system

Abstract

Provide a system. [Solution] a means for capturing a user's voice input in a video chat interface; A means of converting captured voice input into text in real time; and means for transmitting the converted text to a server; a server that utilizes a language model to generate answers based on the text; means for receiving a response from the server and converting the response into speech; means for playing the converted audio to the user; A system including:

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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Today's business leaders and decision makers often face unique challenges and struggle to quickly obtain appropriate advice. They often lack access to direct advice from historical figures and other experts, making it difficult to incorporate their wisdom and insights into their daily work and lives. This creates a need for a system that allows users to leverage the wisdom of historical figures in real time. [Means for solving the problem]

[0005] To solve this problem, the present invention provides a system having the following means: A means for capturing a user's voice input with a video chat interface and converting it to text in real time; A means for transmitting the converted text to a server, which uses a language model to generate an answer based on the text; A system for receiving the generated answer at a terminal, converting the answer to speech, and playing it back to the user; A speech recognition API is used to convert the voice input to text, and a speech synthesis API is used to convert the answer to speech; The language model used by the server is trained based on recordings of historical figures' statements, and the video chat interface is able to simultaneously capture the user's video and audio for communication.

[0006] "User" means any person or entity that uses the System to ask questions and receive answers to solve problems.

[0007] "Voice input" refers to the sound a user makes through a microphone, which the system captures and uses for processing.

[0008] "Video chat interface" refers to a user interface that uses a camera and microphone to capture and communicate with a user's video and audio in real time.

[0009] "Real-time" refers to a situation where there is almost no delay between the moment a user inputs something and the moment the system responds.

[0010] "Text" refers to character string data converted from a user's voice input.

[0011] "Server" refers to the computer that is the central processing unit of the system, parsing text, running language models, and generating answers.

[0012] A "language model" is an algorithm that is trained on a specific dataset and generates appropriate answers based on input text.

[0013] "Answer" refers to the response generated by the language model in response to a user's question.

[0014] "Speech Recognition API" refers to an external application programming interface for converting voice data into text data.

[0015] "Speech synthesis API" refers to an external application programming interface for converting text data into speech data.

[0016] A "great man" is a notable figure in history whose knowledge and insight continue to influence the present day.

[0017] "Records of speeches" refers to records of speeches, writings, interviews, etc. left by great people.

[0018] Based on these definitions, it is possible to clarify what each means or element in the claims specifically refers to. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single 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), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage 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., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] 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.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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.

[0033] 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 (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. 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 process 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.

[0037] 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.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. 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.

[0039] Next, a description will be given of the specific processing performed 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."

[0040] The present invention is a system that provides answers to problems and questions faced by users by utilizing the wisdom of great historical figures. This system is realized by combining voice input, a video chat interface, voice-to-text conversion, answer generation within the server, and voice conversion and playback functions. Specific embodiments are described below.

[0041] System Configuration

[0042] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface and captures the user's voice. The server uses a speech recognition API to convert the voice into text and then uses a language model to generate answers to the user's questions.

[0043] Program flow

[0044] 1. User Action:

[0045] The user launches the application on their device to start a video chat.

[0046] Users voice their questions or concerns.

[0047] 2. Terminal processing:

[0048] The device captures the user's voice in real time and converts it into text via a speech recognition API.

[0049] The converted text data is prepared for transmission to the server.

[0050] 3. Server processing:

[0051] The server receives the text data sent from the terminal.

[0052] Analyze the received data and select an appropriate language model.

[0053] The user's question text is input into the selected language model to generate an answer.

[0054] The generated answer text is prepared for transmission back to the terminal.

[0055] 4. Reprocessing the device:

[0056] The terminal receives the response text sent from the server.

[0057] The received text data is converted into voice data via a voice synthesis API.

[0058] The converted audio data is played back to provide the user with an answer.

[0059] Specific examples

[0060] Scenario: Business Leader Use Case

[0061] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0062] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0063] 2. Device: Captures the audio and converts it into text via a speech recognition API, saying "Please tell me effective coaching methods." This text is then sent to the server.

[0064] 3. Server: Analyzes the received text and uses a language model (e.g., "Management Scholar's Model") to generate an answer such as "The optimal coaching approach involves setting clear goals and providing repeated feedback." This answer is then sent back to the device.

[0065] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0066] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[0070] Step 2:

[0071] The user speaks a question, and the device captures the user's voice in real time through the microphone.

[0072] Step 3:

[0073] The device sends the captured voice data to the speech recognition API in real time and converts the voice into text data. This process converts the voice into text format.

[0074] Step 4:

[0075] The device temporarily stores the converted text data and prepares to send it to the server. For example, the text generated is "Please tell me effective coaching methods."

[0076] Step 5:

[0077] The server receives the text data sent from the terminal, analyzes the received text data, and selects an appropriate language model. In this case, the management scholar model is selected.

[0078] Step 6:

[0079] The server inputs the user's question text into the selected language model and generates an answer: "The best coaching involves clear goal setting and repeated feedback."

[0080] Step 7:

[0081] The server returns the generated answer text to the terminal, which sends the answer text to the terminal as an API response.

[0082] Step 8:

[0083] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[0084] Step 9:

[0085] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the voice data generated by the API.

[0086] Step 10:

[0087] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[0088] Through these steps, users can access the wisdom of great people in real time to answer their questions.

[0089] Example 1

[0090] 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 smart device 14 will be referred to as a "terminal."

[0091] Conventional information search and advice systems have limited ability to provide fast and accurate answers to problems and questions that users face. In addition, when users ask questions by voice, the process of efficiently converting the voice into text and then generating high-quality answers based on that text is complex and time-consuming, which has been an issue.

[0092] 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.

[0093] In this invention, the server includes means for capturing a user's voice input with a video chat interface, means for converting the captured voice input to text in real time, means for transmitting the converted text to the server, the server utilizing a generative AI model for generating answers based on the text, means for receiving answers from the server and converting the answers to speech, and means for playing the converted speech to the user, thereby enabling users to exchange questions and answers in real time and providing information quickly and accurately.

[0094] "User" refers to any individual or organization that uses the system to ask questions or obtain information.

[0095] "Voice input" refers to the audio data spoken by a user that is captured and processed by the system.

[0096] "Video chat interface" means a communication method used by a user to transmit audio in real time, and an interface that processes audio and video data.

[0097] "Capture" refers to the act of capturing a user's audio input or video data.

[0098] "Real-time" refers to a state in which there is only a momentary delay between input and result, meaning that processing occurs almost instantaneously.

[0099] "Means of converting to text" refers to the technology or software used to convert audio data into text data.

[0100] "Server" refers to a computer system for receiving data over a network, processing it, and sending the results.

[0101] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate new text or answers based on input data.

[0102] "Means for converting to audio" refers to the technology or software used to convert text data into audio data.

[0103] "Means for playing" refers to a device or technology that outputs audio data as sound so that the user can hear it.

[0104] This invention is a system that allows users to ask questions by voice and receive answers in real time. This system is realized by combining technologies such as a video chat interface, a speech recognition API, a generative AI model, and a speech synthesis API.

[0105] System Configuration

[0106] This system operates via a user terminal, a server, and internet communication. The main components are described below.

[0107] User Device

[0108] The user terminal is a device that captures the user's voice input in the video chat interface. The terminal has a built-in microphone that collects voice in real time. It also has the ability to convert voice to text using a speech recognition API and send the converted text to the server.

[0109] server

[0110] The server receives the text data and uses a generative AI model to generate answers based on that text. The server has multiple generative AI models and selects the appropriate model depending on the content of the user's question. Specifically, it can use an AI model trained on records of historical figures' statements, for example.

[0111] Speech Recognition API

[0112] As a speech recognition API, for example, Google (registered trademark) Speech-to-Text API can be used, which can convert a user's speech into text with high accuracy.

[0113] Generative AI Models

[0114] For example, the GPT series from OpenAI (registered trademark) can be used as a generative AI model, which can generate appropriate answers to user questions.

[0115] Text-to-Speech API

[0116] For example, Amazon Polly can be used as a speech synthesis API, which converts text responses generated on the server into speech and provides the user with a spoken response.

[0117] Specific examples

[0118] Scenario: Business Leader Use Case

[0119] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0120] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0121] 2. Device: Captures the audio and converts it to text using the Google Speech-to-Text API: "Please tell me effective coaching methods." Sends this text to the server.

[0122] 3. Server: Analyzes the received text and uses a generative AI model such as GPT-3 (registered trademark) to generate an answer such as "The optimal coaching is to set clear goals and provide repeated feedback." This answer is then sent back to the device.

[0123] 4. Device: Receives the answer and converts it into speech using Amazon Polly. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0124] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] User Actions

[0128] The user launches the app on their device and starts a video chat session. The user then inputs a question by voice. The input is the user's voice data. Specifically, the user taps the app on their smartphone, presses the "Start Video Chat" button, and speaks the question, "Please tell me effective coaching methods."

[0129] Step 2:

[0130] Device audio capture

[0131] The device captures the user's voice in real time. The input is the user's voice data, and the output is the captured voice data. Specifically, the device's microphone is used to collect the user's speech.

[0132] Step 3:

[0133] On-device speech recognition and text conversion

[0134] The device converts the captured voice data into text using a speech recognition API. The input is voice data, and the output is the converted text data. Specifically, the voice data is sent to the API in byte stream format, and the string returned as the conversion result is obtained. The Google Speech-to-Text API is used as the voice recognition API.

[0135] Step 4:

[0136] Sending data from the device to the server

[0137] The terminal sends the converted text data to the server using an HTTP request. The input is the text data, and the output is the text data sent to the server. Specifically, a POST request is sent to the " / send_text" endpoint, and the converted text is included in the payload.

[0138] Step 5:

[0139] Data reception and analysis on the server

[0140] The server receives and analyzes text data sent from the device. The input is the text data received from the device, and the output is category data as the analysis result. For example, the server analyzes the text "Please tell me effective coaching methods" and determines a category such as "business management."

[0141] Step 6:

[0142] Answer generation using a server-based AI model

[0143] The server selects an appropriate language model and generates an answer to the user's question. The input is the analyzed text data and categorical data, and the output is the generated answer text. Specifically, the user's question is input as a prompt into the generative AI model, and the generated answer is obtained. OpenAI's GPT series is used as the generative AI model.

[0144] Step 7:

[0145] Sending a response from the server to the device

[0146] The server returns the generated answer text to the terminal. The input is the generated answer text, and the output is the answer text sent to the terminal. Specifically, the answer text is included in the payload of the HTTP response.

[0147] Step 8:

[0148] Answer text-to-speech on your device

[0149] The device converts the response text received from the server into voice data using a speech synthesis API. The input is the response text data, and the output is the converted voice data. Specifically, the text data is sent to the API and the generated voice file is obtained. Amazon Polly is used as the speech synthesis API.

[0150] Step 9:

[0151] Play audio on the device and provide answers to the user

[0152] The device plays the converted audio data and provides the user with an answer. The input is audio data, and the output is audio that the user can hear. Specifically, the audio is played using a speaker within the device, allowing the user to hear the audio answer. For example, the answer audio may say, "The best coaching involves setting clear goals and providing repeated feedback."

[0153] (Application example 1)

[0154] 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."

[0155] Logistics centers need a way to quickly and accurately resolve the questions and problems that staff encounter during their daily work. However, with the current system, staff often spend a lot of time resolving questions, which can reduce productivity. It is also difficult to immediately obtain appropriate advice and knowledge, making it difficult to take immediate action to improve work efficiency and quality. A new method is needed to solve these issues.

[0156] 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.

[0157] In this invention, the server includes means for capturing a user's voice input using a video chat interface, means for converting the captured voice input into text in real time, means for transmitting the converted text to the server, and means for staff working at the logistics center to voice-input business-related questions and for generating and providing answers to those questions based on the wisdom of historical figures. This enables staff to quickly and accurately resolve their questions, which is expected to improve work efficiency and productivity.

[0158] "Users" refer to staff at the logistics center who use the system to input voice data and receive responses.

[0159] "Audio Input" means audio data provided by a user through a microphone or video chat interface.

[0160] "Video chat interface" means an interface for capturing a user's voice input and transmitting it to a server in real time.

[0161] "Means for converting to text" refers to technology for converting voice data into text data using a voice recognition API.

[0162] "Server" refers to a central processing unit that receives the converted speech-to-text data, generates answers using an appropriate language model, and sends them back to the user.

[0163] A "language model" is an algorithm that is primarily based on natural language processing techniques, is trained on recorded statements of historical figures, and generates answers to user questions.

[0164] The "means for converting to voice" refers to a voice synthesis API for converting the generated text-formatted answer into voice data.

[0165] "Real-time" is a time concept that refers to processing occurring immediately after the user makes a voice input, with almost no delay.

[0166] A "speech recognition API" is an application program interface that accurately converts voice data captured from a user into text data.

[0167] A "historical figure" is a famous person who had specialized knowledge or experience in the past and whose recorded statements are still used as useful information today.

[0168] System Configuration

[0169] This system uses a speech recognition API and a speech synthesis API to convert the user's voice input into text, and then uses a generative AI model to generate an answer based on that text, which is then converted back into speech and provided to the user. Specifically, staff working at logistics centers use devices such as smartphones and robots to quickly resolve questions.

[0170] Hardware

[0171] Smartphones: Staff carry and use them.

[0172] Robots: Installed in specific locations within the logistics center.

[0173] Microphone: Used for voice input.

[0174] Speaker: Used for audio playback.

[0175] software

[0176] Speech Recognition API: Uses the Google Speech Recognition API, which converts the user's speech into text.

[0177] Generative AI model: Uses OpenAI's model to provide generated text data as answers.

[0178] Use the speech synthesis API: pyttsx3 to convert text data into speech.

[0179] Operation explanation

[0180] 1. Voice capture: Users voice their questions through a smartphone or robotic video chat interface.

[0181] 2. Speech recognition: The device captures the user's voice in real time and converts it into text through the speech recognition API.

[0182] 3. Send to Server: The converted text is sent to the server.

[0183] 4. Answer generation using language model: The server analyzes the received text and generates an appropriate answer using a language model trained based on the speech records of historical figures.

[0184] 5. Speech synthesis: The generated answer text is converted into speech via a speech synthesis API.

[0185] 6. Audio playback: Play the converted audio back to the user and provide the answer.

[0186] Specific examples

[0187] Imagine a distribution center employee has a question about the best way to manage inventory. They use their smartphone to ask, "What's the best way to manage inventory?"

[0188] Prompt Sentence Examples

[0189] "What's the best way to manage inventory?"

[0190] The device captures this audio and converts it into text using the Google Speech Recognition API: "What is the best way to manage inventory?" This text is sent to a server and input as a prompt to OpenAI's generative AI model: "What would a great historical figure say if they were to answer the question, 'What is the best way to manage inventory?'" The generated answer is something like, "The best way to manage inventory is to periodically check inventory and accurately record the data." This text response is converted into speech using pyttsx3 and played to staff via their smartphones or robot speakers.

[0191] This allows logistics center staff to quickly resolve queries and improve operational efficiency and productivity.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] Audio capture and input

[0195] A user voices a question through a smartphone or robotic video chat interface. For example, the user might say, "What's the best way to manage inventory?" This voice data is captured by the interface.

[0196] Step 2:

[0197] Voice Recognition

[0198] The device sends the captured voice data to the Google Speech Recognition API. The API returns the voice data as text data. The input voice "What is the best way to manage inventory?" is converted to the text "What is the best way to manage inventory?" in real time.

[0199] Step 3:

[0200] Sending text data

[0201] The terminal transmits the converted text data to the server. Specifically, the text "What is the best way to manage inventory?" is transmitted to the server.

[0202] Step 4:

[0203] Using language models to generate answers

[0204] Based on the text data received by the server, an appropriate language model is selected and an answer is generated. Specifically, OpenAI's generative AI model is used, and the prompt sentence is input as "What would a great historical figure say in response to the question, 'What is the best method for inventory management?'" The answer text output by the generative AI model is "The best method for inventory management is to periodically check inventory and accurately record the data."

[0205] Step 5:

[0206] Sending answer text

[0207] The server generates a response text and returns it to the terminal. Specifically, the text "The best way to manage inventory is to periodically check inventory and record the data accurately" is sent to the terminal.

[0208] Step 6:

[0209] Speech synthesis

[0210] The device sends the received response text to the speech synthesis API. The API outputs the text data as voice data. Specifically, the text "The best way to manage inventory is to periodically check inventory and accurately record the data" is converted into voice data.

[0211] Step 7:

[0212] Audio playback and output

[0213] The terminal plays audio data and provides it to the user. Specifically, the audio played through the speaker says, "The best way to manage inventory is to periodically check your inventory and record the data accurately."

[0214] Furthermore, an emotion engine that estimates the user's emotion may be 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.

[0215] The present invention is a system that utilizes the wisdom of historical figures to provide answers to problems and questions faced by users, and also combines an emotion engine to recognize the user's emotions. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, answer generation within the server, and speech conversion and playback functions. Specific embodiments are described below.

[0216] System Configuration

[0217] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the voice into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[0218] Program flow

[0219] 1. User Action:

[0220] The user launches the application on their device to start a video chat.

[0221] Users voice their questions or concerns.

[0222] 2. Terminal processing:

[0223] The device captures the user's voice and video in real time through a microphone and camera.

[0224] The voice data is sent to a voice recognition API, which converts the voice into text data.

[0225] Video data and audio input are sent to an emotion engine to analyze the user's emotional state.

[0226] The converted text data and the analyzed emotion data are prepared for transmission to the server.

[0227] 3. Server processing:

[0228] The server receives the text data and emotion data sent from the terminal.

[0229] Analyzes incoming data, selects appropriate language models, and adjusts response content based on sentiment data.

[0230] The language model inputs the user's question text and generates an answer that reflects the emotional data.

[0231] The generated answer text is prepared for transmission back to the terminal.

[0232] 4. Reprocessing the device:

[0233] The terminal receives the response text sent from the server.

[0234] The received text data is sent to a speech synthesis API, which converts the text into speech data.

[0235] The converted audio data is played back to provide the user with an answer.

[0236] The emotion engine analyzes the user's emotional state and provides feedback to them, for example by displaying a corresponding emoticon or text message.

[0237] Specific examples

[0238] Scenario: Business Leader Use Case

[0239] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0240] 1. User: The business leader launches the app on their device, starts a video chat session, and dictates the question: "What are some effective coaching methods?"

[0241] 2. Device: Captures the audio and converts it into text via a speech recognition API, such as "Please tell me effective coaching methods." At the same time, the emotional engine uses the captured video and audio data to analyze the user's emotional state. This data is then sent to the server.

[0242] 3. Server: Analyzes the received text and sentiment data, and uses a language model developed by past management scholars to generate a response such as, "The best coaching involves clear goal setting and repeated feedback." The generated response is then sent back to the device.

[0243] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching involves clear goal setting and repeated feedback," is played back and provided to the business leader. The emotion engine then analyzes the user's emotional state and provides visual feedback to the user.

[0244] This system allows business leaders to not only access the wisdom of great people in real time in response to their questions, but also receive feedback on their own emotional state, helping them make better decisions.

[0245] The processing flow will be explained below.

[0246] Step 1:

[0247] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[0248] Step 2:

[0249] The user speaks out their question or inquiry, and the device captures the user's voice in real time through the microphone.

[0250] Step 3:

[0251] The device sends the captured voice data to a speech recognition API, which converts the voice into text. For example, the voice input "Please tell me effective coaching methods" is converted into text "Please tell me effective coaching methods."

[0252] Step 4:

[0253] The device captures the user's video data in real time and sends it to the emotion engine, which analyzes the audio and video data to recognize the user's emotional state.

[0254] Step 5:

[0255] The device sends the converted text data and the analyzed emotion data to the server. For example, the text data "Please tell me effective coaching methods" and the emotion data are sent.

[0256] Step 6:

[0257] The server receives the text data and emotion data sent from the device, analyzes the received text data, and selects an appropriate language model. The emotion data is used to adjust the response content.

[0258] Step 7:

[0259] The server inputs the user's question text into the selected language model and generates an answer that reflects the emotional data, such as "The best coaching involves clear goal setting and repeated feedback."

[0260] Step 8:

[0261] The server returns the generated answer text to the terminal, which then sends the answer text as an API response.

[0262] Step 9:

[0263] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[0264] Step 10:

[0265] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the converted voice data.

[0266] Step 11:

[0267] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[0268] Step 12:

[0269] The device will then provide feedback to the user about the emotional state analyzed by the emotion engine, for example by displaying a smiley face icon or a text description of the emotion as visual feedback.

[0270] Through the above steps, the present invention not only allows users to utilize the wisdom of great people in response to their questions in real time, but also provides feedback on their own emotional state, which helps users make better decisions.

[0271] Example 2

[0272] 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 smart device 14 will be referred to as a "terminal."

[0273] Currently, there are many information search systems and virtual assistants, but these systems only provide standardized answers without taking the user's emotional state into account. This makes it difficult to obtain accurate answers that reflect the user's true needs and emotions. Furthermore, there are no systems that provide advanced answers that utilize the wisdom of great historical figures. This limits opportunities for users to gain deep insight into the problems and questions they face.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0275] In this invention, the server includes means for utilizing an emotion model to analyze the user's emotional state, means for utilizing a generative model to generate answers based on text, and means for feeding back the analyzed emotional state to the user, thereby making it possible to provide accurate and deep insights that utilize the wisdom of great people while taking the user's emotional state into consideration.

[0276] "User" means any person or entity that uses the System to resolve a problem or question.

[0277] "Voice input" refers to voice data emitted by a user through a microphone.

[0278] A "communication interface" is an interface for capturing audio input and exchanging data with the system.

[0279] "Convert to text" refers to the process of converting captured audio data into character string data.

[0280] A "server" is a central repository for receiving data submitted by users and generating responses.

[0281] A "generative model" is an AI model that generates appropriate answers based on input text data.

[0282] An "emotion model" is an AI model that analyzes a user's voice and video data to identify their emotional state.

[0283] "Providing feedback" refers to the process of returning the analysis results to the user in an easy-to-understand format.

[0284] A "speech recognition API" is an application programming interface for converting voice data into text data.

[0285] "Records of great people" are records of the words and actions of important historical figures.

[0286] This invention is a system that provides answers to questions or doubts posed by users through voice input, taking into account their emotional state and utilizing the wisdom of great historical figures. This system is realized by combining voice input, a communication interface, a speech recognition API, an emotion model, a generative model, and a speech synthesis API.

[0287] System Configuration

[0288] The system operates via a user device, a server, and a communication network. The user device acts as a communication interface and captures the user's voice and video. The server converts the voice into text using a speech recognition API and then analyzes the user's emotional state using an emotion model. The server then generates an answer using a generative model and finally provides the answer to the user using a speech synthesis API.

[0289] Hardware and Software

[0290] User device: Use a device with a built-in camera and microphone, such as a computer, tablet, or smartphone.

[0291] Communication interface: Uses an internet connection.

[0292] Speech recognition API: Convert speech to text using something like the Google Cloud Speech-to-Text API.

[0293] Emotion model: Analyze the user's emotional state using Microsoft® Azure® Emotion API, etc.

[0294] Generative models: Generate answers using generative AI models such as OpenAI's GPT-4®.

[0295] Text-to-speech API: Convert text to speech using tools such as Amazon Polly.

[0296] Example

[0297] For example, consider a situation where a business leader asks, "What are effective coaching methods?" during a meeting. The user launches an app on their device and starts a video chat session. They then voice-input the question. The device captures the audio and converts it into text, "What are effective coaching methods?" via a speech recognition API. In parallel, the captured video and audio data is sent to an emotion model to analyze the emotional state. This data is then sent to the server, which selects an appropriate generative model and inputs it as a prompt.

[0298] Prompt Sentence Examples

[0299] "Please tell me how to coach effectively."

[0300] The server uses the generative model to generate an answer such as, "Optimal coaching involves clear goal setting and repeated feedback." The generated answer is then sent back to the device. The device then converts the received answer into speech via a speech synthesis API and plays it back to the user. Additionally, the device visually feeds back the analyzed emotional state to the user.

[0301] This system allows users to access the wisdom of great people in real time and also check their own emotional state, allowing them to gain more accurate and deeper insights.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1:

[0304] A user starts a video chat session by launching a video chat application on their device. The user taps the "Start" button to enable audio input, which allows the user's voice and video to be captured.

[0305] Input: User actions (tapping the "Start" button), audio, video

[0306] Output: Captured audio and video data

[0307] Step 2:

[0308] The device uses the built-in microphone and camera to capture the user's voice and video in real time, and the captured voice and video are saved in a temporary file.

[0309] Input: Captured audio and video data

[0310] Output: Audio and video data saved to a temporary file

[0311] Step 3:

[0312] The device sends the captured voice data to the voice recognition API, which converts the voice data into text data. The device sends the voice data to the voice recognition API, and the API returns the text data.

[0313] Input: Audio data

[0314] Output: Text data (e.g., "Please tell me effective coaching methods.")

[0315] Step 4:

[0316] The device sends the captured video and audio data to the emotion model, which analyzes the user's emotional state. The emotion model generates and returns an emotion value (e.g., joy, sadness, etc.) based on the video and audio.

[0317] Input: Video data, audio data

[0318] Output: Emotion data (e.g. "Happiness: 0.8, Sadness: 0.1, Anger: 0.1")

[0319] Step 5:

[0320] The device sends the converted text data and analyzed emotion data to the server, which receives this data and selects an appropriate generative AI model.

[0321] Input: Text data, emotion data

[0322] Output: Text data and emotion data sent to the server

[0323] Step 6:

[0324] The server inputs text data and emotional data into the generative AI model and generates an answer that takes the user's emotions into account. For example, if the prompt sentence is "Please tell me effective coaching methods," the server generates the answer "The best coaching involves clear goal setting and repeated feedback" by taking the emotional data into account.

[0325] Input: Text data (prompt sentence), emotion data

[0326] Output: Text response data (e.g., "The best coaching involves clear goal setting and repeated feedback.")

[0327] Step 7:

[0328] The server returns the generated answer text data to the device. The device then sends the answer text data to the speech synthesis API, which converts it into voice data. The converted voice data is played back through the device's speaker.

[0329] Input: Answer text data

[0330] Output: Audio data

[0331] Step 8:

[0332] The device will then provide feedback to the user based on the emotional state analyzed by the emotion engine. For example, if the user's happiness level is 0.8, a smiley face icon and a message such as "You are happy now" will be displayed on the screen.

[0333] Input: Emotion data

[0334] Output: Visual feedback of emotional state (e.g., smiley face icon and message)

[0335] (Application example 2)

[0336] 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."

[0337] Autonomous driving vehicles require the provision of appropriate information that takes into account the physical and mental state of the user (driver). In particular, systems are needed that can reduce the stress and fatigue that users feel while driving and assist in safe and comfortable driving. Conventional information provision systems only provide uniform information without considering the user's emotional state, which results in the problem of not being able to provide appropriate advice depending on the user's emotional state.

[0338] 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.

[0339] In this invention, the server includes means for analyzing the user's voice input and video data to recognize the user's emotional state, means for using a language model to generate an answer based on the text and emotional data, and means for providing the user with feedback based on the emotional state received from the server, thereby making it possible to grasp the user's emotional state in real time and provide information optimized for the user's state.

[0340] "Means for capturing user's voice input in a video chat interface" refers to an interface device for capturing user's voice along with the video.

[0341] "Means for converting voice data into text in real time" refers to a technical device for instantly converting voice data into text data.

[0342] The "means for transmitting the converted text and video data to a server" refers to a communication means for transmitting the text data and video data to a remote server.

[0343] A "server that uses a language model to generate answers based on text and emotion data" is a server that operates a language model used to create appropriate answers based on the user's input text and the results of emotion analysis.

[0344] The "means for receiving a response from the server and converting the response into speech" is a technical device for converting the text-format response sent from the server into speech format.

[0345] The "means for playing back the converted audio to the user" is a playback device that allows the user to listen to the audio data.

[0346] The "means for recognizing a user's emotional state by analyzing the user's video data and audio input" is an analysis system for reading emotions from the user's video data and audio input.

[0347] The "means for providing the user with feedback based on the emotional state received from the server" is a technical device for providing the user with appropriate feedback or advice based on the analyzed emotional state of the user.

[0348] This invention is a driver assistant AI system for autonomous vehicles that provides appropriate information and advice taking into account the user's physical and mental state. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, response generation within the server, and speech conversion and playback functions.

[0349] System Configuration

[0350] The system operates via a user device, a server, and internet communications. The user device acts as an in-car video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the speech into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[0351] Hardware and software used

[0352] Microphone and camera: Hardware devices that capture the user's voice and video.

[0353] Speech recognition APIs (e.g., Google Cloud Speech-to-Text): Cloud-based services for converting speech to text.

[0354] Emotion Recognition API (e.g., Affectiva or Azure Emotion API): A cloud-based service for analyzing a user's emotional state from video data.

[0355] Speech synthesis API (e.g., Amazon Polly): A cloud-based service that converts text data into audio data that is easy for users to understand.

[0356] Server: Provides the computational resources to process the received data and generate answers, and also operates a language model of historical figures to generate appropriate answers based on the user's question.

[0357] Explanation of program processing

[0358] The server converts the voice data sent from the device into text using the Google Cloud Speech-to-Text API. It then uses emotion recognition APIs such as Affectiva and Azure Emotion API to analyze the user's emotional state from the video data in real time. The analyzed text and emotion data are used to generate answers based on a language model stored on the server. This language model is trained on recordings of historical figures' speeches and can adjust the generated answers based on the emotion data.

[0359] The generated answer is converted into audio data using a speech synthesis API such as Amazon Polly and sent to the user's device. The user's device plays back the audio data and provides the answer to the user. At the same time, feedback (e.g., a visual indicator) based on the results of the sentiment analysis is displayed to the user.

[0360] Specific examples

[0361] Scenario: Route guidance in an autonomous vehicle

[0362] Consider the case where a passenger asks, "What is the nearest cafe from here?" while in the car.

[0363] 1. User: The user speaks to the in-car video chat interface, saying, "What is the nearest cafe from here?"

[0364] 2. Device: Captures audio and converts it into text using the Google Cloud Speech-to-Text API, such as "Please tell me the nearest cafe from here." The captured video and audio data are then analyzed for emotional state using Affectiva and Azure Emotion API. This data is then sent to the server.

[0365] 3. Server: Analyzes the received text and sentiment data and uses a language model of great people from the past to generate an answer such as, "You can see a nearby cafe by turning right at the next intersection. Please relax and enjoy yourself."

[0366] 4. Device: The answer returned from the server is converted into voice data using Amazon Polly and played back to the user through the car speakers. At the same time, visual feedback based on the user's emotional state is displayed on the display.

[0367] Prompt Sentence Examples

[0368] "Can you tell me the nearest cafe? Our users seem a little tired."

[0369] This system will enable users of autonomous vehicles to receive appropriate navigation information and advice in real time that takes their emotional state into account, making for a safer and more comfortable drive.

[0370] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0371] Step 1:

[0372] User Actions

[0373] Users ask questions via voice over an in-car video chat interface.

[0374] Input: Audio data

[0375] Output: Captured audio and video data

[0376] Description: The user asks a question aloud through an in-car video chat interface, such as "What is the nearest cafe from here?" The user's voice and facial expressions are simultaneously captured by the microphone and camera.

[0377] Step 2:

[0378] Device voice recognition processing

[0379] The device sends the voice data to a speech recognition API, which converts it into text in real time.

[0380] Input: Captured audio data

[0381] Output: Text data

[0382] Description: Send the captured audio data to the Google Cloud Speech-to-Text API and obtain the text data "Please tell me the nearest cafe from here." Check the conversion result and verify that there are no errors.

[0383] Step 3:

[0384] Device emotion recognition processing

[0385] The device sends video and audio data to an emotion recognition API to analyze the user's emotional state.

[0386] Input: Captured video and audio data

[0387] Output: Emotion data

[0388] Description: Send video and audio data to Affectiva or Azure Emotion API, and obtain the user's emotional state (e.g., fatigue, relaxation, stress, etc.) as the analysis result. Check the accuracy of the emotional data.

[0389] Step 4:

[0390] Send data from the device to the server

[0391] The text data and the emotion data are transmitted to a server.

[0392] Input: Text data and emotion data

[0393] Output: Data packet sent to the server

[0394] Description: Sends the converted text data and emotion data to the server using an appropriate communication protocol (e.g. HTTP, WebSocket). Checks whether the sending process was successful.

[0395] Step 5:

[0396] Server response generation process

[0397] The server generates an answer using a language model based on the text and emotion data it receives.

[0398] Input: Text data and emotion data

[0399] Output: Generated answer text

[0400] Description: Analyzes the received text and sentiment data and generates answers using a language model of historical figures. For example, when a question text is input, the system processes it so that the answer output is "You can see the nearby cafe by turning right at the next intersection. Please relax and enjoy your visit."

[0401] Step 6:

[0402] Send data from the server to the device

[0403] The generated answer text is sent to the terminal.

[0404] Input: Generated answer text

[0405] Output: Data packets sent to the device

[0406] Description: Sends the generated response text to the terminal using the appropriate communication protocol. Checks the content of the sent data and whether it was sent successfully.

[0407] Step 7:

[0408] Device speech synthesis processing

[0409] The device sends the response text from the server to a speech synthesis API, which converts it into voice data.

[0410] Input: Answer text

[0411] Output: Audio data

[0412] Description: Sends the answer text received from the server to a speech synthesis API such as Amazon Polly to generate audio data that is easy for the user to hear. Checks the quality and clarity of the audio data.

[0413] Step 8:

[0414] Device audio playback and feedback

[0415] The converted audio is played back to provide feedback to the user based on their emotional state.

[0416] Input: Voice data, emotion data

[0417] Output: Audio played, emotional feedback displayed

[0418] Description: The generated voice data is played through the in-car speakers to provide the user with an answer, while emotional feedback (e.g., visual indicators of relaxation or stress) is displayed on the in-car display to provide visual feedback to the user.

[0419] This will assist users in driving safely and efficiently, and allow them to receive appropriate information and advice in real time based on their physical and mental condition.

[0420] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0421] 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 engine).<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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[0422] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 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.

[0426] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] 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.

[0428] 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 audio in accordance with instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0430] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0431] Fig. 4 shows an example of the 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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 smart glasses 214 will be referred to as the "terminal."

[0436] The present invention is a system that provides answers to problems and questions faced by users by utilizing the wisdom of great historical figures. This system is realized by combining voice input, a video chat interface, voice-to-text conversion, answer generation within the server, and voice conversion and playback functions. Specific embodiments are described below.

[0437] System Configuration

[0438] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface and captures the user's voice. The server uses a speech recognition API to convert the voice into text and then uses a language model to generate answers to the user's questions.

[0439] Program flow

[0440] 1. User Action:

[0441] The user launches the application on their device to start a video chat.

[0442] Users voice their questions or concerns.

[0443] 2. Terminal processing:

[0444] The device captures the user's voice in real time and converts it into text via a speech recognition API.

[0445] The converted text data is prepared for transmission to the server.

[0446] 3. Server processing:

[0447] The server receives the text data sent from the terminal.

[0448] Analyze the received data and select an appropriate language model.

[0449] The user's question text is input into the selected language model to generate an answer.

[0450] The generated answer text is prepared for transmission back to the terminal.

[0451] 4. Reprocessing the device:

[0452] The terminal receives the response text sent from the server.

[0453] The received text data is converted into voice data via a voice synthesis API.

[0454] The converted audio data is played back to provide the user with an answer.

[0455] Specific examples

[0456] Scenario: Business Leader Use Case

[0457] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0458] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0459] 2. Device: Captures the audio and converts it into text via a speech recognition API, saying "Please tell me effective coaching methods." This text is then sent to the server.

[0460] 3. Server: Analyzes the received text and uses a language model (e.g., "Management Scholar's Model") to generate an answer such as "The optimal coaching approach involves setting clear goals and providing repeated feedback." This answer is then sent back to the device.

[0461] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0462] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0463] The processing flow will be explained below.

[0464] Step 1:

[0465] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[0466] Step 2:

[0467] The user speaks a question, and the device captures the user's voice in real time through the microphone.

[0468] Step 3:

[0469] The device sends the captured voice data to the speech recognition API in real time and converts the voice into text data. This process converts the voice into text format.

[0470] Step 4:

[0471] The device temporarily stores the converted text data and prepares to send it to the server. For example, the text generated is "Please tell me effective coaching methods."

[0472] Step 5:

[0473] The server receives the text data sent from the terminal, analyzes the received text data, and selects an appropriate language model. In this case, the management scholar model is selected.

[0474] Step 6:

[0475] The server inputs the user's question text into the selected language model and generates an answer: "The best coaching involves clear goal setting and repeated feedback."

[0476] Step 7:

[0477] The server returns the generated answer text to the terminal, which sends the answer text to the terminal as an API response.

[0478] Step 8:

[0479] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[0480] Step 9:

[0481] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the voice data generated by the API.

[0482] Step 10:

[0483] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[0484] Through these steps, users can access the wisdom of great people in real time to answer their questions.

[0485] Example 1

[0486] 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 smart glasses 214 will be referred to as a "terminal."

[0487] Conventional information search and advice systems have limited ability to provide fast and accurate answers to problems and questions that users face. In addition, when users ask questions by voice, the process of efficiently converting the voice into text and then generating high-quality answers based on that text is complex and time-consuming, which has been an issue.

[0488] 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.

[0489] In this invention, the server includes means for capturing a user's voice input with a video chat interface, means for converting the captured voice input to text in real time, means for transmitting the converted text to the server, the server utilizing a generative AI model for generating answers based on the text, means for receiving answers from the server and converting the answers to speech, and means for playing the converted speech to the user, thereby enabling users to exchange questions and answers in real time and providing information quickly and accurately.

[0490] "User" refers to any individual or organization that uses the system to ask questions or obtain information.

[0491] "Voice input" refers to the audio data spoken by a user that is captured and processed by the system.

[0492] "Video chat interface" means a communication method used by a user to transmit audio in real time, and an interface that processes audio and video data.

[0493] "Capture" refers to the act of capturing a user's audio input or video data.

[0494] "Real-time" refers to a state in which there is only a momentary delay between input and result, meaning that processing occurs almost instantaneously.

[0495] "Means of converting to text" refers to the technology or software used to convert audio data into text data.

[0496] "Server" refers to a computer system for receiving data over a network, processing it, and sending the results.

[0497] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate new text or answers based on input data.

[0498] "Means for converting to audio" refers to the technology or software used to convert text data into audio data.

[0499] "Means for playing" refers to a device or technology that outputs audio data as sound so that the user can hear it.

[0500] This invention is a system that allows users to ask questions by voice and receive answers in real time. This system is realized by combining technologies such as a video chat interface, a speech recognition API, a generative AI model, and a speech synthesis API.

[0501] System Configuration

[0502] This system operates via a user terminal, a server, and internet communication. The main components are described below.

[0503] User Device

[0504] The user terminal is a device that captures the user's voice input in the video chat interface. The terminal has a built-in microphone that collects voice in real time. It also has the ability to convert voice to text using a speech recognition API and send the converted text to the server.

[0505] server

[0506] The server receives the text data and uses a generative AI model to generate answers based on that text. The server has multiple generative AI models and selects the appropriate model depending on the content of the user's question. Specifically, it can use an AI model trained on records of historical figures' statements, for example.

[0507] Speech Recognition API

[0508] For example, the Google Speech-to-Text API can be used as a speech recognition API, which allows you to convert the user's voice into text with high accuracy.

[0509] Generative AI Models

[0510] Generative AI models such as OpenAI's GPT series can be used, which can generate appropriate answers to user questions.

[0511] Text-to-Speech API

[0512] For example, Amazon Polly can be used as a speech synthesis API, which converts text responses generated on the server into speech and provides the user with a spoken response.

[0513] Specific examples

[0514] Scenario: Business Leader Use Case

[0515] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0516] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0517] 2. Device: Captures the audio and converts it to text using the Google Speech-to-Text API: "Please tell me effective coaching methods." Sends this text to the server.

[0518] 3. Server: Analyzes the received text and uses a generative AI model such as GPT-3 to generate an answer such as, "The optimal coaching is to set clear goals and provide repeated feedback." This answer is then sent back to the device.

[0519] 4. Device: Receives the answer and converts it into speech using Amazon Polly. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0520] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0522] Step 1:

[0523] User Actions

[0524] The user launches the app on their device and starts a video chat session. The user then inputs a question by voice. The input is the user's voice data. Specifically, the user taps the app on their smartphone, presses the "Start Video Chat" button, and speaks the question, "Please tell me effective coaching methods."

[0525] Step 2:

[0526] Device audio capture

[0527] The device captures the user's voice in real time. The input is the user's voice data, and the output is the captured voice data. Specifically, the device's microphone is used to collect the user's speech.

[0528] Step 3:

[0529] On-device speech recognition and text conversion

[0530] The device converts the captured voice data into text using a speech recognition API. The input is voice data, and the output is the converted text data. Specifically, the voice data is sent to the API in byte stream format, and the string returned as the conversion result is obtained. The Google Speech-to-Text API is used as the voice recognition API.

[0531] Step 4:

[0532] Sending data from the device to the server

[0533] The terminal sends the converted text data to the server using an HTTP request. The input is the text data, and the output is the text data sent to the server. Specifically, a POST request is sent to the " / send_text" endpoint, and the converted text is included in the payload.

[0534] Step 5:

[0535] Data reception and analysis on the server

[0536] The server receives and analyzes text data sent from the device. The input is the text data received from the device, and the output is category data as the analysis result. For example, the server analyzes the text "Please tell me effective coaching methods" and determines a category such as "business management."

[0537] Step 6:

[0538] Answer generation using a server-based AI model

[0539] The server selects an appropriate language model and generates an answer to the user's question. The input is the analyzed text data and categorical data, and the output is the generated answer text. Specifically, the user's question is input as a prompt into the generative AI model, and the generated answer is obtained. OpenAI's GPT series is used as the generative AI model.

[0540] Step 7:

[0541] Sending a response from the server to the device

[0542] The server returns the generated answer text to the terminal. The input is the generated answer text, and the output is the answer text sent to the terminal. Specifically, the answer text is included in the payload of the HTTP response.

[0543] Step 8:

[0544] Answer text-to-speech on your device

[0545] The device converts the response text received from the server into voice data using a speech synthesis API. The input is the response text data, and the output is the converted voice data. Specifically, the text data is sent to the API and the generated voice file is obtained. Amazon Polly is used as the speech synthesis API.

[0546] Step 9:

[0547] Play audio on the device and provide answers to the user

[0548] The device plays the converted audio data and provides the user with an answer. The input is audio data, and the output is audio that the user can hear. Specifically, the audio is played using a speaker within the device, allowing the user to hear the audio answer. For example, the answer audio may say, "The best coaching involves setting clear goals and providing repeated feedback."

[0549] (Application example 1)

[0550] 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."

[0551] Logistics centers need a way to quickly and accurately resolve the questions and problems that staff encounter during their daily work. However, with the current system, staff often spend a lot of time resolving questions, which can reduce productivity. It is also difficult to immediately obtain appropriate advice and knowledge, making it difficult to take immediate action to improve work efficiency and quality. A new method is needed to solve these issues.

[0552] 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.

[0553] In this invention, the server includes means for capturing a user's voice input using a video chat interface, means for converting the captured voice input into text in real time, means for transmitting the converted text to the server, and means for staff working at the logistics center to voice-input business-related questions and for generating and providing answers to those questions based on the wisdom of historical figures. This enables staff to quickly and accurately resolve their questions, which is expected to improve work efficiency and productivity.

[0554] "Users" refer to staff at the logistics center who use the system to input voice data and receive responses.

[0555] "Audio Input" means audio data provided by a user through a microphone or video chat interface.

[0556] "Video chat interface" means an interface for capturing a user's voice input and transmitting it to a server in real time.

[0557] "Means for converting to text" refers to technology for converting voice data into text data using a voice recognition API.

[0558] "Server" refers to a central processing unit that receives the converted speech-to-text data, generates answers using an appropriate language model, and sends them back to the user.

[0559] A "language model" is an algorithm that is primarily based on natural language processing techniques, is trained on recorded statements of historical figures, and generates answers to user questions.

[0560] The "means for converting to voice" refers to a voice synthesis API for converting the generated text-formatted answer into voice data.

[0561] "Real-time" is a time concept that refers to processing occurring immediately after the user makes a voice input, with almost no delay.

[0562] A "speech recognition API" is an application program interface that accurately converts voice data captured from a user into text data.

[0563] A "historical figure" is a famous person who had specialized knowledge or experience in the past and whose recorded statements are still used as useful information today.

[0564] System Configuration

[0565] This system uses a speech recognition API and a speech synthesis API to convert the user's voice input into text, and then uses a generative AI model to generate an answer based on that text, which is then converted back into speech and provided to the user. Specifically, staff working at logistics centers use devices such as smartphones and robots to quickly resolve questions.

[0566] Hardware

[0567] Smartphones: Staff carry and use them.

[0568] Robots: Installed in specific locations within the logistics center.

[0569] Microphone: Used for voice input.

[0570] Speaker: Used for audio playback.

[0571] software

[0572] Speech Recognition API: Uses the Google Speech Recognition API, which converts the user's speech into text.

[0573] Generative AI model: Uses OpenAI's model to provide generated text data as answers.

[0574] Use the speech synthesis API: pyttsx3 to convert text data into speech.

[0575] Operation explanation

[0576] 1. Voice capture: Users voice their questions through a smartphone or robotic video chat interface.

[0577] 2. Speech recognition: The device captures the user's voice in real time and converts it into text through the speech recognition API.

[0578] 3. Send to Server: The converted text is sent to the server.

[0579] 4. Answer generation using language model: The server analyzes the received text and generates an appropriate answer using a language model trained based on the speech records of historical figures.

[0580] 5. Speech synthesis: The generated answer text is converted into speech via a speech synthesis API.

[0581] 6. Audio playback: Play the converted audio back to the user and provide the answer.

[0582] Specific examples

[0583] Imagine a distribution center employee has a question about the best way to manage inventory. They use their smartphone to ask, "What's the best way to manage inventory?"

[0584] Prompt Sentence Examples

[0585] "What's the best way to manage inventory?"

[0586] The device captures this audio and converts it into text using the Google Speech Recognition API: "What is the best way to manage inventory?" This text is sent to a server and input as a prompt to OpenAI's generative AI model: "What would a great historical figure say if they were to answer the question, 'What is the best way to manage inventory?'" The generated answer is something like, "The best way to manage inventory is to periodically check inventory and accurately record the data." This text response is converted into speech using pyttsx3 and played to staff via their smartphones or robot speakers.

[0587] This allows logistics center staff to quickly resolve queries and improve operational efficiency and productivity.

[0588] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0589] Step 1:

[0590] Audio capture and input

[0591] A user voices a question through a smartphone or robotic video chat interface. For example, the user might say, "What's the best way to manage inventory?" This voice data is captured by the interface.

[0592] Step 2:

[0593] Voice Recognition

[0594] The device sends the captured voice data to the Google Speech Recognition API. The API returns the voice data as text data. The input voice "What is the best way to manage inventory?" is converted to the text "What is the best way to manage inventory?" in real time.

[0595] Step 3:

[0596] Sending text data

[0597] The terminal transmits the converted text data to the server. Specifically, the text "What is the best way to manage inventory?" is transmitted to the server.

[0598] Step 4:

[0599] Using language models to generate answers

[0600] Based on the text data received by the server, an appropriate language model is selected and an answer is generated. Specifically, OpenAI's generative AI model is used, and the prompt sentence is input as "What would a great historical figure say in response to the question, 'What is the best method for inventory management?'" The answer text output by the generative AI model is "The best method for inventory management is to periodically check inventory and accurately record the data."

[0601] Step 5:

[0602] Sending answer text

[0603] The server generates a response text and returns it to the terminal. Specifically, the text "The best way to manage inventory is to periodically check inventory and record the data accurately" is sent to the terminal.

[0604] Step 6:

[0605] Speech synthesis

[0606] The device sends the received response text to the speech synthesis API. The API outputs the text data as voice data. Specifically, the text "The best way to manage inventory is to periodically check inventory and accurately record the data" is converted into voice data.

[0607] Step 7:

[0608] Audio playback and output

[0609] The terminal plays audio data and provides it to the user. Specifically, the audio played through the speaker says, "The best way to manage inventory is to periodically check your inventory and record the data accurately."

[0610] Furthermore, 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.

[0611] The present invention is a system that utilizes the wisdom of historical figures to provide answers to problems and questions faced by users, and also combines an emotion engine to recognize the user's emotions. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, answer generation within the server, and speech conversion and playback functions. Specific embodiments are described below.

[0612] System Configuration

[0613] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the voice into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[0614] Program flow

[0615] 1. User Action:

[0616] The user launches the application on their device to start a video chat.

[0617] Users voice their questions or concerns.

[0618] 2. Terminal processing:

[0619] The device captures the user's voice and video in real time through a microphone and camera.

[0620] The voice data is sent to a voice recognition API, which converts the voice into text data.

[0621] Video data and audio input are sent to an emotion engine to analyze the user's emotional state.

[0622] The converted text data and the analyzed emotion data are prepared for transmission to the server.

[0623] 3. Server processing:

[0624] The server receives the text data and emotion data sent from the terminal.

[0625] Analyzes incoming data, selects appropriate language models, and adjusts response content based on sentiment data.

[0626] The language model inputs the user's question text and generates an answer that reflects the emotional data.

[0627] The generated answer text is prepared for transmission back to the terminal.

[0628] 4. Reprocessing the device:

[0629] The terminal receives the response text sent from the server.

[0630] The received text data is sent to a speech synthesis API, which converts the text into speech data.

[0631] The converted audio data is played back to provide the user with an answer.

[0632] The emotion engine analyzes the user's emotional state and provides feedback to them, for example by displaying a corresponding emoticon or text message.

[0633] Specific examples

[0634] Scenario: Business Leader Use Case

[0635] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0636] 1. User: The business leader launches the app on their device, starts a video chat session, and dictates the question: "What are some effective coaching methods?"

[0637] 2. Device: Captures the audio and converts it into text via a speech recognition API, such as "Please tell me effective coaching methods." At the same time, the emotional engine uses the captured video and audio data to analyze the user's emotional state. This data is then sent to the server.

[0638] 3. Server: Analyzes the received text and sentiment data, and uses a language model developed by past management scholars to generate a response such as, "The best coaching involves clear goal setting and repeated feedback." The generated response is then sent back to the device.

[0639] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching involves clear goal setting and repeated feedback," is played back and provided to the business leader. The emotion engine then analyzes the user's emotional state and provides visual feedback to the user.

[0640] This system allows business leaders to not only access the wisdom of great people in real time in response to their questions, but also receive feedback on their own emotional state, helping them make better decisions.

[0641] The processing flow will be explained below.

[0642] Step 1:

[0643] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[0644] Step 2:

[0645] The user speaks out their question or inquiry, and the device captures the user's voice in real time through the microphone.

[0646] Step 3:

[0647] The device sends the captured voice data to a speech recognition API, which converts the voice into text. For example, the voice input "Please tell me effective coaching methods" is converted into text "Please tell me effective coaching methods."

[0648] Step 4:

[0649] The device captures the user's video data in real time and sends it to the emotion engine, which analyzes the audio and video data to recognize the user's emotional state.

[0650] Step 5:

[0651] The device sends the converted text data and the analyzed emotion data to the server. For example, the text data "Please tell me effective coaching methods" and the emotion data are sent.

[0652] Step 6:

[0653] The server receives the text data and emotion data sent from the device, analyzes the received text data, and selects an appropriate language model. The emotion data is used to adjust the response content.

[0654] Step 7:

[0655] The server inputs the user's question text into the selected language model and generates an answer that reflects the emotional data, such as "The best coaching involves clear goal setting and repeated feedback."

[0656] Step 8:

[0657] The server returns the generated answer text to the terminal, which then sends the answer text as an API response.

[0658] Step 9:

[0659] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[0660] Step 10:

[0661] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the converted voice data.

[0662] Step 11:

[0663] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[0664] Step 12:

[0665] The device will then provide feedback to the user about the emotional state analyzed by the emotion engine, for example by displaying a smiley face icon or a text description of the emotion as visual feedback.

[0666] Through the above steps, the present invention not only allows users to utilize the wisdom of great people in response to their questions in real time, but also provides feedback on their own emotional state, which helps users make better decisions.

[0667] Example 2

[0668] 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 smart glasses 214 will be referred to as a "terminal."

[0669] Currently, there are many information search systems and virtual assistants, but these systems only provide standardized answers without taking the user's emotional state into account. This makes it difficult to obtain accurate answers that reflect the user's true needs and emotions. Furthermore, there are no systems that provide advanced answers that utilize the wisdom of great historical figures. This limits opportunities for users to gain deep insight into the problems and questions they face.

[0670] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0671] In this invention, the server includes means for utilizing an emotion model to analyze the user's emotional state, means for utilizing a generative model to generate answers based on text, and means for feeding back the analyzed emotional state to the user, thereby making it possible to provide accurate and deep insights that utilize the wisdom of great people while taking the user's emotional state into consideration.

[0672] "User" means any person or entity that uses the System to resolve a problem or question.

[0673] "Voice input" refers to voice data emitted by a user through a microphone.

[0674] A "communication interface" is an interface for capturing audio input and exchanging data with the system.

[0675] "Convert to text" refers to the process of converting captured audio data into character string data.

[0676] A "server" is a central repository for receiving data submitted by users and generating responses.

[0677] A "generative model" is an AI model that generates appropriate answers based on input text data.

[0678] An "emotion model" is an AI model that analyzes a user's voice and video data to identify their emotional state.

[0679] "Providing feedback" refers to the process of returning the analysis results to the user in an easy-to-understand format.

[0680] A "speech recognition API" is an application programming interface for converting voice data into text data.

[0681] "Records of great people" are records of the words and actions of important historical figures.

[0682] This invention is a system that provides answers to questions or doubts posed by users through voice input, taking into account their emotional state and utilizing the wisdom of great historical figures. This system is realized by combining voice input, a communication interface, a speech recognition API, an emotion model, a generative model, and a speech synthesis API.

[0683] System Configuration

[0684] The system operates via a user device, a server, and a communication network. The user device acts as a communication interface and captures the user's voice and video. The server converts the voice into text using a speech recognition API and then analyzes the user's emotional state using an emotion model. The server then generates an answer using a generative model and finally provides the answer to the user using a speech synthesis API.

[0685] Hardware and Software

[0686] User device: Use a device with a built-in camera and microphone, such as a computer, tablet, or smartphone.

[0687] Communication interface: Uses an internet connection.

[0688] Speech recognition API: Convert speech to text using something like the Google Cloud Speech-to-Text API.

[0689] Emotion model: Analyze the user's emotional state using, for example, the Microsoft Azure Emotion API.

[0690] Generative models: Generate answers using generative AI models such as OpenAI's GPT-4.

[0691] Text-to-speech API: Convert text to speech using tools such as Amazon Polly.

[0692] Example

[0693] For example, consider a situation where a business leader asks, "What are effective coaching methods?" during a meeting. The user launches an app on their device and starts a video chat session. They then voice-input the question. The device captures the audio and converts it into text, "What are effective coaching methods?" via a speech recognition API. In parallel, the captured video and audio data is sent to an emotion model to analyze the emotional state. This data is then sent to the server, which selects an appropriate generative model and inputs it as a prompt.

[0694] Prompt Sentence Examples

[0695] "Please tell me how to coach effectively."

[0696] The server uses the generative model to generate an answer such as, "Optimal coaching involves clear goal setting and repeated feedback." The generated answer is then sent back to the device. The device then converts the received answer into speech via a speech synthesis API and plays it back to the user. Additionally, the device visually feeds back the analyzed emotional state to the user.

[0697] This system allows users to access the wisdom of great people in real time and also check their own emotional state, allowing them to gain more accurate and deeper insights.

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Step 1:

[0700] A user starts a video chat session by launching a video chat application on their device. The user taps the "Start" button to enable audio input, which allows the user's voice and video to be captured.

[0701] Input: User actions (tapping the "Start" button), audio, video

[0702] Output: Captured audio and video data

[0703] Step 2:

[0704] The device uses the built-in microphone and camera to capture the user's voice and video in real time, and the captured voice and video are saved in a temporary file.

[0705] Input: Captured audio and video data

[0706] Output: Audio and video data saved to a temporary file

[0707] Step 3:

[0708] The device sends the captured voice data to the voice recognition API, which converts the voice data into text data. The device sends the voice data to the voice recognition API, and the API returns the text data.

[0709] Input: Audio data

[0710] Output: Text data (e.g., "Please tell me effective coaching methods.")

[0711] Step 4:

[0712] The device sends the captured video and audio data to the emotion model, which analyzes the user's emotional state. The emotion model generates and returns an emotion value (e.g., joy, sadness, etc.) based on the video and audio.

[0713] Input: Video data, audio data

[0714] Output: Emotion data (e.g. "Happiness: 0.8, Sadness: 0.1, Anger: 0.1")

[0715] Step 5:

[0716] The device sends the converted text data and analyzed emotion data to the server, which receives this data and selects an appropriate generative AI model.

[0717] Input: Text data, emotion data

[0718] Output: Text data and emotion data sent to the server

[0719] Step 6:

[0720] The server inputs text data and emotional data into the generative AI model and generates an answer that takes the user's emotions into account. For example, if the prompt sentence is "Please tell me effective coaching methods," the server generates the answer "The best coaching involves clear goal setting and repeated feedback" by taking the emotional data into account.

[0721] Input: Text data (prompt sentence), emotion data

[0722] Output: Text response data (e.g., "The best coaching involves clear goal setting and repeated feedback.")

[0723] Step 7:

[0724] The server returns the generated answer text data to the device. The device then sends the answer text data to the speech synthesis API, which converts it into voice data. The converted voice data is played back through the device's speaker.

[0725] Input: Answer text data

[0726] Output: Audio data

[0727] Step 8:

[0728] The device will then provide feedback to the user based on the emotional state analyzed by the emotion engine. For example, if the user's happiness level is 0.8, a smiley face icon and a message such as "You are happy now" will be displayed on the screen.

[0729] Input: Emotion data

[0730] Output: Visual feedback of emotional state (e.g., smiley face icon and message)

[0731] (Application example 2)

[0732] 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."

[0733] Autonomous driving vehicles require the provision of appropriate information that takes into account the physical and mental state of the user (driver). In particular, systems are needed that can reduce the stress and fatigue that users feel while driving and assist in safe and comfortable driving. Conventional information provision systems only provide uniform information without considering the user's emotional state, which results in the problem of not being able to provide appropriate advice depending on the user's emotional state.

[0734] 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.

[0735] In this invention, the server includes means for analyzing the user's voice input and video data to recognize the user's emotional state, means for using a language model to generate an answer based on the text and emotional data, and means for providing the user with feedback based on the emotional state received from the server, thereby making it possible to grasp the user's emotional state in real time and provide information optimized for the user's state.

[0736] "Means for capturing user's voice input in a video chat interface" refers to an interface device for capturing user's voice along with the video.

[0737] "Means for converting voice data into text in real time" refers to a technical device for instantly converting voice data into text data.

[0738] The "means for transmitting the converted text and video data to a server" refers to a communication means for transmitting the text data and video data to a remote server.

[0739] A "server that uses a language model to generate answers based on text and emotion data" is a server that operates a language model used to create appropriate answers based on the user's input text and the results of emotion analysis.

[0740] The "means for receiving a response from the server and converting the response into speech" is a technical device for converting the text-format response sent from the server into speech format.

[0741] The "means for playing back the converted audio to the user" is a playback device that allows the user to listen to the audio data.

[0742] The "means for recognizing a user's emotional state by analyzing the user's video data and audio input" is an analysis system for reading emotions from the user's video data and audio input.

[0743] The "means for providing the user with feedback based on the emotional state received from the server" is a technical device for providing the user with appropriate feedback or advice based on the analyzed emotional state of the user.

[0744] This invention is a driver assistant AI system for autonomous vehicles that provides appropriate information and advice taking into account the user's physical and mental state. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, response generation within the server, and speech conversion and playback functions.

[0745] System Configuration

[0746] The system operates via a user device, a server, and internet communications. The user device acts as an in-car video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the speech into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[0747] Hardware and software used

[0748] Microphone and camera: Hardware devices that capture the user's voice and video.

[0749] Speech recognition APIs (e.g., Google Cloud Speech-to-Text): Cloud-based services for converting speech to text.

[0750] Emotion Recognition API (e.g., Affectiva or Azure Emotion API): A cloud-based service for analyzing a user's emotional state from video data.

[0751] Speech synthesis API (e.g., Amazon Polly): A cloud-based service that converts text data into audio data that is easy for users to understand.

[0752] Server: Provides the computational resources to process the received data and generate answers, and also operates a language model of historical figures to generate appropriate answers based on the user's question.

[0753] Explanation of program processing

[0754] The server converts the voice data sent from the device into text using the Google Cloud Speech-to-Text API. It then uses emotion recognition APIs such as Affectiva and Azure Emotion API to analyze the user's emotional state from the video data in real time. The analyzed text and emotion data are used to generate answers based on a language model stored on the server. This language model is trained on recordings of historical figures' speeches and can adjust the generated answers based on the emotion data.

[0755] The generated answer is converted into audio data using a speech synthesis API such as Amazon Polly and sent to the user's device. The user's device plays back the audio data and provides the answer to the user. At the same time, feedback (e.g., a visual indicator) based on the results of the sentiment analysis is displayed to the user.

[0756] Specific examples

[0757] Scenario: Route guidance in an autonomous vehicle

[0758] Consider the case where a passenger asks, "What is the nearest cafe from here?" while in the car.

[0759] 1. User: The user speaks to the in-car video chat interface, saying, "What is the nearest cafe from here?"

[0760] 2. Device: Captures audio and converts it into text using the Google Cloud Speech-to-Text API, such as "Please tell me the nearest cafe from here." The captured video and audio data are then analyzed for emotional state using Affectiva and Azure Emotion API. This data is then sent to the server.

[0761] 3. Server: Analyzes the received text and sentiment data and uses a language model of great people from the past to generate an answer such as, "You can see a nearby cafe by turning right at the next intersection. Please relax and enjoy yourself."

[0762] 4. Device: The answer returned from the server is converted into voice data using Amazon Polly and played back to the user through the car speakers. At the same time, visual feedback based on the user's emotional state is displayed on the display.

[0763] Prompt Sentence Examples

[0764] "Can you tell me the nearest cafe? Our users seem a little tired."

[0765] This system will enable users of autonomous vehicles to receive appropriate navigation information and advice in real time that takes their emotional state into account, making for a safer and more comfortable drive.

[0766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0767] Step 1:

[0768] User Actions

[0769] Users ask questions via voice over an in-car video chat interface.

[0770] Input: Audio data

[0771] Output: Captured audio and video data

[0772] Description: The user asks a question aloud through an in-car video chat interface, such as "What is the nearest cafe from here?" The user's voice and facial expressions are simultaneously captured by the microphone and camera.

[0773] Step 2:

[0774] Device voice recognition processing

[0775] The device sends the voice data to a speech recognition API, which converts it into text in real time.

[0776] Input: Captured audio data

[0777] Output: Text data

[0778] Description: Send the captured audio data to the Google Cloud Speech-to-Text API and obtain the text data "Please tell me the nearest cafe from here." Check the conversion result and verify that there are no errors.

[0779] Step 3:

[0780] Device emotion recognition processing

[0781] The device sends video and audio data to an emotion recognition API to analyze the user's emotional state.

[0782] Input: Captured video and audio data

[0783] Output: Emotion data

[0784] Description: Send video and audio data to Affectiva or Azure Emotion API, and obtain the user's emotional state (e.g., fatigue, relaxation, stress, etc.) as the analysis result. Check the accuracy of the emotional data.

[0785] Step 4:

[0786] Send data from the device to the server

[0787] The text data and the emotion data are transmitted to a server.

[0788] Input: Text data and emotion data

[0789] Output: Data packet sent to the server

[0790] Description: Sends the converted text data and emotion data to the server using an appropriate communication protocol (e.g. HTTP, WebSocket). Checks whether the sending process was successful.

[0791] Step 5:

[0792] Server response generation process

[0793] The server generates an answer using a language model based on the text and emotion data it receives.

[0794] Input: Text data and emotion data

[0795] Output: Generated answer text

[0796] Description: Analyzes the received text and sentiment data and generates answers using a language model of historical figures. For example, when a question text is input, the system processes it so that the answer output is "You can see the nearby cafe by turning right at the next intersection. Please relax and enjoy your visit."

[0797] Step 6:

[0798] Send data from the server to the device

[0799] The generated answer text is sent to the terminal.

[0800] Input: Generated answer text

[0801] Output: Data packets sent to the device

[0802] Description: Sends the generated response text to the terminal using the appropriate communication protocol. Checks the content of the sent data and whether it was sent successfully.

[0803] Step 7:

[0804] Device speech synthesis processing

[0805] The device sends the response text from the server to a speech synthesis API, which converts it into voice data.

[0806] Input: Answer text

[0807] Output: Audio data

[0808] Description: Sends the answer text received from the server to a speech synthesis API such as Amazon Polly to generate audio data that is easy for the user to hear. Checks the quality and clarity of the audio data.

[0809] Step 8:

[0810] Device audio playback and feedback

[0811] The converted audio is played back to provide feedback to the user based on their emotional state.

[0812] Input: Voice data, emotion data

[0813] Output: Audio played, emotional feedback displayed

[0814] Description: The generated voice data is played through the in-car speakers to provide the user with an answer, while emotional feedback (e.g., visual indicators of relaxation or stress) is displayed on the in-car display to provide visual feedback to the user.

[0815] This will assist users in driving safely and efficiently, and allow them to receive appropriate information and advice in real time based on their physical and mental condition.

[0816] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0817] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[0818] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0819] [Third embodiment]

[0820] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0821] 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.

[0822] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0823] 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.

[0824] 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 audio in accordance with instructions from the processor 46.

[0825] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0826] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0827] Fig. 6 shows an example of the 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.

[0828] 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.

[0829] 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.

[0830] In the headset type terminal 314, a 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.

[0831] 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."

[0832] The present invention is a system that provides answers to problems and questions faced by users by utilizing the wisdom of great historical figures. This system is realized by combining voice input, a video chat interface, voice-to-text conversion, answer generation within the server, and voice conversion and playback functions. Specific embodiments are described below.

[0833] System Configuration

[0834] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface and captures the user's voice. The server uses a speech recognition API to convert the voice into text and then uses a language model to generate answers to the user's questions.

[0835] Program flow

[0836] 1. User Action:

[0837] The user launches the application on their device to start a video chat.

[0838] Users voice their questions or concerns.

[0839] 2. Terminal processing:

[0840] The device captures the user's voice in real time and converts it into text via a speech recognition API.

[0841] The converted text data is prepared for transmission to the server.

[0842] 3. Server processing:

[0843] The server receives the text data sent from the terminal.

[0844] Analyze the received data and select an appropriate language model.

[0845] The user's question text is input into the selected language model to generate an answer.

[0846] The generated answer text is prepared for transmission back to the terminal.

[0847] 4. Reprocessing the device:

[0848] The terminal receives the response text sent from the server.

[0849] The received text data is converted into voice data via a voice synthesis API.

[0850] The converted audio data is played back to provide the user with an answer.

[0851] Specific examples

[0852] Scenario: Business Leader Use Case

[0853] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0854] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0855] 2. Device: Captures the audio and converts it into text via a speech recognition API, saying "Please tell me effective coaching methods." This text is then sent to the server.

[0856] 3. Server: Analyzes the received text and uses a language model (e.g., "Management Scholar's Model") to generate an answer such as "The optimal coaching approach involves setting clear goals and providing repeated feedback." This answer is then sent back to the device.

[0857] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0858] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0859] The processing flow will be explained below.

[0860] Step 1:

[0861] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[0862] Step 2:

[0863] The user speaks a question, and the device captures the user's voice in real time through the microphone.

[0864] Step 3:

[0865] The device sends the captured voice data to the speech recognition API in real time and converts the voice into text data. This process converts the voice into text format.

[0866] Step 4:

[0867] The device temporarily stores the converted text data and prepares to send it to the server. For example, the text generated is "Please tell me effective coaching methods."

[0868] Step 5:

[0869] The server receives the text data sent from the terminal, analyzes the received text data, and selects an appropriate language model. In this case, the management scholar model is selected.

[0870] Step 6:

[0871] The server inputs the user's question text into the selected language model and generates an answer: "The best coaching involves clear goal setting and repeated feedback."

[0872] Step 7:

[0873] The server returns the generated answer text to the terminal, which sends the answer text to the terminal as an API response.

[0874] Step 8:

[0875] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[0876] Step 9:

[0877] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the voice data generated by the API.

[0878] Step 10:

[0879] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[0880] Through these steps, users can access the wisdom of great people in real time to answer their questions.

[0881] Example 1

[0882] 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."

[0883] Conventional information search and advice systems have limited ability to provide fast and accurate answers to problems and questions that users face. In addition, when users ask questions by voice, the process of efficiently converting the voice into text and then generating high-quality answers based on that text is complex and time-consuming, which has been an issue.

[0884] 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.

[0885] In this invention, the server includes means for capturing a user's voice input with a video chat interface, means for converting the captured voice input to text in real time, means for transmitting the converted text to the server, the server utilizing a generative AI model for generating answers based on the text, means for receiving answers from the server and converting the answers to speech, and means for playing the converted speech to the user, thereby enabling users to exchange questions and answers in real time and providing information quickly and accurately.

[0886] "User" refers to any individual or organization that uses the system to ask questions or obtain information.

[0887] "Voice input" refers to the audio data spoken by a user that is captured and processed by the system.

[0888] "Video chat interface" means a communication method used by a user to transmit audio in real time, and an interface that processes audio and video data.

[0889] "Capture" refers to the act of capturing a user's audio input or video data.

[0890] "Real-time" refers to a state in which there is only a momentary delay between input and result, meaning that processing occurs almost instantaneously.

[0891] "Means of converting to text" refers to the technology or software used to convert audio data into text data.

[0892] "Server" refers to a computer system for receiving data over a network, processing it, and sending the results.

[0893] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate new text or answers based on input data.

[0894] "Means for converting to audio" refers to the technology or software used to convert text data into audio data.

[0895] "Means for playing" refers to a device or technology that outputs audio data as sound so that the user can hear it.

[0896] This invention is a system that allows users to ask questions by voice and receive answers in real time. This system is realized by combining technologies such as a video chat interface, a speech recognition API, a generative AI model, and a speech synthesis API.

[0897] System Configuration

[0898] This system operates via a user terminal, a server, and internet communication. The main components are described below.

[0899] User Device

[0900] The user terminal is a device that captures the user's voice input in the video chat interface. The terminal has a built-in microphone that collects voice in real time. It also has the ability to convert voice to text using a speech recognition API and send the converted text to the server.

[0901] server

[0902] The server receives the text data and uses a generative AI model to generate answers based on that text. The server has multiple generative AI models and selects the appropriate model depending on the content of the user's question. Specifically, it can use an AI model trained on records of historical figures' statements, for example.

[0903] Speech Recognition API

[0904] For example, the Google Speech-to-Text API can be used as a speech recognition API, which allows you to convert the user's voice into text with high accuracy.

[0905] Generative AI Models

[0906] Generative AI models such as OpenAI's GPT series can be used, which can generate appropriate answers to user questions.

[0907] Text-to-Speech API

[0908] For example, Amazon Polly can be used as a speech synthesis API, which converts text responses generated on the server into speech and provides the user with a spoken response.

[0909] Specific examples

[0910] Scenario: Business Leader Use Case

[0911] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[0912] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[0913] 2. Device: Captures the audio and converts it to text using the Google Speech-to-Text API: "Please tell me effective coaching methods." Sends this text to the server.

[0914] 3. Server: Analyzes the received text and uses a generative AI model such as GPT-3 to generate an answer such as, "The optimal coaching is to set clear goals and provide repeated feedback." This answer is then sent back to the device.

[0915] 4. Device: Receives the answer and converts it into speech using Amazon Polly. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[0916] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[0917] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0918] Step 1:

[0919] User Actions

[0920] The user launches the app on their device and starts a video chat session. The user then inputs a question by voice. The input is the user's voice data. Specifically, the user taps the app on their smartphone, presses the "Start Video Chat" button, and speaks the question, "Please tell me effective coaching methods."

[0921] Step 2:

[0922] Device audio capture

[0923] The device captures the user's voice in real time. The input is the user's voice data, and the output is the captured voice data. Specifically, the device's microphone is used to collect the user's speech.

[0924] Step 3:

[0925] On-device speech recognition and text conversion

[0926] The device converts the captured voice data into text using a speech recognition API. The input is voice data, and the output is the converted text data. Specifically, the voice data is sent to the API in byte stream format, and the string returned as the conversion result is obtained. The Google Speech-to-Text API is used as the voice recognition API.

[0927] Step 4:

[0928] Sending data from the device to the server

[0929] The terminal sends the converted text data to the server using an HTTP request. The input is the text data, and the output is the text data sent to the server. Specifically, a POST request is sent to the " / send_text" endpoint, and the converted text is included in the payload.

[0930] Step 5:

[0931] Data reception and analysis on the server

[0932] The server receives and analyzes text data sent from the device. The input is the text data received from the device, and the output is category data as the analysis result. For example, the server analyzes the text "Please tell me effective coaching methods" and determines a category such as "business management."

[0933] Step 6:

[0934] Answer generation using a server-based AI model

[0935] The server selects an appropriate language model and generates an answer to the user's question. The input is the analyzed text data and categorical data, and the output is the generated answer text. Specifically, the user's question is input as a prompt into the generative AI model, and the generated answer is obtained. OpenAI's GPT series is used as the generative AI model.

[0936] Step 7:

[0937] Sending a response from the server to the device

[0938] The server returns the generated answer text to the terminal. The input is the generated answer text, and the output is the answer text sent to the terminal. Specifically, the answer text is included in the payload of the HTTP response.

[0939] Step 8:

[0940] Answer text-to-speech on your device

[0941] The device converts the response text received from the server into voice data using a speech synthesis API. The input is the response text data, and the output is the converted voice data. Specifically, the text data is sent to the API and the generated voice file is obtained. Amazon Polly is used as the speech synthesis API.

[0942] Step 9:

[0943] Play audio on the device and provide answers to the user

[0944] The device plays the converted audio data and provides the user with an answer. The input is audio data, and the output is audio that the user can hear. Specifically, the audio is played using a speaker within the device, allowing the user to hear the audio answer. For example, the answer audio may say, "The best coaching involves setting clear goals and providing repeated feedback."

[0945] (Application example 1)

[0946] 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."

[0947] Logistics centers need a way to quickly and accurately resolve the questions and problems that staff encounter during their daily work. However, with the current system, staff often spend a lot of time resolving questions, which can reduce productivity. It is also difficult to immediately obtain appropriate advice and knowledge, making it difficult to take immediate action to improve work efficiency and quality. A new method is needed to solve these issues.

[0948] 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.

[0949] In this invention, the server includes means for capturing a user's voice input using a video chat interface, means for converting the captured voice input into text in real time, means for transmitting the converted text to the server, and means for staff working at the logistics center to voice-input business-related questions and for generating and providing answers to those questions based on the wisdom of historical figures. This enables staff to quickly and accurately resolve their questions, which is expected to improve work efficiency and productivity.

[0950] "Users" refer to staff at the logistics center who use the system to input voice data and receive responses.

[0951] "Audio Input" means audio data provided by a user through a microphone or video chat interface.

[0952] "Video chat interface" means an interface for capturing a user's voice input and transmitting it to a server in real time.

[0953] "Means for converting to text" refers to technology for converting voice data into text data using a voice recognition API.

[0954] "Server" refers to a central processing unit that receives the converted speech-to-text data, generates answers using an appropriate language model, and sends them back to the user.

[0955] A "language model" is an algorithm that is primarily based on natural language processing techniques, is trained on recorded statements of historical figures, and generates answers to user questions.

[0956] The "means for converting to voice" refers to a voice synthesis API for converting the generated text-formatted answer into voice data.

[0957] "Real-time" is a time concept that refers to processing occurring immediately after the user makes a voice input, with almost no delay.

[0958] A "speech recognition API" is an application program interface that accurately converts voice data captured from a user into text data.

[0959] A "historical figure" is a famous person who had specialized knowledge or experience in the past and whose recorded statements are still used as useful information today.

[0960] System Configuration

[0961] This system uses a speech recognition API and a speech synthesis API to convert the user's voice input into text, and then uses a generative AI model to generate an answer based on that text, which is then converted back into speech and provided to the user. Specifically, staff working at logistics centers use devices such as smartphones and robots to quickly resolve questions.

[0962] Hardware

[0963] Smartphones: Staff carry and use them.

[0964] Robots: Installed in specific locations within the logistics center.

[0965] Microphone: Used for voice input.

[0966] Speaker: Used for audio playback.

[0967] software

[0968] Speech Recognition API: Uses the Google Speech Recognition API, which converts the user's speech into text.

[0969] Generative AI model: Uses OpenAI's model to provide generated text data as answers.

[0970] Use the speech synthesis API: pyttsx3 to convert text data into speech.

[0971] Operation explanation

[0972] 1. Voice capture: Users voice their questions through a smartphone or robotic video chat interface.

[0973] 2. Speech recognition: The device captures the user's voice in real time and converts it into text through the speech recognition API.

[0974] 3. Send to Server: The converted text is sent to the server.

[0975] 4. Answer generation using language model: The server analyzes the received text and generates an appropriate answer using a language model trained based on the speech records of historical figures.

[0976] 5. Speech synthesis: The generated answer text is converted into speech via a speech synthesis API.

[0977] 6. Audio playback: Play the converted audio back to the user and provide the answer.

[0978] Specific examples

[0979] Imagine a distribution center employee has a question about the best way to manage inventory. They use their smartphone to ask, "What's the best way to manage inventory?"

[0980] Prompt Sentence Examples

[0981] "What's the best way to manage inventory?"

[0982] The device captures this audio and converts it into text using the Google Speech Recognition API: "What is the best way to manage inventory?" This text is sent to a server and input as a prompt to OpenAI's generative AI model: "What would a great historical figure say if they were to answer the question, 'What is the best way to manage inventory?'" The generated answer is something like, "The best way to manage inventory is to periodically check inventory and accurately record the data." This text response is converted into speech using pyttsx3 and played to staff via their smartphones or robot speakers.

[0983] This allows logistics center staff to quickly resolve queries and improve operational efficiency and productivity.

[0984] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0985] Step 1:

[0986] Audio capture and input

[0987] A user voices a question through a smartphone or robotic video chat interface. For example, the user might say, "What's the best way to manage inventory?" This voice data is captured by the interface.

[0988] Step 2:

[0989] Voice Recognition

[0990] The device sends the captured voice data to the Google Speech Recognition API. The API returns the voice data as text data. The input voice "What is the best way to manage inventory?" is converted to the text "What is the best way to manage inventory?" in real time.

[0991] Step 3:

[0992] Sending text data

[0993] The terminal transmits the converted text data to the server. Specifically, the text "What is the best way to manage inventory?" is transmitted to the server.

[0994] Step 4:

[0995] Using language models to generate answers

[0996] Based on the text data received by the server, an appropriate language model is selected and an answer is generated. Specifically, OpenAI's generative AI model is used, and the prompt sentence is input as "What would a great historical figure say in response to the question, 'What is the best method for inventory management?'" The answer text output by the generative AI model is "The best method for inventory management is to periodically check inventory and accurately record the data."

[0997] Step 5:

[0998] Sending answer text

[0999] The server generates a response text and returns it to the terminal. Specifically, the text "The best way to manage inventory is to periodically check inventory and record the data accurately" is sent to the terminal.

[1000] Step 6:

[1001] Speech synthesis

[1002] The device sends the received response text to the speech synthesis API. The API outputs the text data as voice data. Specifically, the text "The best way to manage inventory is to periodically check inventory and accurately record the data" is converted into voice data.

[1003] Step 7:

[1004] Audio playback and output

[1005] The terminal plays audio data and provides it to the user. Specifically, the audio played through the speaker says, "The best way to manage inventory is to periodically check your inventory and record the data accurately."

[1006] Furthermore, 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.

[1007] The present invention is a system that utilizes the wisdom of historical figures to provide answers to problems and questions faced by users, and also combines an emotion engine to recognize the user's emotions. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, answer generation within the server, and speech conversion and playback functions. Specific embodiments are described below.

[1008] System Configuration

[1009] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the voice into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[1010] Program flow

[1011] 1. User Action:

[1012] The user launches the application on their device to start a video chat.

[1013] Users voice their questions or concerns.

[1014] 2. Terminal processing:

[1015] The device captures the user's voice and video in real time through a microphone and camera.

[1016] The voice data is sent to a voice recognition API, which converts the voice into text data.

[1017] Video data and audio input are sent to an emotion engine to analyze the user's emotional state.

[1018] The converted text data and the analyzed emotion data are prepared for transmission to the server.

[1019] 3. Server processing:

[1020] The server receives the text data and emotion data sent from the terminal.

[1021] Analyzes incoming data, selects appropriate language models, and adjusts response content based on sentiment data.

[1022] The language model inputs the user's question text and generates an answer that reflects the emotional data.

[1023] The generated answer text is prepared for transmission back to the terminal.

[1024] 4. Reprocessing the device:

[1025] The terminal receives the response text sent from the server.

[1026] The received text data is sent to a speech synthesis API, which converts the text into speech data.

[1027] The converted audio data is played back to provide the user with an answer.

[1028] The emotion engine analyzes the user's emotional state and provides feedback to them, for example by displaying a corresponding emoticon or text message.

[1029] Specific examples

[1030] Scenario: Business Leader Use Case

[1031] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[1032] 1. User: The business leader launches the app on their device, starts a video chat session, and dictates the question: "What are some effective coaching methods?"

[1033] 2. Device: Captures the audio and converts it into text via a speech recognition API, such as "Please tell me effective coaching methods." At the same time, the emotional engine uses the captured video and audio data to analyze the user's emotional state. This data is then sent to the server.

[1034] 3. Server: Analyzes the received text and sentiment data, and uses a language model developed by past management scholars to generate a response such as, "The best coaching involves clear goal setting and repeated feedback." The generated response is then sent back to the device.

[1035] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching involves clear goal setting and repeated feedback," is played back and provided to the business leader. The emotion engine then analyzes the user's emotional state and provides visual feedback to the user.

[1036] This system allows business leaders to not only access the wisdom of great people in real time in response to their questions, but also receive feedback on their own emotional state, helping them make better decisions.

[1037] The processing flow will be explained below.

[1038] Step 1:

[1039] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[1040] Step 2:

[1041] The user speaks out their question or inquiry, and the device captures the user's voice in real time through the microphone.

[1042] Step 3:

[1043] The device sends the captured voice data to a speech recognition API, which converts the voice into text. For example, the voice input "Please tell me effective coaching methods" is converted into text "Please tell me effective coaching methods."

[1044] Step 4:

[1045] The device captures the user's video data in real time and sends it to the emotion engine, which analyzes the audio and video data to recognize the user's emotional state.

[1046] Step 5:

[1047] The device sends the converted text data and the analyzed emotion data to the server. For example, the text data "Please tell me effective coaching methods" and the emotion data are sent.

[1048] Step 6:

[1049] The server receives the text data and emotion data sent from the device, analyzes the received text data, and selects an appropriate language model. The emotion data is used to adjust the response content.

[1050] Step 7:

[1051] The server inputs the user's question text into the selected language model and generates an answer that reflects the emotional data, such as "The best coaching involves clear goal setting and repeated feedback."

[1052] Step 8:

[1053] The server returns the generated answer text to the terminal, which then sends the answer text as an API response.

[1054] Step 9:

[1055] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[1056] Step 10:

[1057] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the converted voice data.

[1058] Step 11:

[1059] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[1060] Step 12:

[1061] The device will then provide feedback to the user about the emotional state analyzed by the emotion engine, for example by displaying a smiley face icon or a text description of the emotion as visual feedback.

[1062] Through the above steps, the present invention not only allows users to utilize the wisdom of great people in response to their questions in real time, but also provides feedback on their own emotional state, which helps users make better decisions.

[1063] Example 2

[1064] 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."

[1065] Currently, there are many information search systems and virtual assistants, but these systems only provide standardized answers without taking the user's emotional state into account. This makes it difficult to obtain accurate answers that reflect the user's true needs and emotions. Furthermore, there are no systems that provide advanced answers that utilize the wisdom of great historical figures. This limits opportunities for users to gain deep insight into the problems and questions they face.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1067] In this invention, the server includes means for utilizing an emotion model to analyze the user's emotional state, means for utilizing a generative model to generate answers based on text, and means for feeding back the analyzed emotional state to the user, thereby making it possible to provide accurate and deep insights that utilize the wisdom of great people while taking the user's emotional state into consideration.

[1068] "User" means any person or entity that uses the System to resolve a problem or question.

[1069] "Voice input" refers to voice data emitted by a user through a microphone.

[1070] A "communication interface" is an interface for capturing audio input and exchanging data with the system.

[1071] "Convert to text" refers to the process of converting captured audio data into character string data.

[1072] A "server" is a central repository for receiving data submitted by users and generating responses.

[1073] A "generative model" is an AI model that generates appropriate answers based on input text data.

[1074] An "emotion model" is an AI model that analyzes a user's voice and video data to identify their emotional state.

[1075] "Providing feedback" refers to the process of returning the analysis results to the user in an easy-to-understand format.

[1076] A "speech recognition API" is an application programming interface for converting voice data into text data.

[1077] "Records of great people" are records of the words and actions of important historical figures.

[1078] This invention is a system that provides answers to questions or doubts posed by users through voice input, taking into account their emotional state and utilizing the wisdom of great historical figures. This system is realized by combining voice input, a communication interface, a speech recognition API, an emotion model, a generative model, and a speech synthesis API.

[1079] System Configuration

[1080] The system operates via a user device, a server, and a communication network. The user device acts as a communication interface and captures the user's voice and video. The server converts the voice into text using a speech recognition API and then analyzes the user's emotional state using an emotion model. The server then generates an answer using a generative model and finally provides the answer to the user using a speech synthesis API.

[1081] Hardware and Software

[1082] User device: Use a device with a built-in camera and microphone, such as a computer, tablet, or smartphone.

[1083] Communication interface: Uses an internet connection.

[1084] Speech recognition API: Convert speech to text using something like the Google Cloud Speech-to-Text API.

[1085] Emotion model: Analyze the user's emotional state using, for example, the Microsoft Azure Emotion API.

[1086] Generative models: Generate answers using generative AI models such as OpenAI's GPT-4.

[1087] Text-to-speech API: Convert text to speech using tools such as Amazon Polly.

[1088] Example

[1089] For example, consider a situation where a business leader asks, "What are effective coaching methods?" during a meeting. The user launches an app on their device and starts a video chat session. They then voice-input the question. The device captures the audio and converts it into text, "What are effective coaching methods?" via a speech recognition API. In parallel, the captured video and audio data is sent to an emotion model to analyze the emotional state. This data is then sent to the server, which selects an appropriate generative model and inputs it as a prompt.

[1090] Prompt Sentence Examples

[1091] "Please tell me how to coach effectively."

[1092] The server uses the generative model to generate an answer such as, "Optimal coaching involves clear goal setting and repeated feedback." The generated answer is then sent back to the device. The device then converts the received answer into speech via a speech synthesis API and plays it back to the user. Additionally, the device visually feeds back the analyzed emotional state to the user.

[1093] This system allows users to access the wisdom of great people in real time and also check their own emotional state, allowing them to gain more accurate and deeper insights.

[1094] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1095] Step 1:

[1096] A user starts a video chat session by launching a video chat application on their device. The user taps the "Start" button to enable audio input, which allows the user's voice and video to be captured.

[1097] Input: User actions (tapping the "Start" button), audio, video

[1098] Output: Captured audio and video data

[1099] Step 2:

[1100] The device uses the built-in microphone and camera to capture the user's voice and video in real time, and the captured voice and video are saved in a temporary file.

[1101] Input: Captured audio and video data

[1102] Output: Audio and video data saved to a temporary file

[1103] Step 3:

[1104] The device sends the captured voice data to the voice recognition API, which converts the voice data into text data. The device sends the voice data to the voice recognition API, and the API returns the text data.

[1105] Input: Audio data

[1106] Output: Text data (e.g., "Please tell me effective coaching methods.")

[1107] Step 4:

[1108] The device sends the captured video and audio data to the emotion model, which analyzes the user's emotional state. The emotion model generates and returns an emotion value (e.g., joy, sadness, etc.) based on the video and audio.

[1109] Input: Video data, audio data

[1110] Output: Emotion data (e.g. "Happiness: 0.8, Sadness: 0.1, Anger: 0.1")

[1111] Step 5:

[1112] The device sends the converted text data and analyzed emotion data to the server, which receives this data and selects an appropriate generative AI model.

[1113] Input: Text data, emotion data

[1114] Output: Text data and emotion data sent to the server

[1115] Step 6:

[1116] The server inputs text data and emotional data into the generative AI model and generates an answer that takes the user's emotions into account. For example, if the prompt sentence is "Please tell me effective coaching methods," the server generates the answer "The best coaching involves clear goal setting and repeated feedback" by taking the emotional data into account.

[1117] Input: Text data (prompt sentence), emotion data

[1118] Output: Text response data (e.g., "The best coaching involves clear goal setting and repeated feedback.")

[1119] Step 7:

[1120] The server returns the generated answer text data to the device. The device then sends the answer text data to the speech synthesis API, which converts it into voice data. The converted voice data is played back through the device's speaker.

[1121] Input: Answer text data

[1122] Output: Audio data

[1123] Step 8:

[1124] The device will then provide feedback to the user based on the emotional state analyzed by the emotion engine. For example, if the user's happiness level is 0.8, a smiley face icon and a message such as "You are happy now" will be displayed on the screen.

[1125] Input: Emotion data

[1126] Output: Visual feedback of emotional state (e.g., smiley face icon and message)

[1127] (Application example 2)

[1128] 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."

[1129] Autonomous driving vehicles require the provision of appropriate information that takes into account the physical and mental state of the user (driver). In particular, systems are needed that can reduce the stress and fatigue that users feel while driving and assist in safe and comfortable driving. Conventional information provision systems only provide uniform information without considering the user's emotional state, which results in the problem of not being able to provide appropriate advice depending on the user's emotional state.

[1130] 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.

[1131] In this invention, the server includes means for analyzing the user's voice input and video data to recognize the user's emotional state, means for using a language model to generate an answer based on the text and emotional data, and means for providing the user with feedback based on the emotional state received from the server, thereby making it possible to grasp the user's emotional state in real time and provide information optimized for the user's state.

[1132] "Means for capturing user's voice input in a video chat interface" refers to an interface device for capturing user's voice along with the video.

[1133] "Means for converting voice data into text in real time" refers to a technical device for instantly converting voice data into text data.

[1134] The "means for transmitting the converted text and video data to a server" refers to a communication means for transmitting the text data and video data to a remote server.

[1135] A "server that uses a language model to generate answers based on text and emotion data" is a server that operates a language model used to create appropriate answers based on the user's input text and the results of emotion analysis.

[1136] The "means for receiving a response from the server and converting the response into speech" is a technical device for converting the text-format response sent from the server into speech format.

[1137] The "means for playing back the converted audio to the user" is a playback device that allows the user to listen to the audio data.

[1138] The "means for recognizing a user's emotional state by analyzing the user's video data and audio input" is an analysis system for reading emotions from the user's video data and audio input.

[1139] The "means for providing the user with feedback based on the emotional state received from the server" is a technical device for providing the user with appropriate feedback or advice based on the analyzed emotional state of the user.

[1140] This invention is a driver assistant AI system for autonomous vehicles that provides appropriate information and advice taking into account the user's physical and mental state. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, response generation within the server, and speech conversion and playback functions.

[1141] System Configuration

[1142] The system operates via a user device, a server, and internet communications. The user device acts as an in-car video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the speech into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[1143] Hardware and software used

[1144] Microphone and camera: Hardware devices that capture the user's voice and video.

[1145] Speech recognition APIs (e.g., Google Cloud Speech-to-Text): Cloud-based services for converting speech to text.

[1146] Emotion Recognition API (e.g., Affectiva or Azure Emotion API): A cloud-based service for analyzing a user's emotional state from video data.

[1147] Speech synthesis API (e.g., Amazon Polly): A cloud-based service that converts text data into audio data that is easy for users to understand.

[1148] Server: Provides the computational resources to process the received data and generate answers, and also operates a language model of historical figures to generate appropriate answers based on the user's question.

[1149] Explanation of program processing

[1150] The server converts the voice data sent from the device into text using the Google Cloud Speech-to-Text API. It then uses emotion recognition APIs such as Affectiva and Azure Emotion API to analyze the user's emotional state from the video data in real time. The analyzed text and emotion data are used to generate answers based on a language model stored on the server. This language model is trained on recordings of historical figures' speeches and can adjust the generated answers based on the emotion data.

[1151] The generated answer is converted into audio data using a speech synthesis API such as Amazon Polly and sent to the user's device. The user's device plays back the audio data and provides the answer to the user. At the same time, feedback (e.g., a visual indicator) based on the results of the sentiment analysis is displayed to the user.

[1152] Specific examples

[1153] Scenario: Route guidance in an autonomous vehicle

[1154] Consider the case where a passenger asks, "What is the nearest cafe from here?" while in the car.

[1155] 1. User: The user speaks to the in-car video chat interface, saying, "What is the nearest cafe from here?"

[1156] 2. Device: Captures audio and converts it into text using the Google Cloud Speech-to-Text API, such as "Please tell me the nearest cafe from here." The captured video and audio data are then analyzed for emotional state using Affectiva and Azure Emotion API. This data is then sent to the server.

[1157] 3. Server: Analyzes the received text and sentiment data and uses a language model of great people from the past to generate an answer such as, "You can see a nearby cafe by turning right at the next intersection. Please relax and enjoy yourself."

[1158] 4. Device: The answer returned from the server is converted into voice data using Amazon Polly and played back to the user through the car speakers. At the same time, visual feedback based on the user's emotional state is displayed on the display.

[1159] Prompt Sentence Examples

[1160] "Can you tell me the nearest cafe? Our users seem a little tired."

[1161] This system will enable users of autonomous vehicles to receive appropriate navigation information and advice in real time that takes their emotional state into account, making for a safer and more comfortable drive.

[1162] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1163] Step 1:

[1164] User Actions

[1165] Users ask questions via voice over an in-car video chat interface.

[1166] Input: Audio data

[1167] Output: Captured audio and video data

[1168] Description: The user asks a question aloud through an in-car video chat interface, such as "What is the nearest cafe from here?" The user's voice and facial expressions are simultaneously captured by the microphone and camera.

[1169] Step 2:

[1170] Device voice recognition processing

[1171] The device sends the voice data to a speech recognition API, which converts it into text in real time.

[1172] Input: Captured audio data

[1173] Output: Text data

[1174] Description: Send the captured audio data to the Google Cloud Speech-to-Text API and obtain the text data "Please tell me the nearest cafe from here." Check the conversion result and verify that there are no errors.

[1175] Step 3:

[1176] Device emotion recognition processing

[1177] The device sends video and audio data to an emotion recognition API to analyze the user's emotional state.

[1178] Input: Captured video and audio data

[1179] Output: Emotion data

[1180] Description: Send video and audio data to Affectiva or Azure Emotion API, and obtain the user's emotional state (e.g., fatigue, relaxation, stress, etc.) as the analysis result. Check the accuracy of the emotional data.

[1181] Step 4:

[1182] Send data from the device to the server

[1183] The text data and the emotion data are transmitted to a server.

[1184] Input: Text data and emotion data

[1185] Output: Data packet sent to the server

[1186] Description: Sends the converted text data and emotion data to the server using an appropriate communication protocol (e.g. HTTP, WebSocket). Checks whether the sending process was successful.

[1187] Step 5:

[1188] Server response generation process

[1189] The server generates an answer using a language model based on the text and emotion data it receives.

[1190] Input: Text data and emotion data

[1191] Output: Generated answer text

[1192] Description: Analyzes the received text and sentiment data and generates answers using a language model of historical figures. For example, when a question text is input, the system processes it so that the answer output is "You can see the nearby cafe by turning right at the next intersection. Please relax and enjoy your visit."

[1193] Step 6:

[1194] Send data from the server to the device

[1195] The generated answer text is sent to the terminal.

[1196] Input: Generated answer text

[1197] Output: Data packets sent to the device

[1198] Description: Sends the generated response text to the terminal using the appropriate communication protocol. Checks the content of the sent data and whether it was sent successfully.

[1199] Step 7:

[1200] Device speech synthesis processing

[1201] The device sends the response text from the server to a speech synthesis API, which converts it into voice data.

[1202] Input: Answer text

[1203] Output: Audio data

[1204] Description: Sends the answer text received from the server to a speech synthesis API such as Amazon Polly to generate audio data that is easy for the user to hear. Checks the quality and clarity of the audio data.

[1205] Step 8:

[1206] Device audio playback and feedback

[1207] The converted audio is played back to provide feedback to the user based on their emotional state.

[1208] Input: Voice data, emotion data

[1209] Output: Audio played, emotional feedback displayed

[1210] Description: The generated voice data is played through the in-car speakers to provide the user with an answer, while emotional feedback (e.g., visual indicators of relaxation or stress) is displayed on the in-car display to provide visual feedback to the user.

[1211] This will assist users in driving safely and efficiently, and allow them to receive appropriate information and advice in real time based on their physical and mental condition.

[1212] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[1213] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[1214] 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.

[1215] [Fourth embodiment]

[1216] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1217] 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.

[1218] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1219] 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1220] 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 audio in accordance with instructions from the processor 46.

[1221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1222] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1223] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. 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.

[1224] Fig. 8 shows an example of the 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.

[1225] 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.

[1226] 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.

[1227] In the robot 414, the processor 46 performs the reception output process. 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.

[1228] Next, a description will be given of the specific processing performed 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."

[1229] The present invention is a system that provides answers to problems and questions faced by users by utilizing the wisdom of great historical figures. This system is realized by combining voice input, a video chat interface, voice-to-text conversion, answer generation within the server, and voice conversion and playback functions. Specific embodiments are described below.

[1230] System Configuration

[1231] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface and captures the user's voice. The server uses a speech recognition API to convert the voice into text and then uses a language model to generate answers to the user's questions.

[1232] Program flow

[1233] 1. User Action:

[1234] The user launches the application on their device to start a video chat.

[1235] Users voice their questions or concerns.

[1236] 2. Terminal processing:

[1237] The device captures the user's voice in real time and converts it into text via a speech recognition API.

[1238] The converted text data is prepared for transmission to the server.

[1239] 3. Server processing:

[1240] The server receives the text data sent from the terminal.

[1241] Analyze the received data and select an appropriate language model.

[1242] The user's question text is input into the selected language model to generate an answer.

[1243] The generated answer text is prepared for transmission back to the terminal.

[1244] 4. Reprocessing the device:

[1245] The terminal receives the response text sent from the server.

[1246] The received text data is converted into voice data via a voice synthesis API.

[1247] The converted audio data is played back to provide the user with an answer.

[1248] Specific examples

[1249] Scenario: Business Leader Use Case

[1250] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[1251] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[1252] 2. Device: Captures the audio and converts it into text via a speech recognition API, saying "Please tell me effective coaching methods." This text is then sent to the server.

[1253] 3. Server: Analyzes the received text and uses a language model (e.g., "Management Scholar's Model") to generate an answer such as "The optimal coaching approach involves setting clear goals and providing repeated feedback." This answer is then sent back to the device.

[1254] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[1255] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[1256] The processing flow will be explained below.

[1257] Step 1:

[1258] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[1259] Step 2:

[1260] The user speaks a question, and the device captures the user's voice in real time through the microphone.

[1261] Step 3:

[1262] The device sends the captured voice data to the speech recognition API in real time and converts the voice into text data. This process converts the voice into text format.

[1263] Step 4:

[1264] The device temporarily stores the converted text data and prepares to send it to the server. For example, the text generated is "Please tell me effective coaching methods."

[1265] Step 5:

[1266] The server receives the text data sent from the terminal, analyzes the received text data, and selects an appropriate language model. In this case, the management scholar model is selected.

[1267] Step 6:

[1268] The server inputs the user's question text into the selected language model and generates an answer: "The best coaching involves clear goal setting and repeated feedback."

[1269] Step 7:

[1270] The server returns the generated answer text to the terminal, which sends the answer text to the terminal as an API response.

[1271] Step 8:

[1272] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[1273] Step 9:

[1274] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the voice data generated by the API.

[1275] Step 10:

[1276] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[1277] Through these steps, users can access the wisdom of great people in real time to answer their questions.

[1278] Example 1

[1279] 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 robot 414 will be referred to as a "terminal."

[1280] Conventional information search and advice systems have limited ability to provide fast and accurate answers to problems and questions that users face. In addition, when users ask questions by voice, the process of efficiently converting the voice into text and then generating high-quality answers based on that text is complex and time-consuming, which has been an issue.

[1281] 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.

[1282] In this invention, the server includes means for capturing a user's voice input with a video chat interface, means for converting the captured voice input to text in real time, means for transmitting the converted text to the server, the server utilizing a generative AI model for generating answers based on the text, means for receiving answers from the server and converting the answers to speech, and means for playing the converted speech to the user, thereby enabling users to exchange questions and answers in real time and providing information quickly and accurately.

[1283] "User" refers to any individual or organization that uses the system to ask questions or obtain information.

[1284] "Voice input" refers to the audio data spoken by a user that is captured and processed by the system.

[1285] "Video chat interface" means a communication method used by a user to transmit audio in real time, and an interface that processes audio and video data.

[1286] "Capture" refers to the act of capturing a user's audio input or video data.

[1287] "Real-time" refers to a state in which there is only a momentary delay between input and result, meaning that processing occurs almost instantaneously.

[1288] "Means of converting to text" refers to the technology or software used to convert audio data into text data.

[1289] "Server" refers to a computer system for receiving data over a network, processing it, and sending the results.

[1290] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate new text or answers based on input data.

[1291] "Means for converting to audio" refers to the technology or software used to convert text data into audio data.

[1292] "Means for playing" refers to a device or technology that outputs audio data as sound so that the user can hear it.

[1293] This invention is a system that allows users to ask questions by voice and receive answers in real time. This system is realized by combining technologies such as a video chat interface, a speech recognition API, a generative AI model, and a speech synthesis API.

[1294] System Configuration

[1295] This system operates via a user terminal, a server, and internet communication. The main components are described below.

[1296] User Device

[1297] The user terminal is a device that captures the user's voice input in the video chat interface. The terminal has a built-in microphone that collects voice in real time. It also has the ability to convert voice to text using a speech recognition API and send the converted text to the server.

[1298] server

[1299] The server receives the text data and uses a generative AI model to generate answers based on that text. The server has multiple generative AI models and selects the appropriate model depending on the content of the user's question. Specifically, it can use an AI model trained on records of historical figures' statements, for example.

[1300] Speech Recognition API

[1301] For example, the Google Speech-to-Text API can be used as a speech recognition API, which allows you to convert the user's voice into text with high accuracy.

[1302] Generative AI Models

[1303] Generative AI models such as OpenAI's GPT series can be used, which can generate appropriate answers to user questions.

[1304] Text-to-Speech API

[1305] For example, Amazon Polly can be used as a speech synthesis API, which converts text responses generated on the server into speech and provides the user with a spoken response.

[1306] Specific examples

[1307] Scenario: Business Leader Use Case

[1308] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[1309] 1. User: The business leader launches the app on their device and starts a video chat session. They voice-type the question, "What are some effective coaching methods?"

[1310] 2. Device: Captures the audio and converts it to text using the Google Speech-to-Text API: "Please tell me effective coaching methods." Sends this text to the server.

[1311] 3. Server: Analyzes the received text and uses a generative AI model such as GPT-3 to generate an answer such as, "The optimal coaching is to set clear goals and provide repeated feedback." This answer is then sent back to the device.

[1312] 4. Device: Receives the answer and converts it into speech using Amazon Polly. The converted speech, "The best coaching is clear goal setting and repeated feedback," is played back and provided to the business leader.

[1313] The system provides business leaders with meaningful advice in real time, enabling them to make more accurate decisions.

[1314] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1315] Step 1:

[1316] User Actions

[1317] The user launches the app on their device and starts a video chat session. The user then inputs a question by voice. The input is the user's voice data. Specifically, the user taps the app on their smartphone, presses the "Start Video Chat" button, and speaks the question, "Please tell me effective coaching methods."

[1318] Step 2:

[1319] Device audio capture

[1320] The device captures the user's voice in real time. The input is the user's voice data, and the output is the captured voice data. Specifically, the device's microphone is used to collect the user's speech.

[1321] Step 3:

[1322] On-device speech recognition and text conversion

[1323] The device converts the captured voice data into text using a speech recognition API. The input is voice data, and the output is the converted text data. Specifically, the voice data is sent to the API in byte stream format, and the string returned as the conversion result is obtained. The Google Speech-to-Text API is used as the voice recognition API.

[1324] Step 4:

[1325] Sending data from the device to the server

[1326] The terminal sends the converted text data to the server using an HTTP request. The input is the text data, and the output is the text data sent to the server. Specifically, a POST request is sent to the " / send_text" endpoint, and the converted text is included in the payload.

[1327] Step 5:

[1328] Data reception and analysis on the server

[1329] The server receives and analyzes text data sent from the device. The input is the text data received from the device, and the output is category data as the analysis result. For example, the server analyzes the text "Please tell me effective coaching methods" and determines a category such as "business management."

[1330] Step 6:

[1331] Answer generation using a server-based AI model

[1332] The server selects an appropriate language model and generates an answer to the user's question. The input is the analyzed text data and categorical data, and the output is the generated answer text. Specifically, the user's question is input as a prompt into the generative AI model, and the generated answer is obtained. OpenAI's GPT series is used as the generative AI model.

[1333] Step 7:

[1334] Sending a response from the server to the device

[1335] The server returns the generated answer text to the terminal. The input is the generated answer text, and the output is the answer text sent to the terminal. Specifically, the answer text is included in the payload of the HTTP response.

[1336] Step 8:

[1337] Answer text-to-speech on your device

[1338] The device converts the response text received from the server into voice data using a speech synthesis API. The input is the response text data, and the output is the converted voice data. Specifically, the text data is sent to the API and the generated voice file is obtained. Amazon Polly is used as the speech synthesis API.

[1339] Step 9:

[1340] Play audio on the device and provide answers to the user

[1341] The device plays the converted audio data and provides the user with an answer. The input is audio data, and the output is audio that the user can hear. Specifically, the audio is played using a speaker within the device, allowing the user to hear the audio answer. For example, the answer audio may say, "The best coaching involves setting clear goals and providing repeated feedback."

[1342] (Application example 1)

[1343] 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."

[1344] Logistics centers need a way to quickly and accurately resolve the questions and problems that staff encounter during their daily work. However, with the current system, staff often spend a lot of time resolving questions, which can reduce productivity. It is also difficult to immediately obtain appropriate advice and knowledge, making it difficult to take immediate action to improve work efficiency and quality. A new method is needed to solve these issues.

[1345] 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.

[1346] In this invention, the server includes means for capturing a user's voice input using a video chat interface, means for converting the captured voice input into text in real time, means for transmitting the converted text to the server, and means for staff working at the logistics center to voice-input business-related questions and for generating and providing answers to those questions based on the wisdom of historical figures. This enables staff to quickly and accurately resolve their questions, which is expected to improve work efficiency and productivity.

[1347] "Users" refer to staff at the logistics center who use the system to input voice data and receive responses.

[1348] "Audio Input" means audio data provided by a user through a microphone or video chat interface.

[1349] "Video chat interface" means an interface for capturing a user's voice input and transmitting it to a server in real time.

[1350] "Means for converting to text" refers to technology for converting voice data into text data using a voice recognition API.

[1351] "Server" refers to a central processing unit that receives the converted speech-to-text data, generates answers using an appropriate language model, and sends them back to the user.

[1352] A "language model" is an algorithm that is primarily based on natural language processing techniques, is trained on recorded statements of historical figures, and generates answers to user questions.

[1353] The "means for converting to voice" refers to a voice synthesis API for converting the generated text-formatted answer into voice data.

[1354] "Real-time" is a time concept that refers to processing occurring immediately after the user makes a voice input, with almost no delay.

[1355] A "speech recognition API" is an application program interface that accurately converts voice data captured from a user into text data.

[1356] A "historical figure" is a famous person who had specialized knowledge or experience in the past and whose recorded statements are still used as useful information today.

[1357] System Configuration

[1358] This system uses a speech recognition API and a speech synthesis API to convert the user's voice input into text, and then uses a generative AI model to generate an answer based on that text, which is then converted back into speech and provided to the user. Specifically, staff working at logistics centers use devices such as smartphones and robots to quickly resolve questions.

[1359] Hardware

[1360] Smartphones: Staff carry and use them.

[1361] Robots: Installed in specific locations within the logistics center.

[1362] Microphone: Used for voice input.

[1363] Speaker: Used for audio playback.

[1364] software

[1365] Speech Recognition API: Uses the Google Speech Recognition API, which converts the user's speech into text.

[1366] Generative AI model: Uses OpenAI's model to provide generated text data as answers.

[1367] Use the speech synthesis API: pyttsx3 to convert text data into speech.

[1368] Operation explanation

[1369] 1. Voice capture: Users voice their questions through a smartphone or robotic video chat interface.

[1370] 2. Speech recognition: The device captures the user's voice in real time and converts it into text through the speech recognition API.

[1371] 3. Send to Server: The converted text is sent to the server.

[1372] 4. Answer generation using language model: The server analyzes the received text and generates an appropriate answer using a language model trained based on the speech records of historical figures.

[1373] 5. Speech synthesis: The generated answer text is converted into speech via a speech synthesis API.

[1374] 6. Audio playback: Play the converted audio back to the user and provide the answer.

[1375] Specific examples

[1376] Imagine a distribution center employee has a question about the best way to manage inventory. They use their smartphone to ask, "What's the best way to manage inventory?"

[1377] Prompt Sentence Examples

[1378] "What's the best way to manage inventory?"

[1379] The device captures this audio and converts it into text using the Google Speech Recognition API: "What is the best way to manage inventory?" This text is sent to a server and input as a prompt to OpenAI's generative AI model: "What would a great historical figure say if they were to answer the question, 'What is the best way to manage inventory?'" The generated answer is something like, "The best way to manage inventory is to periodically check inventory and accurately record the data." This text response is converted into speech using pyttsx3 and played to staff via their smartphones or robot speakers.

[1380] This allows logistics center staff to quickly resolve queries and improve operational efficiency and productivity.

[1381] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1382] Step 1:

[1383] Audio capture and input

[1384] A user voices a question through a smartphone or robotic video chat interface. For example, the user might say, "What's the best way to manage inventory?" This voice data is captured by the interface.

[1385] Step 2:

[1386] Voice Recognition

[1387] The device sends the captured voice data to the Google Speech Recognition API. The API returns the voice data as text data. The input voice "What is the best way to manage inventory?" is converted to the text "What is the best way to manage inventory?" in real time.

[1388] Step 3:

[1389] Sending text data

[1390] The terminal transmits the converted text data to the server. Specifically, the text "What is the best way to manage inventory?" is transmitted to the server.

[1391] Step 4:

[1392] Using language models to generate answers

[1393] Based on the text data received by the server, an appropriate language model is selected and an answer is generated. Specifically, OpenAI's generative AI model is used, and the prompt sentence is input as "What would a great historical figure say in response to the question, 'What is the best method for inventory management?'" The answer text output by the generative AI model is "The best method for inventory management is to periodically check inventory and accurately record the data."

[1394] Step 5:

[1395] Sending answer text

[1396] The server generates a response text and returns it to the terminal. Specifically, the text "The best way to manage inventory is to periodically check inventory and record the data accurately" is sent to the terminal.

[1397] Step 6:

[1398] Speech synthesis

[1399] The device sends the received response text to the speech synthesis API. The API outputs the text data as voice data. Specifically, the text "The best way to manage inventory is to periodically check inventory and accurately record the data" is converted into voice data.

[1400] Step 7:

[1401] Audio playback and output

[1402] The terminal plays audio data and provides it to the user. Specifically, the audio played through the speaker says, "The best way to manage inventory is to periodically check your inventory and record the data accurately."

[1403] Furthermore, 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.

[1404] The present invention is a system that utilizes the wisdom of historical figures to provide answers to problems and questions faced by users, and also combines an emotion engine to recognize the user's emotions. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, answer generation within the server, and speech conversion and playback functions. Specific embodiments are described below.

[1405] System Configuration

[1406] The system operates via a user device, a server, and internet communication. The user device acts as a video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the voice into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[1407] Program flow

[1408] 1. User Action:

[1409] The user launches the application on their device to start a video chat.

[1410] Users voice their questions or concerns.

[1411] 2. Terminal processing:

[1412] The device captures the user's voice and video in real time through a microphone and camera.

[1413] The voice data is sent to a voice recognition API, which converts the voice into text data.

[1414] Video data and audio input are sent to an emotion engine to analyze the user's emotional state.

[1415] The converted text data and the analyzed emotion data are prepared for transmission to the server.

[1416] 3. Server processing:

[1417] The server receives the text data and emotion data sent from the terminal.

[1418] Analyzes incoming data, selects appropriate language models, and adjusts response content based on sentiment data.

[1419] The language model inputs the user's question text and generates an answer that reflects the emotional data.

[1420] The generated answer text is prepared for transmission back to the terminal.

[1421] 4. Reprocessing the device:

[1422] The terminal receives the response text sent from the server.

[1423] The received text data is sent to a speech synthesis API, which converts the text into speech data.

[1424] The converted audio data is played back to provide the user with an answer.

[1425] The emotion engine analyzes the user's emotional state and provides feedback to them, for example by displaying a corresponding emoticon or text message.

[1426] Specific examples

[1427] Scenario: Business Leader Use Case

[1428] Imagine a business leader asks during a meeting, "What are some effective coaching techniques?"

[1429] 1. User: The business leader launches the app on their device, starts a video chat session, and dictates the question: "What are some effective coaching methods?"

[1430] 2. Device: Captures the audio and converts it into text via a speech recognition API, such as "Please tell me effective coaching methods." At the same time, the emotional engine uses the captured video and audio data to analyze the user's emotional state. This data is then sent to the server.

[1431] 3. Server: Analyzes the received text and sentiment data, and uses a language model developed by past management scholars to generate a response such as, "The best coaching involves clear goal setting and repeated feedback." The generated response is then sent back to the device.

[1432] 4. Device: Receives the answer and converts it into speech via a speech synthesis API. The converted speech, "The best coaching involves clear goal setting and repeated feedback," is played back and provided to the business leader. The emotion engine then analyzes the user's emotional state and provides visual feedback to the user.

[1433] This system allows business leaders to not only access the wisdom of great people in real time in response to their questions, but also receive feedback on their own emotional state, helping them make better decisions.

[1434] The processing flow will be explained below.

[1435] Step 1:

[1436] A user launches a video chat application and presses a button to start a video chat, which enables the device's camera and microphone and displays the video chat interface.

[1437] Step 2:

[1438] The user speaks out their question or inquiry, and the device captures the user's voice in real time through the microphone.

[1439] Step 3:

[1440] The device sends the captured voice data to a speech recognition API, which converts the voice into text. For example, the voice input "Please tell me effective coaching methods" is converted into text "Please tell me effective coaching methods."

[1441] Step 4:

[1442] The device captures the user's video data in real time and sends it to the emotion engine, which analyzes the audio and video data to recognize the user's emotional state.

[1443] Step 5:

[1444] The device sends the converted text data and the analyzed emotion data to the server. For example, the text data "Please tell me effective coaching methods" and the emotion data are sent.

[1445] Step 6:

[1446] The server receives the text data and emotion data sent from the device, analyzes the received text data, and selects an appropriate language model. The emotion data is used to adjust the response content.

[1447] Step 7:

[1448] The server inputs the user's question text into the selected language model and generates an answer that reflects the emotional data, such as "The best coaching involves clear goal setting and repeated feedback."

[1449] Step 8:

[1450] The server returns the generated answer text to the terminal, which then sends the answer text as an API response.

[1451] Step 9:

[1452] The device receives the answer text sent from the server and temporarily stores it. For example, the text received may read, "Optimal coaching involves clear goal setting and repeated feedback."

[1453] Step 10:

[1454] The device sends the received response text to the speech synthesis API, converts the text into voice data, and retrieves the converted voice data.

[1455] Step 11:

[1456] The device plays back the captured audio data and provides the user with a response, which they can hear: "The best coaching involves clear goal setting and repeated feedback."

[1457] Step 12:

[1458] The device will then provide feedback to the user about the emotional state analyzed by the emotion engine, for example by displaying a smiley face icon or a text description of the emotion as visual feedback.

[1459] Through the above steps, the present invention not only allows users to utilize the wisdom of great people in response to their questions in real time, but also provides feedback on their own emotional state, which helps users make better decisions.

[1460] Example 2

[1461] 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."

[1462] Currently, there are many information search systems and virtual assistants, but these systems only provide standardized answers without taking the user's emotional state into account. This makes it difficult to obtain accurate answers that reflect the user's true needs and emotions. Furthermore, there are no systems that provide advanced answers that utilize the wisdom of great historical figures. This limits opportunities for users to gain deep insight into the problems and questions they face.

[1463] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1464] In this invention, the server includes means for utilizing an emotion model to analyze the user's emotional state, means for utilizing a generative model to generate answers based on text, and means for feeding back the analyzed emotional state to the user, thereby making it possible to provide accurate and deep insights that utilize the wisdom of great people while taking the user's emotional state into consideration.

[1465] "User" means any person or entity that uses the System to resolve a problem or question.

[1466] "Voice input" refers to voice data emitted by a user through a microphone.

[1467] A "communication interface" is an interface for capturing audio input and exchanging data with the system.

[1468] "Convert to text" refers to the process of converting captured audio data into character string data.

[1469] A "server" is a central repository for receiving data submitted by users and generating responses.

[1470] A "generative model" is an AI model that generates appropriate answers based on input text data.

[1471] An "emotion model" is an AI model that analyzes a user's voice and video data to identify their emotional state.

[1472] "Providing feedback" refers to the process of returning the analysis results to the user in an easy-to-understand format.

[1473] A "speech recognition API" is an application programming interface for converting voice data into text data.

[1474] "Records of great people" are records of the words and actions of important historical figures.

[1475] This invention is a system that provides answers to questions or doubts posed by users through voice input, taking into account their emotional state and utilizing the wisdom of great historical figures. This system is realized by combining voice input, a communication interface, a speech recognition API, an emotion model, a generative model, and a speech synthesis API.

[1476] System Configuration

[1477] The system operates via a user device, a server, and a communication network. The user device acts as a communication interface and captures the user's voice and video. The server converts the voice into text using a speech recognition API and then analyzes the user's emotional state using an emotion model. The server then generates an answer using a generative model and finally provides the answer to the user using a speech synthesis API.

[1478] Hardware and Software

[1479] User device: Use a device with a built-in camera and microphone, such as a computer, tablet, or smartphone.

[1480] Communication interface: Uses an internet connection.

[1481] Speech recognition API: Convert speech to text using something like the Google Cloud Speech-to-Text API.

[1482] Emotion model: Analyze the user's emotional state using, for example, the Microsoft Azure Emotion API.

[1483] Generative models: Generate answers using generative AI models such as OpenAI's GPT-4.

[1484] Text-to-speech API: Convert text to speech using tools such as Amazon Polly.

[1485] Example

[1486] For example, consider a situation where a business leader asks, "What are effective coaching methods?" during a meeting. The user launches an app on their device and starts a video chat session. They then voice-input the question. The device captures the audio and converts it into text, "What are effective coaching methods?" via a speech recognition API. In parallel, the captured video and audio data is sent to an emotion model to analyze the emotional state. This data is then sent to the server, which selects an appropriate generative model and inputs it as a prompt.

[1487] Prompt Sentence Examples

[1488] "Please tell me how to coach effectively."

[1489] The server uses the generative model to generate an answer such as, "Optimal coaching involves clear goal setting and repeated feedback." The generated answer is then sent back to the device. The device then converts the received answer into speech via a speech synthesis API and plays it back to the user. Additionally, the device visually feeds back the analyzed emotional state to the user.

[1490] This system allows users to access the wisdom of great people in real time and also check their own emotional state, allowing them to gain more accurate and deeper insights.

[1491] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1492] Step 1:

[1493] A user starts a video chat session by launching a video chat application on their device. The user taps the "Start" button to enable audio input, which allows the user's voice and video to be captured.

[1494] Input: User actions (tapping the "Start" button), audio, video

[1495] Output: Captured audio and video data

[1496] Step 2:

[1497] The device uses the built-in microphone and camera to capture the user's voice and video in real time, and the captured voice and video are saved in a temporary file.

[1498] Input: Captured audio and video data

[1499] Output: Audio and video data saved to a temporary file

[1500] Step 3:

[1501] The device sends the captured voice data to the voice recognition API, which converts the voice data into text data. The device sends the voice data to the voice recognition API, and the API returns the text data.

[1502] Input: Audio data

[1503] Output: Text data (e.g., "Please tell me effective coaching methods.")

[1504] Step 4:

[1505] The device sends the captured video and audio data to the emotion model, which analyzes the user's emotional state. The emotion model generates and returns an emotion value (e.g., joy, sadness, etc.) based on the video and audio.

[1506] Input: Video data, audio data

[1507] Output: Emotion data (e.g. "Happiness: 0.8, Sadness: 0.1, Anger: 0.1")

[1508] Step 5:

[1509] The device sends the converted text data and analyzed emotion data to the server, which receives this data and selects an appropriate generative AI model.

[1510] Input: Text data, emotion data

[1511] Output: Text data and emotion data sent to the server

[1512] Step 6:

[1513] The server inputs text data and emotional data into the generative AI model and generates an answer that takes the user's emotions into account. For example, if the prompt sentence is "Please tell me effective coaching methods," the server generates the answer "The best coaching involves clear goal setting and repeated feedback" by taking the emotional data into account.

[1514] Input: Text data (prompt sentence), emotion data

[1515] Output: Text response data (e.g., "The best coaching involves clear goal setting and repeated feedback.")

[1516] Step 7:

[1517] The server returns the generated answer text data to the device. The device then sends the answer text data to the speech synthesis API, which converts it into voice data. The converted voice data is played back through the device's speaker.

[1518] Input: Answer text data

[1519] Output: Audio data

[1520] Step 8:

[1521] The device will then provide feedback to the user based on the emotional state analyzed by the emotion engine. For example, if the user's happiness level is 0.8, a smiley face icon and a message such as "You are happy now" will be displayed on the screen.

[1522] Input: Emotion data

[1523] Output: Visual feedback of emotional state (e.g., smiley face icon and message)

[1524] (Application example 2)

[1525] 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."

[1526] Autonomous driving vehicles require the provision of appropriate information that takes into account the physical and mental state of the user (driver). In particular, systems are needed that can reduce the stress and fatigue that users feel while driving and assist in safe and comfortable driving. Conventional information provision systems only provide uniform information without considering the user's emotional state, which results in the problem of not being able to provide appropriate advice depending on the user's emotional state.

[1527] 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.

[1528] In this invention, the server includes means for analyzing the user's voice input and video data to recognize the user's emotional state, means for using a language model to generate an answer based on the text and emotional data, and means for providing the user with feedback based on the emotional state received from the server, thereby making it possible to grasp the user's emotional state in real time and provide information optimized for the user's state.

[1529] "Means for capturing user's voice input in a video chat interface" refers to an interface device for capturing user's voice along with the video.

[1530] "Means for converting voice data into text in real time" refers to a technical device for instantly converting voice data into text data.

[1531] The "means for transmitting the converted text and video data to a server" refers to a communication means for transmitting the text data and video data to a remote server.

[1532] A "server that uses a language model to generate answers based on text and emotion data" is a server that operates a language model used to create appropriate answers based on the user's input text and the results of emotion analysis.

[1533] The "means for receiving a response from the server and converting the response into speech" is a technical device for converting the text-format response sent from the server into speech format.

[1534] The "means for playing back the converted audio to the user" is a playback device that allows the user to listen to the audio data.

[1535] The "means for recognizing a user's emotional state by analyzing the user's video data and audio input" is an analysis system for reading emotions from the user's video data and audio input.

[1536] The "means for providing the user with feedback based on the emotional state received from the server" is a technical device for providing the user with appropriate feedback or advice based on the analyzed emotional state of the user.

[1537] This invention is a driver assistant AI system for autonomous vehicles that provides appropriate information and advice taking into account the user's physical and mental state. This system is realized by combining voice input, a video chat interface, speech-to-text conversion, emotion recognition, response generation within the server, and speech conversion and playback functions.

[1538] System Configuration

[1539] The system operates via a user device, a server, and internet communications. The user device acts as an in-car video chat interface, capturing the user's voice and video. The server uses a speech recognition API to convert the speech into text and a language model to generate answers to the user's questions. The emotion engine also analyzes the user's voice input and video data to recognize the user's emotional state in real time.

[1540] Hardware and software used

[1541] Microphone and camera: Hardware devices that capture the user's voice and video.

[1542] Speech recognition APIs (e.g., Google Cloud Speech-to-Text): Cloud-based services for converting speech to text.

[1543] Emotion Recognition API (e.g., Affectiva or Azure Emotion API): A cloud-based service for analyzing a user's emotional state from video data.

[1544] Speech synthesis API (e.g., Amazon Polly): A cloud-based service that converts text data into audio data that is easy for users to understand.

[1545] Server: Provides the computational resources to process the received data and generate answers, and also operates a language model of historical figures to generate appropriate answers based on the user's question.

[1546] Explanation of program processing

[1547] The server converts the voice data sent from the device into text using the Google Cloud Speech-to-Text API. It then uses emotion recognition APIs such as Affectiva and Azure Emotion API to analyze the user's emotional state from the video data in real time. The analyzed text and emotion data are used to generate answers based on a language model stored on the server. This language model is trained on recordings of historical figures' speeches and can adjust the generated answers based on the emotion data.

[1548] The generated answer is converted into audio data using a speech synthesis API such as Amazon Polly and sent to the user's device. The user's device plays back the audio data and provides the answer to the user. At the same time, feedback (e.g., a visual indicator) based on the results of the sentiment analysis is displayed to the user.

[1549] Specific examples

[1550] Scenario: Route guidance in an autonomous vehicle

[1551] Consider the case where a passenger asks, "What is the nearest cafe from here?" while in the car.

[1552] 1. User: The user speaks to the in-car video chat interface, saying, "What is the nearest cafe from here?"

[1553] 2. Device: Captures audio and converts it into text using the Google Cloud Speech-to-Text API, such as "Please tell me the nearest cafe from here." The captured video and audio data are then analyzed for emotional state using Affectiva and Azure Emotion API. This data is then sent to the server.

[1554] 3. Server: Analyzes the received text and sentiment data and uses a language model of great people from the past to generate an answer such as, "You can see a nearby cafe by turning right at the next intersection. Please relax and enjoy yourself."

[1555] 4. Device: The answer returned from the server is converted into voice data using Amazon Polly and played back to the user through the car speakers. At the same time, visual feedback based on the user's emotional state is displayed on the display.

[1556] Prompt Sentence Examples

[1557] "Can you tell me the nearest cafe? Our users seem a little tired."

[1558] This system will enable users of autonomous vehicles to receive appropriate navigation information and advice in real time that takes their emotional state into account, making for a safer and more comfortable drive.

[1559] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1560] Step 1:

[1561] User Actions

[1562] Users ask questions via voice over an in-car video chat interface.

[1563] Input: Audio data

[1564] Output: Captured audio and video data

[1565] Description: The user asks a question aloud through an in-car video chat interface, such as "What is the nearest cafe from here?" The user's voice and facial expressions are simultaneously captured by the microphone and camera.

[1566] Step 2:

[1567] Device voice recognition processing

[1568] The device sends the voice data to a speech recognition API, which converts it into text in real time.

[1569] Input: Captured audio data

[1570] Output: Text data

[1571] Description: Send the captured audio data to the Google Cloud Speech-to-Text API and obtain the text data "Please tell me the nearest cafe from here." Check the conversion result and verify that there are no errors.

[1572] Step 3:

[1573] Device emotion recognition processing

[1574] The device sends video and audio data to an emotion recognition API to analyze the user's emotional state.

[1575] Input: Captured video and audio data

[1576] Output: Emotion data

[1577] Description: Send video and audio data to Affectiva or Azure Emotion API, and obtain the user's emotional state (e.g., fatigue, relaxation, stress, etc.) as the analysis result. Check the accuracy of the emotional data.

[1578] Step 4:

[1579] Send data from the device to the server

[1580] The text data and the emotion data are transmitted to a server.

[1581] Input: Text data and emotion data

[1582] Output: Data packet sent to the server

[1583] Description: Sends the converted text data and emotion data to the server using an appropriate communication protocol (e.g. HTTP, WebSocket). Checks whether the sending process was successful.

[1584] Step 5:

[1585] Server response generation process

[1586] The server generates an answer using a language model based on the text and emotion data it receives.

[1587] Input: Text data and emotion data

[1588] Output: Generated answer text

[1589] Description: Analyzes the received text and sentiment data and generates answers using a language model of historical figures. For example, when a question text is input, the system processes it so that the answer output is "You can see the nearby cafe by turning right at the next intersection. Please relax and enjoy your visit."

[1590] Step 6:

[1591] Send data from the server to the device

[1592] The generated answer text is sent to the terminal.

[1593] Input: Generated answer text

[1594] Output: Data packets sent to the device

[1595] Description: Sends the generated response text to the terminal using the appropriate communication protocol. Checks the content of the sent data and whether it was sent successfully.

[1596] Step 7:

[1597] Device speech synthesis processing

[1598] The device sends the response text from the server to a speech synthesis API, which converts it into voice data.

[1599] Input: Answer text

[1600] Output: Audio data

[1601] Description: Sends the answer text received from the server to a speech synthesis API such as Amazon Polly to generate audio data that is easy for the user to hear. Checks the quality and clarity of the audio data.

[1602] Step 8:

[1603] Device audio playback and feedback

[1604] The converted audio is played back to provide feedback to the user based on their emotional state.

[1605] Input: Voice data, emotion data

[1606] Output: Audio played, emotional feedback displayed

[1607] Description: The generated voice data is played through the in-car speakers to provide the user with an answer, while emotional feedback (e.g., visual indicators of relaxation or stress) is displayed on the in-car display to provide visual feedback to the user.

[1608] This will assist users in driving safely and efficiently, and allow them to receive appropriate information and advice in real time based on their physical and mental condition.

[1609] 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 voice indicating a user input regarding 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.

[1610] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with 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.

[1611] 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 robot 414.

[1612] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1613] FIG. 9 is a diagram illustrating 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1614] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[1615] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1616] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1617] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1618] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of 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, "relieved," "calm," and "reassuring," have similar emotion values.

[1619] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on 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 running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1620] In the above embodiment, an example was 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 data may be generated in the external device in accordance with input data.

[1621] 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 USB (Universal Serial Bus) 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.

[1622] Alternatively, 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 in response to a request from the data processing device 12.

[1623] 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.

[1624] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1625] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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 processing may be a single processor.

[1626] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[1627] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1628] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1629] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1630] The following is further disclosed regarding the above embodiment.

[1631] (Claim 1)

[1632] a means for capturing a user's voice input in a video chat interface;

[1633] A means of converting captured voice input into text in real time; and

[1634] means for transmitting the converted text to a server;

[1635] a server that utilizes a language model to generate answers based on the text;

[1636] means for receiving a response from the server and converting the response into speech;

[1637] means for playing the converted audio to the user;

[1638] A system including:

[1639] (Claim 2)

[1640] 2. The system according to claim 1, wherein the means for capturing the voice input and converting it into text in real time uses a voice recognition API via Internet communication.

[1641] (Claim 3)

[1642] 2. The system of claim 1, wherein the language model used by the server to generate the answer is trained based on recorded statements of historical figures.

[1643] (Claim 4)

[1644] 2. The system of claim 1, wherein the means for converting the response into speech uses a speech synthesis API.

[1645] (Claim 5)

[1646] 10. The system of claim 1, wherein the video chat interface is capable of simultaneously capturing and communicating with a user's video and audio.

[1647] "Example 1"

[1648] (Claim 1)

[1649] a means for capturing a user's voice input in a video chat interface;

[1650] A means of converting captured voice input into text in real time; and

[1651] means for transmitting the converted text to a server;

[1652] a server utilizing a generative AI model to generate answers based on the text;

[1653] means for receiving a response from the server and converting the response into speech;

[1654] means for playing the converted audio to the user;

[1655] A system including:

[1656] (Claim 2)

[1657] 2. The system according to claim 1, wherein the means for capturing the voice input and converting it into text in real time uses a voice recognition API via Internet communication.

[1658] (Claim 3)

[1659] The system of claim 1, wherein the generative AI model used by the server to generate the answer is trained based on recorded statements of historical figures.

[1660] "Application Example 1"

[1661] (Claim 1)

[1662] a means for capturing a user's voice input in a video chat interface;

[1663] A means of converting captured voice input into text in real time; and

[1664] means for transmitting the converted text to a server;

[1665] a server that utilizes a language model to generate answers based on the text;

[1666] means for receiving a response from the server and converting the response into speech;

[1667] means for playing the converted audio to the user;

[1668] The system includes a means for staff working at a logistics center to input work-related questions by voice, and for generating and providing answers to those questions based on the wisdom of historical figures.

[1669] (Claim 2)

[1670] 2. The system according to claim 1, wherein the means for capturing the voice input and converting it into text in real time uses a voice recognition API via Internet communication.

[1671] (Claim 3)

[1672] 2. The system of claim 1, wherein the language model used by the server to generate the answer is trained based on recorded statements of historical figures.

[1673] "Example 2: Combining Emotion Engines"

[1674] (Claim 1)

[1675] means for capturing user voice input with a communications interface;

[1676] A means of converting captured voice input into text in real time; and

[1677] means for transmitting the converted text to a server;

[1678] a server utilizing a generative model to generate answers based on text;

[1679] a server utilizing an emotion model for analyzing the user's emotional state;

[1680] means for receiving a response from the server and converting the response into speech;

[1681] means for playing the converted audio to the user;

[1682] a means for providing feedback to the user about the analyzed emotional state;

[1683] A system including:

[1684] (Claim 2)

[1685] 2. The system according to claim 1, wherein the means for capturing the voice input and converting it into text in real time uses a voice recognition API via a communication network.

[1686] (Claim 3)

[1687] 2. The system of claim 1, wherein the generative model used by the server to generate the answer is trained based on records of great people.

[1688] "Application example 2 when combining emotion engines"

[1689] (Claim 1)

[1690] a means for capturing a user's voice input in a video chat interface;

[1691] A means of converting captured voice input into text in real time; and

[1692] means for transmitting the converted text and video data to a server;

[1693] a server that utilizes a language model to generate answers based on text and emotion data;

[1694] means for receiving a response from the server and converting the response into speech;

[1695] means for playing the converted audio to the user;

[1696] a means for analyzing a user's video data and audio input to recognize their emotional state;

[1697] means for providing feedback to the user based on the emotional state received from the server;

[1698] A system including:

[1699] (Claim 2)

[1700] The system according to claim 1, characterized in that the means for capturing the voice input and video data, converting it into text in real time, and performing emotion analysis uses a voice recognition API and an emotion recognition API via Internet communication.

[1701] (Claim 3)

[1702] 2. The system of claim 1, wherein the language model used by the server to generate the answer is trained based on recorded statements of historical figures and further adjusts the generated answer based on emotional data. [Explanation of symbols]

[1703] 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. a means for capturing a user's voice input in a video chat interface; A means of converting captured voice input into text in real time; and means for transmitting the converted text to a server; a server that utilizes a language model to generate answers based on the text; means for receiving a response from the server and converting the response into speech; means for playing the converted audio to the user; A system including:

2. 2. The system according to claim 1, wherein the means for capturing the voice input and converting it into text in real time uses a voice recognition API via internet communication.

3. 2. The system of claim 1, wherein the language model used by the server to generate the answer is trained on recorded statements of historical figures.

4. 2. The system of claim 1, wherein the means for converting the response into speech uses a speech synthesis API.

5. 10. The system of claim 1, wherein the video chat interface is capable of simultaneously capturing and communicating with a user's video and audio.

Images