Information processing system and information processing device

Abstract

A virtual agent conversation system (10) uses one virtual agent among a plurality of virtual agents (22) to interact with a user. The virtual agent conversation system (10) comprises: a conversation unit (140B) that instructs an artificial intelligence system (12) to generate conversation content in a virtual agent (22) for a user, acquires the conversation content generated by the artificial intelligence system (12), and presents the conversation content to the user; and a storage control unit (142A) that causes a conversation DB to store information relating to the conversation content presented to the user for each virtual agent (22). The conversation unit (140B) instructs the artificial intelligence system (12) to generate the conversation content such that the conversation content is generated with reference to information relating to a conversation between the user and another virtual agent (22), said information being stored in the conversation DB.

Description

Information Processing System and Information Processing Apparatus

[0001] The present disclosure relates to an information processing system and an information processing apparatus.

[0002] In recent years, virtual agent systems have been developed that use a trained conversation model obtained by machine learning to conduct natural language conversations with users.

[0003] In such a virtual agent system, a terminal such as a smartphone used by a user displays an image of a character corresponding to the virtual agent, and accepts inputs such as questions from the user. The virtual agent is, for example, a two-dimensional or three-dimensional animation character or the like set as the user's conversation partner. In some cases, the user may use a plurality of virtual agents with different specialties and other characteristics separately to have conversations.

[0004] Here, Patent Document 1 describes that it is determined whether or not an input sentence from a user relates to another character different from the character set as the user's conversation partner, and when it is determined that the input sentence relates to the other character, a rule-based response sentence is created or a model response sentence is corrected based on the conversation history between the other character and the user, or the setting data of the other character.

[0005] International Publication No. 2022 / 118869

[0006] Although Patent Document 1 describes creating a rule-based response sentence based on the conversation history between another character and the user, or the setting data of the other character, it is not clear how the conversation history is stored.

[0007] Accordingly, an objective of the present disclosure is to provide an information processing system and an information processing apparatus that generate conversations with a user by utilizing past conversations between the user and other agents.

[0008] The information processing system disclosed herein is an information processing system that interacts with a user through one of a plurality of virtual agents, and comprises a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user, and a storage control unit that stores information regarding the conversation content between each virtual agent and the user in a database, wherein the conversation unit instructs the task processing unit to generate the conversation content by referring to information regarding conversations between other virtual agents and the user stored in the database.

[0009] The information processing system disclosed herein is an information processing system that interacts with a user through one of a plurality of virtual agents, and comprises: a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user; and a storage control unit that stores information regarding the conversation content between the virtual agent and the user in a database, and permits other task processing units that generate conversation content between other virtual agents and the user to refer to the information regarding the conversation between the virtual agent and the user stored in the database.

[0010] The information processing device disclosed herein is an information processing device that interacts with a user through one of a plurality of virtual agents, and comprises a conversation unit that instructs a task processing device that processes tasks using artificial intelligence in response to task processing instructions to generate conversation content of the virtual agent to the user, and acquires the conversation content generated by the task processing device and presents it to the user, and a storage control unit that stores information regarding the conversation content between the virtual agent and the user in a database, and permits other task processing devices that generate conversation content between other virtual agents and the user to refer to the information regarding the conversation between the virtual agent and the user stored in the database.

[0011] According to this disclosure, past conversations between other agents and the user are utilized to generate conversations with the user.

[0012] Figure 1 is a diagram of the virtual agent conversation system of this embodiment. Figure 2 is a diagram showing the hardware configuration of the user terminal of this embodiment. Figure 3 is a diagram showing the hardware configuration of the server of this embodiment. Figure 4 is a functional block diagram of the virtual agent conversation system of this embodiment. Figure 5 is a schematic diagram of the conversation database of this embodiment. Figure 6 is a flowchart showing the flow of the conversation database registration process of this embodiment. Figure 7 is a flowchart showing the flow of conversation processing by the specialist agent of this embodiment.

[0013] Embodiments of this disclosure will be described below with reference to the drawings. The embodiments described below are merely examples of how this disclosure may be implemented, and this disclosure is not limited to the specific configurations described below. In implementing this disclosure, specific configurations may be adopted as appropriate depending on the embodiment.

[0014] Figure 1 shows an example of the configuration of the virtual agent conversation system 10 of this embodiment. As shown in Figure 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 between a virtual agent (AI agent) and 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. Multiple distribution servers 16 and artificial intelligence systems 12 may be provided, as will be described in detail later.

[0016] The virtual agent conversation system 10 may include other servers, terminals, and other equipment. The user terminal 14 and the distribution server 16 communicate with each other via a network NW. The distribution server 16 and the artificial intelligence system 12 also communicate with each other via a network NW. The network NW consists of the Internet, LAN (Local Area Network), various mobile communication systems such as wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the Internet via predetermined access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, Bluetooth®, etc. When connecting via a wired connection, the network also includes connections made directly by USB (Universal Serial Bus) cables, etc.

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

[0018] The user terminal 14 can be implemented as, for example, a smartphone, tablet, notebook PC (Personal Computer), desktop PC, mobile phone, PDA (Personal Digital Assistant), etc. In this embodiment, the user terminal 14 is a smartphone with touch panel functionality.

[0019] In this embodiment, as an example, the user terminal 14 has the function of a voice response system (speech recognition), detects voice information (hereinafter also referred to as "utterances") spoken by the user, and accepts the detected utterances as input information. For example, the user terminal 14 is a terminal device that processes the user's utterances. When the user terminal 14 detects an utterance by the user, it sends the 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's user terminal 14 and distributes content related to the virtual agent 22 that interacts with the user in the virtual agent application launched on the user terminal 14. The distribution server 16 uses the artificial intelligence system 12 to generate the conversation content of the virtual agent 22 to the user and distributes the generated conversation content to the user terminal 14. The distribution server 16 is composed of at least a computer having communication and program execution functions. The distribution server 16 may be implemented with one information processing device or with multiple information processing devices.

[0021] Furthermore, the distribution server 16 may have a speech recognition function. Also, the distribution server 16 may be able to obtain information from a speech recognition server that provides speech recognition services. In this case, the virtual agent conversation system 10 may include a speech recognition server. In this embodiment, it is assumed that the user terminal 14, distribution server 16, and speech recognition server recognize user utterances and identify the user who made the utterances using various conventional technologies as appropriate, so a detailed explanation is omitted.

[0022] The artificial intelligence system 12 is an information processing device that internally incorporates an LLM (Large Language Model) and is capable of outputting output sentences (responses to prompts) in response to input sentences called prompts. For example, the artificial intelligence system 12 may include ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, BERT, etc. The artificial intelligence system 12 may be operated by the business operator providing the virtual agent application of this embodiment, or it may be used via an API (Application Programming Interface) provided by an external artificial intelligence system 12 operated by another business operator.

[0023] The artificial intelligence system 12 is equipped with a dialogue (chat) function. The distribution server 16 can provide the artificial intelligence system 12 with arbitrary inquiries or commands in text form, and obtain answers to those inquiries or commands. Thus, 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 arbitrary inquiries or commands.

[0024] In this embodiment, the distribution server 16 sends a prompt to the artificial intelligence system 12 causing it to generate the content of a conversation between the virtual agent and the user, or the content of a conversation between the virtual agent and the user, thereby obtaining the conversation content as a response.

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

[0026] Figure 2 shows an example of the hardware configuration of the user terminal 14 in this embodiment. The user terminal 14 is a computer (information processing device) such as a smartphone, tablet, notebook PC (Personal Computer), desktop PC, mobile phone, or 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 on power supplied from a battery (not shown). In the following description, the term "device" can be read as a circuit, device, unit, etc. The hardware configuration of the user terminal 14 may include one or more of the devices shown in Figure 2, or some of the devices may be omitted. Alternatively, multiple devices with different enclosures may be connected via communication to constitute the user terminal 14.

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

[0029] The processor 100 controls the entire computer, for example, by running the operating system. The processor 100 may consist of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. Also, for example, a baseband signal processing unit or a call processing unit may be implemented by the processor 100.

[0030] The processor 100 reads programs (program code), 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 accordingly. The program used is one that causes the computer to execute at least a part of the operations described later. Functional blocks of the user terminal 14 may be stored in the memory 102 and implemented by control programs that run on the processor 100. Various processes may be executed by one processor 100, or they may be executed simultaneously or sequentially by two or more processors 100. The processor 100 may be implemented by one or more chips. The program may also be transmitted to the user terminal 14 via a telecommunications line.

[0031] Memory 102 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 102 may also be called a register, cache, main memory, etc. Memory 102 can store executable programs (program code), software modules, etc., for carrying out the method of this embodiment.

[0032] The storage 104 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., Compact Disc, Digital Multipurpose Disc, Blu-ray® Disc), a smart card, flash memory (e.g., a card, stick, key drive), a floppy® disk, a magnetic strip, etc. The storage 104 may also be called 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, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the transmitting and receiving antennas, amplifier section, transmitting and receiving section, transmission path interface, etc., may be implemented by the communication device 106. The transmitting and receiving section may be implemented in a physically or logically separated manner, with a transmitting section and a receiving section.

[0034] The input device 108 is an input device that accepts input from the outside (for example, keys, microphones, cameras, switches, buttons, position information sensors, motion sensors, and various other sensors). The output device 110 is an output device that outputs to the outside (for example, displays, speakers, LED lamps, etc.). In this embodiment, the user terminal 14 includes a touch panel display 20 in which the input device 108 and the output device 110 are integrated.

[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 for each device.

[0036] The user terminal 14 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by this hardware. For example, the processor 100 may be implemented using at least one of these hardware components.

[0037] The distribution server 16 is an information processing device, and as will be described in detail later, it generates responses to questions and other information entered by the user via the user terminal 14 using generative AI (Artificial Intelligence) built with Large Language Models (LLM).

[0038] Figure 3 shows an example of the hardware configuration of the distribution server 16 in this embodiment. The distribution server 16 is an information processing device implemented by, for example, a computer, server device, cloud system, etc. Physically, the distribution server 16 is configured as a computer device including a processor 120, memory 122, storage 124, communication device 126, input device 128, output device 130, and a bus connecting these. The processor 120, memory 122, storage 124, input device 128, and output device 130 are the same hardware as the processor 100, memory 102, storage 104, input device 108, and output device 110 of the user terminal 14, so their description is omitted.

[0039] The communication device 126 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 126 enables communication with the user terminal 14.

[0040] The hardware configuration of the artificial intelligence system 12 in this embodiment is the same as that of the distribution server 16, so its description will be omitted.

[0041] In the virtual agent conversation system 10, as described above, the user converses with the virtual agent 22 using the virtual agent application installed on the user terminal 14.

[0042] The virtual agent application of the present embodiment enables conversations between a user and a plurality of virtual agents 22 of different types. For this reason, a user uses the virtual agent application to select one virtual agent 22 from the plurality of virtual agents 22 of different types and have a conversation therewith. The virtual agent application displays a different 2D or 3D character on the touch panel display 20 of the user terminal 14 according to the virtual agent 22 selected by the user.

[0043] Examples of the virtual agents 22 include a main agent and sub-agents. The main agent is a virtual agent 22 that gives general-purpose responses to the user although its level of expertise is low. For example, the user has daily conversations with the main agent. The sub-agents are virtual agents 22 that have more specialized conversations than the main agent, and are referred to as specialized agents in the following description. The specialized agents are classified by category such as law, home appliances, cooking, and childcare. The user asks specialized questions and the like to the specialized agents.

[0044] In the virtual agent conversation system 10 of the present embodiment, as an example, different artificial intelligence systems 12 (LLM) are constructed for each of the main agent and the specialized agents. In particular, the LLM of the artificial intelligence system 12 corresponding to a specialized agent has undergone learning specialized in the expert content of that specialized agent. Further, in the virtual agent conversation system 10 of the present embodiment, the main agent and each specialized agent are processed by different distribution servers 16, thereby executing responses to the user via the user terminal 14.

[0045] Further, the operators that operate the main agent and the specialized agents may be different. In such a form, the distribution server 16 that operates the main agent and the distribution servers 16 that operate the specialized agents are operated by different operators.

[0046] The virtual agent conversation system 10 of the present embodiment allows a user to have a conversation with a specialized agent in the middle of a conversation with a main agent. For example, this applies to cases where the user asks a question to the main agent, and the question is specialized such that it is appropriate for the specialized agent and the user to have a conversation.

[0047] In this way, when the conversation is switched from the main agent to the specialized agent, the user may need to repeat the same conversation that they had with the main agent to the specialized agent.

[0048] Accordingly, the virtual agent conversation system 10 of the present embodiment generates conversation content by referring to information related to conversations between the user and other virtual agents 22 stored in a database. The other virtual agent 22 referred to here is, as an example, the main agent. That is, the virtual agent conversation system 10 of the present embodiment stores the content of the conversation between the main agent and the user in a database, and generates the content of the conversation between the user and the specialized agent by referring to the conversation content stored in the database.

[0049] Figure 4 is a functional block diagram of the virtual agent conversation system 10. In the example of Figure 4, the business operator operating the main agent 22A and the business operator operating the specialized agent 22B are different business operators. In the following description, the business operator operating the main agent 22A is referred to as business operator A, and the business operator operating the specialized agent 22B is referred to as business operator B. In Figure 4, for the artificial intelligence system 12, distribution server 16 and their functions corresponding to the main agent 22A, "A" is appended to the end of the reference numerals, and for the artificial intelligence system 12, distribution server 16 and their functions corresponding to the specialized agent 22B, "B" is appended to the end of the reference numerals to distinguish each for explanation.

[0050] The artificial intelligence system 12A may be operated by business operator A, or may be operated by a business operator different from business operator A or business operator B. The LLM of the artificial intelligence system 12A is constructed as a highly versatile trained model that is not specialized.

[0051] The distribution server 16A is a distribution server 16 operated by business operator A, and comprises a conversation unit 140A, a memory control unit 142A, and storage 124A. The conversation unit 140A and the memory control unit 142A are functions provided by the processor 120 of the distribution server 16A.

[0052] The conversation unit 140A instructs the artificial intelligence system 12A to generate conversation content for the main agent 22A to the user, and retrieves the conversation content generated by the artificial intelligence system 12A and presents it to the user. The above instruction from the conversation unit 140A is a prompt. Prompts are generated based on questions from the user entered via the user terminal 14. The conversation content is presented to the user as spoken by the main agent 22A displayed on the touch panel display 20 of the user terminal 14.

[0053] The memory control unit 142A stores information regarding the content of conversations between each virtual agent 22 and the user in a database (hereinafter referred to as the "conversation DB"). For this purpose, the artificial intelligence system 12A transmits the content of conversations between the main agent 22A and the user to the memory control unit 142A, and stores the conversation content in the conversation DB. The memory control unit 142A also adds a confidentiality level (hereinafter referred to as the "security level") indicating whether the conversation content can be accessed before storing the information about the conversation content in the conversation DB. Details regarding the security level will be described later. The conversation DB is stored in the storage 124A.

[0054] The LLM of the artificial intelligence system 12B, which corresponds to the specialist agent 22B, is constructed as a specialized trained model corresponding to, for example, law, home appliances, childcare, or cooking. The artificial intelligence system 12B may be operated by business operator B, or by a business operator different from business operator A or business operator B. In this embodiment, the artificial intelligence system 12B transmits the content of the conversation between the specialist agent 22B and the user to the memory control unit 142A, and stores the conversation content in the conversation DB.

[0055] The distribution server 16B is a distribution server 16 operated by business operator B, and is equipped with 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.

[0056] 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 expert agent 22B to the user, and retrieves the conversation content generated by the artificial intelligence system 12B and presents it to the user.

[0057] In this embodiment, the conversation unit 140B can instruct the artificial intelligence system 12B to generate conversation content by referring to information about conversations between the user and another virtual agent 22, which is the main agent 22A, stored in the conversation DB.

[0058] On the other hand, the distribution server 16A allows other virtual agents 22 to access the conversation content stored in the conversation DB. In this embodiment, access permission is granted, as an example, to the artificial intelligence system 12B that generates the conversation content between other virtual agents 22 and the user.

[0059] In other words, artificial intelligence system 12B, which has permission to access the conversation database, can refer to the conversation database to generate responses to user questions. Furthermore, artificial intelligence system 12A, which corresponds to main agent 22A, can refer to the conversation database to generate conversation content for main agent 22A to the user without requiring permission to access the conversation database.

[0060] Figure 5 is a schematic diagram of the conversation database in this embodiment. The conversation database includes, as an example, fields for agent name, conversation content, conversation attributes, registration date and time, and security level.

[0061] The agent name is the name of the virtual agent 22 that conversed with the user.

[0062] The conversation content is a conversation between virtual agent 22 and the user. The conversation content is summarized as an example and stored in the conversation database.

[0063] Conversation attributes are attributes of the content of conversations between the virtual agent 22 and the user, such as personal, legal, and food preferences. Conversation content with the "personal" attribute attached relates to the user's personal information that requires careful handling, such as the user's name, address, telephone number, age, family structure, occupation, and annual income. Conversation content with the "food preferences" attribute attached is about the user's favorite and least favorite foods. Conversation content with the "home appliances" attribute attached is about consultations regarding the purchase of home appliances. Conversation content with the "real estate" attribute attached is about consultations regarding the rental or purchase of real estate. Conversation content with the "legal" attribute attached is about legal consultations.

[0064] The registration date and time is the date and time the conversation content was registered.

[0065] Security levels are assigned based on the content of the conversation. For example, security levels are divided into categories "S," "A," and "B" from highest to lowest, and a security level category is assigned according to the content of the conversation. Security levels are also assigned based on the attributes of the conversation. For example, if the conversation attribute is "personal," security level "S" is assigned; if the conversation attribute is "law," security level "A" is assigned; and if the conversation attribute is "food preferences" or "home appliances," security level "B" is assigned.

[0066] Each specialist agent 22B has a defined security level for the conversations they can access. For example, a legal specialist agent 22B can access all conversations regardless of security level, up to security level "S". A real estate specialist agent 22B can access conversations at security levels "A", "A", and "B". A household and appliance specialist agent 22B can access conversations related to security level "B".

[0067] The memory control unit 142A of this embodiment is built with an LLM (Language Learning Model) that determines conversation attributes (security level classifications) from summarized conversation content. This LLM is a trained model that has been machine-learned to associate, for example, the words and other elements included in the conversation content with conversation attributes (security level classifications). In this way, the security level of this embodiment is determined using artificial intelligence. This makes it possible to easily assign a security level to information related to conversation content.

[0068] Furthermore, security levels may be assigned according to predetermined rules, not limited to this. For example, rules may be predetermined to determine conversation attributes (security level classifications) based on the wording contained in the conversation.

[0069] Furthermore, security levels may be subdivided beyond just "S," "A," and "B." Also, conversation content may not have conversation attributes attached, only a security level may be assigned. In addition, if a user makes a request to main agent 22A during a conversation between the user and main agent 22A, such as "Please keep this conversation secret," the security level of that conversation content may be set to "S" regardless of the conversation attributes. Furthermore, a security level "SS" may be assigned to the conversation content, which prevents any specialist agent 22B from viewing it.

[0070] Furthermore, if a user is posting information on social media, the security level of the posted information may be set to a lower level. The storage control unit 142A obtains the user's social media account in advance, and then determines which conversation content should have a lower security level.

[0071] Figure 6 is a flowchart showing the flow of the conversation database registration process executed by the memory control unit 142A in this embodiment. The conversation database registration process is started when the user and the virtual agent 22 start a conversation.

[0072] First, in step 100, the conversation content is obtained from the artificial intelligence system 12A or the artificial intelligence system 12B. The memory control unit 142A generates a summary of the obtained conversation content.

[0073] In the next step, 102, we determine the conversation attributes from the summarized conversation content.

[0074] In the next step, 104, a security level is added to the conversation content based on the conversation attributes.

[0075] In the next step, 106, the conversation content is registered in the conversation database, with the agent name, conversation attributes, and security level added.

[0076] In the next step 108, it is determined whether the conversation between the user and the virtual agent 22 has ended. If the result is positive, the conversation DB registration process is terminated; otherwise, the process returns to step 100.

[0077] Furthermore, the security level may be assigned not at the same time as registering the conversation content in the conversation database, but after the conversation content has been registered in the conversation database, by determining the conversation attributes of the conversation content and assigning a security level.

[0078] Figure 7 is a flowchart showing the flow of conversation processing by the specialist agent 22B in this embodiment. When a user converses with the specialist agent 22B, for example, when the conversation between the user and the main agent 22A becomes a specialized conversation and the main agent 22A takes over the conversation to the specialist agent 22B, or when the user calls the specialist agent 22B to converse without the main agent 22A taking over the conversation to the specialist agent 22B.

[0079] First, in step 200, a conversation between the user and the specialist agent 22B is initiated. The conversation may begin with a question from the user to the specialist agent 22B, or with a question from the specialist agent 22B to the user.

[0080] In the next step 202, the conversation unit 140B determines whether the specialist agent 22B can access the conversation database. If the determination is positive, the process proceeds to step 204; otherwise, it proceeds to step 206.

[0081] Even if the specialist agent 22B is initially denied access to the conversation database, if the user grants permission to access the conversation database at the start or during the conversation, the specialist agent 22B will be able to access the conversation database. In this case, the user may specify the attributes or security level of the conversation content that should be allowed to be accessed.

[0082] Thus, in the virtual agent conversation system 10 of this embodiment, when the user grants permission while the specialist agent 22B and the user are in conversation, the specialist agent 22B refers to the information regarding the conversation between the main agent 22A and the user stored in the conversation DB.

[0083] Furthermore, even if the specialist agent 22B is allowed to access the conversation database, if the user disables access to the conversation database at the start or during the conversation, the specialist agent 22B will be unable to access the conversation database.

[0084] Furthermore, permission to access the conversation database may be requested from the user by the specialist agent 22B. When the user is requested to grant permission to access the database by the specialist agent 22B, the user can grant or deny permission by voice or by a predetermined operation. In addition, the decision on whether or not to grant permission to access the database from the specialist agent 22B to the user may be predetermined by settings.

[0085] In step 204, the artificial intelligence system 12B (specialized agent 22B) refers to conversation content with a security level it can access from the conversation database and converses with the user, then proceeds to step 208.

[0086] In step 206, the artificial intelligence system 12B (specialized agent 22B) converses with the user without referring to the conversation database, and then proceeds to step 208.

[0087] In step 208, the conversation unit 140B determines whether the conversation between the user and the specialist agent 22B has ended. If the determination is positive, the conversation process ends; otherwise, the process returns to step 202 and the conversation between the user and the specialist agent 22B continues.

[0088] Although this disclosure has been described above using the embodiments described above, the technical scope of this disclosure is not limited to the scope described in the embodiments above. Various modifications or improvements can be made to the embodiments without departing from the gist of the disclosure, and such modified or improved forms are also included in the technical scope of this disclosure.

[0089] This disclosure may be applied to a system consisting of multiple devices or to a single device. Furthermore, this disclosure is also applicable when an information processing program that implements the functions of this embodiment is supplied to a system or device and executed by an internal processor. The technical scope of this disclosure includes programs installed on a computer to implement the functions of this disclosure on a computer, or the medium on which such programs are stored, a server that downloads such programs, and a processor that executes such programs. In particular, at least a non-transitory computer-readable medium containing a program that causes a computer to execute the processing steps included in this embodiment described above is included in the technical scope of this disclosure.

[0090] For example, in the above embodiment, the conversation unit 140 and the memory control unit 142A were described as being provided on a server 16, but this disclosure is not limited thereto. For example, at least one of the conversation unit 140 and the memory control unit 142A may be provided on a user terminal 14. Alternatively, the conversation unit 140 and the memory control unit 142A may be provided on different servers 16. Furthermore, the server 16 or the terminal device 14 or the server 16 may have the functions of an artificial intelligence system 12 (LLM).

[0091] Furthermore, although the above embodiment describes a configuration in which the main agent 22A and the specialized agent 22B are operated by different operators, this disclosure is not limited thereto. The main agent 22A and the specialized agent 22B may be operated by the same operator.

[0092] Furthermore, although the above embodiment describes a configuration in which the user terminal 14 has a speech recognition function, detects speech information uttered by the user, and accepts the detected speech as input information, this disclosure is not limited to this. For example, the user terminal 14 may accept text information, image information, and speech information entered by the user as input information.

[0093] In the above embodiment, the content of the conversation and the security level are determined based on conversation attributes, but other attributes may be used to determine the security level. For example, the content of the conversation and the security level may be determined based on "personality level" in addition to "conversation attributes". That is, the content of the conversation between the user and the virtual agent 22 is stored in the conversation DB with two parameters, "conversation attributes" and "personality level," attached to it.

[0094] Personalization level is a parameter that indicates whether the conversation content relates to the user's personal information. A high personalization level indicates that the conversation content is personal to the user, while a low personalization level indicates that it is not. Therefore, personalization level is typically expressed as two degrees: high and low. In addition to conversation attributes (security level), the personalization level is also considered when determining whether or not to allow access to the conversation database.

[0095] Furthermore, a virtual agent 22 that can access highly personalized conversations can also be said to be a virtual agent 22 with a high degree of intimacy with the user. In other words, personalization is a parameter that represents intimacy with the user, while conversation attributes are parameters that indicate the expertise of the conversation content. Thus, the virtual agent conversation system 10 manages the expertise and intimacy of conversation content with separate parameters by setting personalization not only for conversation attributes but also for each conversation content, enabling more appropriate allocation of the virtual agent 22.

[0096] The following provides a detailed explanation of the case where personalization is also used. Note that the conversations A through C shown in the following example are conversations between the main agent 22A and the user.

[0097] <Example 1> Conversation content A: "My friend has been a victim of a phone scam and is in trouble." This is a scenario where the conversation is handed over to a legal agent.

[0098] The conversation attribute (expertise assessment) of conversation content A is determined to be "law," and the degree of personalization (personality assessment) is determined to be "low" because it concerns the user's friend and not the user personally. Therefore, the legal agent can access conversation content A without the user's permission because the conversation attribute is "law" (security level S) and the degree of personalization is "low." Then, the main agent 22A responds to the user, for example, by saying, "Okay, I'll pass on what I've heard so far," and allows the legal agent, which is the expert agent 22B, to access it without obtaining the user's permission.

[0099] <Example 2> Conversation content B: When the person says, "I've had an affair and I'm in trouble," and then hands the conversation over to a legal agent.

[0100] The conversation attribute of conversation content B is "law," and its personalization level is "high" because it concerns the user personally. Therefore, the legal agent cannot access conversation content B without the user's permission because, although the conversation attribute is "law" (security level S), its personalization level is "high." In order for the legal agent to access conversation content B, the user's permission is required. To obtain the user's permission, the main agent 22A engages in a conversation with the user, for example, by asking, "Is it okay if I tell the legal agent?"

[0101] <Example 3> Conversation content C: When the conversation is handed over to virtual agent 22, an IP character that has a high relationship (intimacy) with the user due to having conversed with the user for several years, although the topic is not highly specialized.

[0102] The conversation attribute for conversation content C is "birth / celebration," and its personalization level is considered "high" because it concerns the user personally. Therefore, since the conversation attribute is "celebration" and the IP character has a "high relationship with the user," the main agent 22A asks the user for permission regarding conversation content C, such as, "Is it okay if I tell the IP character?" If the user gives permission, the virtual agent 22 of the IP character refers to the conversation DB and says to the user, "I heard you had a baby! Congratulations!"

[0103] As shown in examples 1 to 3 above, even a highly specialized virtual agent 22 capable of accessing high-security conversation content may be unable to access highly personal conversation content. On the other hand, even a less specialized virtual agent 22 that cannot access high-security conversation content may be able to access highly personal conversation content if it has a high level of intimacy with the user.

[0104] The following additional notes are provided regarding the embodiments described above. [Addendum 1] The information processing system described in Addendum 1 is an information processing system that interacts with a user through one of a plurality of virtual agents, and comprises a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content of the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user, and a storage control unit that stores information regarding the conversation content of each virtual agent with the user in a database, wherein the conversation unit instructs the task processing unit to generate the conversation content by referring to information regarding conversations between other virtual agents and the user stored in the database.

[0105] In this configuration, the virtual agent refers to a database that stores the conversation content between other virtual agents and the user, and then engages in conversation with the user. Therefore, the current virtual agent can use the conversation content between other virtual agents and the user to engage in conversation with the user.

[0106] [Note 2] The information processing system in Note 2 is an information processing system that interacts with a user through one of a plurality of virtual agents, and comprises a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user, and a storage control unit that stores information regarding the conversation content between the virtual agent and the user in a database, and permits other virtual agents to refer to the information regarding the conversation between the virtual agent and the user stored in the database.

[0107] In this configuration, the virtual agent communicates with the user by referring to a database that stores the conversation content between other virtual agents and the user. Therefore, the current virtual agent can communicate with the user by utilizing the conversation content between other virtual agents and the user.

[0108] [Note 3] In the information processing system of Note 1 or Note 2, the memory control unit may store information relating to the conversation content in the database, adding a confidentiality level that indicates whether or not the virtual agent can access the conversation content.

[0109] In this configuration, virtual agents that can access the content of conversations between other agents and the user are determined according to the level of confidentiality, so that personal information of the user obtained through conversations between the user and other agents can be used appropriately.

[0110] [Note 4] In the information processing system described in Note 3, the secrecy level may be determined using artificial intelligence.

[0111] This configuration allows for easy assignment of confidentiality levels to information related to conversation content.

[0112] [Note 5] In the information processing system described in Note 3, the secrecy level may be assigned in accordance with predetermined rules.

[0113] This configuration allows for easy assignment of confidentiality levels to information related to conversation content.

[0114] [Note 6] In any of the information processing systems described in Notes 1 to 5, a user may converse with a virtual agent using an application that enables conversation with multiple virtual agents of different types.

[0115] This configuration allows users to easily converse with multiple different virtual agents.

[0116] [Note 7] If any of the information processing systems in Notes 1 to 6 is authorized by the user while another virtual agent is in conversation with the user, the other virtual agent may refer to the information stored in the database regarding the conversation between the virtual agent and the user.

[0117] In this configuration, a user can, while conversing with another virtual agent, grant other virtual agents permission to share the database as needed.

[0118] [Note 8] The information processing device described in Note 8 is an information processing device that interacts with a user through one of a plurality of virtual agents, and comprises a conversation unit that instructs a task processing device, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content of the virtual agent to the user, and acquires the conversation content generated by the task processing device and presents it to the user, and a storage control unit that stores information regarding the conversation content of each virtual agent with the user in a database, wherein the conversation unit instructs the task processing device to generate the conversation content by referring to information regarding conversations between other virtual agents and the user stored in the database.

[0119] 10 Virtual agent conversation system 12 Artificial intelligence system (task processing unit) 14 User terminal (information processing unit) 16 Server (information processing unit) 140B Conversation unit 142A Memory control unit

Claims

1. An information processing system that interacts with a user through one of a plurality of virtual agents, comprising: a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user; and a storage control unit that stores information regarding the conversation content between each virtual agent and the user in a database, wherein the conversation unit instructs the task processing unit to generate the conversation content by referring to information regarding conversations between other virtual agents and the user stored in the database.

2. An information processing system that interacts with a user through one of a plurality of virtual agents, comprising: a conversation unit that instructs a task processing unit, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing unit and presents it to the user; and a storage control unit that stores information relating to the conversation content between the virtual agent and the user in a database, and permits other virtual agents to refer to the information relating to the conversation between the virtual agent and the user stored in the database.

3. The information processing system according to claim 1 or 2, wherein the memory control unit stores information relating to the conversation content in the database, adding a confidentiality level indicating whether or not the virtual agent can access the conversation content.

4. The information processing system according to claim 3, wherein the secrecy level is determined using artificial intelligence.

5. The information processing system according to claim 3, wherein the secrecy level is assigned in accordance with predetermined rules.

6. The information processing system according to claim 1 or 2, wherein the user converses with a virtual agent using an application that enables conversation with a plurality of virtual agents of different types.

7. The information processing system according to claim 1 or 2, wherein, when permission is granted by the user while another virtual agent is in conversation with the user, the other virtual agent refers to information stored in the database regarding the conversation between the virtual agent and the user.

8. An information processing device that interacts with a user through one of a plurality of virtual agents, comprising: a conversation unit that instructs a task processing device, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for the virtual agent to the user, and acquires the conversation content generated by the task processing device and presents it to the user; and a storage control unit that stores information regarding the conversation content between each virtual agent and the user in a database, wherein the conversation unit instructs the task processing device to generate the conversation content by referring to information regarding conversations between other virtual agents and the user stored in the database.

Images