System

Abstract

To provide a system.SOLUTION: A system for providing a virtual campus tour includes: means for starting the virtual campus tour by outputting a video related to the virtual campus tour to a terminal in response operation of a terminal by a user; means for detecting voice data by a microphone of the terminal when a video of the virtual campus is output to the terminal operated by the user and the user issues a question or doubt while virtually strolling the virtual campus; means for converting the voice data detected by the terminal into text data; means for transmitting the text data received by a server to a generative system AI and starting analysis; means for analyzing the text data received by the generative system AI and generating an appropriate answer; means for receiving the answer generated by the generative system AI and replying to the user; and means for displaying the answer from the server and providing the answer to the user by the terminal.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional study abroad information systems did not allow students to directly experience the actual atmosphere and facilities of their desired university or campus, which could lead to a lack of information and anxiety for students considering studying abroad. [Means for solving the problem]

[0005] The present invention provides a system that allows students considering studying abroad to virtually visit their desired universities and campuses by providing a virtual campus tour, and have their questions and doubts answered in real time. Specifically, the user operates a terminal to start a virtual campus tour. When the user asks a question while walking around the virtual campus, the terminal's microphone detects the voice data and converts it into text data. The server sends the received text data to a generative AI, which generates an appropriate answer in real time. The user receives the answer from the server and can obtain more specific information about the desired university or campus.

[0006] By the above means, the present invention allows students to obtain more realistic information about the university and campus where they will be studying abroad, thereby eliminating the lack of information and anxiety felt by students considering studying abroad.

[0007] For example, the terminal is a head-mounted display. A "head-mounted display" is a display device that a user wears on his / her head and is used to experience a virtual campus tour. A "head-mounted display" projects an image into the user's field of vision, providing a more immersive experience.

[0008] A "virtual campus tour" is an experience in which a user virtually visits a university or campus of their choice, and can stroll around a realistic campus environment in a virtual space using a "head-mounted display," one example of a terminal.

[0009] A "microphone" is a device for detecting voice, and serves to collect voice data when a user asks a question or inquires during a virtual campus tour.

[0010] "Text data" refers to information obtained by converting voice data into a character string format. The conversion from voice data to text data is used when sending a question or inquiry to a server.

[0011] "Generative AI" is an AI model that uses natural language processing technology to analyze text data and generate appropriate answers. Generative AI plays a role in providing answers to user questions in real time.

[0012] The "server" is a computer system that receives text data sent by users, sends it to the generative AI for analysis, and returns answers generated by the generative AI to the users.

[0013] The above are definitions of important words included in the claims. [Brief description of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] 4 is a sequence diagram showing a process flow of the data processing system according to the first embodiment. FIG. [Figure 12] 11 is a sequence diagram showing a process flow of the data processing system in application example 1. FIG. [Figure 13] FIG. 11 is a sequence diagram showing the flow of processing of the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 11 is a sequence diagram showing the flow of processing in the data processing system in application example 2 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0018] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0019] In the following embodiments, the storage with the code is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g.,

[0020] Examples include hard disks, or magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0036] The embodiment for carrying out the present invention comprises the following elements.

[0037] Element 1: User Interface

[0038] In response to a user's operation of the terminal, the virtual campus tour is started. The terminal outputs an image of the virtual campus to the display 40A, thereby projecting the image of the virtual campus into the user's field of vision.

[0039] Element 2: Detecting and Converting Audio Data

[0040] A microphone 38B mounted on the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0041] Element 3: Communication with Server

[0042] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0043] Element 4: Generative AI to generate answers

[0044] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0045] Element 5: Providing answers

[0046] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0047] With the above elements, in the embodiment of the present invention, a user experiences a virtual campus tour using a terminal, and when he or she asks a question or doubt, the voice data is detected and converted into text data. A generative AI analyzes the data through communication with a server, generates an appropriate answer, and provides it to the user. This allows students considering studying abroad to obtain information about the university and campus of their choice in real time.

[0048] The process flow will be explained below.

[0049] Step 1: Navigate the User Interface

[0050] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus to the display 40A, thereby projecting the image of the virtual campus into the user's field of vision.

[0051] Step 2: Detect and convert audio data

[0052] The microphone 38B of the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0053] Step 3: Communicating with the Server

[0054] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0055] Step 4: Generative AI generates answers

[0056] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0057] Step 5: Provide your answer

[0058] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0059] The above is a specific flow of the program's processing. The user operates the terminal to start the virtual campus tour and utters a question or doubt by voice. The terminal's microphone 38B detects the voice data and converts it into text data. The text data is sent to the server, where the generative AI analyzes it and generates an answer. The server sends the answer to the terminal, where it is provided to the user.

[0060] Example 1

[0061] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0062] In the modern education system, it is difficult for students to understand the facilities and environment of a campus without actually visiting it. In particular, for students considering studying abroad, the means to obtain detailed information about the university before traveling are limited, making it difficult to make a decision. To solve this situation, virtual campus tours are required. However, there is an issue that mere video and text information cannot respond to students' specific questions in real time.

[0063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0064] In this invention, the server includes a means for transferring the received text data to an analysis device and starting the analysis, a means for the analysis device to analyze the received text data and generate an appropriate answer using natural language processing technology, and a means for the server to receive the generated answer and return it to the terminal via the communication network. This allows students to use the terminal to experience a virtual campus tour and obtain appropriate answers to their questions and doubts in real time.

[0065] A "user" is a person who operates a terminal to experience a virtual campus tour.

[0066] A "terminal" is an electronic device that provides a virtual campus tour through a user interface, detects voice data, and transmits and receives data.

[0067] A "virtual campus tour" is an online tour that simulates a real campus and that users experience through their devices.

[0068] A "display" refers to a display device that is connected to a terminal and visually presents an image of the virtual campus and generated answers to a user.

[0069] The "acquisition device" refers to a hardware component that is installed in a terminal and detects voice data uttered by a user.

[0070] "Voice data" refers to voice signals of questions or doubts uttered by a user during a virtual campus tour.

[0071] "Speech recognition technology" refers to technology that analyzes voice data detected by a capture device and converts it into text data.

[0072] "Text data" refers to data that expresses a user's question or inquiry as text, converted using voice recognition technology.

[0073] A "communications network" refers to the infrastructure for transmitting and receiving data between terminals and servers.

[0074] "Server" refers to a central processing unit for analyzing text data received from a terminal and providing generated answers.

[0075] An "analysis device" refers to a device or system that resides within a server and that analyzes text data and generates appropriate answers.

[0076] "Natural language processing technology" refers to technology that enables an analysis device to understand text data and generate appropriate answers in a format that humans can understand.

[0077] An "answer" is text data or voice data generated by the analysis device with the aim of providing appropriate information to a user's question or inquiry.

[0078] A "display device" is a device that is connected to a terminal and that visually presents the generated answers to a user.

[0079] The embodiment of the present invention utilizes a terminal equipped with a user interface. This terminal starts a virtual campus tour when operated by a user, and outputs an image of the virtual campus on a display. The user can visually enjoy this image. Specific hardware that can be used includes a smartphone, tablet, and PC.

[0080] Any questions or doubts posed by the user during the virtual campus tour are captured as voice data by a capture device, i.e., a microphone, installed on the device. This voice data is converted to text data using speech recognition technology within the device, such as the Google® Cloud Speech-to-Text API. This makes the user's utterances available as text information for analysis.

[0081] The converted text data is sent from the device to a server via a communication network. The server runs on Amazon Web Services (AWS®) or other cloud computing platforms. The server forwards the received text data to an analysis device, which uses a generative AI model, such as OpenAI®'s ChatGPT® or other natural language processing technology, to generate an appropriate response.

[0082] The generated answer is sent back to the terminal via the server and is displayed on the terminal's display device. In some cases, the answer can be provided aloud using the terminal's speaker.

[0083] As a concrete example, consider the following scenario: A user starts a virtual campus tour using a smartphone, and while watching the campus image projected on the display, asks, "What is this building?" This question is detected by a microphone and converted into text data using voice recognition technology. The converted text data is sent to a server, and a generative AI model generates an answer, "This is a library." This answer is then sent to the device and provided to the user via the display and speaker.

[0084] And here is an example of a prompt to be input to the generative AI model:

[0085] Example prompt 1:

[0086] "When a user asks, 'What building is this?' during a virtual campus tour, generate an appropriate response."

[0087] Example prompt 2:

[0088] "Generate real-time answers to the question 'Where are the student dorms?' during a virtual campus tour."

[0089] The above is a specific embodiment of the present invention. By using this system, users can obtain detailed information in response to their questions in real time without actually visiting the campus, which can support their decision-making when considering studying abroad.

[0090] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0091] Step 1:

[0092] A user operates a terminal to start a virtual campus tour. As input, the user's operation information (e.g., clicking a button) is sent to the terminal. As output, the terminal projects an image of the virtual campus onto the display.

[0093] Specific behavior:

[0094] The user starts the dedicated smartphone app and taps the "Start Campus Tour" button, which causes the app to acquire user operation information and display a virtual campus image on the display.

[0095] Step 2:

[0096] The voice data of questions and doubts uttered by the user during the virtual campus tour is detected by a capture device (microphone) installed on the terminal. As input, the user's voice is sent to the microphone. As output, the detected voice data is generated.

[0097] Specific behavior:

[0098] When a user asks, "What building is this?", the device's microphone immediately detects the voice, and the capture device activates the noise canceling function to capture high-quality voice data.

[0099] Step 3:

[0100] A voice recognition system in the terminal converts the detected voice data into text data. As input, the voice data is sent to the voice recognition system. As output, text data is generated.

[0101] Specific behavior:

[0102] The device's voice recognition system converts the voice data "What is this building?" into text data "What is this building?" using a voice recognition library such as the Google Cloud Speech-to-Text API.

[0103] Step 4:

[0104] The terminal transmits the converted text data to the server via the communication network. As input, the text data is transmitted from the terminal to the server. As output, the server receives the text data.

[0105] Specific behavior:

[0106] The terminal sends the text data "What is this building?" to the server using the HTTPS protocol. The server receives this data and adds it to the processing queue.

[0107] Step 5:

[0108] The server transfers the received text data to the analysis device and starts the analysis. As input, the text data received by the server is sent to the analysis device. As output, the analysis result is generated.

[0109] Specific behavior:

[0110] The server prepares the text data "What is this building?" to be passed to the generative AI model, which then performs the analysis. For example, it uses OpenAI's ChatGPT for natural language processing.

[0111] Step 6:

[0112] The analysis device analyzes the text data and generates an appropriate answer using natural language processing techniques. As input, the text data is sent to the analysis device. As output, the generated answer is sent to the server.

[0113] Specific behavior:

[0114] Based on the text data "What is this building?", the generative AI model references its internal database and knowledge base to generate the answer "This is a library."

[0115] Step 7:

[0116] The server receives the generated answer and returns it to the terminal via the communication network. As an input, the generated answer is sent to the server. As an output, the server sends the answer to the terminal.

[0117] Specific behavior:

[0118] The server receives the answer from the generative AI model, "This is a library," and sends it to the terminal. A highly efficient data compression algorithm is used for communication.

[0119] Step 8:

[0120] The terminal receives the answer from the server, displays it on the display, and provides it to the user. As an input, the answer from the server is sent to the terminal. As an output, the answer is provided from the display and the speaker.

[0121] Specific behavior:

[0122] The terminal displays the answer "This is a library" on the display and plays "This is a library" aloud from the speaker. The user receives the answer through both sight and hearing.

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] Conventional virtual tour and virtual shopping systems have problems in that it is difficult for users to instantly obtain the information they need, and they are unable to get answers to their questions in real time. In addition, the experience in the virtual environment is limited, and users' needs are often not fully met. The present invention aims to solve these problems and provide a system that allows users to comfortably experience virtual campus tours and virtual stores in real time.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or inquiry while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for the server to transmit the received text data to the generative AI and start analyzing it, a means for the generative AI to analyze the received text data and generate an appropriate answer, a means for the server to receive the answer generated from the generative AI and return it to the user, a means for the terminal to display the answer from the server and provide it to the user, a means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant, and a means for the generative AI to generate an answer including detailed information about the product when the user asks a question about product information. This allows the user to freely explore the virtual environment and obtain information in real time.

[0128] A "terminal" is an information device operated by a user, and specifically includes a smartphone, smart glasses, and the like.

[0129] "Generative AI" is an artificial intelligence system that analyzes input text data and generates appropriate answers using natural language processing technology.

[0130] A "Virtual Campus Tour" is a tour program that allows a user to visit and explore a college campus in a virtual environment.

[0131] A "microphone" is an input device for detecting voice data and has the function of picking up the voice uttered by the user.

[0132] "Text data" is voice data converted into text information by a voice recognition system.

[0133] A "server" is a computer system that processes data and provides information over a network.

[0134] A "virtual shopping assistant" is a virtual support system that allows users to freely walk around a virtual store, search for products, and get answers to their questions in real time.

[0135] A "virtual store image" is an image of a store that a user can visually experience within a virtual environment.

[0136] "Free roam" refers to the user moving freely within the virtual environment and exploring it from different perspectives.

[0137] "Detailed product information" refers to specific information about the product, such as the material, specifications, functions, and price.

[0138] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0139] Generating a Program

[0140] The system that realizes this application example is composed of a program that includes a user interface, a voice recognition system, communication with the server, a generation AI, and answer provision.

[0141] System processing explanation

[0142] Overall flow

[0143] When a user operates a terminal (smartphone or smart glasses), a virtual campus tour or virtual shopping assistant is started. When a user asks a question or inquires in this virtual environment, a microphone installed in the terminal detects the voice data and the voice recognition system converts it into text data. This text data is sent to a server, where an appropriate answer is generated by the generation AI and displayed again on the terminal.

[0144] Hardware used

[0145] Smartphone or smart glasses: Acts as the user interface, showing a virtual campus tour or a virtual shopping assistant.

[0146] Microphone: Used to detect audio data.

[0147] Display and audio output devices: As part of the user interface, they present the virtual environment and generated answers to the user.

[0148] Software used

[0149] Speech recognition system (e.g. Google Cloud Speech-to-Text): Converts detected voice data into text data.

[0150] Generative AI (e.g. OpenAI ChatGPT): Analyzes input text data and generates appropriate answers.

[0151] Communication protocol (e.g. HTTP / HTTPS): Sends and receives data between the terminal and the server.

[0152] User interface software: Has display and operation functions for presenting the virtual environment and generated answers to the user.

[0153] Examples

[0154] The user launches the virtual shopping assistant using smart glasses. They can freely wander around the virtual store, and when they find a product they like, they ask aloud, "What is this product made of?" This question is picked up by a microphone and converted into text data by a voice recognition system. The text data is then sent to a server, where a generative AI analyzes it and generates an answer such as "This product is made from 100% high-quality cotton." The server sends this answer back to the device, where it is displayed in the user's field of vision.

[0155] Example prompt:

[0156] "When a user asks, 'What is this red jacket made of?' Generate a detailed description of the product's materials."

[0157] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0158] Step 1:

[0159] The user operates the device (smartphone or smart glasses) to launch the virtual shopping assistant. The image of the virtual store is displayed on the display, and the experience begins.

[0160] Step 2:

[0161] The user freely explores the virtual store and finds the product they like while viewing the virtual store image projected on the display.

[0162] Step 3:

[0163] The user asks a question about the details of the product. The user speaks a question such as "What material is this product made of?" into the microphone of the terminal.

[0164] Step 4:

[0165] The device detects a user's question through a microphone, receives voice data as input, and begins processing the voice data internally.

[0166] Step 5:

[0167] The device's voice recognition system (e.g., Google Cloud Speech-to-Text) converts the voice data into text data. The voice data is analyzed and the corresponding text data is generated. The input is voice data and the output is text data.

[0168] Step 6:

[0169] The terminal sends the converted text data to the server. The text data is sent to the server via a communication protocol (e.g. HTTP / HTTPS). The input is the text data, and the output is a confirmation of sending to the server.

[0170] Step 7:

[0171] The server sends the received text data to the AI ​​(e.g., OpenAI ChatGPT) and starts the analysis. The input is text data, and the output is the analysis result text data.

[0172] Step 8:

[0173] The generative AI analyzes the text data and generates an appropriate answer. The generative AI processes the input text data using natural language processing technology and generates an appropriate answer in text format. The input is text data, and the output is the generated answer.

[0174] Step 9:

[0175] The server receives the answer generated by the generation AI and sends it to the terminal. The input is the generated answer, and the output is a confirmation of transmission to the terminal.

[0176] Step 10:

[0177] The terminal displays the answer from the server and provides it to the user. The answer is displayed on the terminal's display, allowing the user to visually confirm the required information. The input is the generated answer, and the output is the information displayed on the display.

[0178] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0179] The embodiment for carrying out the present invention comprises the following elements.

[0180] Element 1: User Interface

[0181] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus to the display 40A, thereby projecting the image of the virtual campus into the user's field of vision.

[0182] Element 2: Detecting and Converting Audio Data

[0183] The microphone 38B of the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0184] Element 3: Combining Emotion Engines

[0185] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data and sends it to the server.

[0186] Element 4: Communication with Server

[0187] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[0188] Element 5: Generative AI to generate answers

[0189] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0190] Element 6: Providing answers

[0191] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0192] The above is an embodiment for carrying out the present invention. A user uses a terminal to experience a virtual campus tour and voice a question or doubt. The microphone 38B of the terminal detects the voice data and converts it into text data. The emotion engine recognizes the user's emotion information, converts it into text data, and sends it to the server. The server sends the text data and the emotion information text data to the generative AI, which analyzes and generates an answer that takes into account the emotion information. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes into account the user's emotion information.

[0193] The process flow will be explained below.

[0194] Step 1: Navigate the User Interface

[0195] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus to the display 40A, thereby projecting the image of the virtual campus into the user's field of vision.

[0196] Step 2: Detect and convert audio data

[0197] The microphone 38B of the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0198] Step 3: Recognizing and transforming emotional information using the emotion engine

[0199] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data.

[0200] Step 4: Communicating with the Server

[0201] The device sends the converted text data and the text data of emotion information to the server. The server sends the received text data to the generative AI for analysis.

[0202] Step 5: Generative AI generates answers

[0203] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0204] Step 6: Provide your answer

[0205] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0206] The above is a specific flow of the program's processing. The user operates the terminal to start a virtual campus tour and voices a question or doubt. The terminal's microphone 38B detects the voice data and converts it into text data. At the same time, the emotion engine recognizes the user's emotional information and converts it into text data. The text data and the emotional information text data are sent to the server, where the generative AI analyzes it and generates an answer that takes the emotional information into consideration. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes the user's emotional information into consideration.

[0207] Example 2

[0208] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0209] With the recent advancement of information technology, real-time interactive experiences are now required in educational environments. Especially in virtual campus tours, it is necessary to provide prompt and appropriate answers to the doubts and questions that users have. However, conventional systems have difficulty in providing answers that take into account the user's emotional information, which limits the user experience.

[0210] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for the terminal to display an image of a virtual campus on a display, a means for the voice input device of the terminal to detect voice data, a means for the terminal to convert the detected voice data into text data, a means for the emotion analysis device of the terminal to recognize the user's emotion information and convert it into text data, a means for the terminal to transmit the text data and the emotion information to the server, a means for the server to transmit the received text data and the emotion information to the generative AI model and start the analysis, a means for the generative AI model to analyze the received text data and the emotion information and generate an appropriate answer taking into account the emotion information, a means for the server to receive the answer generated from the generative AI model and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate answer taking into account the user's emotion information in real time.

[0211] A "terminal" is an electronic device that starts a virtual campus tour when operated by a user, and detects, processes, and displays voice data and emotional information.

[0212] A "display" is an image display device mounted on a terminal, and is a device for presenting an image of the virtual campus to a user.

[0213] The "voice input device" is a device such as a microphone mounted on a terminal, and is a device for detecting the user's speech as voice data.

[0214] "Voice data" refers to a digital recording of a user's speech that is detected by a terminal's voice input device.

[0215] "Text data" refers to character string data that is generated by analyzing and converting voice data using a voice recognition system.

[0216] An "emotion analysis device" is a device that recognizes emotional information from the content of a user's speech and facial expressions and converts it into text data.

[0217] "Emotion information" is data indicating the emotional state recognized from the user's speech and facial expressions.

[0218] The "server" is a central processing unit that receives the text data and emotion information sent from the terminal, sends it to the generative AI model for analysis, and returns the generated answer to the user.

[0219] A "generative AI model" is an artificial intelligence system that analyzes text data and emotional information sent from the server and generates appropriate answers that take the emotional information into account.

[0220] A "virtual campus tour" is an interactive simulated experience in which users can walk around a virtual campus through their devices and ask questions or concerns.

[0221] The embodiment of the present invention is a system that allows a user to experience a virtual campus tour using a terminal and to provide appropriate answers in real time that take into account the user's emotional information by vocalizing questions and doubts. The present invention is mainly composed of the following elements.

[0222] User Interface

[0223] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus through the display device, providing the image of the virtual campus within the user's field of vision. This allows the user to experience a realistic campus tour.

[0224] Audio data detection and conversion

[0225] A voice input device (e.g., a microphone) of the terminal detects voice data of questions or doubts uttered by the user during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal. For example, if the user says, "Please tell me the history of this building," the voice recognition system converts the voice data into text data saying, "Please tell me the history of this building."

[0226] Emotion analysis

[0227] The emotion analysis device of the terminal recognizes emotion information from the user's speech and facial expressions. This emotion information is converted into text data and sent to the server. For example, if the user has an interesting expression, the emotion information is converted into text data as "interesting."

[0228] Communicating with the Server

[0229] The device sends text data and emotion information to the server, which receives the data and sends it to the generative AI model to begin analysis.

[0230] Answer generation using generative AI models

[0231] The generative AI model analyzes the received text data and emotional information and generates appropriate answers that take the emotional information into account. For example, if a user asks, "What is the history of this building?", the generative AI model generates an answer such as, "This building was built in the 1950s and is mainly used for student activities."

[0232] Providing answers

[0233] The server sends the generated answer to the terminal, which displays it to the user, allowing the user to proceed with the virtual campus tour with a better understanding.

[0234] As a specific example, if a user asks "What kind of library is this?" during a virtual campus tour, the device's voice input device detects the question, and the voice recognition system converts it into text data saying "What kind of library is this?". The emotion analysis device recognizes the user's facial expression as "curious" and converts it into text data as emotional information. This text data and emotional information are sent to the server, and the generative AI model generates a detailed answer such as "This library has many rare books and is an ideal place for students to study and research." The server sends this answer to the device, which displays it to the user.

[0235] An example of a prompt for a generative AI model is:

[0236] "A user asks a curious question to learn more about a particular library during a virtual campus tour: 'What kind of library is this?'. The sentiment analyzer detects the user's curiosity. With this information, your generative AI model can generate a detailed and interesting answer."

[0237] In this way, the system of the present invention is able to provide answers that take into account the user's emotional information in real time.

[0238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0239] Step 1:

[0240] The user operates the terminal to start the virtual campus tour. When the user inputs a command to start the tour, the terminal starts displaying an image of the virtual campus on the display. The input at this stage is the user's command to start the tour, and the output is an image of the virtual campus. Specifically, the image data is called up from the virtual campus database held by the terminal, and is rendered on the display.

[0241] Step 2:

[0242] When a user asks a question or raises a concern while walking around the virtual campus, the terminal's voice input device (microphone) detects the voice data. At this stage, the input is the voice data generated by the user, and the output is the detected voice signal. The terminal captures the user's speech in real time through the microphone.

[0243] Step 3:

[0244] The voice recognition system in the terminal converts the detected voice data into text data. At this stage, the input is voice data and the output is text data. For example, if a user asks, "What is this building?", the voice recognition system analyzes the voice data and generates the text data, "What is this building?". Specific operations include the process of converting the voice signal into a string of characters using an acoustic model and a speech model.

[0245] Step 4:

[0246] The emotion analysis device on the device recognizes emotional information from the user's speech and facial expressions, and converts it into text data. The input at this stage is the user's speech and facial expression data, and the output is text data of emotional information. For example, if the emotion analysis device determines that the user's facial expression when asking a question looks interesting, the emotional information of "interesting" is converted into text data. Specifically, deep learning is used to analyze facial expressions and tone of voice.

[0247] Step 5:

[0248] The terminal transmits text data and emotion information to the server. At this stage, the input is text data and emotion information, and the output is data transmission to the server. The terminal transmits these data to the server using a secure TCP / IP communication protocol.

[0249] Step 6:

[0250] The server sends the received text data and emotion information to the generative AI model and starts the analysis. At this stage, the input is text data and emotion information, and the output is sending data to the generative AI model. The server packages these data into an appropriate format and passes them to the generative AI model.

[0251] Step 7:

[0252] The generative AI model analyzes the received text data and emotional information and generates an appropriate answer that takes the emotional information into account. The input at this stage is text data and emotional information, and the output is the generated answer. For example, a generative AI model that receives the question "What is this building?" and the emotional information "interesting" generates the answer "This building was built in the 1950s and is used for many student activities." Specifically, an algorithm that combines natural language processing and emotional analysis is used.

[0253] Step 8:

[0254] The server sends the generated answer to the terminal, which displays it to the user. The input at this stage is the generated answer, and the output is the display of the answer to the user. The server uses the TCP / IP communication protocol to send data to the terminal, which renders the answer on the display. Specifically, text data is displayed on the screen, and is provided to the user in an easily readable format.

[0255] These steps enable users to receive real-time responses that take affective information into account during their virtual campus tour.

[0256] (Application example 2)

[0257] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0258] Conventional virtual tour systems were unable to generate responses based on the user's emotions, resulting in inconsistent quality of experience for the user. In addition, when a user utters a question or doubt by voice, there was a lack of a means to provide an appropriate response that takes into account the user's emotions. As a result, the satisfaction and interest felt by the user could decrease.

[0259] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0260] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or doubt while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for an emotion engine to recognize the user's emotion information, convert it into text data and send it to the server, a means for sending the text data and the emotion information text data received by the server to the generative AI and starting analysis, a means for the generative AI to analyze the received text data and emotion information and generate an appropriate answer, a means for the server to receive the answer generated by the generative AI and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate response that takes into account the user's emotion information.

[0261] "User" refers to a person who uses the system.

[0262] A "terminal" refers to a device that includes a user interface and a microphone and is operated by a user.

[0263] A "virtual campus tour" refers to an experience that allows you to wander around a virtual environment and gain information.

[0264] A "microphone" is a device for detecting audio data.

[0265] "Voice data" refers to voice uttered by a user collected as digital information.

[0266] "Text data" is voice data expressed as character information.

[0267] The "emotion engine" is a system that recognizes emotional information from the user's facial expressions and tone of voice and converts it into text data.

[0268] A "server" is a central communication device for receiving and processing text data and emotion information.

[0269] "Generative AI" is an artificial intelligence system that generates appropriate answers based on input data.

[0270] "Response" refers to the answer generated by generative AI.

[0271] In order to implement this invention, a terminal, an emotion engine, a server, and a generative AI are mainly used. Each element and its specific processing content will be explained below.

[0272] Hardware and Software Used

[0273] Hardware:

[0274] In-car microphone

[0275] Smart displays installed in taxis

[0276] In-vehicle computing units

[0277] software:

[0278] Speech recognition systems (e.g. Google Cloud Speech-to-Text)

[0279] Emotion recognition engine (e.g. Affectiva SDK)

[0280] Client-server protocols (e.g. REST API)

[0281] Generative AI (e.g. OpenAI ChatGPT)

[0282] System processing overview

[0283] The terminal collects the user's voice data using a microphone installed in the vehicle. This voice data is converted into text data by a computing unit installed in the taxi using a voice recognition system. At the same time, an emotion recognition engine analyzes the user's facial expressions and tone of voice using the camera and microphone in the vehicle to obtain emotion information. The obtained emotion information is also converted into text data.

[0284] The device then sends the text data and emotion information to a server. The server then sends the data to a generative AI to begin analysis. The generative AI then takes the voice data and emotion information into account to generate an appropriate answer. The answer is then sent to the device via the server, and is finally provided to the user via a smart display or speaker in the taxi.

[0285] Examples

[0286] For example, if a passenger asks, "What's the weather like today?" and the emotion recognition engine determines from the passenger's tone of voice that they sound tired, the generative AI will generate a response such as, "It's sunny today, but I hear you've been busy lately. It might be a good idea to relax for a bit."

[0287] Example of a prompt to be input to a generative AI model:

[0288] Q: What's the weather like today?

[0289] Emotional information: Tired

[0290] In this way, we can build a system that can provide responses that take into account the user's emotions. This system is expected to improve the user's experience in an autonomous taxi and increase satisfaction.

[0291] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0292] Step 1:

[0293] The user speaks a question

[0294] A user utters a voice question while in the car, such as "What's the weather like today?"

[0295] Input: User's voice

[0296] Output: Microphone collects audio data

[0297] Step 2:

[0298] The device collects voice data

[0299] A microphone installed in the terminal collects voice data uttered by the user.

[0300] Input: Raw audio data

[0301] Output: Digital audio data

[0302] Step 3:

[0303] Converting audio data to text

[0304] The voice data collected by the device is converted into text data using a voice recognition system (e.g., Google Cloud Speech-to-Text).

[0305] Input: Digital audio data

[0306] Output: Text data (e.g. "What's the weather today?")

[0307] Step 4:

[0308] Emotional information recognition

[0309] The emotion engine (e.g. Affectiva SDK) analyzes the user's tone of voice and facial expressions, recognizes emotional information, and converts it into text data.

[0310] Input: Digital audio data and camera footage

[0311] Output: Emotional information text data (e.g. "Tired")

[0312] Step 5:

[0313] Text data and emotion information are sent to the server

[0314] The device transmits text data and emotion information to the server.

[0315] Input: Text data, emotion information text data

[0316] Output: Send data to the server

[0317] Step 6:

[0318] The server sends the received data to the generative AI

[0319] The server sends the received text data and emotion information to the generative AI (e.g., OpenAI ChatGPT).

[0320] Input: Text data, emotion information text data

[0321] Output: Send data to generative AI

[0322] Step 7:

[0323] Answer generation by generative AI

[0324] The generative AI analyzes the text data and emotional information it receives and generates an appropriate answer.

[0325] Input: Text data (e.g., "What is the weather today?"), emotion information (e.g., "I'm tired")

[0326] Output: Answer that takes into account emotional information (e.g. "It's sunny today, but I've heard you've been busy lately. Maybe it would be good for you to relax a bit.")

[0327] Step 8:

[0328] The server generates the answer and sends it to the device.

[0329] The server receives the answer generated by the generative AI and sends it to the terminal.

[0330] Input: Answer generated by generative AI

[0331] Output: Sending data to the terminal

[0332] Step 9:

[0333] The device displays the answer to the user

[0334] The answers received by the device are provided to the user via a smart display or speaker.

[0335] Input: Answer generated by generative AI

[0336] Output: Providing a voice or text response to the user

[0337] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0338] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0339] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0340] [Second embodiment]

[0341] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0342] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0343] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0344] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52. The smart glasses 214 also include a display (not shown).

[0345] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0346] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0347] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0348] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0349] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0350] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0351] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0352] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0353] The embodiment for carrying out the present invention comprises the following elements.

[0354] Element 1: User Interface

[0355] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus on a display (not shown), thereby projecting the image of the virtual campus into the user's field of vision.

[0356] Element 2: Detecting and Converting Audio Data

[0357] A microphone 238 mounted on the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0358] Element 3: Communication with Server

[0359] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0360] Element 4: Generative AI to generate answers

[0361] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0362] Element 5: Providing answers

[0363] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0364] With the above elements, in the embodiment of the present invention, a user experiences a virtual campus tour using a terminal, and when he or she asks a question or concerns, the voice data is detected and converted into text data. A generative AI analyzes the data through communication with a server, generates an appropriate answer, and provides it to the user. This allows students considering studying abroad to obtain information about the university and campus of their choice in real time.

[0365] The process flow will be explained below.

[0366] Step 1: Navigate the User Interface

[0367] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus on a display (not shown), thereby projecting the image of the virtual campus into the user's field of vision.

[0368] Step 2: Detect and convert audio data

[0369] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0370] Step 3: Communicating with the Server

[0371] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0372] Step 4: Generative AI generates answers

[0373] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0374] Step 5: Provide your answer

[0375] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0376] The above is a specific flow of the program's processing. The user operates the terminal to start the virtual campus tour and voices a question or doubt. The terminal's microphone 238 detects the voice data and converts it into text data. The text data is sent to the server, where the generative AI analyzes it and generates an answer. The server sends the answer to the terminal, where it is provided to the user.

[0377] Example 1

[0378] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0379] In the modern education system, it is difficult for students to understand the facilities and environment of a campus without actually visiting it. In particular, for students considering studying abroad, the means to obtain detailed information about the university before traveling are limited, making it difficult to make a decision. To solve this situation, virtual campus tours are required. However, there is an issue that mere video and text information cannot respond to students' specific questions in real time.

[0380] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0381] In this invention, the server includes a means for transferring the received text data to an analysis device and starting the analysis, a means for the analysis device to analyze the received text data and generate an appropriate answer using natural language processing technology, and a means for the server to receive the generated answer and return it to the terminal via the communication network. This allows students to use the terminal to experience a virtual campus tour and obtain appropriate answers to their questions and doubts in real time.

[0382] A "user" is a person who operates a terminal to experience a virtual campus tour.

[0383] A "terminal" is an electronic device that provides a virtual campus tour through a user interface, detects voice data, and transmits and receives data.

[0384] A "virtual campus tour" is an online tour that simulates a real campus and that users experience through their devices.

[0385] A "display" refers to a display device that is connected to a terminal and visually presents an image of the virtual campus and generated answers to a user.

[0386] The "acquisition device" refers to a hardware component that is installed in a terminal and detects voice data uttered by a user.

[0387] "Voice data" refers to voice signals of questions or doubts uttered by a user during a virtual campus tour.

[0388] "Speech recognition technology" refers to technology that analyzes voice data detected by a capture device and converts it into text data.

[0389] "Text data" refers to data that expresses a user's question or inquiry as text, converted using voice recognition technology.

[0390] A "communications network" refers to the infrastructure for transmitting and receiving data between terminals and servers.

[0391] "Server" refers to a central processing unit for analyzing text data received from a terminal and providing generated answers.

[0392] An "analysis device" refers to a device or system that resides within a server and that analyzes text data and generates appropriate answers.

[0393] "Natural language processing technology" refers to technology that enables an analysis device to understand text data and generate appropriate answers in a format that humans can understand.

[0394] An "answer" is text data or voice data generated by the analysis device with the aim of providing appropriate information to a user's question or inquiry.

[0395] A "display device" is a device that is connected to a terminal and that visually presents the generated answers to a user.

[0396] The embodiment of the present invention utilizes a terminal equipped with a user interface. This terminal starts a virtual campus tour when operated by a user, and outputs an image of the virtual campus on a display. The user can visually enjoy this image. Specific hardware that can be used includes a smartphone, tablet, and PC.

[0397] Any questions or concerns that users may have during the virtual campus tour are captured as voice data by a capture device, i.e., a microphone, installed on the device. This voice data is converted to text data using speech recognition technology within the device, such as the Google Cloud Speech-to-Text API. This makes the user's comments available for analysis as text information.

[0398] The converted text data is then sent from the device over a communications network to a server that runs on Amazon Web Services (AWS) or another cloud computing platform. The server then forwards the text data to an analysis device, which then uses a generative AI model, such as OpenAI's ChatGPT, a natural language processing technology, to generate an appropriate response.

[0399] The generated answer is sent back to the terminal via the server and is displayed on the terminal's display device. In some cases, the answer can be provided aloud using the terminal's speaker.

[0400] As a concrete example, consider the following scenario: A user starts a virtual campus tour using a smartphone, and while watching the campus image projected on the display, asks, "What is this building?" This question is detected by a microphone and converted into text data using voice recognition technology. The converted text data is sent to a server, and a generative AI model generates an answer, "This is a library." This answer is then sent to the device and provided to the user via the display and speaker.

[0401] And here is an example of a prompt to be input to the generative AI model:

[0402] Example prompt 1:

[0403] "When a user asks, 'What building is this?' during a virtual campus tour, generate an appropriate response."

[0404] Example prompt 2:

[0405] "Generate real-time answers to the question 'Where are the student dorms?' during a virtual campus tour."

[0406] The above is a specific embodiment of the present invention. By using this system, users can obtain detailed information in response to their questions in real time without actually visiting the campus, which can support their decision-making when considering studying abroad.

[0407] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0408] Step 1:

[0409] A user operates a terminal to start a virtual campus tour. As input, the user's operation information (e.g., clicking a button) is sent to the terminal. As output, the terminal projects an image of the virtual campus onto the display.

[0410] Specific behavior:

[0411] The user starts the dedicated smartphone app and taps the "Start Campus Tour" button, which causes the app to acquire user operation information and display a virtual campus image on the display.

[0412] Step 2:

[0413] The voice data of questions and doubts uttered by the user during the virtual campus tour is detected by a capture device (microphone) installed on the terminal. As input, the user's voice is sent to the microphone. As output, the detected voice data is generated.

[0414] Specific behavior:

[0415] When a user asks, "What building is this?", the device's microphone immediately detects the voice, and the capture device activates the noise canceling function to capture high-quality voice data.

[0416] Step 3:

[0417] A voice recognition system in the terminal converts the detected voice data into text data. As input, the voice data is sent to the voice recognition system. As output, text data is generated.

[0418] Specific behavior:

[0419] The device's voice recognition system converts the voice data "What is this building?" into text data "What is this building?" using a voice recognition library such as the Google Cloud Speech-to-Text API.

[0420] Step 4:

[0421] The terminal transmits the converted text data to the server via the communication network. As input, the text data is transmitted from the terminal to the server. As output, the server receives the text data.

[0422] Specific behavior:

[0423] The terminal sends the text data "What is this building?" to the server using the HTTPS protocol. The server receives this data and adds it to the processing queue.

[0424] Step 5:

[0425] The server transfers the received text data to the analysis device and starts the analysis. As input, the text data received by the server is sent to the analysis device. As output, the analysis result is generated.

[0426] Specific behavior:

[0427] The server prepares the text data "What is this building?" to be passed to the generative AI model, which then performs the analysis. For example, it uses OpenAI's ChatGPT for natural language processing.

[0428] Step 6:

[0429] The analysis device analyzes the text data and generates an appropriate answer using natural language processing techniques. As input, the text data is sent to the analysis device. As output, the generated answer is sent to the server.

[0430] Specific behavior:

[0431] Based on the text data "What is this building?", the generative AI model references its internal database and knowledge base to generate the answer "This is a library."

[0432] Step 7:

[0433] The server receives the generated answer and returns it to the terminal via the communication network. As an input, the generated answer is sent to the server. As an output, the server sends the answer to the terminal.

[0434] Specific behavior:

[0435] The server receives the answer from the generative AI model, "This is a library," and sends it to the terminal. A highly efficient data compression algorithm is used for communication.

[0436] Step 8:

[0437] The terminal receives the answer from the server, displays it on the display, and provides it to the user. As an input, the answer from the server is sent to the terminal. As an output, the answer is provided from the display and the speaker.

[0438] Specific behavior:

[0439] The terminal displays the answer "This is a library" on the display and plays "This is a library" aloud from the speaker. The user receives the answer through both sight and hearing.

[0440] (Application example 1)

[0441] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0442] Conventional virtual tour and virtual shopping systems have problems in that it is difficult for users to instantly obtain the information they need, and they are unable to get answers to their questions in real time. In addition, the experience in the virtual environment is limited, and users' needs are often not fully met. The present invention aims to solve these problems and provide a system that allows users to comfortably experience virtual campus tours and virtual stores in real time.

[0443] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0444] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or inquiry while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for the server to transmit the received text data to the generative AI and start analyzing it, a means for the generative AI to analyze the received text data and generate an appropriate answer, a means for the server to receive the answer generated from the generative AI and return it to the user, a means for the terminal to display the answer from the server and provide it to the user, a means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant, and a means for the generative AI to generate an answer including detailed information about the product when the user asks a question about product information. This allows the user to freely explore the virtual environment and obtain information in real time.

[0445] A "terminal" is an information device operated by a user, and specifically includes a smartphone, smart glasses, and the like.

[0446] "Generative AI" is an artificial intelligence system that analyzes input text data and generates appropriate answers using natural language processing technology.

[0447] A "Virtual Campus Tour" is a tour program that allows a user to visit and explore a college campus in a virtual environment.

[0448] A "microphone" is an input device for detecting voice data and has the function of picking up the voice uttered by the user.

[0449] "Text data" is voice data converted into text information by a voice recognition system.

[0450] A "server" is a computer system that processes data and provides information over a network.

[0451] A "virtual shopping assistant" is a virtual support system that allows users to freely walk around a virtual store, search for products, and get answers to their questions in real time.

[0452] A "virtual store image" is an image of a store that a user can visually experience within a virtual environment.

[0453] "Free roam" refers to the user moving freely within the virtual environment and exploring it from different perspectives.

[0454] "Detailed product information" refers to specific information about the product, such as the material, specifications, functions, and price.

[0455] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0456] Generating a Program

[0457] The system that realizes this application example is composed of a program that includes a user interface, a voice recognition system, communication with a server, a generation AI, and answer provision.

[0458] System processing explanation

[0459] Overall flow

[0460] When a user operates a terminal (smartphone or smart glasses), a virtual campus tour or virtual shopping assistant is started. When a user asks a question or inquires in this virtual environment, a microphone installed in the terminal detects the voice data and the voice recognition system converts it into text data. This text data is sent to a server, where an appropriate answer is generated by the generation AI and displayed again on the terminal.

[0461] Hardware used

[0462] Smartphone or smart glasses: Acts as the user interface, showing a virtual campus tour or a virtual shopping assistant.

[0463] Microphone: Used to detect audio data.

[0464] Display and audio output devices: As part of the user interface, they present the virtual environment and generated answers to the user.

[0465] Software used

[0466] Speech recognition system (e.g. Google Cloud Speech-to-Text): Converts detected voice data into text data.

[0467] Generative AI (e.g. OpenAI ChatGPT): Analyzes input text data and generates appropriate answers.

[0468] Communication protocol (e.g. HTTP / HTTPS): Sends and receives data between the terminal and the server.

[0469] User interface software: Has display and operation functions for presenting the virtual environment and generated answers to the user.

[0470] Examples

[0471] The user launches the virtual shopping assistant using smart glasses. They can freely wander around the virtual store, and when they find a product they like, they ask aloud, "What is this product made of?" This question is picked up by a microphone and converted into text data by a voice recognition system. The text data is then sent to a server, where a generative AI analyzes it and generates an answer such as "This product is made from 100% high-quality cotton." The server sends this answer back to the device, where it is displayed in the user's field of vision.

[0472] Example prompt:

[0473] "When a user asks, 'What is this red jacket made of?' Generate a detailed description of the product's materials."

[0474] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0475] Step 1:

[0476] The user operates the device (smartphone or smart glasses) to launch the virtual shopping assistant. The image of the virtual store is displayed on the display, and the experience begins.

[0477] Step 2:

[0478] The user freely explores the virtual store and finds the product they like while viewing the virtual store image projected on the display.

[0479] Step 3:

[0480] The user asks a question about the details of the product. The user speaks a question such as "What material is this product made of?" into the microphone of the terminal.

[0481] Step 4:

[0482] The device detects a user's question through a microphone, receives voice data as input, and begins processing the voice data internally.

[0483] Step 5:

[0484] The device's voice recognition system (e.g., Google Cloud Speech-to-Text) converts the voice data into text data. The voice data is analyzed and the corresponding text data is generated. The input is voice data and the output is text data.

[0485] Step 6:

[0486] The terminal sends the converted text data to the server. The text data is sent to the server via a communication protocol (e.g. HTTP / HTTPS). The input is the text data, and the output is a confirmation of sending to the server.

[0487] Step 7:

[0488] The server sends the received text data to the AI ​​(e.g., OpenAI ChatGPT) and starts the analysis. The input is text data, and the output is the analysis result text data.

[0489] Step 8:

[0490] The generative AI analyzes the text data and generates an appropriate answer. The generative AI processes the input text data using natural language processing technology and generates an appropriate answer in text format. The input is text data, and the output is the generated answer.

[0491] Step 9:

[0492] The server receives the answer generated by the generation AI and sends it to the terminal. The input is the generated answer, and the output is a confirmation of transmission to the terminal.

[0493] Step 10:

[0494] The terminal displays the answer from the server and provides it to the user. The answer is displayed on the terminal's display, allowing the user to visually confirm the required information. The input is the generated answer, and the output is the information displayed on the display.

[0495] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0496] The embodiment for carrying out the present invention comprises the following elements.

[0497] Element 1: User Interface

[0498] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus on a display (not shown), thereby projecting the image of the virtual campus into the user's field of vision.

[0499] Element 2: Detecting and Converting Audio Data

[0500] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0501] Element 3: Combining Emotion Engines

[0502] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data and sends it to the server.

[0503] Element 4: Communication with Server

[0504] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[0505] Element 5: Generative AI to generate answers

[0506] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0507] Element 6: Providing answers

[0508] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0509] The above is an embodiment for carrying out the present invention. A user uses a terminal to experience a virtual campus tour and voices questions and doubts. The microphone 238 of the terminal detects the voice data and converts it into text data. The emotion engine recognizes the user's emotion information, converts it into text data, and sends it to the server. The server sends the text data and the emotion information text data to the generative AI, which analyzes it and generates an answer that takes into account the emotion information. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes into account the user's emotion information.

[0510] The process flow will be explained below.

[0511] Step 1: Navigate the User Interface

[0512] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus on a display (not shown), thereby projecting the image of the virtual campus into the user's field of vision.

[0513] Step 2: Detect and convert audio data

[0514] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0515] Step 3: Recognizing and transforming emotional information using the emotion engine

[0516] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data.

[0517] Step 4: Communicating with the Server

[0518] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[0519] Step 5: Generative AI generates answers

[0520] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0521] Step 6: Provide your answer

[0522] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0523] The above is a specific flow of the program's processing. The user operates the terminal to start a virtual campus tour and voices a question or doubt. The microphone 238 of the terminal detects the voice data and converts it into text data. At the same time, the emotion engine recognizes the user's emotional information and converts it into text data. The text data and the emotional information text data are sent to the server, where the generative AI analyzes it and generates an answer that takes the emotional information into consideration. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes the user's emotional information into consideration.

[0524] Example 2

[0525] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0526] With the recent advancement of information technology, real-time interactive experiences are now required in educational environments. Especially in virtual campus tours, it is necessary to provide prompt and appropriate answers to the doubts and questions that users have. However, conventional systems have difficulty in providing answers that take into account the user's emotional information, which limits the user experience.

[0527] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for the terminal to display an image of a virtual campus on a display, a means for the voice input device of the terminal to detect voice data, a means for the terminal to convert the detected voice data into text data, a means for the emotion analysis device of the terminal to recognize the user's emotion information and convert it into text data, a means for the terminal to transmit the text data and the emotion information to the server, a means for the server to transmit the received text data and the emotion information to the generative AI model and start the analysis, a means for the generative AI model to analyze the received text data and the emotion information and generate an appropriate answer taking into account the emotion information, a means for the server to receive the answer generated from the generative AI model and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate answer taking into account the user's emotion information in real time.

[0528] A "terminal" is an electronic device that starts a virtual campus tour when operated by a user, and detects, processes, and displays voice data and emotional information.

[0529] A "display" is an image display device mounted on a terminal, and is a device for presenting an image of the virtual campus to a user.

[0530] The "voice input device" is a device such as a microphone mounted on a terminal, and is a device for detecting the user's speech as voice data.

[0531] "Voice data" refers to a digital recording of a user's speech that is detected by a terminal's voice input device.

[0532] "Text data" refers to character string data that is generated by analyzing and converting voice data using a voice recognition system.

[0533] An "emotion analysis device" is a device that recognizes emotional information from the content of a user's speech and facial expressions and converts it into text data.

[0534] "Emotion information" is data indicating the emotional state recognized from the user's speech and facial expressions.

[0535] The "server" is a central processing unit that receives the text data and emotion information sent from the terminal, sends it to the generative AI model for analysis, and returns the generated answer to the user.

[0536] A "generative AI model" is an artificial intelligence system that analyzes text data and emotional information sent from the server and generates appropriate answers that take the emotional information into account.

[0537] A "virtual campus tour" is an interactive simulated experience in which users can walk around a virtual campus through their devices and ask questions or concerns.

[0538] The embodiment of the present invention is a system that allows a user to experience a virtual campus tour using a terminal and to provide appropriate answers in real time that take into account the user's emotional information by vocalizing questions and doubts. The present invention is mainly composed of the following elements.

[0539] User Interface

[0540] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus through the display device, providing the image of the virtual campus within the user's field of vision. This allows the user to experience a realistic campus tour.

[0541] Audio data detection and conversion

[0542] A voice input device (e.g., a microphone) of the terminal detects voice data of questions or doubts uttered by the user during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal. For example, if the user says, "Please tell me the history of this building," the voice recognition system converts the voice data into text data saying, "Please tell me the history of this building."

[0543] Emotion analysis

[0544] The emotion analysis device of the terminal recognizes emotion information from the user's speech and facial expressions. This emotion information is converted into text data and sent to the server. For example, if the user has an interesting expression, the emotion information is converted into text data as "interesting."

[0545] Communicating with the Server

[0546] The device sends text data and emotion information to the server, which receives the data and sends it to the generative AI model to begin analysis.

[0547] Answer generation using generative AI models

[0548] The generative AI model analyzes the received text data and emotional information and generates appropriate answers that take the emotional information into account. For example, if a user asks, "What is the history of this building?", the generative AI model generates an answer such as, "This building was built in the 1950s and is mainly used for student activities."

[0549] Providing answers

[0550] The server sends the generated answer to the terminal, which displays it to the user, allowing the user to proceed with the virtual campus tour with a better understanding.

[0551] As a specific example, if a user asks "What kind of library is this?" during a virtual campus tour, the device's voice input device detects the question, and the voice recognition system converts it into text data saying "What kind of library is this?". The emotion analysis device recognizes the user's facial expression as "curious" and converts it into text data as emotional information. This text data and emotional information are sent to the server, and the generative AI model generates a detailed answer such as "This library has many rare books and is an ideal place for students to study and research." The server sends this answer to the device, which displays it to the user.

[0552] An example of a prompt for a generative AI model is:

[0553] "A user asks a curious question to learn more about a particular library during a virtual campus tour: 'What kind of library is this?'. The sentiment analyzer detects the user's curiosity. With this information, your generative AI model can generate a detailed and interesting answer."

[0554] In this way, the system of the present invention is able to provide answers that take into account the user's emotional information in real time.

[0555] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0556] Step 1:

[0557] The user operates the terminal to start the virtual campus tour. When the user inputs a command to start the tour, the terminal starts displaying an image of the virtual campus on the display. The input at this stage is the user's command to start the tour, and the output is an image of the virtual campus. Specifically, the image data is called up from the virtual campus database held by the terminal, and is rendered on the display.

[0558] Step 2:

[0559] When a user asks a question or raises a concern while walking around the virtual campus, the terminal's voice input device (microphone) detects the voice data. At this stage, the input is the voice data generated by the user, and the output is the detected voice signal. The terminal captures the user's speech in real time through the microphone.

[0560] Step 3:

[0561] The voice recognition system in the terminal converts the detected voice data into text data. At this stage, the input is voice data and the output is text data. For example, if a user asks, "What is this building?", the voice recognition system analyzes the voice data and generates the text data, "What is this building?". Specific operations include the process of converting the voice signal into a string of characters using an acoustic model and a speech model.

[0562] Step 4:

[0563] The emotion analysis device on the device recognizes emotional information from the user's speech and facial expressions, and converts it into text data. The input at this stage is the user's speech and facial expression data, and the output is text data of emotional information. For example, if the emotion analysis device determines that the user's facial expression when asking a question looks interesting, the emotional information of "interesting" is converted into text data. Specifically, deep learning is used to analyze facial expressions and tone of voice.

[0564] Step 5:

[0565] The terminal transmits text data and emotion information to the server. At this stage, the input is text data and emotion information, and the output is data transmission to the server. The terminal transmits these data to the server using a secure TCP / IP communication protocol.

[0566] Step 6:

[0567] The server sends the received text data and emotion information to the generative AI model and starts the analysis. At this stage, the input is text data and emotion information, and the output is sending data to the generative AI model. The server packages these data into an appropriate format and passes them to the generative AI model.

[0568] Step 7:

[0569] The generative AI model analyzes the received text data and emotional information and generates an appropriate answer that takes the emotional information into account. The input at this stage is text data and emotional information, and the output is the generated answer. For example, a generative AI model that receives the question "What is this building?" and the emotional information "interesting" generates the answer "This building was built in the 1950s and is used for many student activities." Specifically, an algorithm that combines natural language processing and emotional analysis is used.

[0570] Step 8:

[0571] The server sends the generated answer to the terminal, which displays it to the user. The input at this stage is the generated answer, and the output is the display of the answer to the user. The server uses the TCP / IP communication protocol to send data to the terminal, which renders the answer on the display. Specifically, text data is displayed on the screen, and is provided to the user in an easily readable format.

[0572] These steps enable users to receive real-time responses that take affective information into account during their virtual campus tour.

[0573] (Application example 2)

[0574] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0575] Conventional virtual tour systems were unable to generate responses based on the user's emotions, resulting in inconsistent quality of experience for the user. In addition, when a user utters a question or doubt by voice, there was a lack of a means to provide an appropriate response that takes into account the user's emotions. As a result, the satisfaction and interest felt by the user could decrease.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0577] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or doubt while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for an emotion engine to recognize the user's emotion information, convert it into text data and send it to the server, a means for sending the text data and the emotion information text data received by the server to the generative AI and starting analysis, a means for the generative AI to analyze the received text data and emotion information and generate an appropriate answer, a means for the server to receive the answer generated by the generative AI and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate response that takes into account the user's emotion information.

[0578] "User" refers to a person who uses the system.

[0579] A "terminal" refers to a device that includes a user interface and a microphone and is operated by a user.

[0580] A "virtual campus tour" refers to an experience that allows you to wander around a virtual environment and gain information.

[0581] A "microphone" is a device for detecting audio data.

[0582] "Voice data" refers to voice uttered by a user collected as digital information.

[0583] "Text data" is voice data expressed as character information.

[0584] The "emotion engine" is a system that recognizes emotional information from the user's facial expressions and tone of voice and converts it into text data.

[0585] A "server" is a central communication device for receiving and processing text data and emotion information.

[0586] "Generative AI" is an artificial intelligence system that generates appropriate answers based on input data.

[0587] "Response" refers to the answer generated by generative AI.

[0588] In order to implement this invention, a terminal, an emotion engine, a server, and a generative AI are mainly used. Each element and its specific processing content will be explained below.

[0589] Hardware and Software Used

[0590] Hardware:

[0591] In-car microphone

[0592] Smart displays installed in taxis

[0593] In-vehicle computing units

[0594] software:

[0595] Speech recognition systems (e.g. Google Cloud Speech-to-Text)

[0596] Emotion recognition engine (e.g. Affectiva SDK)

[0597] Client-server protocols (e.g. REST API)

[0598] Generative AI (e.g. OpenAI ChatGPT)

[0599] System processing overview

[0600] The terminal collects the user's voice data using a microphone installed in the vehicle. This voice data is converted into text data by a computing unit installed in the taxi using a voice recognition system. At the same time, an emotion recognition engine analyzes the user's facial expressions and tone of voice using the camera and microphone in the vehicle to obtain emotion information. The obtained emotion information is also converted into text data.

[0601] The device then sends the text data and emotion information to a server. The server then sends the data to a generative AI to begin analysis. The generative AI then takes the voice data and emotion information into account to generate an appropriate answer. The answer is then sent to the device via the server, and is finally provided to the user via a smart display or speaker in the taxi.

[0602] Examples

[0603] For example, if a passenger asks, "What's the weather like today?" and the emotion recognition engine determines from the passenger's tone of voice that they sound tired, the generative AI will generate a response such as, "It's sunny today, but I hear you've been busy lately. It might be a good idea to relax for a bit."

[0604] Example of a prompt to be input to a generative AI model:

[0605] Q: What's the weather like today?

[0606] Emotional information: Tired

[0607] In this way, we can build a system that can provide responses that take into account the user's emotions. This system is expected to improve the user's experience in an autonomous taxi and increase satisfaction.

[0608] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0609] Step 1:

[0610] The user speaks a question

[0611] A user utters a voice question while in the car, such as "What's the weather like today?"

[0612] Input: User's voice

[0613] Output: Microphone collects audio data

[0614] Step 2:

[0615] The device collects voice data

[0616] A microphone installed in the terminal collects voice data uttered by the user.

[0617] Input: Raw audio data

[0618] Output: Digital audio data

[0619] Step 3:

[0620] Converting audio data to text

[0621] The voice data collected by the device is converted into text data using a voice recognition system (e.g., Google Cloud Speech-to-Text).

[0622] Input: Digital audio data

[0623] Output: Text data (e.g. "What's the weather today?")

[0624] Step 4:

[0625] Emotional information recognition

[0626] The emotion engine (e.g. Affectiva SDK) analyzes the user's tone of voice and facial expressions, recognizes emotional information, and converts it into text data.

[0627] Input: Digital audio data and camera footage

[0628] Output: Emotional information text data (e.g. "Tired")

[0629] Step 5:

[0630] Text data and emotion information are sent to the server

[0631] The device transmits text data and emotion information to the server.

[0632] Input: Text data, emotion information text data

[0633] Output: Send data to the server

[0634] Step 6:

[0635] The server sends the received data to the generative AI

[0636] The server sends the received text data and emotion information to the generative AI (e.g., OpenAI ChatGPT).

[0637] Input: Text data, emotion information text data

[0638] Output: Send data to generative AI

[0639] Step 7:

[0640] Answer generation by generative AI

[0641] The generative AI analyzes the text data and emotional information it receives and generates an appropriate answer.

[0642] Input: Text data (e.g., "What is the weather today?"), emotion information (e.g., "I'm tired")

[0643] Output: Answer that takes into account emotional information (e.g. "It's sunny today, but I've heard you've been busy lately. Maybe it would be good for you to relax a bit.")

[0644] Step 8:

[0645] The server generates the answer and sends it to the device.

[0646] The server receives the answer generated by the generative AI and sends it to the terminal.

[0647] Input: Answer generated by generative AI

[0648] Output: Sending data to the terminal

[0649] Step 9:

[0650] The device displays the answer to the user

[0651] The answers received by the device are provided to the user via a smart display or speaker.

[0652] Input: Answer generated by generative AI

[0653] Output: Providing a voice or text response to the user

[0654] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0655] The data generation model 58 is a so-called generative AI (Artificial Intelligence).

[0656] One example of a data generation model58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image are also input. The data generation model 58 converts the input inference data into the instruction indicated by the prompt.

[0657] Therefore, inference is performed and the inference result is output in the form of data such as voice data and text data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization, etc.

[0658] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0659] [Third embodiment]

[0660] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0661] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0662] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0663] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0664] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0665] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0666] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0667] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0668] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0669] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0670] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0671] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server", and the headset type terminal 314 will be referred to as the "terminal".

[0672] The embodiment for carrying out the present invention comprises the following elements.

[0673] Element 1: User Interface

[0674] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display 343, thereby projecting the image of the virtual campus into the user's field of vision.

[0675] Element 2: Detecting and Converting Audio Data

[0676] A microphone 238 mounted on the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0677] Element 3: Communication with Server

[0678] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0679] Element 4: Generative AI to generate answers

[0680] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0681] Element 5: Providing answers

[0682] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0683] With the above elements, in the embodiment of the present invention, a user experiences a virtual campus tour using a terminal, and when he or she asks a question or concerns, the voice data is detected and converted into text data. A generative AI analyzes the data through communication with a server, generates an appropriate answer, and provides it to the user. This allows students considering studying abroad to obtain information about the university and campus of their choice in real time.

[0684] The process flow will be explained below.

[0685] Step 1: Navigate the User Interface

[0686] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display 343, thereby projecting the image of the virtual campus into the user's field of vision.

[0687] Step 2: Detect and convert audio data

[0688] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0689] Step 3: Communicating with the Server

[0690] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[0691] Step 4: Generative AI generates answers

[0692] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[0693] Step 5: Provide your answer

[0694] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0695] The above is a specific flow of the program's processing. The user operates the terminal to start the virtual campus tour and voices a question or doubt. The terminal's microphone 238 detects the voice data and converts it into text data. The text data is sent to the server, where the generative AI analyzes it and generates an answer. The server sends the answer to the terminal, where it is provided to the user.

[0696] Example 1

[0697] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[0698] In the modern education system, it is difficult for students to understand the facilities and environment of a campus without actually visiting it. In particular, for students considering studying abroad, the means to obtain detailed information about the university before traveling are limited, making it difficult to make a decision. To solve this situation, virtual campus tours are required. However, there is an issue that mere video and text information cannot respond to students' specific questions in real time.

[0699] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0700] In this invention, the server includes a means for transferring the received text data to an analysis device and starting the analysis, a means for the analysis device to analyze the received text data and generate an appropriate answer using natural language processing technology, and a means for the server to receive the generated answer and return it to the terminal via the communication network. This allows students to use the terminal to experience a virtual campus tour and obtain appropriate answers to their questions and doubts in real time.

[0701] A "user" is a person who operates a terminal to experience a virtual campus tour.

[0702] A "terminal" is an electronic device that provides a virtual campus tour through a user interface, detects voice data, and transmits and receives data.

[0703] A "virtual campus tour" is an online tour that simulates a real campus and that users experience through their devices.

[0704] A "display" refers to a display device that is connected to a terminal and visually presents an image of the virtual campus and generated answers to a user.

[0705] The "acquisition device" refers to a hardware component that is installed in a terminal and detects voice data uttered by a user.

[0706] "Voice data" refers to voice signals of questions or doubts uttered by a user during a virtual campus tour.

[0707] "Speech recognition technology" refers to technology that analyzes voice data detected by a capture device and converts it into text data.

[0708] "Text data" refers to data that expresses a user's question or inquiry as text, converted using voice recognition technology.

[0709] A "communications network" refers to the infrastructure for transmitting and receiving data between terminals and servers.

[0710] "Server" refers to a central processing unit for analyzing text data received from a terminal and providing generated answers.

[0711] An "analysis device" refers to a device or system that resides within a server and that analyzes text data and generates appropriate answers.

[0712] "Natural language processing technology" refers to technology that enables an analysis device to understand text data and generate appropriate answers in a format that humans can understand.

[0713] An "answer" is text data or voice data generated by the analysis device with the aim of providing appropriate information to a user's question or inquiry.

[0714] A "display device" is a device that is connected to a terminal and that visually presents the generated answers to a user.

[0715] The embodiment of the present invention utilizes a terminal equipped with a user interface. This terminal starts a virtual campus tour when operated by a user, and outputs an image of the virtual campus on a display. The user can visually enjoy this image. Specific hardware that can be used includes a smartphone, tablet, and PC.

[0716] Any questions or concerns that users may have during the virtual campus tour are captured as voice data by a capture device, i.e., a microphone, installed on the device. This voice data is converted to text data using speech recognition technology within the device, such as the Google Cloud Speech-to-Text API. This makes the user's comments available for analysis as text information.

[0717] The converted text data is then sent from the device over a communications network to a server that runs on Amazon Web Services (AWS) or another cloud computing platform. The server then forwards the text data to an analysis device, which then uses a generative AI model, such as OpenAI's ChatGPT, a natural language processing technology, to generate an appropriate response.

[0718] The generated answer is sent back to the terminal via the server and is displayed on the terminal's display device. In some cases, the answer can be provided aloud using the terminal's speaker.

[0719] As a concrete example, consider the following scenario: A user starts a virtual campus tour using a smartphone, and while watching the campus image projected on the display, asks, "What is this building?" This question is detected by a microphone and converted into text data using voice recognition technology. The converted text data is sent to a server, and a generative AI model generates an answer, "This is a library." This answer is then sent to the device and provided to the user via the display and speaker.

[0720] And here is an example of a prompt to be input to the generative AI model:

[0721] Example prompt 1:

[0722] "When a user asks, 'What building is this?' during a virtual campus tour, generate an appropriate response."

[0723] Example prompt 2:

[0724] "Generate real-time answers to the question 'Where are the student dorms?' during a virtual campus tour."

[0725] The above is a specific embodiment of the present invention. By using this system, users can obtain detailed information in response to their questions in real time without actually visiting the campus, which can support their decision-making when considering studying abroad.

[0726] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0727] Step 1:

[0728] A user operates a terminal to start a virtual campus tour. As input, the user's operation information (e.g., clicking a button) is sent to the terminal. As output, the terminal projects an image of the virtual campus onto the display.

[0729] Specific behavior:

[0730] The user starts the dedicated smartphone app and taps the "Start Campus Tour" button, which causes the app to acquire user operation information and display a virtual campus image on the display.

[0731] Step 2:

[0732] The voice data of questions and doubts uttered by the user during the virtual campus tour is detected by a capture device (microphone) installed on the terminal. As input, the user's voice is sent to the microphone. As output, the detected voice data is generated.

[0733] Specific behavior:

[0734] When a user asks, "What building is this?", the device's microphone immediately detects the voice, and the capture device activates the noise canceling function to capture high-quality voice data.

[0735] Step 3:

[0736] A voice recognition system in the terminal converts the detected voice data into text data. As input, the voice data is sent to the voice recognition system. As output, text data is generated.

[0737] Specific behavior:

[0738] The device's voice recognition system converts the voice data "What is this building?" into text data "What is this building?" using a voice recognition library such as the Google Cloud Speech-to-Text API.

[0739] Step 4:

[0740] The terminal transmits the converted text data to the server via the communication network. As input, the text data is transmitted from the terminal to the server. As output, the server receives the text data.

[0741] Specific behavior:

[0742] The terminal sends the text data "What is this building?" to the server using the HTTPS protocol. The server receives this data and adds it to the processing queue.

[0743] Step 5:

[0744] The server transfers the received text data to the analysis device and starts the analysis. As input, the text data received by the server is sent to the analysis device. As output, the analysis result is generated.

[0745] Specific behavior:

[0746] The server prepares the text data "What is this building?" to be passed to the generative AI model, which then performs the analysis. For example, it uses OpenAI's ChatGPT for natural language processing.

[0747] Step 6:

[0748] The analysis device analyzes the text data and generates an appropriate answer using natural language processing techniques. As input, the text data is sent to the analysis device. As output, the generated answer is sent to the server.

[0749] Specific behavior:

[0750] Based on the text data "What is this building?", the generative AI model references its internal database and knowledge base to generate the answer "This is a library."

[0751] Step 7:

[0752] The server receives the generated answer and returns it to the terminal via the communication network. As an input, the generated answer is sent to the server. As an output, the server sends the answer to the terminal.

[0753] Specific behavior:

[0754] The server receives the answer from the generative AI model, "This is a library," and sends it to the terminal. A highly efficient data compression algorithm is used for communication.

[0755] Step 8:

[0756] The terminal receives the answer from the server, displays it on the display, and provides it to the user. As an input, the answer from the server is sent to the terminal. As an output, the answer is provided from the display and the speaker.

[0757] Specific behavior:

[0758] The terminal displays the answer "This is a library" on the display and plays "This is a library" aloud from the speaker. The user receives the answer through both sight and hearing.

[0759] (Application example 1)

[0760] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0761] Conventional virtual tour and virtual shopping systems have problems in that it is difficult for users to instantly obtain the information they need, and they are unable to get answers to their questions in real time. In addition, the experience in the virtual environment is limited, and users' needs are often not fully met. The present invention aims to solve these problems and provide a system that allows users to comfortably experience virtual campus tours and virtual stores in real time.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0763] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or inquiry while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for the server to transmit the received text data to the generative AI and start analyzing it, a means for the generative AI to analyze the received text data and generate an appropriate answer, a means for the server to receive the answer generated from the generative AI and return it to the user, a means for the terminal to display the answer from the server and provide it to the user, a means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant, and a means for the generative AI to generate an answer including detailed information about the product when the user asks a question about product information. This allows the user to freely explore the virtual environment and obtain information in real time.

[0764] A "terminal" is an information device operated by a user, and specifically includes a smartphone, smart glasses, and the like.

[0765] "Generative AI" is an artificial intelligence system that analyzes input text data and generates appropriate answers using natural language processing technology.

[0766] A "Virtual Campus Tour" is a tour program that allows a user to visit and explore a college campus in a virtual environment.

[0767] A "microphone" is an input device for detecting voice data and has the function of picking up the voice uttered by the user.

[0768] "Text data" is voice data converted into text information by a voice recognition system.

[0769] A "server" is a computer system that processes data and provides information over a network.

[0770] A "virtual shopping assistant" is a virtual support system that allows users to freely walk around a virtual store, search for products, and get answers to their questions in real time.

[0771] A "virtual store image" is an image of a store that a user can visually experience within a virtual environment.

[0772] "Free roam" refers to the user moving freely within the virtual environment and exploring it from different perspectives.

[0773] "Detailed product information" refers to specific information about the product, such as the material, specifications, functions, and price.

[0774] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0775] Generating a Program

[0776] The system that realizes this application example is composed of a program that includes a user interface, a voice recognition system, communication with the server, a generation AI, and answer provision.

[0777] System processing explanation

[0778] Overall flow

[0779] When a user operates a terminal (smartphone or smart glasses), a virtual campus tour or virtual shopping assistant is started. When a user asks a question or inquires in this virtual environment, a microphone installed in the terminal detects the voice data and the voice recognition system converts it into text data. This text data is sent to a server, where an appropriate answer is generated by the generation AI and displayed again on the terminal.

[0780] Hardware used

[0781] Smartphone or smart glasses: Acts as the user interface, showing a virtual campus tour or a virtual shopping assistant.

[0782] Microphone: Used to detect audio data.

[0783] Display and audio output devices: As part of the user interface, they present the virtual environment and generated answers to the user.

[0784] Software used

[0785] Speech recognition system (e.g. Google Cloud Speech-to-Text): Converts detected voice data into text data.

[0786] Generative AI (e.g. OpenAI ChatGPT): Analyzes input text data and generates appropriate answers.

[0787] Communication protocol (e.g. HTTP / HTTPS): Sends and receives data between the terminal and the server.

[0788] User interface software: Has display and operation functions for presenting the virtual environment and generated answers to the user.

[0789] Examples

[0790] The user launches the virtual shopping assistant using smart glasses. They can freely wander around the virtual store, and when they find a product they like, they ask aloud, "What is this product made of?" This question is picked up by a microphone and converted into text data by a voice recognition system. The text data is then sent to a server, where a generative AI analyzes it and generates an answer such as "This product is made from 100% high-quality cotton." The server sends this answer back to the device, where it is displayed in the user's field of vision.

[0791] Example prompt:

[0792] "When a user asks, 'What is this red jacket made of?' Generate a detailed description of the product's materials."

[0793] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0794] Step 1:

[0795] The user operates the device (smartphone or smart glasses) to launch the virtual shopping assistant. The image of the virtual store is displayed on the display, and the experience begins.

[0796] Step 2:

[0797] The user freely explores the virtual store and finds the product they like while viewing the virtual store image projected on the display.

[0798] Step 3:

[0799] The user asks a question about the details of the product. The user speaks a question such as "What material is this product made of?" into the microphone of the terminal.

[0800] Step 4:

[0801] The device detects a user's question through a microphone, receives voice data as input, and begins processing the voice data internally.

[0802] Step 5:

[0803] The device's voice recognition system (e.g., Google Cloud Speech-to-Text) converts the voice data into text data. The voice data is analyzed and the corresponding text data is generated. The input is voice data and the output is text data.

[0804] Step 6:

[0805] The terminal sends the converted text data to the server. The text data is sent to the server via a communication protocol (e.g. HTTP / HTTPS). The input is the text data, and the output is a confirmation of sending to the server.

[0806] Step 7:

[0807] The server sends the received text data to the AI ​​(e.g., OpenAI ChatGPT) and starts the analysis. The input is text data, and the output is the analysis result text data.

[0808] Step 8:

[0809] The generative AI analyzes the text data and generates an appropriate answer. The generative AI processes the input text data using natural language processing technology and generates an appropriate answer in text format. The input is text data, and the output is the generated answer.

[0810] Step 9:

[0811] The server receives the answer generated by the generation AI and sends it to the terminal. The input is the generated answer, and the output is a confirmation of transmission to the terminal.

[0812] Step 10:

[0813] The terminal displays the answer from the server and provides it to the user. The answer is displayed on the terminal's display, allowing the user to visually confirm the required information. The input is the generated answer, and the output is the information displayed on the display.

[0814] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0815] The embodiment for carrying out the present invention comprises the following elements.

[0816] Element 1: User Interface

[0817] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display 343, thereby projecting the image of the virtual campus into the user's field of vision.

[0818] Element 2: Detecting and Converting Audio Data

[0819] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0820] Element 3: Combining Emotion Engines

[0821] The emotion engine recognizes emotion information from the user's speech and facial expressions.

[0822] The recognized emotion information is converted into text data and sent to the server.

[0823] Element 4: Communication with Server

[0824] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[0825] Element 5: Generative AI to generate answers

[0826] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0827] Element 6: Providing answers

[0828] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0829] The above is an embodiment for carrying out the present invention. A user uses a terminal to experience a virtual campus tour and voices questions and doubts. The microphone 238 of the terminal detects the voice data and converts it into text data. The emotion engine recognizes the user's emotion information, converts it into text data, and sends it to the server. The server sends the text data and the emotion information text data to the generative AI, which analyzes it and generates an answer that takes into account the emotion information. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes into account the user's emotion information.

[0830] The process flow will be explained below.

[0831] Step 1: Navigate the User Interface

[0832] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display 343, thereby projecting the image of the virtual campus into the user's field of vision.

[0833] Step 2: Detect and convert audio data

[0834] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[0835] Step 3: Recognizing and transforming emotional information using the emotion engine

[0836] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data.

[0837] Step 4: Communicating with the Server

[0838] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[0839] Step 5: Generative AI generates answers

[0840] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[0841] Step 6: Provide your answer

[0842] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[0843] The above is a specific flow of the program's processing. The user operates the terminal to start a virtual campus tour and voices a question or doubt. The microphone 238 of the terminal detects the voice data and converts it into text data. At the same time, the emotion engine recognizes the user's emotional information and converts it into text data. The text data and the emotional information text data are sent to the server, where the generative AI analyzes it and generates an answer that takes the emotional information into consideration. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes the user's emotional information into consideration.

[0844] Example 2

[0845] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[0846] With the recent advancement of information technology, real-time interactive experiences are now required in educational environments. Especially in virtual campus tours, it is necessary to provide prompt and appropriate answers to the doubts and questions that users have. However, conventional systems have difficulty in providing answers that take into account the user's emotional information, which limits the user experience.

[0847] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for the terminal to display an image of a virtual campus on a display, a means for the voice input device of the terminal to detect voice data, a means for the terminal to convert the detected voice data into text data, a means for the emotion analysis device of the terminal to recognize the user's emotion information and convert it into text data, a means for the terminal to transmit the text data and the emotion information to the server, a means for the server to transmit the received text data and the emotion information to the generative AI model and start the analysis, a means for the generative AI model to analyze the received text data and the emotion information and generate an appropriate answer taking into account the emotion information, a means for the server to receive the answer generated from the generative AI model and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate answer taking into account the user's emotion information in real time.

[0848] A "terminal" is an electronic device that starts a virtual campus tour when operated by a user, and detects, processes, and displays voice data and emotional information.

[0849] A "display" is an image display device mounted on a terminal, and is a device for presenting an image of the virtual campus to a user.

[0850] The "voice input device" is a device such as a microphone mounted on a terminal, and is a device for detecting the user's speech as voice data.

[0851] "Voice data" refers to a digital recording of a user's speech that is detected by a terminal's voice input device.

[0852] "Text data" refers to character string data that is generated by analyzing and converting voice data using a voice recognition system.

[0853] An "emotion analysis device" is a device that recognizes emotional information from the content of a user's speech and facial expressions and converts it into text data.

[0854] "Emotion information" is data indicating the emotional state recognized from the user's speech and facial expressions.

[0855] The "server" is a central processing unit that receives the text data and emotion information sent from the terminal, sends it to the generative AI model for analysis, and returns the generated answer to the user.

[0856] A "generative AI model" is an artificial intelligence system that analyzes text data and emotional information sent from the server and generates appropriate answers that take the emotional information into account.

[0857] A "virtual campus tour" is an interactive simulated experience in which users can walk around a virtual campus through their devices and ask questions or concerns.

[0858] The embodiment of the present invention is a system that allows a user to experience a virtual campus tour using a terminal and to provide appropriate answers in real time that take into account the user's emotional information by vocalizing questions and doubts. The present invention is mainly composed of the following elements.

[0859] User Interface

[0860] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus through the display device, providing the image of the virtual campus within the user's field of vision. This allows the user to experience a realistic campus tour.

[0861] Audio data detection and conversion

[0862] A voice input device (e.g., a microphone) of the terminal detects voice data of questions or doubts uttered by the user during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal. For example, if the user says, "Please tell me the history of this building," the voice recognition system converts the voice data into text data saying, "Please tell me the history of this building."

[0863] Emotion analysis

[0864] The emotion analysis device of the terminal recognizes emotion information from the user's speech and facial expressions. This emotion information is converted into text data and sent to the server. For example, if the user has an interesting expression, the emotion information is converted into text data as "interesting."

[0865] Communicating with the Server

[0866] The device sends text data and emotion information to the server, which receives the data and sends it to the generative AI model to begin analysis.

[0867] Answer generation using generative AI models

[0868] The generative AI model analyzes the received text data and emotional information and generates appropriate answers that take the emotional information into account. For example, if a user asks, "What is the history of this building?", the generative AI model generates an answer such as, "This building was built in the 1950s and is mainly used for student activities."

[0869] Providing answers

[0870] The server sends the generated answer to the terminal, which displays it to the user, allowing the user to proceed with the virtual campus tour with a better understanding.

[0871] As a specific example, if a user asks "What kind of library is this?" during a virtual campus tour, the device's voice input device detects the question, and the voice recognition system converts it into text data saying "What kind of library is this?". The emotion analysis device recognizes the user's facial expression as "curious" and converts it into text data as emotional information. This text data and emotional information are sent to the server, and the generative AI model generates a detailed answer such as "This library has many rare books and is an ideal place for students to study and research." The server sends this answer to the device, which displays it to the user.

[0872] An example of a prompt for a generative AI model is:

[0873] "A user asks a curious question to learn more about a particular library during a virtual campus tour: 'What kind of library is this?'. The sentiment analyzer detects the user's curiosity. With this information, your generative AI model can generate a detailed and interesting answer."

[0874] In this way, the system of the present invention is able to provide answers that take into account the user's emotional information in real time.

[0875] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0876] Step 1:

[0877] The user operates the terminal to start the virtual campus tour. When the user inputs a command to start the tour, the terminal starts displaying an image of the virtual campus on the display. The input at this stage is the user's command to start the tour, and the output is an image of the virtual campus. Specifically, the image data is called up from the virtual campus database held by the terminal, and is rendered on the display.

[0878] Step 2:

[0879] When a user asks a question or raises a concern while walking around the virtual campus, the terminal's voice input device (microphone) detects the voice data. At this stage, the input is the voice data generated by the user, and the output is the detected voice signal. The terminal captures the user's speech in real time through the microphone.

[0880] Step 3:

[0881] The voice recognition system in the terminal converts the detected voice data into text data. At this stage, the input is voice data and the output is text data. For example, if a user asks, "What is this building?", the voice recognition system analyzes the voice data and generates the text data, "What is this building?". Specific operations include the process of converting the voice signal into a string of characters using an acoustic model and a speech model.

[0882] Step 4:

[0883] The emotion analysis device on the device recognizes emotional information from the user's speech and facial expressions, and converts it into text data. The input at this stage is the user's speech and facial expression data, and the output is text data of emotional information. For example, if the emotion analysis device determines that the user's facial expression when asking a question looks interesting, the emotional information of "interesting" is converted into text data. Specifically, deep learning is used to analyze facial expressions and tone of voice.

[0884] Step 5:

[0885] The terminal transmits text data and emotion information to the server. At this stage, the input is text data and emotion information, and the output is data transmission to the server. The terminal transmits these data to the server using a secure TCP / IP communication protocol.

[0886] Step 6:

[0887] The server sends the received text data and emotion information to the generative AI model and starts the analysis. At this stage, the input is text data and emotion information, and the output is sending data to the generative AI model. The server packages these data into an appropriate format and passes them to the generative AI model.

[0888] Step 7:

[0889] The generative AI model analyzes the received text data and emotional information and generates an appropriate answer that takes the emotional information into account. The input at this stage is text data and emotional information, and the output is the generated answer. For example, a generative AI model that receives the question "What is this building?" and the emotional information "interesting" generates the answer "This building was built in the 1950s and is used for many student activities." Specifically, an algorithm that combines natural language processing and emotional analysis is used.

[0890] Step 8:

[0891] The server sends the generated answer to the terminal, which displays it to the user. The input at this stage is the generated answer, and the output is the display of the answer to the user. The server uses the TCP / IP communication protocol to send data to the terminal, which renders the answer on the display. Specifically, text data is displayed on the screen, and is provided to the user in an easily readable format.

[0892] These steps enable users to receive real-time responses that take affective information into account during their virtual campus tour.

[0893] (Application example 2)

[0894] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[0895] Conventional virtual tour systems were unable to generate responses based on the user's emotions, resulting in inconsistent quality of experience for the user. In addition, when a user utters a question or doubt by voice, there was a lack of a means to provide an appropriate response that takes into account the user's emotions. As a result, the satisfaction and interest felt by the user could decrease.

[0896] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0897] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or doubt while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for an emotion engine to recognize the user's emotion information, convert it into text data and send it to the server, a means for sending the text data and the emotion information text data received by the server to the generative AI and starting analysis, a means for the generative AI to analyze the received text data and emotion information and generate an appropriate answer, a means for the server to receive the answer generated by the generative AI and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate response that takes into account the user's emotion information.

[0898] "User" refers to a person who uses the system.

[0899] A "terminal" refers to a device that includes a user interface and a microphone and is operated by a user.

[0900] A "virtual campus tour" refers to an experience that allows you to wander around a virtual environment and gain information.

[0901] A "microphone" is a device for detecting audio data.

[0902] "Voice data" refers to voice uttered by a user collected as digital information.

[0903] "Text data" is voice data expressed as character information.

[0904] The "emotion engine" is a system that recognizes emotional information from the user's facial expressions and tone of voice and converts it into text data.

[0905] A "server" is a central communication device for receiving and processing text data and emotion information.

[0906] "Generative AI" is an artificial intelligence system that generates appropriate answers based on input data.

[0907] "Response" refers to the answer generated by generative AI.

[0908] In order to implement this invention, a terminal, an emotion engine, a server, and a generative AI are mainly used. Each element and its specific processing content will be explained below.

[0909] Hardware and Software Used

[0910] Hardware:

[0911] In-vehicle microphone

[0912] Smart displays installed in taxis

[0913] In-vehicle computing units

[0914] software:

[0915] Speech recognition systems (e.g. Google Cloud Speech-to-Text)

[0916] Emotion recognition engine (e.g. Affectiva SDK)

[0917] Client-server protocols (e.g. REST API)

[0918] Generative AI (e.g. OpenAI ChatGPT)

[0919] System processing overview

[0920] The terminal collects the user's voice data using a microphone installed in the vehicle. This voice data is converted into text data by a computing unit installed in the taxi using a voice recognition system. At the same time, an emotion recognition engine analyzes the user's facial expressions and tone of voice using the camera and microphone in the vehicle to obtain emotion information. The obtained emotion information is also converted into text data.

[0921] The device then sends the text data and emotion information to a server. The server then sends the data to a generative AI to begin analysis. The generative AI then takes the voice data and emotion information into account to generate an appropriate answer. The answer is then sent to the device via the server, and is finally provided to the user via a smart display or speaker in the taxi.

[0922] Examples

[0923] For example, if a passenger asks, "What's the weather like today?" and the emotion recognition engine determines from the passenger's tone of voice that they sound tired, the generative AI will generate a response such as, "It's sunny today, but I hear you've been busy lately. It might be a good idea to relax for a bit."

[0924] Example of a prompt to be input to a generative AI model:

[0925] Q: What's the weather like today?

[0926] Emotional information: Tired

[0927] In this way, we can build a system that can provide responses that take into account the user's emotions. This system is expected to improve the user's experience in an autonomous taxi and increase satisfaction.

[0928] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0929] Step 1:

[0930] The user speaks a question

[0931] A user utters a voice question while in the car, such as "What's the weather like today?"

[0932] Input: User's voice

[0933] Output: Microphone collects audio data

[0934] Step 2:

[0935] The device collects voice data

[0936] A microphone installed in the terminal collects voice data uttered by the user.

[0937] Input: Raw audio data

[0938] Output: Digital audio data

[0939] Step 3:

[0940] Converting audio data to text

[0941] The voice data collected by the device is converted into text data using a voice recognition system (e.g., Google Cloud Speech-to-Text).

[0942] Input: Digital audio data

[0943] Output: Text data (e.g. "What's the weather today?")

[0944] Step 4:

[0945] Emotional information recognition

[0946] The emotion engine (e.g. Affectiva SDK) analyzes the user's tone of voice and facial expressions, recognizes emotional information, and converts it into text data.

[0947] Input: Digital audio data and camera footage

[0948] Output: Emotional information text data (e.g. "Tired")

[0949] Step 5:

[0950] Text data and emotion information are sent to the server

[0951] The device transmits text data and emotion information to the server.

[0952] Input: Text data, emotion information text data

[0953] Output: Send data to the server

[0954] Step 6:

[0955] The server sends the received data to the generative AI

[0956] The server sends the received text data and emotion information to the generative AI (e.g., OpenAI ChatGPT).

[0957] Input: Text data, emotion information text data

[0958] Output: Send data to generative AI

[0959] Step 7:

[0960] Answer generation by generative AI

[0961] The generative AI analyzes the text data and emotional information it receives and generates an appropriate answer.

[0962] Input: Text data (e.g., "What is the weather today?"), emotion information (e.g., "I'm tired")

[0963] Output: Answer that takes into account emotional information (e.g. "It's sunny today, but I've heard you've been busy lately. Maybe it would be good for you to relax a bit.")

[0964] Step 8:

[0965] The server generates the answer and sends it to the device.

[0966] The server receives the answer generated by the generative AI and sends it to the terminal.

[0967] Input: Answer generated by generative AI

[0968] Output: Sending data to the terminal

[0969] Step 9:

[0970] The device displays the answer to the user

[0971] The answers received by the device are provided to the user via a smart display or speaker.

[0972] Input: Answer generated by generative AI

[0973] Output: Providing a voice or text response to the user

[0974] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0975] The data generation model 58 is a so-called generative AI (Artificial Intelligence).

[0976] One example of a data generation model58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0977] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0978] [Fourth embodiment]

[0979] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0980] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0981] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0982] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0983] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0984] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0985] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0986] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0987] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0988] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0989] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0990] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0991] Next, a description will be given of the specific processing by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[0992] The embodiment for carrying out the present invention comprises the following elements.

[0993] Element 1: User Interface

[0994] The user wears the terminal and starts a virtual campus tour. The terminal is a control object 443.

[0995] An image of the virtual campus is projected into the user's field of vision by outputting the image of the virtual campus on a certain display device.

[0996] Element 2: Detecting and Converting Audio Data

[0997] A microphone 238 mounted on the terminal detects voice data when the user asks a question or makes a query during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal.

[0998] Element 3: Communication with Server

[0999] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[1000] Element 4: Generative AI to generate answers

[1001] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[1002] Element 5: Providing answers

[1003] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[1004] With the above elements, in the embodiment of the present invention, a user experiences a virtual campus tour using a terminal, and when he or she asks a question or doubt, the voice data is detected and converted into text data. A generative AI analyzes the data through communication with a server, generates an appropriate answer, and provides it to the user. This allows students considering studying abroad to obtain information about the university and campus of their choice in real time.

[1005] The process flow will be explained below.

[1006] Step 1: Navigate the User Interface

[1007] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display device, which is the control target 443, and projects the image of the virtual campus into the user's field of vision.

[1008] Step 2: Detect and convert audio data

[1009] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[1010] Step 3: Communicating with the Server

[1011] The device sends the converted text data to the server, and the server sends the received text data to the generative AI for analysis.

[1012] Step 4: Generative AI generates answers

[1013] Generative AI analyzes the text data it receives and generates appropriate answers. Generative AI uses natural language processing techniques to provide answers to questions in real time.

[1014] Step 5: Provide your answer

[1015] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[1016] The above is a specific flow of the program's processing. The user operates the terminal to start the virtual campus tour and voices a question or doubt. The terminal's microphone 238 detects the voice data and converts it into text data. The text data is sent to the server, where the generative AI analyzes it and generates an answer. The server sends the answer to the terminal, where it is provided to the user.

[1017] Example 1

[1018] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[1019] In the modern education system, it is difficult for students to understand the facilities and environment of a campus without actually visiting it. In particular, for students considering studying abroad, the means to obtain detailed information about the university before traveling are limited, making it difficult to make a decision. To solve this situation, virtual campus tours are required. However, there is an issue that mere video and text information cannot respond to students' specific questions in real time.

[1020] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1021] In this invention, the server includes a means for transferring the received text data to an analysis device and starting the analysis, a means for the analysis device to analyze the received text data and generate an appropriate answer using natural language processing technology, and a means for the server to receive the generated answer and return it to the terminal via the communication network. This allows students to use the terminal to experience a virtual campus tour and obtain appropriate answers to their questions and doubts in real time.

[1022] A "user" is a person who operates a terminal to experience a virtual campus tour.

[1023] A "terminal" is an electronic device that provides a virtual campus tour through a user interface, detects voice data, and transmits and receives data.

[1024] A "virtual campus tour" is an online tour that simulates a real campus and that users experience through their devices.

[1025] A "display" refers to a display device that is connected to a terminal and visually presents an image of the virtual campus and generated answers to a user.

[1026] The "acquisition device" refers to a hardware component that is installed in a terminal and detects voice data uttered by a user.

[1027] "Voice data" refers to voice signals of questions or doubts uttered by a user during a virtual campus tour.

[1028] "Speech recognition technology" refers to technology that analyzes voice data detected by a capture device and converts it into text data.

[1029] "Text data" refers to data that expresses a user's question or inquiry as text, converted using voice recognition technology.

[1030] A "communications network" refers to the infrastructure for transmitting and receiving data between terminals and servers.

[1031] "Server" refers to a central processing unit for analyzing text data received from a terminal and providing generated answers.

[1032] An "analysis device" refers to a device or system that resides within a server and that analyzes text data and generates appropriate answers.

[1033] "Natural language processing technology" refers to technology that enables an analysis device to understand text data and generate appropriate answers in a format that humans can understand.

[1034] An "answer" is text data or voice data generated by the analysis device with the aim of providing appropriate information to a user's question or inquiry.

[1035] A "display device" is a device that is connected to a terminal and that visually presents the generated answers to a user.

[1036] The embodiment of the present invention utilizes a terminal equipped with a user interface. This terminal starts a virtual campus tour when operated by a user, and outputs an image of the virtual campus on a display. The user can visually enjoy this image. Specific hardware that can be used includes a smartphone, tablet, and PC.

[1037] Any questions or concerns that users may have during the virtual campus tour are captured as voice data by a capture device, i.e., a microphone, installed on the device. This voice data is converted to text data using speech recognition technology within the device, such as the Google Cloud Speech-to-Text API. This makes the user's comments available for analysis as text information.

[1038] The converted text data is then sent from the device over a communications network to a server that runs on Amazon Web Services (AWS) or another cloud computing platform. The server then forwards the text data to an analysis device, which then uses a generative AI model, such as OpenAI's ChatGPT, a natural language processing technology, to generate an appropriate response.

[1039] The generated answer is sent back to the terminal via the server and is displayed on the terminal's display device. In some cases, the answer can be provided aloud using the terminal's speaker.

[1040] As a concrete example, consider the following scenario: A user starts a virtual campus tour using a smartphone, and while watching the campus image projected on the display, asks, "What is this building?" This question is detected by a microphone and converted into text data using voice recognition technology. The converted text data is sent to a server, and a generative AI model generates an answer, "This is a library." This answer is then sent to the device and provided to the user via the display and speaker.

[1041] And here is an example of a prompt to be input to the generative AI model:

[1042] Example prompt 1:

[1043] "When a user asks, 'What building is this?' during a virtual campus tour, generate an appropriate response."

[1044] Example prompt 2:

[1045] "Generate real-time answers to the question 'Where are the student dorms?' during a virtual campus tour."

[1046] The above is a specific embodiment of the present invention. By using this system, users can obtain detailed information in response to their questions in real time without actually visiting the campus, which can support their decision-making when considering studying abroad.

[1047] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1048] Step 1:

[1049] A user operates a terminal to start a virtual campus tour. As input, the user's operation information (e.g., clicking a button) is sent to the terminal. As output, the terminal projects an image of the virtual campus onto the display.

[1050] Specific behavior:

[1051] The user starts the dedicated smartphone app and taps the "Start Campus Tour" button, which causes the app to acquire user operation information and display a virtual campus image on the display.

[1052] Step 2:

[1053] The voice data of questions and doubts uttered by the user during the virtual campus tour is detected by a capture device (microphone) installed on the terminal. As input, the user's voice is sent to the microphone. As output, the detected voice data is generated.

[1054] Specific behavior:

[1055] When a user asks, "What building is this?", the device's microphone immediately detects the voice, and the capture device activates the noise canceling function to capture high-quality voice data.

[1056] Step 3:

[1057] A voice recognition system in the terminal converts the detected voice data into text data. As input, the voice data is sent to the voice recognition system. As output, text data is generated.

[1058] Specific behavior:

[1059] The device's voice recognition system converts the voice data "What is this building?" into text data "What is this building?" using a voice recognition library such as the Google Cloud Speech-to-Text API.

[1060] Step 4:

[1061] The terminal transmits the converted text data to the server via the communication network. As input, the text data is transmitted from the terminal to the server. As output, the server receives the text data.

[1062] Specific behavior:

[1063] The terminal sends the text data "What is this building?" to the server using the HTTPS protocol. The server receives this data and adds it to the processing queue.

[1064] Step 5:

[1065] The server transfers the received text data to the analysis device and starts the analysis. As input, the text data received by the server is sent to the analysis device. As output, the analysis result is generated.

[1066] Specific behavior:

[1067] The server prepares the text data "What is this building?" to be passed to the generative AI model, which then performs the analysis. For example, it uses OpenAI's ChatGPT for natural language processing.

[1068] Step 6:

[1069] The analysis device analyzes the text data and generates an appropriate answer using natural language processing techniques. As input, the text data is sent to the analysis device. As output, the generated answer is sent to the server.

[1070] Specific behavior:

[1071] Based on the text data "What is this building?", the generative AI model references its internal database and knowledge base to generate the answer "This is a library."

[1072] Step 7:

[1073] The server receives the generated answer and returns it to the terminal via the communication network. As an input, the generated answer is sent to the server. As an output, the server sends the answer to the terminal.

[1074] Specific behavior:

[1075] The server receives the answer from the generative AI model, "This is a library," and sends it to the terminal. A highly efficient data compression algorithm is used for communication.

[1076] Step 8:

[1077] The terminal receives the answer from the server, displays it on the display, and provides it to the user. As an input, the answer from the server is sent to the terminal. As an output, the answer is provided from the display and the speaker.

[1078] Specific behavior:

[1079] The terminal displays the answer "This is a library" on the display and plays "This is a library" aloud from the speaker. The user receives the answer through both sight and hearing.

[1080] (Application example 1)

[1081] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1082] Conventional virtual tour and virtual shopping systems have problems in that it is difficult for users to instantly obtain the information they need, and they are unable to get answers to their questions in real time. In addition, the experience in the virtual environment is limited, and users' needs are often not fully met. The present invention aims to solve these problems and provide a system that allows users to comfortably experience virtual campus tours and virtual stores in real time.

[1083] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1084] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or inquiry while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for the server to transmit the received text data to the generative AI and start analyzing it, a means for the generative AI to analyze the received text data and generate an appropriate answer, a means for the server to receive the answer generated from the generative AI and return it to the user, a means for the terminal to display the answer from the server and provide it to the user, a means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant, and a means for the generative AI to generate an answer including detailed information about the product when the user asks a question about product information. This allows the user to freely explore the virtual environment and obtain information in real time.

[1085] A "terminal" is an information device operated by a user, and specifically includes a smartphone, smart glasses, and the like.

[1086] "Generative AI" is an artificial intelligence system that analyzes input text data and generates appropriate answers using natural language processing technology.

[1087] A "Virtual Campus Tour" is a tour program that allows a user to visit and explore a college campus in a virtual environment.

[1088] A "microphone" is an input device for detecting voice data and has the function of picking up the voice uttered by the user.

[1089] "Text data" is voice data converted into text information by a voice recognition system.

[1090] A "server" is a computer system that processes data and provides information over a network.

[1091] A "virtual shopping assistant" is a virtual support system that allows users to freely walk around a virtual store, search for products, and get answers to their questions in real time.

[1092] A "virtual store image" is an image of a store that a user can visually experience within a virtual environment.

[1093] "Free roam" refers to the user moving freely within the virtual environment and exploring it from different perspectives.

[1094] "Detailed product information" refers to specific information about the product, such as the material, specifications, functions, and price.

[1095] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1096] Generating a Program

[1097] The system that realizes this application example is composed of a program that includes a user interface, a voice recognition system, communication with the server, a generation AI, and answer provision.

[1098] System processing explanation

[1099] Overall flow

[1100] When a user operates a terminal (smartphone or smart glasses), a virtual campus tour or virtual shopping assistant is started. When a user asks a question or inquires in this virtual environment, a microphone installed in the terminal detects the voice data and the voice recognition system converts it into text data. This text data is sent to a server, where an appropriate answer is generated by the generation AI and displayed again on the terminal.

[1101] Hardware used

[1102] Smartphone or smart glasses: Acts as the user interface, showing a virtual campus tour or a virtual shopping assistant.

[1103] Microphone: Used to detect audio data.

[1104] Display and audio output devices: As part of the user interface, they present the virtual environment and generated answers to the user.

[1105] Software used

[1106] Speech recognition system (e.g. Google Cloud Speech-to-Text): Converts detected voice data into text data.

[1107] Generative AI (e.g. OpenAI ChatGPT): Analyzes input text data and generates appropriate answers.

[1108] Communication protocol (e.g. HTTP / HTTPS): Sends and receives data between the terminal and the server.

[1109] User interface software: Has display and operation functions for presenting the virtual environment and generated answers to the user.

[1110] Examples

[1111] The user launches the virtual shopping assistant using smart glasses. They can freely wander around the virtual store, and when they find a product they like, they ask aloud, "What is this product made of?" This question is picked up by a microphone and converted into text data by a voice recognition system. The text data is then sent to a server, where a generative AI analyzes it and generates an answer such as "This product is made from 100% high-quality cotton." The server sends this answer back to the device, where it is displayed in the user's field of vision.

[1112] Example prompt:

[1113] "When a user asks, 'What is this red jacket made of?' Generate a detailed description of the product's materials."

[1114] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1115] Step 1:

[1116] The user operates the device (smartphone or smart glasses) to launch the virtual shopping assistant. The image of the virtual store is displayed on the display, and the experience begins.

[1117] Step 2:

[1118] The user freely explores the virtual store and finds the product they like while viewing the virtual store image projected on the display.

[1119] Step 3:

[1120] The user asks a question about the details of the product. The user speaks a question such as "What material is this product made of?" into the microphone of the terminal.

[1121] Step 4:

[1122] The device detects a user's question through a microphone, receives voice data as input, and begins processing the voice data internally.

[1123] Step 5:

[1124] The device's voice recognition system (e.g., Google Cloud Speech-to-Text) converts the voice data into text data. The voice data is analyzed and the corresponding text data is generated. The input is voice data and the output is text data.

[1125] Step 6:

[1126] The terminal sends the converted text data to the server. The text data is sent to the server via a communication protocol (e.g. HTTP / HTTPS). The input is the text data, and the output is a confirmation of sending to the server.

[1127] Step 7:

[1128] The server sends the received text data to the AI ​​(e.g., OpenAI ChatGPT) and starts the analysis. The input is text data, and the output is the analysis result text data.

[1129] Step 8:

[1130] The generative AI analyzes the text data and generates an appropriate answer. The generative AI processes the input text data using natural language processing technology and generates an appropriate answer in text format. The input is text data, and the output is the generated answer.

[1131] Step 9:

[1132] The server receives the answer generated by the generation AI and sends it to the terminal. The input is the generated answer, and the output is a confirmation of transmission to the terminal.

[1133] Step 10:

[1134] The terminal displays the answer from the server and provides it to the user. The answer is displayed on the terminal's display, allowing the user to visually confirm the required information. The input is the generated answer, and the output is the information displayed on the display.

[1135] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1136] The embodiment for carrying out the present invention comprises the following elements.

[1137] Element 1: User Interface

[1138] The user wears the terminal and starts the virtual campus tour. The terminal outputs an image of the virtual campus to the display device, which is the control target 443, and projects the image of the virtual campus into the user's field of vision.

[1139] Element 2: Detecting and Converting Audio Data

[1140] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[1141] Element 3: Combining Emotion Engines

[1142] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data and sends it to the server.

[1143] Element 4: Communication with Server

[1144] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[1145] Element 5: Generative AI to generate answers

[1146] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[1147] Element 6: Providing answers

[1148] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[1149] The above is an embodiment for carrying out the present invention. A user uses a terminal to experience a virtual campus tour and voices questions and doubts. The microphone 238 of the terminal detects the voice data and converts it into text data. The emotion engine recognizes the user's emotion information, converts it into text data, and sends it to the server. The server sends the text data and the emotion information text data to the generative AI, which analyzes it and generates an answer that takes into account the emotion information. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes into account the user's emotion information.

[1150] The process flow will be explained below.

[1151] Step 1: Navigate the User Interface

[1152] The user wears the terminal and starts a virtual campus tour. The terminal is a control object 443.

[1153] An image of the virtual campus is projected into the user's field of vision by outputting the image of the virtual campus on a certain display device.

[1154] Step 2: Detect and convert audio data

[1155] The microphone 238 of the terminal detects voice data when the user utters a question or inquiry during the virtual campus tour, and the detected voice data is converted into text data by a voice recognition system in the terminal.

[1156] Step 3: Recognizing and transforming emotional information using the emotion engine

[1157] The emotion engine recognizes emotion information from the user's speech, facial expressions, etc. The emotion engine converts the recognized emotion information into text data.

[1158] Step 4: Communicating with the Server

[1159] The device sends the converted text data and the emotional information text data to the server. The server then sends the received text data to the generative AI for analysis.

[1160] Step 5: Generative AI generates answers

[1161] The generative AI analyzes the received text data and emotional text data, and generates an appropriate answer taking into account the emotional information.

[1162] Step 6: Provide your answer

[1163] The server receives the answer generated by the generative AI and sends it to the terminal, which displays the answer and provides it to the user.

[1164] The above is a specific flow of the program's processing. The user operates the terminal to start a virtual campus tour and voices a question or doubt. The microphone 238 of the terminal detects the voice data and converts it into text data. At the same time, the emotion engine recognizes the user's emotional information and converts it into text data. The text data and the emotional information text data are sent to the server, where the generative AI analyzes it and generates an answer that takes the emotional information into consideration. The server sends the answer to the terminal and provides it to the user. This makes it possible to provide an answer that takes the user's emotional information into consideration.

[1165] Example 2

[1166] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1167] With the recent advancement of information technology, real-time interactive experiences are now required in educational environments. Especially in virtual campus tours, it is necessary to provide prompt and appropriate answers to the doubts and questions that users have. However, conventional systems have difficulty in providing answers that take into account the user's emotional information, which limits the user experience.

[1168] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for the terminal to display an image of a virtual campus on a display, a means for the voice input device of the terminal to detect voice data, a means for the terminal to convert the detected voice data into text data, a means for the emotion analysis device of the terminal to recognize the user's emotion information and convert it into text data, a means for the terminal to transmit the text data and the emotion information to the server, a means for the server to transmit the received text data and the emotion information to the generative AI model and start the analysis, a means for the generative AI model to analyze the received text data and the emotion information and generate an appropriate answer taking into account the emotion information, a means for the server to receive the answer generated from the generative AI model and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate answer taking into account the user's emotion information in real time.

[1169] A "terminal" is an electronic device that starts a virtual campus tour when operated by a user, and detects, processes, and displays voice data and emotional information.

[1170] A "display" is an image display device mounted on a terminal, and is a device for presenting an image of the virtual campus to a user.

[1171] The "voice input device" is a device such as a microphone mounted on a terminal, and is a device for detecting the user's speech as voice data.

[1172] "Voice data" refers to a digital recording of a user's speech that is detected by a terminal's voice input device.

[1173] "Text data" refers to character string data that is generated by analyzing and converting voice data using a voice recognition system.

[1174] An "emotion analysis device" is a device that recognizes emotional information from the content of a user's speech and facial expressions and converts it into text data.

[1175] "Emotion information" is data indicating the emotional state recognized from the user's speech and facial expressions.

[1176] The "server" is a central processing unit that receives the text data and emotion information sent from the terminal, sends it to the generative AI model for analysis, and returns the generated answer to the user.

[1177] A "generative AI model" is an artificial intelligence system that analyzes text data and emotional information sent from the server and generates appropriate answers that take the emotional information into account.

[1178] A "virtual campus tour" is an interactive simulated experience in which users can walk around a virtual campus through their devices and ask questions or concerns.

[1179] The embodiment of the present invention is a system that allows a user to experience a virtual campus tour using a terminal and to provide appropriate answers in real time that take into account the user's emotional information by vocalizing questions and doubts. The present invention is mainly composed of the following elements.

[1180] User Interface

[1181] The user operates the terminal to start the virtual campus tour. The terminal outputs an image of the virtual campus through the display device, providing the image of the virtual campus within the user's field of vision. This allows the user to experience a realistic campus tour.

[1182] Audio data detection and conversion

[1183] A voice input device (e.g., a microphone) of the terminal detects voice data of questions or doubts uttered by the user during the virtual campus tour. The detected voice data is converted into text data by a voice recognition system in the terminal. For example, if the user says, "Please tell me the history of this building," the voice recognition system converts the voice data into text data saying, "Please tell me the history of this building."

[1184] Emotion analysis

[1185] The emotion analysis device of the terminal recognizes emotion information from the user's speech and facial expressions. This emotion information is converted into text data and sent to the server. For example, if the user has an interesting expression, the emotion information is converted into text data as "interesting."

[1186] Communicating with the Server

[1187] The device sends text data and emotion information to the server, which receives the data and sends it to the generative AI model to begin analysis.

[1188] Answer generation using generative AI models

[1189] The generative AI model analyzes the received text data and emotional information and generates appropriate answers that take the emotional information into account. For example, if a user asks, "What is the history of this building?", the generative AI model generates an answer such as, "This building was built in the 1950s and is mainly used for student activities."

[1190] Providing answers

[1191] The server sends the generated answer to the terminal, which displays it to the user, allowing the user to proceed with the virtual campus tour with a better understanding.

[1192] As a specific example, if a user asks "What kind of library is this?" during a virtual campus tour, the device's voice input device detects the question, and the voice recognition system converts it into text data saying "What kind of library is this?". The emotion analysis device recognizes the user's facial expression as "curious" and converts it into text data as emotional information. This text data and emotional information are sent to the server, and the generative AI model generates a detailed answer such as "This library has many rare books and is an ideal place for students to study and research." The server sends this answer to the device, which displays it to the user.

[1193] An example of a prompt for a generative AI model is:

[1194] "A user asks a curious question to learn more about a particular library during a virtual campus tour: 'What kind of library is this?'. The sentiment analyzer detects the user's curiosity. With this information, your generative AI model can generate a detailed and interesting answer."

[1195] In this way, the system of the present invention is able to provide answers that take into account the user's emotional information in real time.

[1196] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] The user operates the terminal to start the virtual campus tour. When the user inputs a command to start the tour, the terminal starts displaying an image of the virtual campus on the display. The input at this stage is the user's command to start the tour, and the output is an image of the virtual campus. Specifically, the image data is called up from the virtual campus database held by the terminal, and is rendered on the display.

[1199] Step 2:

[1200] When a user asks a question or raises a concern while walking around the virtual campus, the terminal's voice input device (microphone) detects the voice data. At this stage, the input is the voice data generated by the user, and the output is the detected voice signal. The terminal captures the user's speech in real time through the microphone.

[1201] Step 3:

[1202] The voice recognition system in the terminal converts the detected voice data into text data. At this stage, the input is voice data and the output is text data. For example, if a user asks, "What is this building?", the voice recognition system analyzes the voice data and generates the text data, "What is this building?". Specific operations include the process of converting the voice signal into a string of characters using an acoustic model and a speech model.

[1203] Step 4:

[1204] The emotion analysis device on the device recognizes emotional information from the user's speech and facial expressions, and converts it into text data. The input at this stage is the user's speech and facial expression data, and the output is text data of emotional information. For example, if the emotion analysis device determines that the user's facial expression when asking a question looks interesting, the emotional information of "interesting" is converted into text data. Specifically, deep learning is used to analyze facial expressions and tone of voice.

[1205] Step 5:

[1206] The terminal transmits text data and emotion information to the server. At this stage, the input is text data and emotion information, and the output is data transmission to the server. The terminal transmits these data to the server using a secure TCP / IP communication protocol.

[1207] Step 6:

[1208] The server sends the received text data and emotion information to the generative AI model and starts the analysis. At this stage, the input is text data and emotion information, and the output is sending data to the generative AI model. The server packages these data into an appropriate format and passes them to the generative AI model.

[1209] Step 7:

[1210] The generative AI model analyzes the received text data and emotional information and generates an appropriate answer that takes the emotional information into account. The input at this stage is text data and emotional information, and the output is the generated answer. For example, a generative AI model that receives the question "What is this building?" and the emotional information "interesting" generates the answer "This building was built in the 1950s and is used for many student activities." Specifically, an algorithm that combines natural language processing and emotional analysis is used.

[1211] Step 8:

[1212] The server sends the generated answer to the terminal, which displays it to the user. The input at this stage is the generated answer, and the output is the display of the answer to the user. The server uses the TCP / IP communication protocol to send data to the terminal, which renders the answer on the display. Specifically, text data is displayed on the screen, and is provided to the user in an easily readable format.

[1213] These steps enable users to receive real-time responses that take affective information into account during their virtual campus tour.

[1214] (Application example 2)

[1215] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1216] Conventional virtual tour systems were unable to generate responses based on the user's emotions, resulting in inconsistent quality of experience for the user. In addition, when a user utters a question or doubt by voice, there was a lack of a means to provide an appropriate response that takes into account the user's emotions. As a result, the satisfaction and interest felt by the user could decrease.

[1217] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1218] In this invention, the server includes a means for starting a virtual campus tour in response to a user's operation of the terminal, a means for a microphone of the terminal to detect voice data when the user asks a question or doubt while walking around the virtual campus, a means for the terminal to convert the detected voice data into text data, a means for an emotion engine to recognize the user's emotion information, convert it into text data and send it to the server, a means for sending the text data and the emotion information text data received by the server to the generative AI and starting analysis, a means for the generative AI to analyze the received text data and emotion information and generate an appropriate answer, a means for the server to receive the answer generated by the generative AI and return it to the user, and a means for the terminal to display the answer from the server and provide it to the user. This makes it possible to provide an appropriate response that takes into account the user's emotion information.

[1219] "User" refers to a person who uses the system.

[1220] A "terminal" refers to a device that includes a user interface and a microphone and is operated by a user.

[1221] A "virtual campus tour" refers to an experience that allows you to wander around a virtual environment and gain information.

[1222] A "microphone" is a device for detecting audio data.

[1223] "Voice data" refers to voice uttered by a user collected as digital information.

[1224] "Text data" is voice data expressed as character information.

[1225] The "emotion engine" is a system that recognizes emotional information from the user's facial expressions and tone of voice and converts it into text data.

[1226] A "server" is a central communication device for receiving and processing text data and emotion information.

[1227] "Generative AI" is an artificial intelligence system that generates appropriate answers based on input data.

[1228] "Response" refers to the answer generated by generative AI.

[1229] In order to implement this invention, a terminal, an emotion engine, a server, and a generative AI are mainly used. Each element and its specific processing content will be explained below.

[1230] Hardware and Software Used

[1231] Hardware:

[1232] In-car microphone

[1233] Smart displays installed in taxis

[1234] In-vehicle computing units

[1235] software:

[1236] Speech recognition systems (e.g. Google Cloud Speech-to-Text)

[1237] Emotion recognition engine (e.g. Affectiva SDK)

[1238] Client-server protocols (e.g. REST API)

[1239] Generative AI (e.g. OpenAI ChatGPT)

[1240] System processing overview

[1241] The terminal collects the user's voice data using a microphone installed in the vehicle. This voice data is converted into text data by a computing unit installed in the taxi using a voice recognition system. At the same time, an emotion recognition engine analyzes the user's facial expressions and tone of voice using the camera and microphone in the vehicle to obtain emotion information. The obtained emotion information is also converted into text data.

[1242] The device then sends the text data and emotion information to a server. The server then sends the data to a generative AI to begin analysis. The generative AI then takes the voice data and emotion information into account to generate an appropriate answer. The answer is then sent to the device via the server, and is finally provided to the user via a smart display or speaker in the taxi.

[1243] Examples

[1244] For example, if a passenger asks, "What's the weather like today?" and the emotion recognition engine determines from the passenger's tone of voice that they sound tired, the generative AI will generate a response such as, "It's sunny today, but I hear you've been busy lately. It might be a good idea to relax for a bit."

[1245] Example of a prompt to be input to a generative AI model:

[1246] Q: What's the weather like today?

[1247] Emotional information: Tired

[1248] In this way, we can build a system that can provide responses that take into account the user's emotions. This system is expected to improve the user's experience in an autonomous taxi and increase satisfaction.

[1249] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1250] Step 1:

[1251] The user speaks a question

[1252] A user utters a voice question while in the car, such as "What's the weather like today?"

[1253] Input: User's voice

[1254] Output: Microphone collects audio data

[1255] Step 2:

[1256] The device collects voice data

[1257] A microphone installed in the terminal collects voice data uttered by the user.

[1258] Input: Raw audio data

[1259] Output: Digital audio data

[1260] Step 3:

[1261] Converting audio data to text

[1262] The voice data collected by the device is converted into text data using a voice recognition system (e.g., Google Cloud Speech-to-Text).

[1263] Input: Digital audio data

[1264] Output: Text data (e.g. "What's the weather today?")

[1265] Step 4:

[1266] Emotional information recognition

[1267] The emotion engine (e.g. Affectiva SDK) analyzes the user's tone of voice and facial expressions, recognizes emotional information, and converts it into text data.

[1268] Input: Digital audio data and camera footage

[1269] Output: Emotional information text data (e.g. "Tired")

[1270] Step 5:

[1271] Text data and emotion information are sent to the server

[1272] The device transmits text data and emotion information to the server.

[1273] Input: Text data, emotion information text data

[1274] Output: Send data to the server

[1275] Step 6:

[1276] The server sends the received data to the generative AI

[1277] The server sends the received text data and emotion information to the generative AI (e.g., OpenAI ChatGPT).

[1278] Input: Text data, emotion information text data

[1279] Output: Send data to generative AI

[1280] Step 7:

[1281] Answer generation by generative AI

[1282] The generative AI analyzes the text data and emotional information it receives and generates an appropriate answer.

[1283] Input: Text data (e.g., "What is the weather today?"), emotion information (e.g., "I'm tired")

[1284] Output: Answer that takes into account emotional information (e.g. "It's sunny today, but I've heard you've been busy lately. Maybe it would be good for you to relax a bit.")

[1285] Step 8:

[1286] The server generates the answer and sends it to the device.

[1287] The server receives the answer generated by the generative AI and sends it to the terminal.

[1288] Input: Answer generated by generative AI

[1289] Output: Sending data to the terminal

[1290] Step 9:

[1291] The device displays the answer to the user

[1292] The answers received by the device are provided to the user via a smart display or speaker.

[1293] Input: Answer generated by generative AI

[1294] Output: Providing a voice or text response to the user

[1295] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1296] The data generation model 58 is a so-called generative AI (Artificial Intelligence).

[1297] One example of a data generation model58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1298] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the robot 414.

[1299] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[1300] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1301] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1302] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1303] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[1304] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[1305] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[1306] Although the system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, the system according to the present disclosure is not necessarily implemented in a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program that runs on a personal computer, or an application that runs on a smartphone or the like. The method according to the present disclosure may be provided to a user in the form of SaaS (Software as a Service).

[1307] In the above embodiment, an example is given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to input data.

[1308] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1309] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[1310] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1311] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[1312] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[1313] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration in which a processor is used that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1314] Furthermore, as the hardware structure of these various processors, more specifically, an electric circuit combining circuit elements such as semiconductor elements can be used. Also, the above specific processing is merely an example. Therefore, unnecessary steps can be omitted without departing from the spirit of the invention.

[1315] It goes without saying that steps may be deleted, new steps may be added, and the processing order may be changed.

[1316] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[1317] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference.

[1318] The following is further disclosed regarding the above embodiment.

[1319] (Claim 1) 1. A system for providing a virtual campus tour, comprising: A means for starting a virtual campus tour in response to a user's operation of the terminal; A means for detecting voice data by a microphone of a terminal when a user utters a question or inquiry while walking around the virtual campus; A means for converting the detected voice data into text data by the terminal; A means for the server to send the received text data to the generative AI and start analyzing it; A means for the generative AI to analyze the text data it receives and generate appropriate answers; A means for the server to receive the answer generated by the generative AI and send it back to the user; A means for the terminal to display a response from the server and provide it to the user; A system including: (Claim 2) The system of claim 1 , wherein when a user asks a question during the virtual campus tour, a microphone on the terminal detects voice data and converts it into text data. (Claim 3)

[1320] The server receives the answer generated by the generative AI and sends it back to the user. The system of claim 1. (Claim 4) The system further includes an emotion engine that recognizes the emotion of a user, A means for the emotion engine to recognize information such as the user's speech and facial expressions; A means for converting the user's emotion information recognized by the emotion engine into text data; A means for transmitting the text data of the emotion information received by the server to the generative AI for analysis; A means for generative AI to generate answers by taking into account emotional information; The system of claim 1 further comprising: (Claim 5) The system of claim 1 further comprising an emotion engine for recognizing an emotion of a user, the system comprising: A means by which the emotion engine recognises the user's voice, facial expressions, language nuances, etc. A means for converting the user's emotional information recognized by the emotion engine into text data. A means for the server to send the text data of emotional information received to a generative AI for analysis. A means by which generative AI generates answers that take emotional information into account. (Claim 6) The system of claim 1 further comprising an emotion engine for recognizing an emotion of a user, the system comprising: A means by which the emotion engine recognizes the user's voice, facial expressions, heart rate, and other biometric information. A means for converting the user's emotional information recognized by the emotion engine into text data. A means for the server to send the text data of emotional information received to a generative AI for analysis. A means by which generative AI generates answers that take emotional information into account. The above is a claim for an invention that further combines an emotion engine that recognizes the user's emotions. This makes it possible to obtain the user's emotion information in addition to the system described in claim 1, and for the generative AI to generate an answer taking the emotion information into account. (Claim 5) 1. A system for providing a virtual campus tour, comprising: a means for starting the virtual campus tour by outputting an image related to the virtual campus tour to the terminal in response to a user's operation of the terminal; A device operated by a user displays an image of the virtual campus, and when the user asks a question or inquires while virtually walking around the virtual campus, a microphone of the device detects the voice data; A means for converting voice data detected by the terminal into text data; A means for the server to send the received text data to the generative AI and start analyzing it; A means for the generative AI to analyze the text data it receives and generate appropriate answers; A means for the server to receive the answer generated by the generative AI and send it back to the user; A means for the terminal to display a response from the server and provide it to the user; A system including: (Claim 6) The means for starting the analysis transmits the text data to the generation AI together with a predetermined prompt when transmitting the text data to the generation AI. The system of claim 1. (Claim 7) A means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant; The method further includes a means for the generative AI to generate an answer including detailed information about the product when the user asks a question about the product information. The system of claim 1.

[1321] "Example 1" (Claim 1) A means for starting a virtual campus tour in response to a user's operation of the terminal; A terminal has a means for projecting an image of the virtual campus onto a display; A means for detecting voice data of questions or doubts uttered by a user during a virtual campus tour by an acquisition device of the terminal; A means for converting the detected voice data into text data using a voice recognition technique; A means for transmitting the converted text data to a server via a communication network by the terminal; A means for the server to transfer the received text data to an analysis device and start analysis; An analysis device is a means for analyzing the received text data and generating an appropriate answer using natural language processing technology; A means for the server to receive the generated answer and return it to the terminal via the communication network; a means for displaying the answer received from the server on a display device of the terminal and providing it to the user; A system including: (Claim 2) 10. The system of claim 1, wherein when a user asks a question during the virtual campus tour, a capture device of the terminal detects voice data and converts it into text data using voice recognition technology. (Claim 3) 10. The system of claim 1, wherein the server receives the generated answer from the analysis device and transmits it back to the user over the communication network.

[1322] "Application example 1" (Claim 1) A means for starting a virtual campus tour in response to a user's operation of the terminal; A means for detecting voice data by a microphone of a terminal when a user utters a question or inquiry while walking around the virtual campus; A means for converting the detected voice data into text data by the terminal; A means for the server to send the received text data to the generative AI and start analyzing it; A means for the generative AI to analyze the text data it receives and generate appropriate answers; A means for the server to receive the answer generated by the generative AI and send it back to the user; A means for the terminal to display a response from the server and provide it to the user; A means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant; A means for the generative AI to generate an answer including detailed information about a product when a user asks a question about the product; A system including: (Claim 2) 10. The system of claim 1, wherein when a user asks a question during the virtual campus tour, a microphone on the terminal detects voice data and converts it into text data. (Claim 3) The system of claim 1, wherein the server receives the answer generated from the generative AI and returns it to the user.

[1323] "Example 2 of combining emotion engines" (Claim 1) A means for starting a virtual campus tour in response to a user's operation of the terminal; A means for displaying an image of the virtual campus on a display of the terminal; A means for detecting voice data by a voice input device of the terminal when a user utters a question or inquiry while walking around the virtual campus; A means for converting the detected voice data into text data by the terminal; A means for an emotion analysis device of the terminal to recognize emotion information of a user and convert it into text data; A means for the terminal to transmit text data and emotion information to a server; A means for the server to send the received text data and emotion information to the generative AI model and start analysis; A means for the generative AI model to analyze the received text data and emotional information and generate an appropriate answer taking into account the emotional information; A means for the server to receive the answer generated from the generative AI model and return it to the user; A means for the terminal to display a response from the server and provide it to the user; A system including:

[1324] (Claim 2) 10. The system of claim 1, wherein when a user utters a question by voice during the virtual campus tour, a voice input device of the terminal detects the voice data and converts it into text data. (Claim 3) 2. The system of claim 1, wherein the server receives the answer generated from the generative AI model and returns it to the user.

[1325] "Application example 2 when combining emotion engines" (Claim 1) 1. A system for providing a virtual campus tour, comprising: A means for starting a virtual campus tour in response to a user's operation of the terminal; A means for detecting voice data by a microphone of a terminal when a user utters a question or inquiry while walking around the virtual campus; A means for converting the detected voice data into text data by the terminal; A means for the emotion engine to recognize emotion information of a user, convert it into text data, and transmit it to a server; A means for transmitting the received text data and the text data of emotion information to the generative AI and for starting the analysis; A means for the generative AI to analyze the received text data and emotional information and generate an appropriate response; A means for the server to receive the answer generated by the generative AI and send it back to the user; A means for the terminal to display a response from the server and provide it to the user; A system including: (Claim 2) 10. The system of claim 1, wherein when a user asks a question during the virtual campus tour, a microphone on the terminal detects voice data and converts it into text data. (Claim 3) 2. The system of claim 1, wherein the emotion engine recognizes the user's emotion information, converts it into text data, and transmits it to the server. [Explanation of symbols]

[1326] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. 1. A system for providing a virtual campus tour, comprising: a means for starting the virtual campus tour by outputting an image related to the virtual campus tour to the terminal in response to a user's operation of the terminal; A device operated by a user displays an image of the virtual campus, and when the user asks a question or inquires while virtually walking around the virtual campus, a microphone of the device detects the voice data; A means for converting voice data detected by the terminal into text data; A means for transmitting the text data received by the server to a generative AI and starting analysis; A means for the generative AI to analyze the received text data and generate an appropriate answer; A means for the server to receive the answer generated from the generative AI and return it to the user; A means for the terminal to display a response from the server and provide it to the user; A system including:

2. The means for starting the analysis transmits the text data to the generation AI together with a predetermined prompt when transmitting the text data to the generation AI. The system of claim 1 .

3. A means for displaying a virtual store image in which the user can freely walk around the image of the virtual store and search for products as a virtual shopping assistant; Further comprising: a means for generating an answer including detailed information of the product when the user asks a question about the product information; The system of claim 1 .

4. The system further includes an emotion engine that recognizes the emotion of a user, A means for the emotion engine to recognize information such as the user's speech and facial expressions; A means for converting the user's emotion information recognized by the emotion engine into text data; A means for transmitting the text data of the emotion information received by the server to a generative AI for analysis; A means for generating an answer by a generative AI taking into account emotional information; The system of claim 1 further comprising:

Images