determined not only by the total conversation time with the virtual agent 22, but also by, for example, the number of conversations the user has had with the virtual agent 22 (hereinafter referred to as the "number of conversations"). In other words, the more conversations the virtual agent 22 has with the user, the higher the intimacy level is considered to be.

[0070] 5 is a flowchart showing the flow of conversation processing when a conversation is handed over from the main agent 22A to the specialized agent 22B in this embodiment. Note that, as an example, when a conversation is handed over from the main agent 22A to the specialized agent 22B, a handover performance is always performed.

[0071] First, in step 100, a conversation takes place between the user and the main agent 22A.

[0072] In the next step 102, the artificial intelligence system 12A determines whether or not to hand over the conversation with the user to the specialized agent 22B, and if the determination is affirmative, the process proceeds to step 104, and if the determination is negative, the process proceeds to step 108. This handover is performed, for example, when the conversation with the user becomes specialized, or when the user wishes to have a conversation with the specialized agent 22B.

[0073] In step 104, the effect control unit 144A performs a takeover effect to make the user aware that the specialized agent 22B will take over the conversation. As a result, the takeover effect is displayed on the touch panel display 20 of the user terminal 14.

[0074] In the next step 106, a conversation takes place between the user and the specialized agent 22B. Note that the presentation control unit 144BA may perform a handover presentation before the conversation between the user and the specialized agent 22B starts.

[0075] In step 108, the conversation unit 140A determines whether the conversation between the user and the main agent 22A has ended. If the determination is affirmative, the conversation process ends, and if the determination is negative, the process returns to step 100.

[0076] FIG. 6 is a flowchart showing the flow of conversation processing when a conversation is handed over from the specialized agent 22B to another virtual agent 22 in this embodiment.

[0077] In step 200, a conversation takes place between the user and the specialized agent 22B.

[0078] In the next step 202, the artificial intelligence system 12B determines whether or not to hand over the conversation with the user to another virtual agent 22. If the determination is affirmative, the process proceeds to step 204, and if the determination is negative, the process proceeds to step 210. This handover is performed, for example, when it is preferable for the conversation with the user to be taken over by another expert agent 22B, or when the user wishes to have a conversation with another virtual agent 22.

[0079] In the next step 204, the performance control unit 144B determines whether the intimacy of the other virtual agent 22 to be the takeover target is higher than the intimacy of the virtual agent 22 currently conversing with the user, and if the determination is affirmative, the process proceeds to step 208, whereas if the determination is negative, the process proceeds to step 206. Note that the virtual agents 22 with high intimacy include specific virtual agents 22 that have been set in advance to have high intimacy, such as the main agent 22A.

[0080] In step 206, the presentation control unit 144B performs a takeover presentation to make the user aware that another virtual agent 22 will take over the conversation.

[0081] In step 208, a conversation takes place between the user and the other virtual agent 22. That is, when the process moves from step 204 to step 208, no handover effect is performed. Also, when the process moves from step 206 to step 208, the effect control unit 144 corresponding to the other virtual agent 22 may perform a handover effect before the conversation between the user and the other virtual agent 22 starts.

[0082] In step 210, the conversation unit 140B determines whether the conversation between the user and the specialized agent 22B has ended. If the determination is affirmative, the conversation process ends, and if the determination is negative, the process returns to step 200.

[0083] Although the present invention has been described above using the above-mentioned embodiment, the technical scope of the present invention is not limited to the scope described in the above-mentioned embodiment. Various changes or improvements can be made to the above-mentioned embodiment without departing from the gist of the invention, and such changes or improvements are also included in the technical scope of the present invention.

[0084] The present invention may be applied to a system consisting of multiple devices or to a single device. Furthermore, the present invention may also be applied when an information processing program that realizes the functions of the present embodiment is supplied to a system or device and executed by a built-in processor. The technical scope of the present invention also includes a program installed on a computer to realize the functions of the present invention, a medium storing the program, a server from which the program is downloaded, and a processor that executes the program. In particular, the technical scope of the present invention includes at least a non-transitory computer-readable medium storing a program that causes a computer to execute the processing steps included in the above-described present embodiment.

[0085] For example, in the above embodiment, the conversation unit 140 and the performance control unit 144A are described as being provided in the server 16, but the present invention is not limited to this. For example, at least one of the conversation unit 140 and the performance control unit 144A may be provided in the user terminal 14. Also, the conversation unit 140 and the performance control unit 144A may each be provided in a different server 16. Also, the server 16, the terminal device 14, or the server 16 may have the functionality of the artificial intelligence system 12 (LLM).

[0086] Furthermore, in the above embodiment, a configuration in which the user has one main agent 22A has been described, but the present invention is not limited to this. The user may have multiple main agents 22A. In this configuration, a handover effect may also be performed when a conversation is handed over from one main agent 22A to another main agent 22A.

[0087] In the above embodiment, a form has been described in which a handover effect is not performed when a conversation is handed over to the main agent 22A or to a virtual agent 22 with a higher intimacy level, but the present invention is not limited to this. For example, a handover effect may be performed whenever a conversation is handed over from one virtual agent 22 to another virtual agent 22.

[0088] In the above embodiment, the main agent 22A and the specialist agent 22B are operated by different companies, but the present invention is not limited to this. The main agent 22A and the specialist agent 22B may be operated by the same company.

[0089] In the above embodiment, the user terminal 14 has a voice recognition function, detects voice information uttered by the user, and accepts the detected voice information as input information. However, the present invention is not limited to this. For example, the user terminal 14 may accept text information, image information, voice information, etc. input by the user as input information.

[0090] The following additional notes are provided regarding the above-described embodiment.

[0091] [Appendix 1] The information processing system of Appendix 1 comprises a conversation unit that instructs a task processing device, which processes a task using artificial intelligence in accordance with a task processing instruction, to generate conversation content for the virtual agent with a user, and acquires the conversation content generated by the task processing device and presents it to the user; and a performance control unit that, when a dialogue is being conducted by one of a plurality of virtual agents and the conversation is being handed over from one virtual agent to another virtual agent, performs a performance to make the user aware that the conversation has been handed over.

[0092] According to this configuration, when a conversation with a user is handed over from one virtual agent to another virtual agent, a special effect is produced to make the user aware of the handover, thereby enabling the conversation with the user to be handed over from one virtual agent to another virtual agent without causing discomfort to the user.

[0093] [Appendix 2] In the information processing system of Appendix 1, the one virtual agent may be a virtual agent that conducts general conversations with the user, and the other virtual agent may be a virtual agent that conducts more specialized conversations than the one virtual agent.

[0094] According to this configuration, a special effect is given when the conversation is handed over to a specialized agent, so the user does not feel uncomfortable even if the specialized agent refers to the content of the conversation up to that point.

[0095] [Appendix 3] In the information processing system of Appendix 2, the performance control unit may perform the performance when a handover occurs from one virtual agent to another virtual agent, and may not perform the performance when a handover occurs from the other virtual agent to the one virtual agent.

[0096] According to this configuration, it is unlikely that the user will feel uncomfortable with the handover from the specialized agent to the main agent, so there is no need to perform unnecessary effects.

[0097] [Appendix 4] In any of the information processing systems of Supplementary Note 1 to Supplementary Note 3, the degree of intimacy with the user may be specified for each virtual agent, and the performance may not be performed when a handover occurs from one virtual agent with a low degree of intimacy to another virtual agent with a high degree of intimacy.

[0098] According to this configuration, it is unlikely that the user will feel uncomfortable when a virtual agent with a low level of intimacy is replaced by a virtual agent with a high level of intimacy, and therefore unnecessary effects are not required. For example, the level of intimacy increases as the duration of conversation with the user increases.

[0099] [Appendix 5] In any of the information processing systems of Supplementary Note 1 to Supplementary Note 4, information regarding the content of a conversation between the one virtual agent and the user may be stored in a database, and the conversation unit may instruct the task processing device to generate the conversation content by referring to the information regarding the conversation between the one virtual agent and the user stored in the database.

[0100] According to this configuration, even when a conversation is handed over from one virtual agent to another virtual agent, the content of the conversation with the other virtual agent remains smooth.

[0101] [Appendix 6] In the information processing system of any one of Supplementary Note 1 to Supplementary Note 5, the effect may be at least one of an image display on a display of a terminal device operated by a user and an audio output.

[0102] With this configuration, the user can easily recognize that the conversation has been taken over by another virtual agent.

[0103] [Appendix 7] The information processing device of Supplementary Note 7 comprises: a conversation unit that instructs a task processing device that processes a task using artificial intelligence in accordance with a task processing instruction to generate a conversation content for a virtual agent to have with a user, acquires the conversation content generated by the task processing device, and presents the conversation content to the user; The device is provided with a performance control section that performs a performance to make a user aware that a conversation has been taken over when a conversation is being conducted by one of the virtual agents among the plurality of virtual agents and the conversation is taken over from one virtual agent to another virtual agent. [Explanation of symbols]

[0104] 10 Virtual Agent Conversation System 12 Artificial Intelligence System (Task Processing Device) 14 User terminal (terminal device, information processing device) 16 Server (information processing device) 22 Virtual Agent 22A Main Agent 22B Specialist Agent 140A Conversation Section 144A Production Control Unit

Claims

1. a conversation unit that instructs a task processing device that processes a task using artificial intelligence in response to a task processing instruction to generate a conversation content for a virtual agent to have with a user, acquires the conversation content generated by the task processing device, and presents it to the user; a performance control unit that performs a performance to make a user aware that a conversation has been taken over when a conversation is being conducted using one of the virtual agents among the plurality of virtual agents and the conversation is taken over from one virtual agent to another virtual agent; Equipped with Identifying the degree of intimacy with the user for each of the virtual agents; The effect is not performed when a handover is performed from the one virtual agent with a low intimacy level to the other virtual agent with a high intimacy level. Information processing system.

2. the one virtual agent is a virtual agent that has a general conversation with the user, The other virtual agent is a virtual agent that has a more specialized conversation than the one virtual agent. The information processing system according to claim 1 .

3. The information processing system of claim 2, wherein the performance control unit performs the performance when a handover occurs from one virtual agent to another virtual agent, and does not perform the performance when a handover occurs from the other virtual agent to the one virtual agent.

4. information about the content of a conversation between the one virtual agent and the user is stored in a database; 3. The information processing system according to claim 1, wherein the conversation unit instructs the task processing device to generate the conversation content by referring to information about the conversation between the one virtual agent and the user stored in the database.

5. 3. The information processing system according to claim 1, wherein the effect is at least one of an image display on a display of a terminal device operated by a user and an audio output.

6. a conversation unit that instructs a task processing device that processes a task using artificial intelligence in response to a task processing instruction to generate a conversation content for a virtual agent to have with a user, acquires the conversation content generated by the task processing device, and presents it to the user; a performance control unit that performs a performance to make a user aware that a conversation has been taken over when a conversation is being conducted using one of the virtual agents among the plurality of virtual agents and the conversation is taken over from one virtual agent to another virtual agent; Equipped with Identifying the degree of intimacy with the user for each of the virtual agents; The effect is not performed when a handover is performed from the one virtual agent with a low intimacy level to the other virtual agent with a high intimacy level. Information processing device.

Images