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

Abstract

An information processing system, method, and device are provided that create an opportunity to start a conversation with a virtual agent and increase a user's motivation to launch an application. [Solution] In an information processing system in which a user terminal, a distribution server, and an artificial intelligence system are connected to each other via a network, the distribution server includes a widget content output unit (222) that outputs content to be displayed in a widget content block selected from multiple contents in a content command memory unit, a detection unit (223) that detects an operation to start using a service via the content block in which the content is displayed, a prompt generation unit (224) that, when the operation to start using the service is detected, includes commands corresponding to the content in a prompt, a transmission unit (225) that transmits the prompt to a generative artificial intelligence model, a reception unit (226) that receives the generated conversation content, and a conversation content output unit (227) that outputs the received conversation content.

Description

[Technical Field]

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

[0002] Conventionally, there are applications that allow users to converse with AI agents (virtual agents) (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-028844 Summary of the Invention [Problem to be solved by the invention]

[0004] However, since users do not know what kind of conversation the AI ​​agent will have with them unless they start the application, they do not start the application unless they specifically want to talk to the AI ​​agent. As a result, users have little motivation to start the application.

[0005] In view of the above background, an object of the present invention is to provide an information processing system and the like that can create an opportunity to start a conversation with a virtual agent and increase the user's motivation to launch an application. [Means for solving the problem]

[0006] The information processing system of the present invention comprises: a widget content output unit that outputs content selected from a plurality of contents stored in a content command memory unit that stores a plurality of contents to be displayed in a content block included in a widget and connected to a service that generates conversation content of a virtual agent to a user using a generative artificial intelligence model; a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the operation to start using the service via the content block, includes an instruction corresponding to the content in a prompt to cause the generative artificial intelligence model to generate conversation content of the virtual agent; a transmission unit that transmits the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; and a conversation content output unit that outputs the conversation content received as the response by the receiving unit.

[0007] The information processing method of the present invention includes the steps of outputting content selected from a plurality of contents in a content command memory unit that stores a plurality of contents to be displayed in a content block included in a widget and connected to a service that generates conversation content of a virtual agent to a user using a generative artificial intelligence model; detecting an operation to start using the service via the content block on the widget in which the content is displayed; when the operation to start using the service via the content block is detected, including an instruction corresponding to the content in a prompt to cause the generative artificial intelligence model to generate conversation content of the virtual agent; sending the prompt to the generative artificial intelligence model; receiving the conversation content generated by the generative artificial intelligence model as a response to the prompt; and outputting the received conversation content as the response.

[0008] The information processing device of the present invention comprises: a widget content output unit that outputs content selected from a plurality of contents in a content command memory unit that stores a plurality of contents to be displayed in a content block included in a widget and connected to a service that generates conversation content of a virtual agent to a user using a generative artificial intelligence model; a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the operation to start using the service via the content block, includes an instruction corresponding to the content in a prompt to cause the generative artificial intelligence model to generate conversation content of the virtual agent; a transmission unit that transmits the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; and a conversation content output unit that outputs the conversation content as the response received by the receiving unit. [Effects of the Invention]

[0009] According to the present invention, it is possible to create an opportunity to start a conversation with a virtual agent and increase the motivation of the user to start an application. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of a system configuration of an information processing system S according to the present embodiment. [Figure 2] FIG. 2 is a diagram showing an example of information processing implemented by the information processing system S according to this embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the hardware configuration of the user terminal 10 according to the present embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the hardware configuration of distribution server 20 according to the present embodiment. [Figure 5]FIG. 5 is a diagram showing the functional configuration of the user terminal 10. As shown in FIG. [Figure 6] FIG. 6 is a diagram showing the functional configuration of the distribution server 20. As shown in FIG. [Figure 7] FIG. 7 is a diagram showing an example of content command information stored in content command storage unit 211 according to this embodiment. [Figure 8] FIG. 8 is a diagram showing an example of user information stored in user information storage unit 212 according to this embodiment. [Figure 9] FIG. 9 is a diagram showing an example of conversation history information stored in conversation history information storage unit 213 according to this embodiment. [Figure 10] FIG. 10 is a flowchart illustrating an example of a process executed by the user terminal 10 and the distribution server 20 of the information processing system S according to this embodiment to display widget content of the virtual agent app Appl in a content block CB1 included in a widget W displayed on the display unit 13 of the user terminal 10. [Figure 11] FIG. 11 is a flowchart showing an example of processing executed in the information processing system S according to this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] An information processing system according to the present embodiment will be described below with reference to the drawings. Note that the following description merely shows one example of a preferred embodiment, and is not intended to limit the invention described in the claims. In all figures describing the present embodiment, common components are designated by the same reference numerals, and repeated description will be omitted.

[0012] [Outline of Information Processing System S] Fig. 1 is a diagram showing an example of the system configuration of an information processing system S according to this embodiment. As shown in Fig. 1, the information processing system S according to this embodiment is an information processing system that uses an artificial intelligence system (generative artificial intelligence model) 30 to provide a service of generating conversation content for a virtual agent (AI agent) for a user.

[0013] The information processing system S according to this embodiment includes a user terminal 10, a distribution server 20, and an artificial intelligence system 30. The information processing system S may also include other devices such as servers and terminals. The user terminal 10 and the distribution server 20 are communicatively connected to each other via a network NW. The distribution server 20 and the artificial intelligence system 30 are communicatively connected to each other via the network NW. The network NW is configured with 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. For wireless connections, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). For wired connections, the network also includes networks directly connected using a USB (Universal Serial Bus) cable, etc.

[0014] The user terminal 10 is an information processing device used by a user. The user terminal 10 accepts operations by the user. The user terminal 10 launches an application according to this embodiment (hereinafter may be simply referred to as an "app") in response to a user operation. The app according to this embodiment is a virtual agent app that provides a conversation service with a virtual agent. In response to a user operation, the user terminal 10 requests content to be displayed or played by the app from the distribution server 20. Note that the user terminal 10 may display content using any app as long as it can display or play content distributed by the distribution server 20. For example, the user terminal 10 may display or play content using a dedicated application such as the virtual agent app according to this embodiment, or may display or play content using a browser app (hereinafter may be simply referred to as a "browser").

[0015] The user terminal 10 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 case where the user terminal 10 is a smartphone having a touch panel function is shown.

[0016] In this embodiment, the user terminal 10 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 10 is a terminal device that performs processing on the user's utterance. When the user terminal 10 detects the user's utterance, it transmits input information based on the user's utterance to the distribution server 20, receives content corresponding to the user's utterance, and presents it to the user.

[0017] The distribution server 20 accepts a content distribution request from the user terminal 10 of the user, and distributes content related to a virtual agent that interacts with the user in a virtual agent app launched on the user terminal 10. The distribution server 20 uses an artificial intelligence system 30 to generate conversation content for the virtual agent to the user, and distributes the generated conversation content to the user terminal 10. The distribution server 20 is configured by a computer having at least a communication function and a program execution function. The distribution server 20 may be realized by one information processing device or by multiple information processing devices.

[0018] The distribution server 20 may also have a voice recognition function. The distribution server 20 may also be able to acquire information from a voice recognition server that provides a voice recognition service. In this case, the information processing system S may include the voice recognition server. In this embodiment, the user terminal 10, the distribution server 20, 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.

[0019] The artificial intelligence system 30 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 30 include ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, and BERT. The artificial intelligence system 30 may be operated by a business that provides the virtual agent app according to the present embodiment, or may be used via an API (Application Programming Interface) provided by an external artificial intelligence system 30 operated by another business.

[0020] The artificial intelligence system 30 has a dialogue response (chat) function, and by giving any inquiry or command instruction to the artificial intelligence system 30 in text, an answer to the inquiry or command instruction can be obtained. In this embodiment, by sending to the artificial intelligence system 30 a prompt for causing the artificial intelligence system 30 to generate the content of the conversation between the virtual agent and the user, or the content of the conversation that the virtual agent will use to talk to the user, the content of the conversation can be obtained as an answer. Note that the content of the conversation that the virtual agent will use to talk to the user is an example of the content of the conversation between the virtual agent and the user, and is the first thing the virtual agent says to the user.

[0021] Furthermore, in this embodiment, the artificial intelligence system 30 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.

[0022] An example of information processing realized by the information processing system S according to this embodiment will be described below with reference to Fig. 2. Fig. 2 is a diagram showing an example of information processing realized by the information processing system S according to this embodiment. Fig. 2 shows a case where a user is identified by a user ID "U1" (hereinafter, may be referred to as "user U1"). In Fig. 1, user U1 is assumed to be a user currently using a conversation service with a virtual agent VA provided by distribution server 20.

[0023] In step S1, the distribution server 20 distributes widget content to the user terminal 10 of the user U1. The widget content is displayed in a content block CB1 included in a widget W displayed on the display unit of the user terminal 10. When the distribution server 20 receives a widget content distribution request from the user terminal 10, the distribution server 20 selects content from among multiple widget content items stored in a content command storage unit 211 (described later) and distributes the selected content to the user terminal 10. The distribution server 20 may distribute the selected widget content to the user terminal 10 without receiving a widget content distribution request from the user terminal 10. The distributed widget content is displayed in a content block CB1 included in a widget W displayed on the display unit of the user terminal 10. In the example of FIG. 2, the content block CB1 displays text data such as "That's the kind of day it was today!" The distribution server 20 may also select multiple widget content items from multiple stored widget content items and distribute them to the user terminal 10 at once.

[0024] Here, a "widget" is, for example, a graphical user interface that places information or content related to a predetermined function on a predetermined screen. The predetermined screen is, for example, a home screen (standby screen). A "content block" is, for example, an area in which information or content related to a predetermined function is displayed. A content block is associated with a service that provides content and is connected to the service. "Content" is, for example, content provided by the provider of the service. Note that a widget may also include other content blocks that are not connected to a service (for example, content blocks related to functions in which the service is completed within the user terminal 10). "A content block connecting to a service" includes, for example, a content block being connected to a server that provides a service via a network based on a predetermined operation or instruction, or being able to connect to the server via a network.

[0025] In the example of FIG. 2, three content blocks CB1, CB2, and CB3 are displayed in a widget W displayed on the display unit of the user terminal 10. The content block CB1 is connected to a conversation service with a virtual agent VA using a virtual agent application Appl according to this embodiment. The content block CB2 is connected to, for example, a weather forecast service. The content block CB3 is connected to, for example, a schedule management service.

[0026] In step S2, user U1 performs an operation to launch the virtual agent app Appl (an example of an operation (operation to start using) to start using a conversation service with the virtual agent VA) via content block CB1 included in widget W displayed on the display unit of user terminal 10. Specifically, user U1 can launch the virtual agent app Appl by tapping content block CB1 connected to the conversation service with the virtual agent VA using the virtual agent app Appl.

[0027] In step S3, the user terminal 10 transmits to the distribution server 20 information that an operation to start the virtual agent application Appl has been performed via the content block CB1.

[0028] In step S4, the distribution server 20 receives information that a launch operation of the virtual agent app Appl has been performed via the content block CB1, and in response to receiving the information, detects that the user U1 has performed a launch operation of the virtual agent app Appl via the content block CB1.

[0029] In step S5, the distribution server 20 detects the user U1's operation to launch the virtual agent application Appl via the content block CB1. The distribution server 20 generates a prompt by including a command (see FIG. 7) corresponding to the content distributed in step S1 in a prompt for the artificial intelligence system 30 to generate a conversation content for the virtual agent VA to talk to the user U1. In the example of FIG. 2, the content distributed in step S1 is "That's the kind of day it was today!", so the command corresponding to this content is "Please tell the user some trivia about today's date" (see FIG. 7). Note that in this embodiment, the description will be given assuming that commands corresponding to the content are linked to the content and stored in advance in the content command storage unit 211 (described later). By storing commands linked to the content in advance, it is not necessary to construct commands from scratch, thereby reducing processing time.

[0030] In step S6, the distribution server 20 transmits the prompt generated in step S5 to the artificial intelligence system 30.

[0031] In step S7, the artificial intelligence system 30 receives the prompt from the distribution server 20 and generates a conversation content as a response to the prompt. The conversation content generated by the artificial intelligence system 30 is text data, but may also be audio data. Furthermore, in addition to the text data or audio data of the conversation content, the artificial intelligence system 30 may also generate image data related to the conversation content, motion data of the virtual agent VA related to the conversation content, and the like.

[0032] In step S8, the distribution server 20 receives the conversation content generated by the artificial intelligence system 30 from the artificial intelligence system 30.

[0033] In step S9, the distribution server 20 receives the conversation content generated by the artificial intelligence system 30 (the conversation content for the virtual agent VA to talk to the user U1) and outputs the received conversation content to the user terminal 10. At this time, if the received conversation content is text data, the distribution server 20 may convert the text data into voice data and transmit it to the user terminal 10. The conversion from text data to voice data may be performed on the user terminal 10 side.

[0034] In step S10, the user terminal 10 that has received the conversation content launches the virtual agent app Appl and outputs the conversation content. Specifically, the user terminal 10 outputs the voice data of the conversation content from a speaker and / or displays the text data of the conversation content on a display unit. The user terminal 10 may also play back the motion data of the virtual agent VA related to the conversation content on a display unit. In the example shown in FIG. 2, the user terminal 10 outputs voice data and text data of the conversation content of the virtual agent VA speaking to the user U1, such as "Hey, did you know? Today is Cat Day!" Note that the timing of launching the virtual agent app is not limited to step S7. It may also be launched immediately after the operation to launch the virtual agent app in step S2.

[0035] In step S11, user U1 recognizes the voice data and / or text data of "Hey, did you know? Today is Cat Day!" and, as an example, utters "I didn't know. Tell me more!" to the microphone icon MI displayed on the display unit of the user terminal 10. As a result, the user terminal 10 acquires text data corresponding to "I didn't know. Tell me more!" through voice recognition.

[0036] In step S12, the user terminal 10 sends a delivery request for the conversation content of the virtual agent VA to the user U1 to the delivery server 20, including the text data corresponding to the acquired "I didn't know that. Tell me more!"

[0037] When the distribution server 20 receives a distribution request including text data corresponding to "I didn't know that. Tell me more!", it generates a prompt by including the text data as speech information of the user U1, and transmits the generated prompt to the artificial intelligence system 30.

[0038] The subsequent processing is the same as steps S7 to S10, and the processing is repeated until the user U1 stops talking to the virtual agent VA.

[0039] As described above, in the information processing system S according to this embodiment, the user U1 launches the virtual agent app Appl via the content block CB1 on the widget W displayed on the display unit of his / her user terminal 10, and the virtual agent VA starts a conversation related to the content displayed in the content block CB1 ("That's the kind of day it was today!" in the example of FIG. 2). This allows the user U1 to predict what kind of conversation he / she will have with the virtual agent VA just by looking at the content displayed on the widget W, thereby creating an opportunity to start a conversation with the virtual agent VA and increasing the motivation for the user U1 to launch the virtual agent app Appl.

[0040] The configurations of the user terminal 10 and the distribution server 20 will be described in detail below.

[0041] 3 is a diagram showing an example of the hardware configuration of a user terminal 10 according to the present embodiment. The user terminal 10 is a computer such as a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, or a PDA (Personal Digital Assistant).

[0042] The user terminal 10 is physically configured as a computer including a processor 101, memory 102, storage 103, communication device 104, input device 105, output device 106, 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 10 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 10 may be configured by communicating and connecting multiple devices each having a different housing.

[0043] Each function of the user terminal 10 is realized by loading specific software (programs) onto hardware such as the processor 101 and memory 102, causing the processor 101 to perform calculations, control communication via the communication device 104, and control at least one of reading and writing data in the memory 102 and storage 103.

[0044] The processor 101 controls the entire computer by running, for example, an operating system. The processor 101 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 101.

[0045] The processor 101 reads programs (program codes), software modules, data, etc. from at least one of the storage 103 and the communication device 104 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. The functional blocks of the user terminal 10 may be implemented by a control program stored in the memory 102 and running on the processor 101. Various processes may be executed by one processor 101, or may be executed simultaneously or sequentially by two or more processors 101. The processor 101 may be implemented by one or more chips. The programs may be transmitted to the user terminal 10 via a telecommunications line.

[0046] 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 according to this embodiment.

[0047] Storage 103 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® disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 103 may also be referred to as an auxiliary storage device.

[0048] The communication device 104 enables communication with the distribution server 20. The communication device 104 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 104. The transmitting / receiving unit may be implemented as a transmitting unit and a receiving unit that are physically or logically separated.

[0049] The input device 105 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 106 is an output device that outputs to the outside (for example, a display, speakers, LED lamps, etc.). The input device 105 and the output device 106 may be integrated into one device (for example, a touch panel).

[0050] Each device, such as the processor 101 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.

[0051] The user terminal 10 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 101 may be implemented using at least one of these pieces of hardware.

[0052] FIG. 4 is a diagram illustrating an example of the hardware configuration of distribution server 20 according to this embodiment. The hardware configuration of artificial intelligence system 30 according to this embodiment is similar to that of distribution server 20, and therefore a description thereof will be omitted. Distribution server 20 is an information processing device realized by, for example, a computer, a server device, a cloud system, or the like. Physically, distribution server 20 is configured as a computer device including processor 201, memory 202, storage 203, communication device 204, input device 205, output device 206, and buses connecting these. Since processor 201, memory 202, storage 203, input device 205, and output device 206 are similar in hardware to processor 101, memory 102, storage 103, input device 105, and output device 106 of user terminal 10, a description thereof will be omitted.

[0053] The communication device 204 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 204 enables communication with the user terminal 10.

[0054] [Functional configuration of user terminal 10] Next, a functional configuration of the user terminal 10 according to this embodiment will be described. Fig. 5 is a diagram showing the functional configuration of the user terminal 10. The user terminal 10 has a storage unit 11, a control unit 12, a display unit 13, and an audio output unit 14.

[0055] The display unit 13 is, for example, a display that displays various types of information, and is an example of the output device 106 shown in FIG. 3. The display unit 13 displays various images related to the virtual agent app according to this embodiment under the control of the display control unit 124. The display unit 13 displays, for example, text data of the conversation content of the virtual agent VA under the control of the display control unit 124. Furthermore, the display unit 13 may also display, under the control of the display control unit 124, an image of the virtual agent VA corresponding to the motion data of the virtual agent VA related to the conversation content of the virtual agent VA.

[0056] The audio output unit 14 is, for example, a speaker that outputs (plays back) various types of sound information, and is an example of the output device 106 shown in Fig. 3. The audio output unit 14 plays back various sounds related to the virtual agent app according to this embodiment under the control of the audio control unit 125. The audio output unit 14 plays back audio data of the conversation content of the virtual agent VA under the control of the audio control unit 125, for example.

[0057] The storage unit 11 stores various types of data. For example, the storage unit 11 stores a program executed by the control unit 12. The storage unit 11 stores a program that causes the control unit 12 to function as a reception unit 121, a transmission unit 122, a reception unit 123, a display control unit 124, and a voice control unit 125. The storage unit 11 stores various image data of the virtual agent VA.

[0058] The control unit 12 executes the programs stored in the storage unit 11 to function as a widget generation unit 120, a reception unit 121, a transmission unit 122, a reception unit 123, a display control unit 124, and an audio control unit 125.

[0059] The widget generation unit 120 generates a widget W to be placed on the home screen of the user terminal 10 and content blocks CB1 to CB3 on the widget.

[0060] The reception unit 121 receives various inputs from the user. For example, the reception unit 121 receives inputs from the user via an operation unit such as a touch panel provided on the surface of the display unit 13, a microphone, or the like. When the reception unit 121 receives a touch operation on an application icon for starting the virtual agent application Appl, the reception unit 121 starts the virtual agent application Appl and notifies the transmission unit 122 of the operation content.

[0061] Furthermore, when a user operates a widget W, the reception unit 121 identifies the content block of the operated widget W. For example, when the user taps on content block CB1 corresponding to virtual agent app Appl, the reception unit 121 identifies content block CB1 and notifies the transmission unit 122 of information that the operation to launch the virtual agent app Appl has been performed via content block CB1. When the reception unit 121 receives a delivery request for the conversation content of the virtual agent VA, including utterance information from the user to the virtual agent VA, the reception unit 121 notifies the transmission unit 122 of the delivery request.

[0062] The transmitter 122 transmits a content delivery request to the distribution server 20 via the communication device 104. For example, the transmitter 122 transmits a widget content delivery request to the distribution server 20. The widget content delivery request is transmitted to the distribution server 20 at a predetermined timing. For example, the widget content delivery request may be transmitted to the distribution server 20 every predetermined time, such as every hour, every two hours, or every three hours, or may be transmitted to the distribution server 20 at random timing. Alternatively, the widget content delivery request may be transmitted to the distribution server 20 when the user taps to launch the virtual agent app Appl via the content block CB1.

[0063] When the transmitting unit 122 is notified by the receiving unit 121 via the content block CB1 that an operation to launch the virtual agent app has been performed, the transmitting unit 122 transmits the information to the distribution server 20. The transmitting unit 122 can also be said to be a request to the distribution server 20 to deliver the conversation content of the virtual agent VA, because the distribution server 20, having received the information, causes the artificial intelligence system 30 to generate the conversation content of the virtual agent VA by including a command linked to the content in a prompt. Furthermore, when the transmitting unit 122 is notified by the receiving unit 121 of the user's utterance information to the virtual agent VA, the transmitting unit 122 transmits to the distribution server 20 a request to deliver the conversation content of the virtual agent VA, including text data corresponding to the utterance information.

[0064] The receiving unit 123 receives the conversation content transmitted from the distribution server 20.

[0065] The display control unit 124 causes the display unit 13 to display text data of the conversation content of the virtual agent VA. The display control unit 124 may also cause the display unit 13 to display an image of the virtual agent VA corresponding to the motion data of the virtual agent VA related to the conversation content of the virtual agent VA.

[0066] The voice control unit 125 causes the voice output unit 14 to reproduce the voice data of the conversation content of the virtual agent VA.

[0067] [Functional configuration of distribution server 20] Next, a description will be given of the functional configuration of distribution server 20 according to this embodiment. 6 is a diagram showing the functional configuration of distribution server 20. Distribution server 20 has storage unit 21 and control unit 22.

[0068] The storage unit 21 stores various types of data. For example, the storage unit 21 stores programs executed by the control unit 22. The storage unit 21 stores programs that cause the control unit 22 to function as a delivery request acquisition unit 221, a widget content output unit 222, a detection unit 223, a prompt generation unit 224, a transmission unit 225, a reception unit 226, a conversation content output unit 227, and an extraction unit 228. The storage unit 21 also stores various types of information related to content, including the conversation content of the virtual agent VA, to be delivered to the user terminal 10.

[0069] The storage unit 21 includes a content command storage unit 211 , a user information storage unit 212 , and a conversation history information storage unit 213 .

[0070] (Content command storage unit 211) The content command storage unit 211 stores, in association with each other, a plurality of widget contents to be displayed in the content block CB1 included in the widget W displayed on the display unit 13 of the user terminal 10, which is connected to a conversation service with a virtual agent VA using a virtual agent application Appl, and a plurality of commands for generating stories related to each widget content. FIG. 7 is a diagram showing an example of content command information stored in the content command storage unit 211 according to this embodiment. As shown in FIG. 7, the content command information stored in the content command storage unit 211 consists of two items: "content" and "commands to virtual agent."

[0071] The "content" consists of a plurality of predetermined widget contents, and the "commands to the virtual agent" also consists of a plurality of predetermined commands, the same number as the number of widget contents in the "content." These commands are linked to each other. In this embodiment, as shown in FIG. 7, six widget contents are exemplified as the "content," but the number of widget contents stored in the content command storage unit 211 is not limited to this.

[0072] In the example in Figure 7, the content for widget No. 1 is "That's the day it was today!". This content is linked to the command "Tell the user some trivia about today's date" as a "command to the virtual agent."

[0073] The widget content for No. 2 is "That's an interesting thing!". This content is linked to the "command to the virtual agent" command "Tell the user something interesting."

[0074] The content for widget No. 3 is "I was a little surprised!". This content is linked to the command "Tell the user what surprised you" as a "command to the virtual agent."

[0075] The content for widget No. 4 is "I didn't know that!". This content is linked to the command "Tell the user some simple trivia" as a "command to the virtual agent."

[0076] The content for widget No. 5 is "Do you know any interesting stories about Kyoto?". This content is linked to the command "Tell the user an interesting story about Kyoto" as a "command to the virtual agent."

[0077] The content for widget No. 6 is "Here's what's happening in Kyoto!". This content is linked to the "command to the virtual agent" which is "Tell the user about events happening in Kyoto today or tomorrow."

[0078] In this way, each of the plurality of widget contents stored in the content command storage unit 211 is content that makes the user want to launch the virtual agent application Appl and have a conversation with the virtual agent VA. In other words, each of the plurality of widget contents is content that prompts the user to launch the virtual agent application Appl.

[0079] In this embodiment, the widget contents stored in the content command storage unit 211 are text data, but the widget contents may include at least either text data or image data. The text data may be an exclamation or question.

[0080] (User information storage unit 212) The user information storage unit 212 stores various pieces of user information related to the user. FIG. 8 is a diagram showing an example of user information stored in the user information storage unit 212 according to this embodiment. As shown in FIG. 8, the user information storage unit 212 stores user information for items such as "fixed information," "extracted information," and "current information" for each "user ID." The user information storage unit 212 may store at least one of "fixed information," "extracted information," and "current information" as the user information for each "user ID." By referring to this information as user information, the virtual agent VA can have a conversation with the user that is more suited to the user's situation.

[0081] "User ID" indicates identification information for identifying a user. For example, a user identified by a user ID "U1" corresponds to user U1 shown in the example of FIG.

[0082] "Fixed information" is fixed information about a user identified by a user ID. The "fixed information" includes information such as "age," "gender," "place of residence," "occupation," "place of work," "working hours," "break time," and "holidays." "Age" indicates the age of the user identified by the user ID. "Gender" indicates the gender of the user identified by the user ID. "Place of residence" indicates the place of residence of the user identified by the user ID. "Occupation" indicates the occupation of the user identified by the user ID. "Place of work" indicates the place of work of the user identified by the user ID. "Working hours" indicates the working hours of the user identified by the user ID. "Break time" indicates the break time of the user identified by the user ID. "Holidays" indicates the holidays of the user identified by the user ID. The "fixed information" can be provided in advance by the user, for example, when the user identified by the user ID starts using the virtual agent app Appl according to this embodiment. The user can also edit or update the fixed information when using the virtual agent app Appl.

[0083] "Extracted information" is extracted information about the user extracted from the conversation history between the user and the virtual agent VA stored in the conversation history information storage unit 213. "Extracted information" includes information such as "interests and hobbies," "personality," "physical condition," and "upcoming plans." "Interests and hobbies" indicates the interests and hobbies of the user identified by the user ID extracted from the conversation history between the user and the virtual agent VA. "Personality" indicates the personality of the user extracted from the conversation history between the user identified by the user ID and the virtual agent VA. "Physical condition" indicates the physical condition of the user extracted from the conversation history between the user identified by the user ID and the virtual agent VA. "Upcoming plans" indicates the upcoming plans of the user extracted from the conversation history between the user identified by the user ID and the virtual agent VA.

[0084] "Current information" is current information about the user. "Current information" includes information such as "location information" and "location information movement." "Location information" indicates the current location information of a user identified by a user ID. "Location information movement" indicates the current location information movement of a user identified by a user ID. These pieces of information are acquired by the location information sensor of the user terminal 10 and are transmitted from the user terminal 10 to the distribution server 20 when a request for distribution of content (e.g., conversation content) is transmitted.

[0085] The user information storage unit 212 may store various information according to the purpose, not limited to the above information. For example, the user information storage unit 212 may store other demographic attribute information and psychographic attribute information in addition to the above information. For example, the user information storage unit 212 may store information such as name, interests, family structure, income, lifestyle, current trends, emotions, etc.

[0086] (Conversation history information storage unit 213) The conversation history information storage unit 213 stores various information related to the conversation history between the user and the virtual agent VA. FIG. 9 is a diagram showing an example of conversation history information stored in the conversation history information storage unit 213 according to this embodiment. As shown in FIG. 9, the information stored in the conversation history information storage unit 213 consists of two items: "user ID" and "conversation history information." The "conversation history information" includes items such as "type," "date and time," "conversation content," and "other."

[0087] "User ID" indicates identification information for identifying a user. "Conversation history information" indicates the conversation history between the user and the virtual agent VA in the virtual agent application Appl according to this embodiment. "Type" indicates the type of content in the virtual agent application Appl. In the example of FIG. 9, "Type" stores either "Output," which indicates that content has been output to the user, or "Input," which indicates that speech information has been input by the user's speech.

[0088] "Date and time" indicates the date and time when each content was input or output. In the example of Figure 9, "date and time" is illustrated using an abstract symbol such as "date and time DA-1." "Conversation content" indicates text data included in the content output at the corresponding date and time. "Other" indicates various information such as audio data and image data included in the content output at the corresponding date and time.

[0089] For example, as shown in FIG. 9, it indicates that content was output by the distribution server 20 to the user terminal 10 of a user (user U1) identified by a user ID "U1" at the date and time "Date and time DA-1." For example, it indicates that the content output by the distribution server 20 at the date and time "Date and time DA-1" includes the conversation content "It was that kind of day today!" Note that this conversation content is content for a widget.

[0090] It also indicates that content was output by the distribution server 20 to the user terminal 10 of user U1 at the date and time "Date and time DA-2." For example, it indicates that the content output to the distribution server 20 at the date and time "Date and time DA-2" includes the conversation content "Hey, did you know? Today is Cat Day!". Note that this conversation content is the conversation content generated by the artificial intelligence system 30 by including in a prompt a command to the virtual agent VA linked to the widget content "So that's the day today!", "Tell the user some trivia about today's date," and sending the prompt to the artificial intelligence system 30.

[0091] It also indicates that content corresponding to user U1's speech information was input from user U1's user terminal 10 at the date and time "Date and time DA-3." For example, it indicates that the content input to the distribution server 20 at the date and time "Date and time DA-3" includes the conversation content "I didn't know that. Tell me more!"

[0092] Returning to FIG. 6, the control unit 22 executes the programs stored in the memory unit 21 to function as a distribution request acquisition unit 221, a widget content output unit 222, a detection unit 223, a prompt generation unit 224, a transmission unit 225, a reception unit 226, a conversation content output unit 227, and an extraction unit 228.

[0093] The delivery request acquisition unit 221 acquires various information including a content delivery request. The delivery request acquisition unit 221 acquires a delivery request for the conversation content of the virtual agent VA with the user. The delivery request acquisition unit 221 acquires a delivery request for widget content. The delivery request acquisition unit 221 also acquires information that a launch operation for the virtual agent app Appl has been performed via the content block CB1 as a delivery request for the conversation content of the virtual agent VA. The delivery request acquisition unit 221 also acquires fixed information about the user and current information about the user from the user terminal 10.

[0094] The widget content output unit 222 selects a widget content from among the plurality of widget contents stored in the content command storage unit 211 and outputs the selected widget content. Specifically, when the distribution request acquisition unit 221 acquires a widget content distribution request, the widget content output unit 222 selects a widget content from among the plurality of widget contents stored in the content command storage unit 211 and distributes the selected widget content to the user terminal 10. Note that the widget content output unit 222 may distribute the selected widget content to the user terminal 10 without acquiring a widget content distribution request.

[0095] The widget content output unit 222 also changes the widget content to be output at a predetermined timing. That is, the widget content output unit 222 changes the widget content to be delivered to the user terminal 10 at a predetermined timing.

[0096] The predetermined timing may be a fixed timing such as every hour, every two hours, or every three hours, or may be random timing. The predetermined timing may also be the timing when the user performs a tap operation to launch the virtual agent app Appl via the content block CB1.

[0097] If the widget content displayed on the widget W is always the same, there is a risk that motivation to launch the virtual agent app Appl will weaken even if the conversation content after launching the virtual agent app Appl is different each time. Therefore, motivation to launch the virtual agent app Appl can be increased by changing the widget content displayed on the widget W at a predetermined timing, such as every hour or when the virtual agent app Appl is launched from the widget content once.

[0098] Furthermore, the widget content output unit 222 may determine a widget content to be output (specifically, delivered to the user terminal 10) from among the multiple widget contents stored in the content command storage unit 211, based on the user information stored in the user information storage unit 212. For example, if the widget content output unit 222 extracts information that the user likes trivia from the user information, the widget content output unit 222 may output the widget content No. 4, "I didn't know that!". If the widget content output unit 222 extracts information that the user is currently in Kyoto from the user information, the widget content output unit 222 may output the widget content No. 5, "Do you know any interesting stories about Kyoto?". The widget content output unit 222 may also determine a content to be output based on some rule base using the user information.

[0099] By using user information to determine widget content, widget content suited to the user's situation can be displayed in the content block CB1, further increasing the motivation to launch the virtual agent application Appl.

[0100] The widget content output unit 222 may be implemented using an LLM such as the artificial intelligence system 30, or may be implemented using a locally executable LLM provided in the distribution server 20. Examples of locally executable LLMs include Llama 3, Gema 2, and Deep Seek-R1.

[0101] In this case, the prompt for causing the LLM to determine the widget content to be output by the widget content output unit 222 includes the information stored in the content command storage unit 211 (the information in FIG. 7) and the user information stored in the user information storage unit 212 (the information in FIG. 8). The prompt also includes a command to select widget content from the plurality of widget contents stored in the content command storage unit 211 using the user information. The LLM may also be configured to generate new widget content other than the plurality of widget contents stored in the content command storage unit 211. In this case, the prompt may include a command to generate new widget content, for example, using the plurality of widget contents stored in the content command storage unit 211.

[0102] The detection unit 223 detects an operation to launch the virtual agent app Appl via the content block CB1 in which widget content is displayed on the widget W. Specifically, when the distribution request acquisition unit 221 acquires information that an operation to launch the virtual agent app Appl has been performed via the content block CB1, the detection unit 223 detects the launch operation.

[0103] The prompt generation unit 224 generates a prompt for causing the artificial intelligence system 30 to generate a conversation content of the virtual agent VA with the user. Specifically, when the detection unit 223 detects an operation to launch the virtual agent app Appl via the content block CB1, the prompt generation unit 224 generates the prompt by including a command linked to the widget content to be delivered in the prompt for causing the artificial intelligence system 30 to generate a conversation content of the virtual agent VA. At this time, the prompt generation unit 224 may include user information of the user in the prompt.

[0104] By including the user's user information in the prompt, the virtual agent VA will be able to start a conversation based on the user information, allowing the conversation to focus on topics that are of interest to the user.

[0105] Furthermore, when the delivery request acquisition unit 221 acquires user utterance information, the prompt generation unit 224 includes the utterance information in a prompt for generating a conversation between the virtual agent VA and the user. At this time, the prompt generation unit 224 may include user information in the prompt.

[0106] This allows the virtual agent VA to expand on the topic from the conversation and conduct a conversation that suits the user's situation.

[0107] The transmitting unit 225 transmits the prompt to the artificial intelligence system 30. For example, the transmitting unit 225 transmits the prompt to the artificial intelligence system 30 to cause the artificial intelligence system 30 to generate conversation content of the virtual agent VA to the user.

[0108] The receiving unit 226 receives the conversation content of the virtual agent VA to the user, which is generated by the artificial intelligence system 30 as a response to the prompt generated by the prompt generating unit 224.

[0109] The conversation content output unit 227 outputs the conversation content received by the receiving unit 226 as a response to the prompt to the user terminal 10. When the conversation content is text data, the conversation content output unit 227 may convert the text data into audio data and output it to the user terminal 10 together with or instead of the text data.

[0110] The extraction unit 228 extracts user information of the user from the conversation history between the user and the virtual agent VA stored in the conversation history information storage unit 213. The information extracted by the extraction unit 228 is added to or overwritten in the "extracted information" field in the user information storage unit 212. The information extracted by the extraction unit 228 may be added to or overwritten in the "fixed information" and "current information" fields in the user information storage unit 212. Whether or not to add or overwrite the information extracted by the extraction unit 228 in the "fixed information" and "current information" fields in the user information storage unit 212 may be determined by the artificial intelligence system 30.

[0111] By the extraction unit 228 extracting information from the conversation history, the distribution server 20 can refer to information other than the fixed information provided in advance by the user as user information, and the virtual agent VA can speak to the user in a way that is more suited to the user's situation, using greetings and topics that are more suited to the user's situation.

[0112] [Operation flow] FIG. 10 is a flowchart illustrating an example of a process executed by the user terminal 10 and the distribution server 20 of the information processing system S according to this embodiment to display widget content of the virtual agent app Appl in a content block CB1 included in a widget W displayed on the display unit 13 of the user terminal 10.

[0113] In step S101, the transmitting unit 122 of the user terminal 10 transmits to the distribution server 20 a distribution request for the widget content of the virtual agent application Appl.

[0114] In step S102, the widget content output unit 222 of the distribution server 20 receives the widget content distribution request from the user terminal 10. The widget content output unit 222 selects a widget content from the plurality of widget contents stored in the content command storage unit 211 and distributes the selected widget content to the user terminal 10.

[0115] In step S103, the display control unit 124 of the user terminal 10 receives the widget content distributed from the distribution server 20 and displays the received widget content in the content block CB1 of the widget W displayed on the display unit 13. Through the above process, the user terminal 10 can display the widget content of the virtual agent app Appl in the content block CB1 of the widget W displayed on the display unit 13. Note that the process for updating and displaying the widget content is similar to the above process.

[0116] 11 is a flowchart showing an example of processing executed in the information processing system S according to this embodiment. Note that this flowchart starts from a state in which, as a result of the processing in FIG. 10, widget content of the virtual agent app Appl is displayed in the content block CB1 of the widget W on the display unit 13 of the user terminal 10.

[0117] In step S201, the reception unit 121 of the user terminal 10 determines whether or not the user has performed an operation to launch the virtual agent app Appl via the content block CB1 corresponding to the virtual agent app Appl. If the reception unit 121 determines that the user has performed the launch operation, the reception unit 121 notifies the transmission unit 122 of information that the operation to launch the virtual agent app Appl has been performed via the content block CB1.

[0118] In step S202, the transmitter 122 transmits to the distribution server 20, via the content block CB1, information that an operation to start the virtual agent application Appl has been performed.

[0119] In step S203, the detection unit 223 of the distribution server 20 that has received the information detects the activation operation of the virtual agent application Appl via the content block CB1.

[0120] In step S204, when the detection unit 223 detects an operation to launch the virtual agent app Appl via the content block CB1, the prompt generation unit 224 generates a prompt by including in the prompt a command linked to the widget content distributed to the distribution server 20 and displayed in the content block CB1, the command linking the command linking the widget content distributed to the distribution server 20 and displayed in the content block CB1, for the artificial intelligence system 30 to generate the conversation content of the virtual agent VA. For example, when the widget content displayed in the content block CB1 is "That's the kind of day it was today!", the prompt generation unit 224 includes in the prompt a command saying "Tell the user some trivia about today's date."

[0121] In step S205, the sending unit 225 sends the prompt generated in step S204 to the artificial intelligence system 30.

[0122] In step S206, the artificial intelligence system 30 receives the prompt from the distribution server 20 and generates a conversation content as a response to the prompt. Here, for example, the conversation content generated is, "Hey, did you know? Today is Cat Day!"

[0123] In step S207, the receiving unit 226 of the distribution server 20 receives from the artificial intelligence system 30 the conversation content generated by the artificial intelligence system 30 in step S206.

[0124] In step S208, the conversation content output unit 227 of the distribution server 20 receives the conversation content generated by the artificial intelligence system 30 and outputs the received conversation content to the user terminal 10.

[0125] In step S209, the user terminal 10 that has received the conversation content starts the virtual agent application Appl and outputs the conversation content. Specifically, the voice control unit 125 of the user terminal 10 causes the voice output unit 14 to play back the voice data of the conversation content, and / or the display control unit 124 causes the display unit 13 to display the text data of the conversation content.

[0126] The user who has recognized the voice data and / or text data of the conversation content speaks as a reply to the conversation content into the microphone icon MI displayed on the display unit 13 of the user terminal 10. As a result, in step S210, the reception unit 121 of the user terminal 10 acquires, by voice recognition, speech information that is text data corresponding to the utterance.

[0127] In step S211, the transmitting unit 122 of the user terminal 10 transmits to the distribution server 20 a request for distribution of the conversation content of the virtual agent VA to the user, including the acquired speech information.

[0128] When the distribution request acquisition unit 221 of the distribution server 20 receives a distribution request including utterance information, in step S212 the prompt generation unit 224 of the distribution server 20 generates a prompt by including the utterance information in the prompt.

[0129] In step S213, the transmission unit 225 of the distribution server 20 transmits the prompt generated in step S212 to the artificial intelligence system 30.

[0130] In step S214, the artificial intelligence system 30 receives the prompt from the distribution server 20 and generates a conversation content (a conversation content of the virtual agent VA in response to the user's utterance) as a response to the prompt.

[0131] In step S215, the receiving unit 226 of the distribution server 20 receives from the artificial intelligence system 30 the conversation content generated by the artificial intelligence system 30 in step S214.

[0132] In step S216, the conversation content output unit 227 of the distribution server 20 receives the conversation content generated by the artificial intelligence system 30 and outputs the received conversation content to the user terminal 10.

[0133] In step S217, the user terminal 10 that has received the conversation content outputs the conversation content. Specifically, the audio control unit 125 of the user terminal 10 causes the audio output unit 14 to play back the audio data of the conversation content, and / or the display control unit 124 causes the display unit 13 to display the text data of the conversation content.

[0134] Thereafter, the processes of steps S210 to S217 are repeated until the user stops talking to the virtual agent VA.

[0135] As described above, in the distribution server 20 of the information processing system S according to this embodiment, a user launches the virtual agent app Appl via the content block CB1 on the widget W displayed on the display unit 13 of the user terminal 10, and the virtual agent VA starts a conversation related to the widget content displayed in the content block CB1. This allows the user to predict what kind of conversation he or she will have with the virtual agent VA simply by looking at the widget content displayed on the widget W, thereby creating an opportunity to start a conversation with the virtual agent VA and increasing the user's motivation to launch the virtual agent app Appl.

[0136] [Other embodiments] The information processing system S of the present invention has been described above with reference to the present embodiment, but the information processing system S of the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the technical scope of the present invention. Furthermore, systems or devices that combine the separate features included in the present embodiment in any way are also included in the technical scope of the present invention.

[0137] The present invention may also be applied to a system consisting of multiple devices, or to a single device. Furthermore, the present invention is also applicable 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 that downloads the program, 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 embodiments.

[0138] In the above embodiment, the user terminal 10 interacts with the artificial intelligence system 30 via the distribution server 20, allowing the user to converse with the virtual agent VA. If the user terminal 10 can have the functions of the control unit 22 of the distribution server 20 (the functions shown in FIG. 5 ) and can access the data in the storage unit 21 of the distribution server 20, the user terminal 10 can interact directly with the artificial intelligence system 30, allowing the user to converse with the virtual agent VA. Furthermore, the user terminal 10 may be provided with at least some of the functions of the control unit 22 of the distribution server 20 (the functions shown in FIG. 5 ), allowing the user terminal 10 to access the data in the storage unit 21 of the distribution server 20.

[0139] The following additional notes are provided regarding the above-described embodiments.

[0140] [Appendix 1] The information processing system a widget content output unit that outputs content selected from a plurality of contents stored in a content command storage unit that stores a plurality of contents to be displayed in a content block included in a widget and that is connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; and a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the start-of-use operation via the content block, includes a command corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; a sending unit that sends the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; a conversation content output unit that outputs the conversation content received by the receiving unit as the answer;

[0141] With the above configuration, when a user starts using a service via a content block on a widget, the virtual agent starts a conversation related to the content displayed in the content block. This allows the user to predict what kind of conversation they will have with the virtual agent just by looking at the content displayed on the widget, creating an opportunity to start a conversation with the virtual agent and increasing the user's motivation to use the service.

[0142] [Appendix 2] In the information processing system described in Supplementary Note 1, the content command storage unit stores the plurality of contents in association with a plurality of commands for generating stories related to each of the contents.

[0143] With the above configuration, since commands are already associated with each piece of content and stored, there is no need to create commands from scratch, and processing time can be reduced.

[0144] [Appendix 3] In the information processing system according to Supplementary Note 1 or 2, each of the plurality of contents is content that encourages use of the service.

[0145] [Appendix 4] In any of the information processing systems of Supplementary Notes 1 to 3, when the detection unit detects the start-of-use operation, the prompt generation unit includes user information of the user in the prompt in addition to an instruction corresponding to the content.

[0146] With the above configuration, the virtual agent will start a conversation based on user information, allowing the conversation to focus on topics that interest the user.

[0147] [Appendix 5] In the information processing system according to any one of Supplementary Notes 1 to 4, the plurality of contents include at least one of text data and image data.

[0148] With the above configuration, it is possible to effectively encourage use of the service by using either text data or image data.

[0149] [Appendix 6] In any of the information processing systems of Appendices 1 to 5, the widget content output unit changes the content to be output at regular intervals, random times, or when the start-of-use operation is performed via the content block.

[0150] If the content displayed in the widget is always the same, motivation to use the service may be weakened. With the above configuration, the content displayed in the widget can be changed, for example, at regular intervals, random times, or when an operation to start using the service via a content block is performed, thereby increasing motivation to use the service.

[0151] [Appendix 7] In the information processing system according to any one of Supplementary Notes 1 to 6, the widget content output unit determines a content to be output from the plurality of contents based on user information.

[0152] With the above configuration, content determined based on user information can be displayed in the content block, which can further increase motivation to use the service.

[0153] [Appendix 8] The information processing method is outputting content selected from a plurality of contents stored in a content instruction storage unit that stores a plurality of contents to be displayed in a content block included in a widget, the content block being connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; detecting an operation to start using the service via the content block in which the content on the widget is displayed; When the start-of-use operation via the content block is detected, a step of including an instruction corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; sending the prompt to the generative artificial intelligence model; receiving the conversation content generated by the generative artificial intelligence model in response to the prompt; and outputting the conversation content as the received answer.

[0154] This configuration provides the same operational effects as the information processing system of Supplementary Note 1. The information processing method of Supplementary Note 8 may include various configurations of the information processing systems described in Supplementary Notes 2 to 7.

[0155] [Appendix 9] The information processing device a widget content output unit that outputs content selected from a plurality of contents stored in a content command storage unit that stores a plurality of contents to be displayed in a content block included in a widget and that is connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; and a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the start-of-use operation via the content block, includes a command corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; a sending unit that sends the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; a conversation content output unit that outputs the conversation content received by the receiving unit as the answer;

[0156] This configuration provides the same operational effects as the information processing system of Supplementary Note 1. The information processing device of Supplementary Note 9 may include various configurations of the information processing systems described in Supplementary Notes 2 to 7. [Explanation of symbols]

[0157] 10 User terminal 11 Storage section 12 Control Unit 13 Display section 14 Audio output section 120 Widget Generation Unit 121 Reception 122 Transmitter 123 Receiving unit 124 Display control unit 125 Audio control unit 20 Distribution server (information processing device) 21 Memory section 211 Content command storage unit 212 User information storage unit 213 Conversation history information storage unit 22 Control Unit 221 Delivery request acquisition unit 222 Widget content output section 223 Detection unit 224 Prompt Generation Unit 225 Transmitter 226 Receiving unit 227 Conversation content output section 228 Extraction part 30 Artificial Intelligence Systems (Generative AI Models)

Claims

1. a widget content output unit that outputs content selected from a plurality of contents stored in a content command storage unit that stores a plurality of contents to be displayed in a content block included in a widget and that is connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; and a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the start-of-use operation via the content block, includes a command corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; a sending unit that sends the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; a conversation content output unit that outputs the conversation content received by the receiving unit as the answer.

2. The information processing system according to claim 1 , wherein the content command storage unit stores the plurality of pieces of content in association with a plurality of commands for generating stories related to each piece of content.

3. The information processing system according to claim 1 , wherein each of the plurality of contents is content that encourages use of the service.

4. The information processing system according to claim 1 , wherein when the detection unit detects the start-of-use operation, the prompt generation unit includes user information of the user in the prompt in addition to a command corresponding to the content.

5. The information processing system according to claim 1 , wherein the plurality of contents include at least one of text data and image data.

6. 2. The information processing system according to claim 1, wherein the widget content output unit changes the content to be output at any one of a fixed time interval, a random time interval, and a time interval when the start-of-use operation is performed via the content block.

7. The information processing system according to claim 1 , wherein the widget content output unit determines the content to be output from the plurality of contents based on user information.

8. outputting content selected from a plurality of contents stored in a content instruction storage unit that stores a plurality of contents to be displayed in a content block included in a widget, the content block being connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; detecting an operation to start using the service via the content block in which the content on the widget is displayed; When the start-of-use operation via the content block is detected, a step of including an instruction corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; sending the prompt to the generative artificial intelligence model; receiving the conversation content generated by the generative artificial intelligence model in response to the prompt; and outputting the conversation content as the received answer.

9. a widget content output unit that outputs content selected from a plurality of contents stored in a content command storage unit that stores a plurality of contents to be displayed in a content block included in a widget and that is connected to a service that generates conversation content for a virtual agent to a user using a generative artificial intelligence model; and a detection unit that detects an operation to start using the service via the content block in which the content on the widget is displayed; a prompt generation unit that, when the detection unit detects the start-of-use operation via the content block, includes a command corresponding to the content in a prompt for causing the generative artificial intelligence model to generate a conversation content of the virtual agent; a sending unit that sends the prompt to the generative artificial intelligence model; a receiving unit that receives the conversation content generated by the generative artificial intelligence model as a response to the prompt; a conversation content output unit that outputs the conversation content received by the receiving unit as the answer.

Images