system

Abstract

The system provides users with quick and accurate answers to specific questions regarding how to use their smartphones. [Solution] A system comprising: means for a user to input a question using a personal digital assistant (PDA); means for the PDA to acquire voice or text data; means for the PDA to convert voice data into text; means for the PDA to send text data to a server; means for the server to analyze text data using a natural language processing engine and understand the intent of the question; means for the server to generate an answer based on the text data using an AI model; means for the server to convert the generated text answer into voice data; means for the server to send voice data and text data to the PDA; and means for the PDA to play voice data and display text data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Describe "Problems to be Solved by the Invention" and "Means for Solving the Problems".

[0005] Modern mobile information terminals are multifunctional, and it is often difficult for ordinary users to understand and master all functions. Therefore, users may not be able to quickly understand the operation methods and setting methods they need and may get lost in operations. Existing solutions to address this problem include online manuals and official FAQs, etc., but these lack immediacy, and there is a need for a method that allows users to quickly and individually respond to specific questions.

Means for Solving the Problems

[0006] To solve this problem, the present invention provides a system that links a mobile information terminal (PDT) with a server. The system has a means for the user to input a question using the PDT in voice or text, and the PDT acquires the voice data and converts it to text as needed. Next, the text data is sent to the server, which uses a natural language processing engine to understand the intent of the question. Furthermore, the server uses an AI model to generate an appropriate answer and converts this answer text into voice data using a speech synthesis engine. Finally, the generated voice data and text data are sent to the PDT, and the user can receive the answer in voice and text format. In this way, the user can quickly and accurately obtain answers to specific problems regarding the use of their smartphone.

[0007] A "personal information terminal" is an electronic device that a user can carry with them, equipped with communication functions and various applications.

[0008] "Voice input" refers to a method of inputting voice data spoken by the user through a microphone into an interface.

[0009] "Text input" refers to the method by which a user enters text information using an input device such as a keyboard.

[0010] "Speech recognition technology" is a technology for converting speech data into text data.

[0011] A "natural language processing engine" is a computational technology and software used to understand, analyze, and generate responses to human language.

[0012] An "AI model" is a collection of algorithms that use machine learning and deep learning methodologies to learn from data and automatically make decisions and predictions.

[0013] A "speech synthesis engine" is a technology and software used to convert text data into speech data.

[0014] A "server" is a computer system that provides various types of services and resources to client devices over a network. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0036] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0037] System Configuration

[0038] 1. Mobile device

[0039] These are electronic devices such as smartphones and tablets that users carry with them.

[0040] It is equipped with means for voice input and text input.

[0041] It has communication capabilities to process input data and send it to the server.

[0042] It has the function of converting voice input into text using speech recognition technology.

[0043] 2. Server

[0044] This refers to a computing system installed on the cloud or on-premises.

[0045] It is equipped with a natural language processing engine and analyzes the received text data.

[0046] The AI ​​model (e.g., machine learning or deep learning algorithms) is used to generate the answer.

[0047] A speech synthesis engine is used to convert text responses into audio data.

[0048] 3. Network

[0049] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0050] Program processing

[0051] Overall flow

[0052] The overall operation of this system consists of a series of steps, starting with user input and culminating in the provision of a response to the user. The specific processing flow is described below in natural language.

[0053] 1. User input of question

[0054] Users input questions about how to use their smartphones using their mobile devices. Questions can be entered via voice or text. For example, a user might ask, "How do I take a screenshot?" using voice.

[0055] 2. Input data acquisition and preprocessing

[0056] The mobile device acquires user input data. In the case of voice input, it uses a microphone to acquire voice data and converts it into text data using speech recognition technology. In the case of text input, it is treated as text data as is.

[0057] 3. Sending queries to the server

[0058] The mobile device sends the acquired text data to the server. The server then prepares to perform the next processing based on the received text data.

[0059] 4. Question Analysis and Intent Understanding

[0060] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the meaning of the question "How to take a screenshot" and extracts information to generate an appropriate answer.

[0061] 5. Generating the answer

[0062] The server uses an AI model to generate the best answer to a question. In this step, the AI ​​model generates the text of the answer based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0063] 6. Execute speech synthesis.

[0064] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[0065] 7. Send the response to the device.

[0066] The server generates audio and text data and sends it to the mobile device. This is how the final output is displayed on the user's device.

[0067] 8. Presenting answers to the user

[0068] The mobile device provides the user with received audio and text data. The audio data is played through the speaker, and the text data is displayed on the screen. This allows the user to obtain specific answers to their questions.

[0069] Specific example

[0070] Consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit a photo?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine and generates an answer using an AI model, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data using a speech synthesis engine and sent back to the mobile device. Finally, the mobile device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0071] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0072] The following describes the processing flow.

[0073] Step 1:

[0074] The user uses a mobile device to input a question via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[0075] Step 2:

[0076] The device acquires voice input via the microphone, or text input from a field.

[0077] Step 3:

[0078] The device uses speech recognition technology to convert the voice data into text data. The resulting text might be something like, "Tell me how to take a screenshot."

[0079] Step 4:

[0080] The terminal sends the acquired text data to the server. The data is transferred to the server via the network.

[0081] Step 5:

[0082] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information.

[0083] Step 6:

[0084] The server uses an AI model to generate the best answer to a question. For example, it might generate an answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0085] Step 7:

[0086] The server generates text responses, which are then passed to a speech synthesis engine to produce audio data. The generated audio data allows users to hear the responses even if they cannot visually verify them.

[0087] Step 8:

[0088] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0089] Step 9:

[0090] The device plays back received audio data and displays text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button simultaneously," both audibly and as text.

[0091] In this way, users can get immediate and appropriate answers to their questions. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means.

[0092] (Example 1)

[0093] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] With the widespread adoption of modern smartphones and mobile devices, there is a growing demand for systems that can resolve user questions about device usage in real time. Senior users and tech-savvy users, in particular, often struggle to understand how to operate their devices, making a system that provides quick and accurate instructions essential. However, conventional systems have struggled to provide appropriate answers to user questions in real time, and their low accuracy in speech recognition and natural language processing has made them unuser-friendly. This invention aims to solve these problems.

[0095] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0096] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative artificial intelligence model, and means for using a speech synthesis engine when generating audio data. This makes it possible for users to input questions about how to use smartphones or mobile devices in real time, and for the system to acquire and analyze audio or text data to provide a quick and appropriate answer.

[0097] A "user" refers to a person who operates the system and enters questions.

[0098] "Personal information terminals" refer to portable electronic devices such as smartphones and tablets.

[0099] A "question" refers to the content that a user inputs using a mobile device, and which the system then uses to generate an answer.

[0100] "Speech recognition technology" refers to the technology that converts speech data into text data.

[0101] A "natural language processing engine" refers to software that analyzes text data and understands its meaning.

[0102] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that generates answers based on past data and context.

[0103] A "speech synthesis engine" refers to a technology used to convert text data into speech data.

[0104] A "server" refers to a remote computer system that performs data processing.

[0105] "Network" refers to the communication channel that connects a mobile device to a server.

[0106] "Text data" refers to voice input converted by speech recognition technology or strings of characters entered directly.

[0107] "Audio data" refers to digital audio information generated by a speech synthesis engine based on text generated by speech recognition technology.

[0108] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0109] System Configuration

[0110] 1. Mobile device

[0111] These are electronic devices such as smartphones and tablets that users carry with them.

[0112] It is equipped with means for voice input and text input.

[0113] It has communication capabilities to process input data and send it to the server.

[0114] It has the functionality to convert voice input into text using speech recognition technology (for example, Google® Speech-to-Text API).

[0115] 2. Server

[0116] This refers to a computing system installed on the cloud or on-premises.

[0117] It is equipped with a natural language processing engine (such as Python's NLTK library or SpaCy) to analyze the received text data.

[0118] The system generates answers using generative artificial intelligence models (e.g., GPT-3® or BERT).

[0119] Convert text responses into audio data using a speech synthesis engine (e.g., Google Text-to-Speech API).

[0120] 3. Network

[0121] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0122] Program processing

[0123] The user enters a question about how to use their smartphone using a mobile device. The question can be entered by voice or text. For example, consider a case where the user asks by voice, "How do I take a screenshot?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I take a screenshot?", using voice recognition technology.

[0124] Next, this text data is sent to the server. The server uses a natural language processing engine to analyze the text data and understand the intent of the question. For example, it might identify "how to take a screenshot" and generate an appropriate answer.

[0125] The server uses a generative artificial intelligence model to generate the best possible answer to a question. The model generates the answer text based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0126] Next, the server passes the generated text of the response to a speech synthesis engine to generate audio data. This allows the user to hear the response even if they cannot visually confirm it. The generated audio and text data are sent to the mobile device, which reads the response aloud and displays it as text on the screen.

[0127] Specific example

[0128] Consider a scenario where a user asks a voice question using a mobile device: "How do I edit a photo?" The device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine. An AI model generates the answer, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data by a speech synthesis engine and sent back to the mobile device. The device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0129] Example of a prompt

[0130] Here are some examples of prompt messages:

[0131] "How do I take a screenshot?"

[0132] "How do I lower the volume on my smartphone?"

[0133] "Please tell me how to edit photos."

[0134] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0135] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0136] Step 1:

[0137] The user enters a question using a mobile device. The input method is either voice input or text input. Specifically, the user asks a question by voice into the device, such as "Tell me how to take a screenshot." In this process, the mobile device uses its microphone to acquire voice data and receives it as input data.

[0138] Step 2:

[0139] The device acquires the user's voice data and converts it into text data using speech recognition technology. Specifically, the device sends the acquired voice data to a cloud-based speech recognition service (for example, Google Speech-to-Text API), which then converts the voice data into text data and returns it. The output of this process is the text data obtained by speech recognition technology: "Tell me how to take a screenshot."

[0140] Step 3:

[0141] The terminal sends the acquired text data to the server. In this process, the terminal uses the HTTPS protocol over the internet to send the text data to the server as a POST request. The input is text data, and the output is the transmission of data to the server.

[0142] Step 4:

[0143] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. Specifically, the server tokenizes the text data, extracts important keywords, and analyzes the context. The input is the text data "Tell me how to take a screenshot," and the output is the understood intent of the question, "How to take a screenshot."

[0144] Step 5:

[0145] The server uses a generative artificial intelligence model to generate the best answer to a question. In this step, the server passes the prompt "How do I take a screenshot?" to the generative AI model, which outputs the answer "To take a screenshot, press the side button and the volume up button at the same time." The input is the understood intent of the question, and the output is the generated answer text "To take a screenshot, press the side button and the volume up button at the same time."

[0146] Step 6:

[0147] The server generates the text response, which is then passed to a text-to-speech engine to produce audio data. In this process, the server sends the text data to a text-to-speech service such as the Google Text-to-Speech API, which generates and receives the audio data (e.g., an MP3 file). The input is the generated text response, and the output is the generated audio data.

[0148] Step 7:

[0149] The server generates audio and text data and sends it to the mobile device. In this process, the server again uses the HTTPS protocol to send the data to the device. The input is audio and text data, and the output is the transmission of data to the device.

[0150] Step 8:

[0151] The device provides the user with the audio and text data it receives. Specifically, the device plays the audio data and displays the text data on the screen. The input is the audio and text data received from the server, and the output is audio playback and text display to the user.

[0152] The above outlines the specific processing steps of this system's program.

[0153] (Application Example 1)

[0154] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0155] Conventional technologies had limitations in how users could input questions using digital information terminals and receive answers in real time. In particular, there was a lack of systems capable of providing efficient and effective support when using smartphones. Furthermore, it was difficult to quickly generate accurate answers to a wide range of user questions. This resulted in reduced user convenience and hindered the smooth use of digital services.

[0156] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0157] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative AI model, and means for appropriately processing information using prompt sentences to generate an answer. As a result, when a user inputs a question using an information terminal, the server can generate a quick and accurate answer, thereby improving user convenience and enabling smooth use of digital services.

[0158] An "information terminal" refers to an electronic device such as a smartphone or tablet that a user carries with them.

[0159] A "natural language processing engine" is a software technology that analyzes text data to understand the meaning of sentences and the intent of questions.

[0160] A "generative AI model" is an artificial intelligence program that uses machine learning and deep learning algorithms to make predictions and generate information based on input data.

[0161] A "prompt sentence" is an input sentence given to an AI model, and it is an instruction sentence that generates an appropriate answer to a specific question or task.

[0162] A "speech synthesis engine" is a technology for converting text data into speech data, and is software that enables speech output.

[0163] "Text data" refers to data that represents user-entered questions, server-generated answers, and other information as text.

[0164] "Voice data" refers to data generated by a speech synthesis engine or recorded from user input.

[0165] Modes for carrying out the invention

[0166] System Overview

[0167] This invention is a system for users to input questions using an information terminal and receive answers in real time. The system includes an information terminal, a server, and a network connecting the two. The system of this invention is designed to efficiently provide user support, particularly in content distribution services.

[0168] System Configuration

[0169] 1. Information terminal

[0170] These are electronic devices such as smartphones and tablets that users carry with them.

[0171] It is equipped with means for voice input and text input.

[0172] It has communication capabilities to process input data and send it to the server.

[0173] It has the function of converting voice input into text data using speech recognition technology.

[0174] 2. Server

[0175] This refers to a computing system installed on the cloud or on-premises.

[0176] It is equipped with a natural language processing engine and analyzes the received text data.

[0177] The system generates answers using generative AI models (e.g., machine learning or deep learning algorithms).

[0178] Use prompt statements to properly process the intent of the question and generate an answer.

[0179] A speech synthesis engine is used to convert text responses into audio data.

[0180] 3. Network

[0181] This refers to a communication channel that connects information terminals and servers, such as the internet and mobile networks.

[0182] Program processing details

[0183] The system operates as follows: When a user enters a question using an information terminal, the data is sent to the server. The server analyzes the text data using a natural language processing engine and generates the optimal answer using a generative AI model. During this process, prompts are used to improve the accuracy of the answer. The generated answer is converted into audio data by a speech synthesis engine and sent back to the information terminal.

[0184] Specific example

[0185] For example, consider a case where a user inputs the question, "What are some of the latest dramas you recommend?". In this case, the information terminal acquires the voice data and converts it into text data, "What are some of the latest dramas you recommend?", using speech recognition technology. Next, the text data is sent to the server, which analyzes the question using a natural language processing engine. Then, a generative AI model generates an answer using the following prompt sentence.

[0186] Example of a prompt

[0187] "What are some of the latest dramas you recommend?"

[0188] Based on this prompt, the server generates a response such as "The current recommended drama is 'XX Drama'," and converts it into audio data using a speech synthesis engine. Finally, this audio data and text data are sent to the information terminal and provided to the user.

[0189] In this way, the system is designed to allow users to obtain quick and accurate answers to their questions. This improves user convenience and enables smoother use of the content delivery service.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Detailed program processing steps

[0192] Step 1:

[0193] The user enters a question using an information terminal. Input can be via voice or text. For example, the user might voice-input the question, "What are some recommended new dramas?" The information terminal acquires the voice data through its microphone and uses speech recognition technology to convert this voice data into text data. The input is voice data, and the output is text data.

[0194] Step 2:

[0195] The information terminal sends the converted text data to the server. Here, the information terminal uses a network (Internet or mobile network) to send the text data to the server as a POST request. The input is text data, and the output is the query text delivered to the server.

[0196] Step 3:

[0197] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. In this step, the input text data is subjected to morphological and contextual analysis to identify the subject and meaning of the question. The input is the received text data, and the output is the analyzed intent of the question.

[0198] Step 4:

[0199] The server uses a generative AI model to generate answers based on the analyzed question intent. In this process, prompts are used to provide clear instructions to the AI ​​model, enabling it to produce appropriate answers. The input consists of the analyzed question intent and prompts, while the output is the generated answer text.

[0200] Step 5:

[0201] The server passes the generated response text to the speech synthesis engine, which converts the text data into speech data. In this step, the speech synthesis engine converts the text data into a speech waveform, making it a format that is easy for humans to understand. The input is the response text, and the output is the generated speech data.

[0202] Step 6:

[0203] The server sends the generated audio and text data to the information terminal. Here, the generated data is retransmitted to the information terminal via the network. The input is the audio and text data, and the output is the data sent to the information terminal.

[0204] Step 7:

[0205] The information terminal plays the received audio data and displays the text data on the screen. This allows the user to confirm the answer through both sight and sound. Specifically, it plays the audio data using the speaker and displays the text data on the display. The input is the received audio data and text data, and the output is the played audio and the displayed text.

[0206] Step 8:

[0207] The user confirms that they have received an answer to their question by listening to voice instructions from the device and confirming the text displayed on the screen. This resolves the user's doubts and completes the information retrieval through the system. The input is the played audio and displayed text, and the output is the user's understanding and confirmation.

[0208] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0209] This invention is a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers according to the user's emotional state. This system includes a mobile device, a server, and a network connecting the two.

[0210] System Configuration

[0211] 1. Mobile device

[0212] These are electronic devices such as smartphones and tablets that users can carry with them.

[0213] It is equipped with means for voice input and text input, and has a function to acquire input data.

[0214] It has the ability to convert voice input into text data using speech recognition technology.

[0215] It has the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to the server.

[0216] 2. Server

[0217] This refers to a computing system installed on the cloud or on-premises.

[0218] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[0219] Using AI models (e.g., machine learning or deep learning algorithms), we generate appropriate answers to user questions.

[0220] It has the functionality to analyze the user's emotional state using an emotion engine and generate adaptive responses that correspond to those emotions.

[0221] Convert the text response generated using a speech synthesis engine into audio data.

[0222] 3. Network

[0223] This includes the internet and mobile networks as communication channels connecting mobile devices and servers.

[0224] Program processing

[0225] The program's processing is explained below in natural language.

[0226] Overall flow

[0227] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer.

[0228] 1. User input of question

[0229] The user uses a mobile device to input a question via voice or text. For example, consider the case where the user asks a question by voice, "How do I take a screenshot?"

[0230] 2. Input data acquisition and preprocessing

[0231] The device acquires user input data. In the case of voice input, voice data is acquired through the microphone and converted into text data using speech recognition technology. In the case of text input, it is processed as text data as is.

[0232] 3. Emotion analysis

[0233] The device analyzes the user's voice data through an emotion engine to determine their emotions. For example, it identifies the user's emotional state, such as being excited, calm, or irritated.

[0234] 4. Sending queries to the server

[0235] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[0236] 5. Question Analysis and Intent Understanding

[0237] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the specific steps for "how to take a screenshot."

[0238] 6. Generating the answer

[0239] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0240] 7. Adjusting responses to emotions

[0241] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it will generate text that explains things in a gentle tone.

[0242] 8. Execute speech synthesis

[0243] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[0244] 9. Sending the response to the device

[0245] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0246] 10. Presenting answers to the user

[0247] The device plays the received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," and simultaneously display it as text.

[0248] Specific example

[0249] For example, consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit photos?" In this case, the device uses voice recognition technology to convert the voice data into text data, "How do I edit photos?", while simultaneously analyzing the user's emotions using an emotion engine. The text data, along with the analysis results, is then sent to the server.

[0250] The server uses a natural language processing engine to understand the intent of the question and generates a response such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, it generates a response such as, "Please calm down. Now, open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," which is then converted into audio data using a speech synthesis engine and sent to the device.

[0251] The mobile device plays back received audio data and simultaneously displays text data on the screen. Users can confirm information through both sight and sound, and receive appropriate support tailored to their emotions.

[0252] In this way, the system can provide quick and appropriate answers to user questions, and further enhance the user experience using sentiment analysis.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The user inputs the question via voice or text using a mobile device. For example, the user might input "How do I take a screenshot?" via voice.

[0256] Step 2:

[0257] The device acquires voice input via the microphone, or text input from a field.

[0258] Step 3:

[0259] The device uses speech recognition technology to convert voice data into text data. For example, the voice "Tell me how to take a screenshot" is converted into the text "Tell me how to take a screenshot".

[0260] Step 4:

[0261] The device uses an emotion engine to analyze the user's emotions from their voice data. For example, the emotion engine analyzes the tone, speed, and volume of the user's voice to identify their emotional state, such as whether they are excited or calm.

[0262] Step 5:

[0263] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[0264] Step 6:

[0265] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information. For example, it identifies the specific steps involved in a question like "How to take a screenshot."

[0266] Step 7:

[0267] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0268] Step 8:

[0269] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it might generate a gentle response such as, "Please calm down. Now, to take a screenshot, press the side button and the volume up button at the same time."

[0270] Step 9:

[0271] The server passes the generated text response to the speech synthesis engine, which then generates audio data. For example, it might generate audio data saying, "To take a screenshot, press the side button and the volume up button at the same time."

[0272] Step 10:

[0273] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0274] Step 11:

[0275] The device plays back received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," while simultaneously displaying the text on the screen.

[0276] In this way, users can receive appropriate answers to their questions immediately. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means. Additionally, sentiment analysis is used to provide appropriate responses tailored to the user's emotions, thus improving the user experience.

[0277] (Example 2)

[0278] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0279] Traditional question-answering systems often provided uniform answers without considering the user's emotional state. As a result, they failed to provide appropriate support, especially to frustrated or confused users, leading to a poor user experience. Furthermore, delays in providing answers, both verbally and text-based, resulted in insufficient problem-solving in situations requiring quick responses.

[0280] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0281] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intention of a question, means for generating an answer based on the text data using a generative AI model, and means for adjusting the answer generated based on the sentiment analysis result. Thereby, an adaptive answer according to the user's emotional state is provided, enabling a prompt and appropriate response.

[0282] A "user" is an individual who inputs a question and receives an answer using the system.

[0283] A "portable information terminal" is an electronic device such as a smartphone or a tablet that a user can carry around.

[0284] "Voice data" is the digital representation of a voice signal obtained through the microphone of a portable information terminal.

[0285] "Text data" refers to the speech recognition result of voice data or directly input character information.

[0286] "Sentiment analysis" is a process of analyzing the emotional state of a user from their voice or text.

[0287] A "server" is a computer system for analyzing questions and generating answers.

[0288] A "natural language processing engine" is a software engine for analyzing text data and understanding its meaning and intention.

[0289] A "generative AI model" is a model for generating answers based on natural language using machine learning and deep learning algorithms.

[0290] A "speech synthesis engine" is a software engine used to convert text data into speech data.

[0291] "Emotional analysis results" refer to data that indicates the user's emotional state, obtained through emotional analysis.

[0292] "Response adjustment" refers to the process of modifying the content and tone of generated responses to better suit the user's emotional state.

[0293] A "network" refers to the communication infrastructure used for data communication between mobile devices and servers.

[0294] A "protocol" is a set of communication rules used to exchange data between a terminal and a server.

[0295] Modes for carrying out the invention

[0296] This invention provides a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers that correspond to the user's emotional state. This system uses a mobile device, a server, and a network connecting the two.

[0297] System Configuration

[0298] 1. Mobile device

[0299] These are electronic devices such as smartphones and tablets that users can carry with them. The devices are equipped with means of voice input and text input, and have the function of acquiring input data. They also have the function of converting voice input into text data using speech recognition technology. Specifically, Google Cloud Speech-to-Text is used. Furthermore, they have the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to a server. For emotion analysis, IBM Watson®'s emotion analysis API is used, among others.

[0300] 2. Server

[0301] This is a computing system located in the cloud or on-premises. The server is equipped with a natural language processing engine and uses tools such as Google Cloud Natural Language API and spaCy to analyze incoming text data and understand the intent of the user's questions. It also uses a generative AI model (e.g., OpenAI®'s GPT-3) to generate appropriate answers to the user's questions. Furthermore, it can use an emotion engine to analyze the user's emotional state and generate adaptive answers that correspond to those emotions. The generated answers are converted into speech data using a speech synthesis engine (e.g., Amazon Polly or Google Cloud Text-to-Speech).

[0302] 3. Network

[0303] This includes the internet and mobile networks as communication channels connecting mobile devices and servers. HTTP or HTTPS protocols are used for communication.

[0304] Program processing

[0305] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer. The following details each process of the system and the technologies used.

[0306] 1. Input of questions by the user

[0307] The user uses a mobile information terminal to input a question either by voice or text. For example, the user may ask a question by voice such as "Please teach me how to take a screenshot."

[0308] 2. Acquisition and preprocessing of input data

[0309] The terminal acquires the user's voice data through the microphone. The acquired voice data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). In the case of text input, it is acquired as text data as it is.

[0310] 3. Sentiment analysis

[0311] The built-in sentiment engine of the terminal is used to analyze the user's emotional state from voice or text data. For example, by using the sentiment analysis API of IBM Watson, emotional states such as "excited," "calm," and "frustrated" can be identified. As an analysis result, it may be determined that the user is a little confused.

[0312] 4. Sending a query to the server

[0313] The terminal sends the text data and the sentiment analysis result obtained to the server. The communication is carried out via the Internet or a mobile network through the HTTP or HTTPS protocol.

[0314] 5. Analysis of questions and understanding of intentions

[0315] The server uses a natural language processing engine (NLP) to analyze the received text data and uses tools such as Google Cloud Natural Language API and spaCy to understand the intent of the question. For example, it can recognize the specific steps for "how to take a screenshot."

[0316] 6. Generating the answer

[0317] The server uses a generated AI model (e.g., OpenAI's GPT-3) to generate the best possible answer to the user's question. Specifically, it might generate text such as, "To take a screenshot, press the side button and the volume up button simultaneously."

[0318] 7. Adjusting responses to emotions

[0319] The server uses sentiment analysis results to generate adaptive responses. For example, if the user is frustrated, it might generate a response in a gentle tone such as, "I know you're in a hurry, but don't worry, to take a screenshot, just press the side button and the volume up button at the same time."

[0320] 8. Execute speech synthesis

[0321] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. This audio data allows users to verify the answers through means other than sight.

[0322] 9. Sending the response to the device

[0323] The server sends the generated audio and text data to the terminal. This is also done via the internet or mobile network, using the HTTP or HTTPS protocol.

[0324] 10. Presenting answers to the user

[0325] The device plays the received audio data and simultaneously displays the text data on the screen. The user hears an audio message saying, "To take a screenshot, press the side button and the volume up button at the same time," and can also visually confirm this in text.

[0326] Specific example

[0327] For example, consider a scenario where a user asks a question by voice to their mobile device: "Tell me how to edit photos." The device uses voice recognition technology to convert the voice data into text data, "Tell me how to edit photos," and an emotion engine analyzes the user's emotions. The text data, along with the analysis results, is then sent to the server.

[0328] The server understands the intent of the question through a natural language processing engine and generates an answer such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, a response such as, "Please calm down. Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," is generated and converted into speech data by a speech synthesis engine.

[0329] The mobile device plays the received audio data and simultaneously displays the message "Open the photo app, select the photo you want to edit, and tap the edit button in the upper right corner" on the screen. The user can confirm the specific steps through both sight and sound. In this way, the system provides quick and appropriate answers to the user's questions and can further enhance the user experience using sentiment analysis.

[0330] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0331] Step 1: The user enters the question using a mobile device.

[0332] The user inputs a question by voice using the microphone on their smartphone or tablet. For example, they might voice the question, "How do I take a screenshot?" The input data is an audio signal, which then becomes the input for the next step.

[0333] Step 2: The terminal acquires the audio data and performs preprocessing.

[0334] The device acquires the user's voice data through the microphone. The acquired voice data is processed as a digital signal and passed to the speech recognition engine. For example, the Google Cloud Speech-to-Text engine is used to convert this voice data into text data. The voice signal is the input data, and the converted text data is the output.

[0335] Step 3: The device performs emotion analysis.

[0336] The device receives text data and uses an emotion engine to analyze the user's emotional state. For example, it uses IBM Watson's emotion analysis API to identify emotions such as "irritated" from the text data. The input data is text data, and the emotion analysis results are the output.

[0337] Step 4: The device sends text data and sentiment analysis results to the server.

[0338] The terminal sends the acquired text data and sentiment analysis results to the server. HTTP or HTTPS protocols are used for communication, and the data is sent to the server over the network. The input data consists of text data and sentiment analysis results, and the output of this step is the success of the data transmission to the server.

[0339] Step 5: The server analyzes the question and understands its intent.

[0340] The server analyzes the received text data using a natural language processing engine to understand the intent of the question. For example, it uses the Google Cloud Natural Language API or spaCy to identify "how to take a screenshot." The input data is text data, and the output is the analysis result that identifies the intent of the question.

[0341] Step 6: The server generates an answer using the generated AI model.

[0342] The server uses a generative AI model (e.g., OpenAI's GPT-3) based on the analysis results to generate the best answer to the question. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button simultaneously." The input data is the analysis results used to identify the intent of the question, and the generated answer (text data) is the output.

[0343] Step 7: The server adjusts the response based on emotion.

[0344] The server uses sentiment analysis results to generate adaptive responses that match the user's emotional state. For example, if the user is frustrated, it will generate a gentle response such as, "You're in a hurry, aren't you? But don't worry, to take a screenshot, press the side button and the volume up button at the same time." The input data consists of the generated response and the sentiment analysis results, and the adjusted response is the output.

[0345] Step 8: The server converts the data into speech data using a speech synthesis engine.

[0346] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. The input data is the text response, and the output is the converted audio data.

[0347] Step 9: The server sends the response to the terminal.

[0348] The server sends the generated audio and text data to the terminal. The data is then transmitted to the terminal over the network using the HTTP or HTTPS protocol. The input data consists of audio and text data, and the output of this step is the success of the data transmission to the terminal.

[0349] Step 10: The device presents the answer to the user.

[0350] The device plays the received audio data while simultaneously displaying text data on the screen. The user hears specific instructions, such as "To take a screenshot, press the side button and the volume up button simultaneously," through audio and can visually confirm them through text. The input data consists of audio and text data, and the output is the response presented to the user.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0353] Conventional question-answering systems using mobile devices generate answers without considering the user's emotional state, resulting in a limited user experience and often failing to provide appropriate support. Furthermore, in in-store purchasing support, simply providing text-based answers is insufficient; it's necessary to respond to the user's real-time emotional changes. Therefore, the challenge lies in realizing a system that analyzes user emotions and provides adaptive support tailored to those emotions.

[0354] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for analyzing the user's emotional state using an emotion engine and generating an adaptive answer corresponding to the emotion. This makes it possible to provide a quick and appropriate answer to the user's question and to improve the user experience using emotion analysis.

[0355] A "user" refers to a person who uses a mobile device to input questions and receive answers.

[0356] A "personal digital assistant" (PDA) is an electronic device that a user can carry with them, such as a smartphone or tablet.

[0357] "Voice data" refers to the user's voice information acquired using a microphone.

[0358] "Text data" refers to character information converted from audio data or character information entered by the user.

[0359] A "server" is a computing system that performs data analysis and response generation.

[0360] A "natural language processing engine" is a technology that analyzes text data and understands the intent behind a question.

[0361] A "generative AI model" is a system that uses machine learning and deep learning algorithms to generate the optimal answer to a question.

[0362] An "emotion engine" is a technology that analyzes a user's emotional state from their voice and text data.

[0363] A "speech synthesis engine" is a technology that converts text data into speech data.

[0364] "Network" is a general term for the communication lines and infrastructure that connect mobile devices and servers.

[0365] "Speech recognition technology" is a technology that converts speech data into text data.

[0366] An "adaptive response" refers to a response that is adjusted according to the user's emotional state.

[0367] This invention is a system in which a user inputs a question using a mobile device and receives an appropriate answer in real time. Furthermore, the system aims to analyze the user's emotions and generate adaptive answers that correspond to those emotions. The system includes a mobile device, a server, and a network connecting them.

[0368] 1. Mobile device

[0369] Personal digital assistants (PDAs) are electronic devices that users can carry with them, such as smartphones and tablets. These devices have the following functions:

[0370] A means of enabling voice input and text input.

[0371] A means of converting voice input into text data using speech recognition technology.

[0372] A means of analyzing a user's emotional state using an emotion engine and sending the analysis results to a server.

[0373] 2. Server

[0374] A server is a computing system that performs data analysis and response generation. The server has the following functions:

[0375] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[0376] A means of generating the optimal response based on text data using a generative AI model.

[0377] A means of analyzing a user's emotional state using an emotion engine and generating adaptive responses that correspond to those emotions.

[0378] A method for converting text responses generated using a speech synthesis engine into speech data.

[0379] Means for transmitting voice data and text data to a mobile information terminal

[0380] 3. Network

[0381] A network is a general term for communication lines and infrastructure used to connect mobile devices and servers. This includes the internet and mobile networks. Various types of data are exchanged between servers and devices through this network.

[0382] Processing flow

[0383] 1. The user enters their question via voice or text using a mobile device. For example, they might ask, "What does this wine pair well with?"

[0384] 2. The device uses speech recognition technology to convert speech data into text data, and an emotion engine analyzes the user's emotional state.

[0385] 3. The analysis results, along with the text data, are sent to the server.

[0386] 4. The server uses a natural language processing engine to understand the intent of the question and generates the best answer using a generative AI model.

[0387] 5. An emotion engine is used to prepare adaptive responses that correspond to the user's emotional state.

[0388] 6. The text response generated by the speech synthesis engine is converted into audio data.

[0389] 7. The response data is sent to the mobile device, which plays the audio data and displays the text data.

[0390] Specific example

[0391] For example, consider a scenario where a user asks a question about wine in a physical store. The user uses their smartphone to ask a question by voice, "What does this wine pair well with?" The smartphone converts the voice into text and simultaneously analyzes the user's emotions. When this information is sent to the server, the server analyzes the intent of the question and generates an answer such as, "This wine pairs particularly well with red meat dishes and pasta." If the server analyzes that the user is confused, it generates a gentler response such as, "Please calm down. This wine pairs particularly well with red meat dishes and pasta," converts it into voice data, and sends it to the smartphone.

[0392] Example of a prompt

[0393] User question: "What does this wine pair well with?"

[0394] System response: "This wine pairs particularly well with red meat dishes and pasta. Is there anything else you'd like to order?"

[0395] This system allows users to receive appropriate answers in real time, even in physical stores, and to receive support tailored to their emotional state.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The user enters a question.

[0399] Input: The user enters the question by voice using the microphone on their mobile device, or by typing text using the keyboard.

[0400] Action: The user asks a voice question: "What does this wine pair well with?"

[0401] Output: Audio data or text data.

[0402] Step 2:

[0403] Convert audio data to text data

[0404] Input: Audio data

[0405] Operation: The device uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the audio data into text data.

[0406] Output: Converted text data (e.g., "What does this wine pair well with?").

[0407] Step 3:

[0408] Analysis of emotional states

[0409] Input: Converted text data

[0410] Operation: The device uses an emotion engine (e.g., Microsoft® Azure® Text Analytics) to analyze the user's emotional state. The analysis takes into account the user's tone of voice and text content.

[0411] Output: Sentiment analysis results (e.g., interesting, confused, etc.).

[0412] Step 4:

[0413] Send text data and sentiment analysis results to the server.

[0414] Input: Converted text data and sentiment analysis results

[0415] Operation: The device sends text data and sentiment analysis results to the server via the network.

[0416] Output: Data received on the server side.

[0417] Step 5:

[0418] Analyze the intent of the question

[0419] Input: Received text data

[0420] Operation: The server uses a natural language processing engine (e.g., NLTK or spaCy) to analyze text data and understand the intent of the question. For example, the question "What does this wine pair well with?" is interpreted as an attempt to find out which wines pair well with food.

[0421] Output: Analysis results that understand the intent of the question.

[0422] Step 6:

[0423] Generate an answer

[0424] Input: Analysis results that understand the intent of the question

[0425] Operation: The server generates the optimal answer using an AI model (e.g., GPT-4®). For example, "This wine pairs particularly well with red meat dishes and pasta."

[0426] Output: Generated answer text.

[0427] Step 7:

[0428] Adjusting responses based on emotions

[0429] Input: Generated response text and sentiment analysis results

[0430] How it works: The server uses an emotion engine to adjust its responses based on the user's emotional state. For example, if the user is confused, it might prepare a gentle response such as, "Please calm down. This wine pairs especially well with red meat dishes and pasta."

[0431] Output: Adaptive response text that responds to emotions.

[0432] Step 8:

[0433] Convert the answer into audio data.

[0434] Input: Emotionally adaptive response text

[0435] Operation: The server uses a text-to-speech engine (e.g., Google Text-to-Speech API) to convert the response text into audio data.

[0436] Output: Converted audio data.

[0437] Step 9:

[0438] Send audio and text data to the device.

[0439] Input: Converted audio data and response text data

[0440] Operation: The server transmits voice and text data to the mobile device over the network.

[0441] Output: Data received on the terminal side.

[0442] Step 10:

[0443] Providing answers to users

[0444] Input: Audio and text data received by the device

[0445] Operation: The device plays audio data and displays text data on the screen. For example, it might play the response "This wine pairs particularly well with red meat dishes and pasta" as audio and simultaneously display it on the screen.

[0446] Output: Users can verify the answer visually and aurally.

[0447] The above outlines the specific processing steps of the system program that implements the application example. This allows users to receive appropriate answers in real time and support tailored to their emotional state.

[0448] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0449] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0450] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0451] [Second Embodiment]

[0452] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0453] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0454] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0455] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0456] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0457] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0458] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0459] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0460] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0461] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0462] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0463] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0464] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0465] System Configuration

[0466] 1. Mobile device

[0467] These are electronic devices such as smartphones and tablets that users carry with them.

[0468] It is equipped with means for voice input and text input.

[0469] It has communication capabilities to process input data and send it to the server.

[0470] It has the function of converting voice input into text using speech recognition technology.

[0471] 2. Server

[0472] This refers to a computing system installed on the cloud or on-premises.

[0473] It is equipped with a natural language processing engine and analyzes the received text data.

[0474] The AI ​​model (e.g., machine learning or deep learning algorithms) is used to generate the answer.

[0475] A speech synthesis engine is used to convert text responses into audio data.

[0476] 3. Network

[0477] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0478] Program processing

[0479] Overall flow

[0480] The overall operation of this system consists of a series of steps, starting with user input and culminating in the provision of a response to the user. The specific processing flow is described below in natural language.

[0481] 1. User input of question

[0482] Users input questions about how to use their smartphones using their mobile devices. Questions can be entered via voice or text. For example, a user might ask, "How do I take a screenshot?" using voice.

[0483] 2. Input data acquisition and preprocessing

[0484] The mobile device acquires user input data. In the case of voice input, it uses a microphone to acquire voice data and converts it into text data using speech recognition technology. In the case of text input, it is treated as text data as is.

[0485] 3. Sending queries to the server

[0486] The mobile device sends the acquired text data to the server. The server then prepares to perform the next processing based on the received text data.

[0487] 4. Question Analysis and Intent Understanding

[0488] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the meaning of the question "How to take a screenshot" and extracts information to generate an appropriate answer.

[0489] 5. Generating the answer

[0490] The server uses an AI model to generate the best answer to a question. In this step, the AI ​​model generates the text of the answer based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0491] 6. Execute speech synthesis.

[0492] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[0493] 7. Send the response to the device.

[0494] The server generates audio and text data and sends it to the mobile device. This is how the final output is displayed on the user's device.

[0495] 8. Presenting answers to the user

[0496] The mobile device provides the user with received audio and text data. The audio data is played through the speaker, and the text data is displayed on the screen. This allows the user to obtain specific answers to their questions.

[0497] Specific example

[0498] Consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit a photo?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine and generates an answer using an AI model, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data using a speech synthesis engine and sent back to the mobile device. Finally, the mobile device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0499] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The user uses a mobile device to input a question via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[0503] Step 2:

[0504] The device acquires voice input via the microphone, or text input from a field.

[0505] Step 3:

[0506] The device uses speech recognition technology to convert the voice data into text data. The resulting text might be something like, "Tell me how to take a screenshot."

[0507] Step 4:

[0508] The terminal sends the acquired text data to the server. The data is transferred to the server via the network.

[0509] Step 5:

[0510] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information.

[0511] Step 6:

[0512] The server uses an AI model to generate the best answer to a question. For example, it might generate an answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0513] Step 7:

[0514] The server generates text responses, which are then passed to a speech synthesis engine to produce audio data. The generated audio data allows users to hear the responses even if they cannot visually verify them.

[0515] Step 8:

[0516] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0517] Step 9:

[0518] The device plays back received audio data and displays text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button simultaneously," both audibly and as text.

[0519] In this way, users can get immediate and appropriate answers to their questions. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means.

[0520] (Example 1)

[0521] Next, we will describe Example 1. 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".

[0522] With the widespread adoption of modern smartphones and mobile devices, there is a growing demand for systems that can resolve user questions about device usage in real time. Senior users and tech-savvy users, in particular, often struggle to understand how to operate their devices, making a system that provides quick and accurate instructions essential. However, conventional systems have struggled to provide appropriate answers to user questions in real time, and their low accuracy in speech recognition and natural language processing has made them unuser-friendly. This invention aims to solve these problems.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0524] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative artificial intelligence model, and means for using a speech synthesis engine when generating audio data. This makes it possible for users to input questions about how to use smartphones or mobile devices in real time, and for the system to acquire and analyze audio or text data to provide a quick and appropriate answer.

[0525] A "user" refers to a person who operates the system and enters questions.

[0526] "Personal information terminals" refer to portable electronic devices such as smartphones and tablets.

[0527] A "question" refers to the content that a user inputs using a mobile device, and which the system then uses to generate an answer.

[0528] "Speech recognition technology" refers to the technology that converts speech data into text data.

[0529] A "natural language processing engine" refers to software that analyzes text data and understands its meaning.

[0530] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that generates answers based on past data and context.

[0531] A "speech synthesis engine" refers to a technology used to convert text data into speech data.

[0532] A "server" refers to a remote computer system that performs data processing.

[0533] "Network" refers to the communication channel that connects a mobile device to a server.

[0534] "Text data" refers to voice input converted by speech recognition technology or strings of characters entered directly.

[0535] "Audio data" refers to digital audio information generated by a speech synthesis engine based on text generated by speech recognition technology.

[0536] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0537] System Configuration

[0538] 1. Mobile device

[0539] These are electronic devices such as smartphones and tablets that users carry with them.

[0540] It is equipped with means for voice input and text input.

[0541] It has communication capabilities to process input data and send it to the server.

[0542] It has the functionality to convert voice input into text using speech recognition technology (for example, Google Speech-to-Text API).

[0543] 2. Server

[0544] This refers to a computing system installed on the cloud or on-premises.

[0545] It is equipped with a natural language processing engine (such as Python's NLTK library or SpaCy) to analyze the received text data.

[0546] The system generates answers using generative artificial intelligence models (e.g., GPT-3 or BERT).

[0547] Convert text responses into audio data using a speech synthesis engine (e.g., Google Text-to-Speech API).

[0548] 3. Network

[0549] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0550] Program processing

[0551] The user enters a question about how to use their smartphone using a mobile device. The question can be entered by voice or text. For example, consider a case where the user asks by voice, "How do I take a screenshot?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I take a screenshot?", using voice recognition technology.

[0552] Next, this text data is sent to the server. The server uses a natural language processing engine to analyze the text data and understand the intent of the question. For example, it might identify "how to take a screenshot" and generate an appropriate answer.

[0553] The server uses a generative artificial intelligence model to generate the best possible answer to a question. The model generates the answer text based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0554] Next, the server passes the generated text of the response to a speech synthesis engine to generate audio data. This allows the user to hear the response even if they cannot visually confirm it. The generated audio and text data are sent to the mobile device, which reads the response aloud and displays it as text on the screen.

[0555] Specific example

[0556] Consider a scenario where a user asks a voice question using a mobile device: "How do I edit a photo?" The device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine. An AI model generates the answer, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data by a speech synthesis engine and sent back to the mobile device. The device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0557] Example of a prompt

[0558] Here are some examples of prompt messages:

[0559] "How do I take a screenshot?"

[0560] "How do I lower the volume on my smartphone?"

[0561] "Please tell me how to edit photos."

[0562] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0563] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0564] Step 1:

[0565] The user enters a question using a mobile device. The input method is either voice input or text input. Specifically, the user asks a question by voice into the device, such as "Tell me how to take a screenshot." In this process, the mobile device uses its microphone to acquire voice data and receives it as input data.

[0566] Step 2:

[0567] The device acquires the user's voice data and converts it into text data using speech recognition technology. Specifically, the device sends the acquired voice data to a cloud-based speech recognition service (for example, Google Speech-to-Text API), which then converts the voice data into text data and returns it. The output of this process is the text data obtained by speech recognition technology: "Tell me how to take a screenshot."

[0568] Step 3:

[0569] The terminal sends the acquired text data to the server. In this process, the terminal uses the HTTPS protocol over the internet to send the text data to the server as a POST request. The input is text data, and the output is the transmission of data to the server.

[0570] Step 4:

[0571] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. Specifically, the server tokenizes the text data, extracts important keywords, and analyzes the context. The input is the text data "Tell me how to take a screenshot," and the output is the understood intent of the question, "How to take a screenshot."

[0572] Step 5:

[0573] The server uses a generative artificial intelligence model to generate the best answer to a question. In this step, the server passes the prompt "How do I take a screenshot?" to the generative AI model, which outputs the answer "To take a screenshot, press the side button and the volume up button at the same time." The input is the understood intent of the question, and the output is the generated answer text "To take a screenshot, press the side button and the volume up button at the same time."

[0574] Step 6:

[0575] The server generates the text response, which is then passed to a text-to-speech engine to produce audio data. In this process, the server sends the text data to a text-to-speech service such as the Google Text-to-Speech API, which generates and receives the audio data (e.g., an MP3 file). The input is the generated text response, and the output is the generated audio data.

[0576] Step 7:

[0577] The server generates audio and text data and sends it to the mobile device. In this process, the server again uses the HTTPS protocol to send the data to the device. The input is audio and text data, and the output is the transmission of data to the device.

[0578] Step 8:

[0579] The device provides the user with the audio and text data it receives. Specifically, the device plays the audio data and displays the text data on the screen. The input is the audio and text data received from the server, and the output is audio playback and text display to the user.

[0580] The above outlines the specific processing steps of this system's program.

[0581] (Application Example 1)

[0582] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0583] Conventional technologies had limitations in how users could input questions using digital information terminals and receive answers in real time. In particular, there was a lack of systems capable of providing efficient and effective support when using smartphones. Furthermore, it was difficult to quickly generate accurate answers to a wide range of user questions. This resulted in reduced user convenience and hindered the smooth use of digital services.

[0584] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0585] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative AI model, and means for appropriately processing information using prompt sentences to generate an answer. As a result, when a user inputs a question using an information terminal, the server can generate a quick and accurate answer, thereby improving user convenience and enabling smooth use of digital services.

[0586] An "information terminal" refers to an electronic device such as a smartphone or tablet that a user carries with them.

[0587] A "natural language processing engine" is a software technology that analyzes text data to understand the meaning of sentences and the intent of questions.

[0588] A "generative AI model" is an artificial intelligence program that uses machine learning and deep learning algorithms to make predictions and generate information based on input data.

[0589] A "prompt sentence" is an input sentence given to an AI model, and it is an instruction sentence that generates an appropriate answer to a specific question or task.

[0590] A "speech synthesis engine" is a technology for converting text data into speech data, and is software that enables speech output.

[0591] "Text data" refers to data that represents user-entered questions, server-generated answers, and other information as text.

[0592] "Voice data" refers to data generated by a speech synthesis engine or recorded from user input.

[0593] Modes for carrying out the invention

[0594] System Overview

[0595] This invention is a system for users to input questions using an information terminal and receive answers in real time. The system includes an information terminal, a server, and a network connecting the two. The system of this invention is designed to efficiently provide user support, particularly in content distribution services.

[0596] System Configuration

[0597] 1. Information terminal

[0598] These are electronic devices such as smartphones and tablets that users carry with them.

[0599] It is equipped with means for voice input and text input.

[0600] It has communication capabilities to process input data and send it to the server.

[0601] It has the function of converting voice input into text data using speech recognition technology.

[0602] 2. Server

[0603] This refers to a computing system installed on the cloud or on-premises.

[0604] It is equipped with a natural language processing engine and analyzes the received text data.

[0605] The system generates answers using generative AI models (e.g., machine learning or deep learning algorithms).

[0606] Use prompt statements to properly process the intent of the question and generate an answer.

[0607] A speech synthesis engine is used to convert text responses into audio data.

[0608] 3. Network

[0609] This refers to a communication channel that connects information terminals and servers, such as the internet and mobile networks.

[0610] Program processing details

[0611] The system operates as follows: When a user enters a question using an information terminal, the data is sent to the server. The server analyzes the text data using a natural language processing engine and generates the optimal answer using a generative AI model. During this process, prompts are used to improve the accuracy of the answer. The generated answer is converted into audio data by a speech synthesis engine and sent back to the information terminal.

[0612] Specific example

[0613] For example, consider a case where a user inputs the question, "What are some of the latest dramas you recommend?". In this case, the information terminal acquires the voice data and converts it into text data, "What are some of the latest dramas you recommend?", using speech recognition technology. Next, the text data is sent to the server, which analyzes the question using a natural language processing engine. Then, a generative AI model generates an answer using the following prompt sentence.

[0614] Example of a prompt

[0615] "What are some of the latest dramas you recommend?"

[0616] Based on this prompt, the server generates a response such as "The current recommended drama is 'XX Drama'," and converts it into audio data using a speech synthesis engine. Finally, this audio data and text data are sent to the information terminal and provided to the user.

[0617] In this way, the system is designed to allow users to obtain quick and accurate answers to their questions. This improves user convenience and enables smoother use of the content delivery service.

[0618] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0619] Detailed program processing steps

[0620] Step 1:

[0621] The user enters a question using an information terminal. Input can be via voice or text. For example, the user might voice-input the question, "What are some recommended new dramas?" The information terminal acquires the voice data through its microphone and uses speech recognition technology to convert this voice data into text data. The input is voice data, and the output is text data.

[0622] Step 2:

[0623] The information terminal sends the converted text data to the server. Here, the information terminal uses a network (Internet or mobile network) to send the text data to the server as a POST request. The input is text data, and the output is the query text delivered to the server.

[0624] Step 3:

[0625] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. In this step, the input text data is subjected to morphological and contextual analysis to identify the subject and meaning of the question. The input is the received text data, and the output is the analyzed intent of the question.

[0626] Step 4:

[0627] The server uses a generative AI model to generate answers based on the analyzed question intent. In this process, prompts are used to provide clear instructions to the AI ​​model, enabling it to produce appropriate answers. The input consists of the analyzed question intent and prompts, while the output is the generated answer text.

[0628] Step 5:

[0629] The server passes the generated response text to the speech synthesis engine, which converts the text data into speech data. In this step, the speech synthesis engine converts the text data into a speech waveform, making it a format that is easy for humans to understand. The input is the response text, and the output is the generated speech data.

[0630] Step 6:

[0631] The server sends the generated audio and text data to the information terminal. Here, the generated data is retransmitted to the information terminal via the network. The input is the audio and text data, and the output is the data sent to the information terminal.

[0632] Step 7:

[0633] The information terminal plays the received audio data and displays the text data on the screen. This allows the user to confirm the answer through both sight and sound. Specifically, it plays the audio data using the speaker and displays the text data on the display. The input is the received audio data and text data, and the output is the played audio and the displayed text.

[0634] Step 8:

[0635] The user confirms that they have received an answer to their question by listening to voice instructions from the device and confirming the text displayed on the screen. This resolves the user's doubts and completes the information retrieval through the system. The input is the played audio and displayed text, and the output is the user's understanding and confirmation.

[0636] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0637] This invention is a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers according to the user's emotional state. This system includes a mobile device, a server, and a network connecting the two.

[0638] System Configuration

[0639] 1. Mobile device

[0640] These are electronic devices such as smartphones and tablets that users can carry with them.

[0641] It is equipped with means for voice input and text input, and has a function to acquire input data.

[0642] It has the ability to convert voice input into text data using speech recognition technology.

[0643] It has the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to the server.

[0644] 2. Server

[0645] This refers to a computing system installed on the cloud or on-premises.

[0646] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[0647] Using AI models (e.g., machine learning or deep learning algorithms), we generate appropriate answers to user questions.

[0648] It has the functionality to analyze the user's emotional state using an emotion engine and generate adaptive responses that correspond to those emotions.

[0649] Convert the text response generated using a speech synthesis engine into audio data.

[0650] 3. Network

[0651] This includes the internet and mobile networks as communication channels connecting mobile devices and servers.

[0652] Program processing

[0653] The program's processing is explained below in natural language.

[0654] Overall flow

[0655] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer.

[0656] 1. User input of question

[0657] The user uses a mobile device to input a question via voice or text. For example, consider the case where the user asks a question by voice, "How do I take a screenshot?"

[0658] 2. Input data acquisition and preprocessing

[0659] The device acquires user input data. In the case of voice input, voice data is acquired through the microphone and converted into text data using speech recognition technology. In the case of text input, it is processed as text data as is.

[0660] 3. Emotion analysis

[0661] The device analyzes the user's voice data through an emotion engine to determine their emotions. For example, it identifies the user's emotional state, such as being excited, calm, or irritated.

[0662] 4. Sending queries to the server

[0663] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[0664] 5. Question Analysis and Intent Understanding

[0665] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the specific steps for "how to take a screenshot."

[0666] 6. Generating the answer

[0667] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0668] 7. Adjusting responses to emotions

[0669] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it will generate text that explains things in a gentle tone.

[0670] 8. Execute speech synthesis

[0671] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[0672] 9. Sending the response to the device

[0673] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0674] 10. Presenting answers to the user

[0675] The device plays the received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," and simultaneously display it as text.

[0676] Specific example

[0677] For example, consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit photos?" In this case, the device uses voice recognition technology to convert the voice data into text data, "How do I edit photos?", while simultaneously analyzing the user's emotions using an emotion engine. The text data, along with the analysis results, is then sent to the server.

[0678] The server uses a natural language processing engine to understand the intent of the question and generates a response such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, it generates a response such as, "Please calm down. Now, open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," which is then converted into audio data using a speech synthesis engine and sent to the device.

[0679] The mobile device plays back received audio data and simultaneously displays text data on the screen. Users can confirm information through both sight and sound, and receive appropriate support tailored to their emotions.

[0680] In this way, the system can provide quick and appropriate answers to user questions, and further enhance the user experience using sentiment analysis.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The user inputs the question via voice or text using a mobile device. For example, the user might input "How do I take a screenshot?" via voice.

[0684] Step 2:

[0685] The device acquires voice input via the microphone, or text input from a field.

[0686] Step 3:

[0687] The device uses speech recognition technology to convert voice data into text data. For example, the voice "Tell me how to take a screenshot" is converted into the text "Tell me how to take a screenshot".

[0688] Step 4:

[0689] The device uses an emotion engine to analyze the user's emotions from their voice data. For example, the emotion engine analyzes the tone, speed, and volume of the user's voice to identify their emotional state, such as whether they are excited or calm.

[0690] Step 5:

[0691] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[0692] Step 6:

[0693] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information. For example, it identifies the specific steps involved in a question like "How to take a screenshot."

[0694] Step 7:

[0695] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0696] Step 8:

[0697] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it might generate a gentle response such as, "Please calm down. Now, to take a screenshot, press the side button and the volume up button at the same time."

[0698] Step 9:

[0699] The server passes the generated text response to the speech synthesis engine, which then generates audio data. For example, it might generate audio data saying, "To take a screenshot, press the side button and the volume up button at the same time."

[0700] Step 10:

[0701] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0702] Step 11:

[0703] The device plays back received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," while simultaneously displaying the text on the screen.

[0704] In this way, users can receive appropriate answers to their questions immediately. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means. Additionally, sentiment analysis is used to provide appropriate responses tailored to the user's emotions, thus improving the user experience.

[0705] (Example 2)

[0706] Next, we will describe Example 2. 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".

[0707] Traditional question-answering systems often provided uniform answers without considering the user's emotional state. As a result, they failed to provide appropriate support, especially to frustrated or confused users, leading to a poor user experience. Furthermore, delays in providing answers, both verbally and text-based, resulted in insufficient problem-solving in situations requiring quick responses.

[0708] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0709] In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for adjusting the generated answer based on the sentiment analysis results. This enables the provision of adaptive answers that correspond to the user's emotional state, allowing for a quick and appropriate response.

[0710] A "user" is an individual who uses the system to input questions and receive answers.

[0711] A "personal digital assistant" (PDA) refers to an electronic device that a user can carry with them, such as a smartphone or tablet.

[0712] "Audio data" refers to the digital representation of an audio signal acquired through the microphone of a mobile device.

[0713] "Text data" refers to speech recognition results from audio data or directly entered text information.

[0714] "Emotional analysis" is the process of analyzing a user's emotional state from their voice or text.

[0715] A "server" is a computing system used to analyze questions and generate answers.

[0716] A "natural language processing engine" is a software engine that analyzes text data to understand its meaning and intent.

[0717] A "generative AI model" is a model that uses machine learning and deep learning algorithms to generate responses based on natural language.

[0718] A "speech synthesis engine" is a software engine used to convert text data into speech data.

[0719] "Emotional analysis results" refer to data that indicates the user's emotional state, obtained through emotional analysis.

[0720] "Response adjustment" refers to the process of modifying the content and tone of generated responses to better suit the user's emotional state.

[0721] A "network" refers to the communication infrastructure used for data communication between mobile devices and servers.

[0722] A "protocol" is a set of communication rules used to exchange data between a terminal and a server.

[0723] Modes for carrying out the invention

[0724] This invention provides a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers that correspond to the user's emotional state. This system uses a mobile device, a server, and a network connecting the two.

[0725] System Configuration

[0726] 1. Mobile device

[0727] These are electronic devices such as smartphones and tablets that users can carry with them. The devices are equipped with means of voice input and text input, and have the function of acquiring input data. They also have the function of converting voice input into text data using speech recognition technology. Specifically, Google Cloud Speech-to-Text is used. Furthermore, they have the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to a server. IBM Watson's emotion analysis API is used for emotion analysis.

[0728] 2. Server

[0729] This is a computing system located in the cloud or on-premises. The server is equipped with a natural language processing engine and uses tools such as Google Cloud Natural Language API and spaCy to analyze incoming text data and understand the intent of the user's questions. It also uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate answers to the user's questions. Furthermore, it can use an emotion engine to analyze the user's emotional state and generate adaptive answers that correspond to those emotions. The generated answers are converted into speech data using a speech synthesis engine (e.g., Amazon Polly or Google Cloud Text-to-Speech).

[0730] 3. Network

[0731] This includes the internet and mobile networks as communication channels connecting mobile devices and servers. HTTP or HTTPS protocols are used for communication.

[0732] Program processing

[0733] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer. The following details each process of the system and the technologies used.

[0734] 1. User input of question

[0735] Users input questions using their mobile devices via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[0736] 2. Input data acquisition and preprocessing

[0737] The device acquires the user's voice data through the microphone. The acquired voice data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). In the case of text input, it is acquired as text data as is.

[0738] 3. Emotion analysis

[0739] The device's built-in emotion engine is used to analyze the user's emotional state from voice or text data. For example, IBM Watson's emotion analysis API can be used to identify emotional states such as "excited," "calm," or "irritated." In some cases, the analysis may determine that the user is slightly confused.

[0740] 4. Sending queries to the server

[0741] The device sends the acquired text data and sentiment analysis results to the server. Communication takes place via the HTTP or HTTPS protocol over the internet or mobile network.

[0742] 5. Question Analysis and Intent Understanding

[0743] The server uses a natural language processing engine (NLP) to analyze the received text data and uses tools such as Google Cloud Natural Language API and spaCy to understand the intent of the question. For example, it can recognize the specific steps for "how to take a screenshot."

[0744] 6. Generating the answer

[0745] The server uses a generated AI model (e.g., OpenAI's GPT-3) to generate the best possible answer to the user's question. Specifically, it might generate text such as, "To take a screenshot, press the side button and the volume up button simultaneously."

[0746] 7. Adjusting responses to emotions

[0747] The server uses sentiment analysis results to generate adaptive responses. For example, if the user is frustrated, it might generate a response in a gentle tone such as, "I know you're in a hurry, but don't worry, to take a screenshot, just press the side button and the volume up button at the same time."

[0748] 8. Execute speech synthesis

[0749] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. This audio data allows users to verify the answers through means other than sight.

[0750] 9. Sending the response to the device

[0751] The server sends the generated audio and text data to the terminal. This is also done via the internet or mobile network, using the HTTP or HTTPS protocol.

[0752] 10. Presenting answers to the user

[0753] The device plays the received audio data and simultaneously displays the text data on the screen. The user hears an audio message saying, "To take a screenshot, press the side button and the volume up button at the same time," and can also visually confirm this in text.

[0754] Specific example

[0755] For example, consider a scenario where a user asks a question by voice to their mobile device: "Tell me how to edit photos." The device uses voice recognition technology to convert the voice data into text data, "Tell me how to edit photos," and an emotion engine analyzes the user's emotions. The text data, along with the analysis results, is then sent to the server.

[0756] The server understands the intent of the question through a natural language processing engine and generates an answer such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, a response such as, "Please calm down. Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," is generated and converted into speech data by a speech synthesis engine.

[0757] The mobile device plays the received audio data and simultaneously displays the message "Open the photo app, select the photo you want to edit, and tap the edit button in the upper right corner" on the screen. The user can confirm the specific steps through both sight and sound. In this way, the system provides quick and appropriate answers to the user's questions and can further enhance the user experience using sentiment analysis.

[0758] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0759] Step 1: The user enters the question using a mobile device.

[0760] The user inputs a question by voice using the microphone on their smartphone or tablet. For example, they might voice the question, "How do I take a screenshot?" The input data is an audio signal, which then becomes the input for the next step.

[0761] Step 2: The terminal acquires the audio data and performs preprocessing.

[0762] The device acquires the user's voice data through the microphone. The acquired voice data is processed as a digital signal and passed to the speech recognition engine. For example, the Google Cloud Speech-to-Text engine is used to convert this voice data into text data. The voice signal is the input data, and the converted text data is the output.

[0763] Step 3: The device performs emotion analysis.

[0764] The device receives text data and uses an emotion engine to analyze the user's emotional state. For example, it uses IBM Watson's emotion analysis API to identify emotions such as "irritated" from the text data. The input data is text data, and the emotion analysis results are the output.

[0765] Step 4: The device sends text data and sentiment analysis results to the server.

[0766] The terminal sends the acquired text data and sentiment analysis results to the server. HTTP or HTTPS protocols are used for communication, and the data is sent to the server over the network. The input data consists of text data and sentiment analysis results, and the output of this step is the success of the data transmission to the server.

[0767] Step 5: The server analyzes the question and understands its intent.

[0768] The server analyzes the received text data using a natural language processing engine to understand the intent of the question. For example, it uses the Google Cloud Natural Language API or spaCy to identify "how to take a screenshot." The input data is text data, and the output is the analysis result that identifies the intent of the question.

[0769] Step 6: The server generates an answer using the generated AI model.

[0770] The server uses a generative AI model (e.g., OpenAI's GPT-3) based on the analysis results to generate the best answer to the question. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button simultaneously." The input data is the analysis results used to identify the intent of the question, and the generated answer (text data) is the output.

[0771] Step 7: The server adjusts the response based on emotion.

[0772] The server uses sentiment analysis results to generate adaptive responses that match the user's emotional state. For example, if the user is frustrated, it will generate a gentle response such as, "You're in a hurry, aren't you? But don't worry, to take a screenshot, press the side button and the volume up button at the same time." The input data consists of the generated response and the sentiment analysis results, and the adjusted response is the output.

[0773] Step 8: The server converts the data into speech data using a speech synthesis engine.

[0774] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. The input data is the text response, and the output is the converted audio data.

[0775] Step 9: The server sends the response to the terminal.

[0776] The server sends the generated audio and text data to the terminal. The data is then transmitted to the terminal over the network using the HTTP or HTTPS protocol. The input data consists of audio and text data, and the output of this step is the success of the data transmission to the terminal.

[0777] Step 10: The device presents the answer to the user.

[0778] The device plays the received audio data while simultaneously displaying text data on the screen. The user hears specific instructions, such as "To take a screenshot, press the side button and the volume up button simultaneously," through audio and can visually confirm them through text. The input data consists of audio and text data, and the output is the response presented to the user.

[0779] (Application Example 2)

[0780] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0781] Conventional question-answering systems using mobile devices generate answers without considering the user's emotional state, resulting in a limited user experience and often failing to provide appropriate support. Furthermore, in in-store purchasing support, simply providing text-based answers is insufficient; it's necessary to respond to the user's real-time emotional changes. Therefore, the challenge lies in realizing a system that analyzes user emotions and provides adaptive support tailored to those emotions.

[0782] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for analyzing the user's emotional state using an emotion engine and generating an adaptive answer corresponding to the emotion. This makes it possible to provide a quick and appropriate answer to the user's question and to improve the user experience using emotion analysis.

[0783] A "user" refers to a person who uses a mobile device to input questions and receive answers.

[0784] A "personal digital assistant" (PDA) is an electronic device that a user can carry with them, such as a smartphone or tablet.

[0785] "Voice data" refers to the user's voice information acquired using a microphone.

[0786] "Text data" refers to character information converted from audio data or character information entered by the user.

[0787] A "server" is a computing system that performs data analysis and response generation.

[0788] A "natural language processing engine" is a technology that analyzes text data and understands the intent behind a question.

[0789] A "generative AI model" is a system that uses machine learning and deep learning algorithms to generate the optimal answer to a question.

[0790] An "emotion engine" is a technology that analyzes a user's emotional state from their voice and text data.

[0791] A "speech synthesis engine" is a technology that converts text data into speech data.

[0792] "Network" is a general term for the communication lines and infrastructure that connect mobile devices and servers.

[0793] "Speech recognition technology" is a technology that converts speech data into text data.

[0794] An "adaptive response" refers to a response that is adjusted according to the user's emotional state.

[0795] This invention is a system in which a user inputs a question using a mobile device and receives an appropriate answer in real time. Furthermore, the system aims to analyze the user's emotions and generate adaptive answers that correspond to those emotions. The system includes a mobile device, a server, and a network connecting them.

[0796] 1. Mobile device

[0797] Personal digital assistants (PDAs) are electronic devices that users can carry with them, such as smartphones and tablets. These devices have the following functions:

[0798] A means of enabling voice input and text input.

[0799] A means of converting voice input into text data using speech recognition technology.

[0800] A means of analyzing a user's emotional state using an emotion engine and sending the analysis results to a server.

[0801] 2. Server

[0802] A server is a computing system that performs data analysis and response generation. The server has the following functions:

[0803] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[0804] A means of generating the optimal response based on text data using a generative AI model.

[0805] A means of analyzing a user's emotional state using an emotion engine and generating adaptive responses that correspond to those emotions.

[0806] A method for converting text responses generated using a speech synthesis engine into speech data.

[0807] Means for transmitting voice data and text data to a mobile information terminal

[0808] 3. Network

[0809] A network is a general term for communication lines and infrastructure used to connect mobile devices and servers. This includes the internet and mobile networks. Various types of data are exchanged between servers and devices through this network.

[0810] Processing flow

[0811] 1. The user enters their question via voice or text using a mobile device. For example, they might ask, "What does this wine pair well with?"

[0812] 2. The device uses speech recognition technology to convert speech data into text data, and an emotion engine analyzes the user's emotional state.

[0813] 3. The analysis results, along with the text data, are sent to the server.

[0814] 4. The server uses a natural language processing engine to understand the intent of the question and generates the best answer using a generative AI model.

[0815] 5. An emotion engine is used to prepare adaptive responses that correspond to the user's emotional state.

[0816] 6. The text response generated by the speech synthesis engine is converted into audio data.

[0817] 7. The response data is sent to the mobile device, which plays the audio data and displays the text data.

[0818] Specific example

[0819] For example, consider a scenario where a user asks a question about wine in a physical store. The user uses their smartphone to ask a question by voice, "What does this wine pair well with?" The smartphone converts the voice into text and simultaneously analyzes the user's emotions. When this information is sent to the server, the server analyzes the intent of the question and generates an answer such as, "This wine pairs particularly well with red meat dishes and pasta." If the server analyzes that the user is confused, it generates a gentler response such as, "Please calm down. This wine pairs particularly well with red meat dishes and pasta," converts it into voice data, and sends it to the smartphone.

[0820] Example of a prompt

[0821] User question: "What does this wine pair well with?"

[0822] System response: "This wine pairs particularly well with red meat dishes and pasta. Is there anything else you'd like to order?"

[0823] This system allows users to receive appropriate answers in real time, even in physical stores, and to receive support tailored to their emotional state.

[0824] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0825] Step 1:

[0826] The user enters a question.

[0827] Input: The user enters the question by voice using the microphone on their mobile device, or by typing text using the keyboard.

[0828] Action: The user asks a voice question: "What does this wine pair well with?"

[0829] Output: Audio data or text data.

[0830] Step 2:

[0831] Convert audio data to text data

[0832] Input: Audio data

[0833] Operation: The device uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the audio data into text data.

[0834] Output: Converted text data (e.g., "What does this wine pair well with?").

[0835] Step 3:

[0836] Analysis of emotional states

[0837] Input: Converted text data

[0838] Operation: The device uses an emotion engine (e.g., Microsoft Azure Text Analytics) to analyze the user's emotional state. The analysis takes into account the user's tone of voice and text content.

[0839] Output: Sentiment analysis results (e.g., interesting, confused, etc.).

[0840] Step 4:

[0841] Send text data and sentiment analysis results to the server.

[0842] Input: Converted text data and sentiment analysis results

[0843] Operation: The device sends text data and sentiment analysis results to the server via the network.

[0844] Output: Data received on the server side.

[0845] Step 5:

[0846] Analyze the intent of the question

[0847] Input: Received text data

[0848] Operation: The server uses a natural language processing engine (e.g., NLTK or spaCy) to analyze text data and understand the intent of the question. For example, the question "What does this wine pair well with?" is interpreted as an attempt to find out which wines pair well with food.

[0849] Output: Analysis results that understand the intent of the question.

[0850] Step 6:

[0851] Generate an answer

[0852] Input: Analysis results that understand the intent of the question

[0853] Operation: The server generates the optimal answer using an AI model (e.g., GPT-4). For example, "This wine pairs particularly well with red meat dishes and pasta."

[0854] Output: Generated answer text.

[0855] Step 7:

[0856] Adjusting responses based on emotions

[0857] Input: Generated response text and sentiment analysis results

[0858] How it works: The server uses an emotion engine to adjust its responses based on the user's emotional state. For example, if the user is confused, it might prepare a gentle response such as, "Please calm down. This wine pairs especially well with red meat dishes and pasta."

[0859] Output: Adaptive response text that responds to emotions.

[0860] Step 8:

[0861] Convert the answer into audio data.

[0862] Input: Emotionally adaptive response text

[0863] Operation: The server uses a text-to-speech engine (e.g., Google Text-to-Speech API) to convert the response text into audio data.

[0864] Output: Converted audio data.

[0865] Step 9:

[0866] Send audio and text data to the device.

[0867] Input: Converted audio data and response text data

[0868] Operation: The server transmits voice and text data to the mobile device over the network.

[0869] Output: Data received on the terminal side.

[0870] Step 10:

[0871] Providing answers to users

[0872] Input: Audio and text data received by the device

[0873] Operation: The device plays audio data and displays text data on the screen. For example, it might play the response "This wine pairs particularly well with red meat dishes and pasta" as audio and simultaneously display it on the screen.

[0874] Output: Users can verify the answer visually and aurally.

[0875] The above outlines the specific processing steps of the system program that implements the application example. This allows users to receive appropriate answers in real time and support tailored to their emotional state.

[0876] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0877] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0878] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0879] [Third Embodiment]

[0880] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0881] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0882] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0883] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0884] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0885] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0886] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0887] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0888] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0889] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0890] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0891] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0892] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0893] System Configuration

[0894] 1. Mobile device

[0895] These are electronic devices such as smartphones and tablets that users carry with them.

[0896] It is equipped with means for voice input and text input.

[0897] It has communication capabilities to process input data and send it to the server.

[0898] It has the function of converting voice input into text using speech recognition technology.

[0899] 2. Server

[0900] This refers to a computing system installed on the cloud or on-premises.

[0901] It is equipped with a natural language processing engine and analyzes the received text data.

[0902] The AI ​​model (e.g., machine learning or deep learning algorithms) is used to generate the answer.

[0903] A speech synthesis engine is used to convert text responses into audio data.

[0904] 3. Network

[0905] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0906] Program processing

[0907] Overall flow

[0908] The overall operation of this system consists of a series of steps, starting with user input and culminating in the provision of a response to the user. The specific processing flow is described below in natural language.

[0909] 1. User input of question

[0910] Users input questions about how to use their smartphones using their mobile devices. Questions can be entered via voice or text. For example, a user might ask, "How do I take a screenshot?" using voice.

[0911] 2. Input data acquisition and preprocessing

[0912] The mobile device acquires user input data. In the case of voice input, it uses a microphone to acquire voice data and converts it into text data using speech recognition technology. In the case of text input, it is treated as text data as is.

[0913] 3. Sending queries to the server

[0914] The mobile device sends the acquired text data to the server. The server then prepares to perform the next processing based on the received text data.

[0915] 4. Question Analysis and Intent Understanding

[0916] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the meaning of the question "How to take a screenshot" and extracts information to generate an appropriate answer.

[0917] 5. Generating the answer

[0918] The server uses an AI model to generate the best answer to a question. In this step, the AI ​​model generates the text of the answer based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0919] 6. Execute speech synthesis.

[0920] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[0921] 7. Send the response to the device.

[0922] The server generates audio and text data and sends it to the mobile device. This is how the final output is displayed on the user's device.

[0923] 8. Presenting answers to the user

[0924] The mobile device provides the user with received audio and text data. The audio data is played through the speaker, and the text data is displayed on the screen. This allows the user to obtain specific answers to their questions.

[0925] Specific example

[0926] Consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit a photo?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine and generates an answer using an AI model, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data using a speech synthesis engine and sent back to the mobile device. Finally, the mobile device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0927] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0928] The following describes the processing flow.

[0929] Step 1:

[0930] The user uses a mobile device to input a question via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[0931] Step 2:

[0932] The device acquires voice input via the microphone, or text input from a field.

[0933] Step 3:

[0934] The device uses speech recognition technology to convert the voice data into text data. The resulting text might be something like, "Tell me how to take a screenshot."

[0935] Step 4:

[0936] The terminal sends the acquired text data to the server. The data is transferred to the server via the network.

[0937] Step 5:

[0938] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information.

[0939] Step 6:

[0940] The server uses an AI model to generate the best answer to a question. For example, it might generate an answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[0941] Step 7:

[0942] The server generates text responses, which are then passed to a speech synthesis engine to produce audio data. The generated audio data allows users to hear the responses even if they cannot visually verify them.

[0943] Step 8:

[0944] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[0945] Step 9:

[0946] The device plays back received audio data and displays text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button simultaneously," both audibly and as text.

[0947] In this way, users can get immediate and appropriate answers to their questions. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means.

[0948] (Example 1)

[0949] Next, we will describe Example 1. 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."

[0950] With the widespread adoption of modern smartphones and mobile devices, there is a growing demand for systems that can resolve user questions about device usage in real time. Senior users and tech-savvy users, in particular, often struggle to understand how to operate their devices, making a system that provides quick and accurate instructions essential. However, conventional systems have struggled to provide appropriate answers to user questions in real time, and their low accuracy in speech recognition and natural language processing has made them unuser-friendly. This invention aims to solve these problems.

[0951] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0952] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative artificial intelligence model, and means for using a speech synthesis engine when generating audio data. This makes it possible for users to input questions about how to use smartphones or mobile devices in real time, and for the system to acquire and analyze audio or text data to provide a quick and appropriate answer.

[0953] A "user" refers to a person who operates the system and enters questions.

[0954] "Personal information terminals" refer to portable electronic devices such as smartphones and tablets.

[0955] A "question" refers to the content that a user inputs using a mobile device, and which the system then uses to generate an answer.

[0956] "Speech recognition technology" refers to the technology that converts speech data into text data.

[0957] A "natural language processing engine" refers to software that analyzes text data and understands its meaning.

[0958] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that generates answers based on past data and context.

[0959] A "speech synthesis engine" refers to a technology used to convert text data into speech data.

[0960] A "server" refers to a remote computer system that performs data processing.

[0961] "Network" refers to the communication channel that connects a mobile device to a server.

[0962] "Text data" refers to voice input converted by speech recognition technology or strings of characters entered directly.

[0963] "Audio data" refers to digital audio information generated by a speech synthesis engine based on text generated by speech recognition technology.

[0964] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[0965] System Configuration

[0966] 1. Mobile device

[0967] These are electronic devices such as smartphones and tablets that users carry with them.

[0968] It is equipped with means for voice input and text input.

[0969] It has communication capabilities to process input data and send it to the server.

[0970] It has the functionality to convert voice input into text using speech recognition technology (for example, Google Speech-to-Text API).

[0971] 2. Server

[0972] This refers to a computing system installed on the cloud or on-premises.

[0973] It is equipped with a natural language processing engine (such as Python's NLTK library or SpaCy) to analyze the received text data.

[0974] The system generates answers using generative artificial intelligence models (e.g., GPT-3 or BERT).

[0975] Convert text responses into audio data using a speech synthesis engine (e.g., Google Text-to-Speech API).

[0976] 3. Network

[0977] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[0978] Program processing

[0979] The user enters a question about how to use their smartphone using a mobile device. The question can be entered by voice or text. For example, consider a case where the user asks by voice, "How do I take a screenshot?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I take a screenshot?", using voice recognition technology.

[0980] Next, this text data is sent to the server. The server uses a natural language processing engine to analyze the text data and understand the intent of the question. For example, it might identify "how to take a screenshot" and generate an appropriate answer.

[0981] The server uses a generative artificial intelligence model to generate the best possible answer to a question. The model generates the answer text based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[0982] Next, the server passes the generated text of the response to a speech synthesis engine to generate audio data. This allows the user to hear the response even if they cannot visually confirm it. The generated audio and text data are sent to the mobile device, which reads the response aloud and displays it as text on the screen.

[0983] Specific example

[0984] Consider a scenario where a user asks a voice question using a mobile device: "How do I edit a photo?" The device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine. An AI model generates the answer, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data by a speech synthesis engine and sent back to the mobile device. The device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[0985] Example of a prompt

[0986] Here are some examples of prompt messages:

[0987] "How do I take a screenshot?"

[0988] "How do I lower the volume on my smartphone?"

[0989] "Please tell me how to edit photos."

[0990] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[0991] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0992] Step 1:

[0993] The user enters a question using a mobile device. The input method is either voice input or text input. Specifically, the user asks a question by voice into the device, such as "Tell me how to take a screenshot." In this process, the mobile device uses its microphone to acquire voice data and receives it as input data.

[0994] Step 2:

[0995] The device acquires the user's voice data and converts it into text data using speech recognition technology. Specifically, the device sends the acquired voice data to a cloud-based speech recognition service (for example, Google Speech-to-Text API), which then converts the voice data into text data and returns it. The output of this process is the text data obtained by speech recognition technology: "Tell me how to take a screenshot."

[0996] Step 3:

[0997] The terminal sends the acquired text data to the server. In this process, the terminal uses the HTTPS protocol over the internet to send the text data to the server as a POST request. The input is text data, and the output is the transmission of data to the server.

[0998] Step 4:

[0999] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. Specifically, the server tokenizes the text data, extracts important keywords, and analyzes the context. The input is the text data "Tell me how to take a screenshot," and the output is the understood intent of the question, "How to take a screenshot."

[1000] Step 5:

[1001] The server uses a generative artificial intelligence model to generate the best answer to a question. In this step, the server passes the prompt "How do I take a screenshot?" to the generative AI model, which outputs the answer "To take a screenshot, press the side button and the volume up button at the same time." The input is the understood intent of the question, and the output is the generated answer text "To take a screenshot, press the side button and the volume up button at the same time."

[1002] Step 6:

[1003] The server generates the text response, which is then passed to a text-to-speech engine to produce audio data. In this process, the server sends the text data to a text-to-speech service such as the Google Text-to-Speech API, which generates and receives the audio data (e.g., an MP3 file). The input is the generated text response, and the output is the generated audio data.

[1004] Step 7:

[1005] The server generates audio and text data and sends it to the mobile device. In this process, the server again uses the HTTPS protocol to send the data to the device. The input is audio and text data, and the output is the transmission of data to the device.

[1006] Step 8:

[1007] The device provides the user with the audio and text data it receives. Specifically, the device plays the audio data and displays the text data on the screen. The input is the audio and text data received from the server, and the output is audio playback and text display to the user.

[1008] The above outlines the specific processing steps of this system's program.

[1009] (Application Example 1)

[1010] Next, we will explain Application Example 1. In the following explanation, 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."

[1011] Conventional technologies had limitations in how users could input questions using digital information terminals and receive answers in real time. In particular, there was a lack of systems capable of providing efficient and effective support when using smartphones. Furthermore, it was difficult to quickly generate accurate answers to a wide range of user questions. This resulted in reduced user convenience and hindered the smooth use of digital services.

[1012] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1013] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative AI model, and means for appropriately processing information using prompt sentences to generate an answer. As a result, when a user inputs a question using an information terminal, the server can generate a quick and accurate answer, thereby improving user convenience and enabling smooth use of digital services.

[1014] An "information terminal" refers to an electronic device such as a smartphone or tablet that a user carries with them.

[1015] A "natural language processing engine" is a software technology that analyzes text data to understand the meaning of sentences and the intent of questions.

[1016] A "generative AI model" is an artificial intelligence program that uses machine learning and deep learning algorithms to make predictions and generate information based on input data.

[1017] A "prompt sentence" is an input sentence given to an AI model, and it is an instruction sentence that generates an appropriate answer to a specific question or task.

[1018] A "speech synthesis engine" is a technology for converting text data into speech data, and is software that enables speech output.

[1019] "Text data" refers to data that represents user-entered questions, server-generated answers, and other information as text.

[1020] "Voice data" refers to data generated by a speech synthesis engine or recorded from user input.

[1021] Modes for carrying out the invention

[1022] System Overview

[1023] This invention is a system for users to input questions using an information terminal and receive answers in real time. The system includes an information terminal, a server, and a network connecting the two. The system of this invention is designed to efficiently provide user support, particularly in content distribution services.

[1024] System Configuration

[1025] 1. Information terminal

[1026] These are electronic devices such as smartphones and tablets that users carry with them.

[1027] It is equipped with means for voice input and text input.

[1028] It has communication capabilities to process input data and send it to the server.

[1029] It has the function of converting voice input into text data using speech recognition technology.

[1030] 2. Server

[1031] This refers to a computing system installed on the cloud or on-premises.

[1032] It is equipped with a natural language processing engine and analyzes the received text data.

[1033] The system generates answers using generative AI models (e.g., machine learning or deep learning algorithms).

[1034] Use prompt statements to properly process the intent of the question and generate an answer.

[1035] A speech synthesis engine is used to convert text responses into audio data.

[1036] 3. Network

[1037] This refers to a communication channel that connects information terminals and servers, such as the internet and mobile networks.

[1038] Program processing details

[1039] The system operates as follows: When a user enters a question using an information terminal, the data is sent to the server. The server analyzes the text data using a natural language processing engine and generates the optimal answer using a generative AI model. During this process, prompts are used to improve the accuracy of the answer. The generated answer is converted into audio data by a speech synthesis engine and sent back to the information terminal.

[1040] Specific example

[1041] For example, consider a case where a user inputs the question, "What are some of the latest dramas you recommend?". In this case, the information terminal acquires the voice data and converts it into text data, "What are some of the latest dramas you recommend?", using speech recognition technology. Next, the text data is sent to the server, which analyzes the question using a natural language processing engine. Then, a generative AI model generates an answer using the following prompt sentence.

[1042] Example of a prompt

[1043] "What are some of the latest dramas you recommend?"

[1044] Based on this prompt, the server generates a response such as "The current recommended drama is 'XX Drama'," and converts it into audio data using a speech synthesis engine. Finally, this audio data and text data are sent to the information terminal and provided to the user.

[1045] In this way, the system is designed to allow users to obtain quick and accurate answers to their questions. This improves user convenience and enables smoother use of the content delivery service.

[1046] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1047] Detailed program processing steps

[1048] Step 1:

[1049] The user enters a question using an information terminal. Input can be via voice or text. For example, the user might voice-input the question, "What are some recommended new dramas?" The information terminal acquires the voice data through its microphone and uses speech recognition technology to convert this voice data into text data. The input is voice data, and the output is text data.

[1050] Step 2:

[1051] The information terminal sends the converted text data to the server. Here, the information terminal uses a network (Internet or mobile network) to send the text data to the server as a POST request. The input is text data, and the output is the query text delivered to the server.

[1052] Step 3:

[1053] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. In this step, the input text data is subjected to morphological and contextual analysis to identify the subject and meaning of the question. The input is the received text data, and the output is the analyzed intent of the question.

[1054] Step 4:

[1055] The server uses a generative AI model to generate answers based on the analyzed question intent. In this process, prompts are used to provide clear instructions to the AI ​​model, enabling it to produce appropriate answers. The input consists of the analyzed question intent and prompts, while the output is the generated answer text.

[1056] Step 5:

[1057] The server passes the generated response text to the speech synthesis engine, which converts the text data into speech data. In this step, the speech synthesis engine converts the text data into a speech waveform, making it a format that is easy for humans to understand. The input is the response text, and the output is the generated speech data.

[1058] Step 6:

[1059] The server sends the generated audio and text data to the information terminal. Here, the generated data is retransmitted to the information terminal via the network. The input is the audio and text data, and the output is the data sent to the information terminal.

[1060] Step 7:

[1061] The information terminal plays the received audio data and displays the text data on the screen. This allows the user to confirm the answer through both sight and sound. Specifically, it plays the audio data using the speaker and displays the text data on the display. The input is the received audio data and text data, and the output is the played audio and the displayed text.

[1062] Step 8:

[1063] The user confirms that they have received an answer to their question by listening to voice instructions from the device and confirming the text displayed on the screen. This resolves the user's doubts and completes the information retrieval through the system. The input is the played audio and displayed text, and the output is the user's understanding and confirmation.

[1064] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1065] This invention is a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers according to the user's emotional state. This system includes a mobile device, a server, and a network connecting the two.

[1066] System Configuration

[1067] 1. Mobile device

[1068] These are electronic devices such as smartphones and tablets that users can carry with them.

[1069] It is equipped with means for voice input and text input, and has a function to acquire input data.

[1070] It has the ability to convert voice input into text data using speech recognition technology.

[1071] It has the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to the server.

[1072] 2. Server

[1073] This refers to a computing system installed on the cloud or on-premises.

[1074] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[1075] Using AI models (e.g., machine learning or deep learning algorithms), we generate appropriate answers to user questions.

[1076] It has the functionality to analyze the user's emotional state using an emotion engine and generate adaptive responses that correspond to those emotions.

[1077] Convert the text response generated using a speech synthesis engine into audio data.

[1078] 3. Network

[1079] This includes the internet and mobile networks as communication channels connecting mobile devices and servers.

[1080] Program processing

[1081] The program's processing is explained below in natural language.

[1082] Overall flow

[1083] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer.

[1084] 1. User input of question

[1085] The user uses a mobile device to input a question via voice or text. For example, consider the case where the user asks a question by voice, "How do I take a screenshot?"

[1086] 2. Input data acquisition and preprocessing

[1087] The device acquires user input data. In the case of voice input, voice data is acquired through the microphone and converted into text data using speech recognition technology. In the case of text input, it is processed as text data as is.

[1088] 3. Emotion analysis

[1089] The device analyzes the user's voice data through an emotion engine to determine their emotions. For example, it identifies the user's emotional state, such as being excited, calm, or irritated.

[1090] 4. Sending queries to the server

[1091] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[1092] 5. Question Analysis and Intent Understanding

[1093] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the specific steps for "how to take a screenshot."

[1094] 6. Generating the answer

[1095] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[1096] 7. Adjusting responses to emotions

[1097] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it will generate text that explains things in a gentle tone.

[1098] 8. Execute speech synthesis

[1099] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[1100] 9. Sending the response to the device

[1101] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[1102] 10. Presenting answers to the user

[1103] The device plays the received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," and simultaneously display it as text.

[1104] Specific example

[1105] For example, consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit photos?" In this case, the device uses voice recognition technology to convert the voice data into text data, "How do I edit photos?", while simultaneously analyzing the user's emotions using an emotion engine. The text data, along with the analysis results, is then sent to the server.

[1106] The server uses a natural language processing engine to understand the intent of the question and generates a response such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, it generates a response such as, "Please calm down. Now, open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," which is then converted into audio data using a speech synthesis engine and sent to the device.

[1107] The mobile device plays back received audio data and simultaneously displays text data on the screen. Users can confirm information through both sight and sound, and receive appropriate support tailored to their emotions.

[1108] In this way, the system can provide quick and appropriate answers to user questions, and further enhance the user experience using sentiment analysis.

[1109] The following describes the processing flow.

[1110] Step 1:

[1111] The user inputs the question via voice or text using a mobile device. For example, the user might input "How do I take a screenshot?" via voice.

[1112] Step 2:

[1113] The device acquires voice input via the microphone, or text input from a field.

[1114] Step 3:

[1115] The device uses speech recognition technology to convert voice data into text data. For example, the voice "Tell me how to take a screenshot" is converted into the text "Tell me how to take a screenshot".

[1116] Step 4:

[1117] The device uses an emotion engine to analyze the user's emotions from their voice data. For example, the emotion engine analyzes the tone, speed, and volume of the user's voice to identify their emotional state, such as whether they are excited or calm.

[1118] Step 5:

[1119] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[1120] Step 6:

[1121] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information. For example, it identifies the specific steps involved in a question like "How to take a screenshot."

[1122] Step 7:

[1123] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[1124] Step 8:

[1125] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it might generate a gentle response such as, "Please calm down. Now, to take a screenshot, press the side button and the volume up button at the same time."

[1126] Step 9:

[1127] The server passes the generated text response to the speech synthesis engine, which then generates audio data. For example, it might generate audio data saying, "To take a screenshot, press the side button and the volume up button at the same time."

[1128] Step 10:

[1129] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[1130] Step 11:

[1131] The device plays back received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," while simultaneously displaying the text on the screen.

[1132] In this way, users can receive appropriate answers to their questions immediately. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means. Additionally, sentiment analysis is used to provide appropriate responses tailored to the user's emotions, thus improving the user experience.

[1133] (Example 2)

[1134] Next, we will describe Example 2. 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."

[1135] Traditional question-answering systems often provided uniform answers without considering the user's emotional state. As a result, they failed to provide appropriate support, especially to frustrated or confused users, leading to a poor user experience. Furthermore, delays in providing answers, both verbally and text-based, resulted in insufficient problem-solving in situations requiring quick responses.

[1136] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1137] In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for adjusting the generated answer based on the sentiment analysis results. This enables the provision of adaptive answers that correspond to the user's emotional state, allowing for a quick and appropriate response.

[1138] A "user" is an individual who uses the system to input questions and receive answers.

[1139] A "personal digital assistant" (PDA) refers to an electronic device that a user can carry with them, such as a smartphone or tablet.

[1140] "Audio data" refers to the digital representation of an audio signal acquired through the microphone of a mobile device.

[1141] "Text data" refers to speech recognition results from audio data or directly entered text information.

[1142] "Emotional analysis" is the process of analyzing a user's emotional state from their voice or text.

[1143] A "server" is a computing system used to analyze questions and generate answers.

[1144] A "natural language processing engine" is a software engine that analyzes text data to understand its meaning and intent.

[1145] A "generative AI model" is a model that uses machine learning and deep learning algorithms to generate responses based on natural language.

[1146] A "speech synthesis engine" is a software engine used to convert text data into speech data.

[1147] "Emotional analysis results" refer to data that indicates the user's emotional state, obtained through emotional analysis.

[1148] "Response adjustment" refers to the process of modifying the content and tone of generated responses to better suit the user's emotional state.

[1149] A "network" refers to the communication infrastructure used for data communication between mobile devices and servers.

[1150] A "protocol" is a set of communication rules used to exchange data between a terminal and a server.

[1151] Modes for carrying out the invention

[1152] This invention provides a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers that correspond to the user's emotional state. This system uses a mobile device, a server, and a network connecting the two.

[1153] System Configuration

[1154] 1. Mobile device

[1155] These are electronic devices such as smartphones and tablets that users can carry with them. The devices are equipped with means of voice input and text input, and have the function of acquiring input data. They also have the function of converting voice input into text data using speech recognition technology. Specifically, Google Cloud Speech-to-Text is used. Furthermore, they have the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to a server. IBM Watson's emotion analysis API is used for emotion analysis.

[1156] 2. Server

[1157] This is a computing system located in the cloud or on-premises. The server is equipped with a natural language processing engine and uses tools such as Google Cloud Natural Language API and spaCy to analyze incoming text data and understand the intent of the user's questions. It also uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate answers to the user's questions. Furthermore, it can use an emotion engine to analyze the user's emotional state and generate adaptive answers that correspond to those emotions. The generated answers are converted into speech data using a speech synthesis engine (e.g., Amazon Polly or Google Cloud Text-to-Speech).

[1158] 3. Network

[1159] This includes the internet and mobile networks as communication channels connecting mobile devices and servers. HTTP or HTTPS protocols are used for communication.

[1160] Program processing

[1161] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer. The following details each process of the system and the technologies used.

[1162] 1. User input of question

[1163] Users input questions using their mobile devices via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[1164] 2. Input data acquisition and preprocessing

[1165] The device acquires the user's voice data through the microphone. The acquired voice data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). In the case of text input, it is acquired as text data as is.

[1166] 3. Emotion analysis

[1167] The device's built-in emotion engine is used to analyze the user's emotional state from voice or text data. For example, IBM Watson's emotion analysis API can be used to identify emotional states such as "excited," "calm," or "irritated." In some cases, the analysis may determine that the user is slightly confused.

[1168] 4. Sending queries to the server

[1169] The device sends the acquired text data and sentiment analysis results to the server. Communication takes place via the HTTP or HTTPS protocol over the internet or mobile network.

[1170] 5. Question Analysis and Intent Understanding

[1171] The server uses a natural language processing engine (NLP) to analyze the received text data and uses tools such as Google Cloud Natural Language API and spaCy to understand the intent of the question. For example, it can recognize the specific steps for "how to take a screenshot."

[1172] 6. Generating the answer

[1173] The server uses a generated AI model (e.g., OpenAI's GPT-3) to generate the best possible answer to the user's question. Specifically, it might generate text such as, "To take a screenshot, press the side button and the volume up button simultaneously."

[1174] 7. Adjusting responses to emotions

[1175] The server uses sentiment analysis results to generate adaptive responses. For example, if the user is frustrated, it might generate a response in a gentle tone such as, "I know you're in a hurry, but don't worry, to take a screenshot, just press the side button and the volume up button at the same time."

[1176] 8. Execute speech synthesis

[1177] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. This audio data allows users to verify the answers through means other than sight.

[1178] 9. Sending the response to the device

[1179] The server sends the generated audio and text data to the terminal. This is also done via the internet or mobile network, using the HTTP or HTTPS protocol.

[1180] 10. Presenting answers to the user

[1181] The device plays the received audio data and simultaneously displays the text data on the screen. The user hears an audio message saying, "To take a screenshot, press the side button and the volume up button at the same time," and can also visually confirm this in text.

[1182] Specific example

[1183] For example, consider a scenario where a user asks a question by voice to their mobile device: "Tell me how to edit photos." The device uses voice recognition technology to convert the voice data into text data, "Tell me how to edit photos," and an emotion engine analyzes the user's emotions. The text data, along with the analysis results, is then sent to the server.

[1184] The server understands the intent of the question through a natural language processing engine and generates an answer such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, a response such as, "Please calm down. Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," is generated and converted into speech data by a speech synthesis engine.

[1185] The mobile device plays the received audio data and simultaneously displays the message "Open the photo app, select the photo you want to edit, and tap the edit button in the upper right corner" on the screen. The user can confirm the specific steps through both sight and sound. In this way, the system provides quick and appropriate answers to the user's questions and can further enhance the user experience using sentiment analysis.

[1186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1187] Step 1: The user enters the question using a mobile device.

[1188] The user inputs a question by voice using the microphone on their smartphone or tablet. For example, they might voice the question, "How do I take a screenshot?" The input data is an audio signal, which then becomes the input for the next step.

[1189] Step 2: The terminal acquires the audio data and performs preprocessing.

[1190] The device acquires the user's voice data through the microphone. The acquired voice data is processed as a digital signal and passed to the speech recognition engine. For example, the Google Cloud Speech-to-Text engine is used to convert this voice data into text data. The voice signal is the input data, and the converted text data is the output.

[1191] Step 3: The device performs emotion analysis.

[1192] The device receives text data and uses an emotion engine to analyze the user's emotional state. For example, it uses IBM Watson's emotion analysis API to identify emotions such as "irritated" from the text data. The input data is text data, and the emotion analysis results are the output.

[1193] Step 4: The device sends text data and sentiment analysis results to the server.

[1194] The terminal sends the acquired text data and sentiment analysis results to the server. HTTP or HTTPS protocols are used for communication, and the data is sent to the server over the network. The input data consists of text data and sentiment analysis results, and the output of this step is the success of the data transmission to the server.

[1195] Step 5: The server analyzes the question and understands its intent.

[1196] The server analyzes the received text data using a natural language processing engine to understand the intent of the question. For example, it uses the Google Cloud Natural Language API or spaCy to identify "how to take a screenshot." The input data is text data, and the output is the analysis result that identifies the intent of the question.

[1197] Step 6: The server generates an answer using the generated AI model.

[1198] The server uses a generative AI model (e.g., OpenAI's GPT-3) based on the analysis results to generate the best answer to the question. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button simultaneously." The input data is the analysis results used to identify the intent of the question, and the generated answer (text data) is the output.

[1199] Step 7: The server adjusts the response based on emotion.

[1200] The server uses sentiment analysis results to generate adaptive responses that match the user's emotional state. For example, if the user is frustrated, it will generate a gentle response such as, "You're in a hurry, aren't you? But don't worry, to take a screenshot, press the side button and the volume up button at the same time." The input data consists of the generated response and the sentiment analysis results, and the adjusted response is the output.

[1201] Step 8: The server converts the data into speech data using a speech synthesis engine.

[1202] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. The input data is the text response, and the output is the converted audio data.

[1203] Step 9: The server sends the response to the terminal.

[1204] The server sends the generated audio and text data to the terminal. The data is then transmitted to the terminal over the network using the HTTP or HTTPS protocol. The input data consists of audio and text data, and the output of this step is the success of the data transmission to the terminal.

[1205] Step 10: The device presents the answer to the user.

[1206] The device plays the received audio data while simultaneously displaying text data on the screen. The user hears specific instructions, such as "To take a screenshot, press the side button and the volume up button simultaneously," through audio and can visually confirm them through text. The input data consists of audio and text data, and the output is the response presented to the user.

[1207] (Application Example 2)

[1208] Next, we will explain application example 2. In the following explanation, 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."

[1209] Conventional question-answering systems using mobile devices generate answers without considering the user's emotional state, resulting in a limited user experience and often failing to provide appropriate support. Furthermore, in in-store purchasing support, simply providing text-based answers is insufficient; it's necessary to respond to the user's real-time emotional changes. Therefore, the challenge lies in realizing a system that analyzes user emotions and provides adaptive support tailored to those emotions.

[1210] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for analyzing the user's emotional state using an emotion engine and generating an adaptive answer corresponding to the emotion. This makes it possible to provide a quick and appropriate answer to the user's question and to improve the user experience using emotion analysis.

[1211] A "user" refers to a person who uses a mobile device to input questions and receive answers.

[1212] A "personal digital assistant" (PDA) is an electronic device that a user can carry with them, such as a smartphone or tablet.

[1213] "Voice data" refers to the user's voice information acquired using a microphone.

[1214] "Text data" refers to character information converted from audio data or character information entered by the user.

[1215] A "server" is a computing system that performs data analysis and response generation.

[1216] A "natural language processing engine" is a technology that analyzes text data and understands the intent behind a question.

[1217] A "generative AI model" is a system that uses machine learning and deep learning algorithms to generate the optimal answer to a question.

[1218] An "emotion engine" is a technology that analyzes a user's emotional state from their voice and text data.

[1219] A "speech synthesis engine" is a technology that converts text data into speech data.

[1220] "Network" is a general term for the communication lines and infrastructure that connect mobile devices and servers.

[1221] "Speech recognition technology" is a technology that converts speech data into text data.

[1222] An "adaptive response" refers to a response that is adjusted according to the user's emotional state.

[1223] This invention is a system in which a user inputs a question using a mobile device and receives an appropriate answer in real time. Furthermore, the system aims to analyze the user's emotions and generate adaptive answers that correspond to those emotions. The system includes a mobile device, a server, and a network connecting them.

[1224] 1. Mobile device

[1225] Personal digital assistants (PDAs) are electronic devices that users can carry with them, such as smartphones and tablets. These devices have the following functions:

[1226] A means of enabling voice input and text input.

[1227] A means of converting voice input into text data using speech recognition technology.

[1228] A means of analyzing a user's emotional state using an emotion engine and sending the analysis results to a server.

[1229] 2. Server

[1230] A server is a computing system that performs data analysis and response generation. The server has the following functions:

[1231] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[1232] A means of generating the optimal response based on text data using a generative AI model.

[1233] A means of analyzing a user's emotional state using an emotion engine and generating adaptive responses that correspond to those emotions.

[1234] A method for converting text responses generated using a speech synthesis engine into speech data.

[1235] Means for transmitting voice data and text data to a mobile information terminal

[1236] 3. Network

[1237] A network is a general term for communication lines and infrastructure used to connect mobile devices and servers. This includes the internet and mobile networks. Various types of data are exchanged between servers and devices through this network.

[1238] Processing flow

[1239] 1. The user enters their question via voice or text using a mobile device. For example, they might ask, "What does this wine pair well with?"

[1240] 2. The device uses speech recognition technology to convert speech data into text data, and an emotion engine analyzes the user's emotional state.

[1241] 3. The analysis results, along with the text data, are sent to the server.

[1242] 4. The server uses a natural language processing engine to understand the intent of the question and generates the best answer using a generative AI model.

[1243] 5. An emotion engine is used to prepare adaptive responses that correspond to the user's emotional state.

[1244] 6. The text response generated by the speech synthesis engine is converted into audio data.

[1245] 7. The response data is sent to the mobile device, which plays the audio data and displays the text data.

[1246] Specific example

[1247] For example, consider a scenario where a user asks a question about wine in a physical store. The user uses their smartphone to ask a question by voice, "What does this wine pair well with?" The smartphone converts the voice into text and simultaneously analyzes the user's emotions. When this information is sent to the server, the server analyzes the intent of the question and generates an answer such as, "This wine pairs particularly well with red meat dishes and pasta." If the server analyzes that the user is confused, it generates a gentler response such as, "Please calm down. This wine pairs particularly well with red meat dishes and pasta," converts it into voice data, and sends it to the smartphone.

[1248] Example of a prompt

[1249] User question: "What does this wine pair well with?"

[1250] System response: "This wine pairs particularly well with red meat dishes and pasta. Is there anything else you'd like to order?"

[1251] This system allows users to receive appropriate answers in real time, even in physical stores, and to receive support tailored to their emotional state.

[1252] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1253] Step 1:

[1254] The user enters a question.

[1255] Input: The user enters the question by voice using the microphone on their mobile device, or by typing text using the keyboard.

[1256] Action: The user asks a voice question: "What does this wine pair well with?"

[1257] Output: Audio data or text data.

[1258] Step 2:

[1259] Convert audio data to text data

[1260] Input: Audio data

[1261] Operation: The device uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the audio data into text data.

[1262] Output: Converted text data (e.g., "What does this wine pair well with?").

[1263] Step 3:

[1264] Analysis of emotional states

[1265] Input: Converted text data

[1266] Operation: The device uses an emotion engine (e.g., Microsoft Azure Text Analytics) to analyze the user's emotional state. The analysis takes into account the user's tone of voice and text content.

[1267] Output: Sentiment analysis results (e.g., interesting, confused, etc.).

[1268] Step 4:

[1269] Send text data and sentiment analysis results to the server.

[1270] Input: Converted text data and sentiment analysis results

[1271] Operation: The device sends text data and sentiment analysis results to the server via the network.

[1272] Output: Data received on the server side.

[1273] Step 5:

[1274] Analyze the intent of the question

[1275] Input: Received text data

[1276] Operation: The server uses a natural language processing engine (e.g., NLTK or spaCy) to analyze text data and understand the intent of the question. For example, the question "What does this wine pair well with?" is interpreted as an attempt to find out which wines pair well with food.

[1277] Output: Analysis results that understand the intent of the question.

[1278] Step 6:

[1279] Generate an answer

[1280] Input: Analysis results that understand the intent of the question

[1281] Operation: The server generates the optimal answer using an AI model (e.g., GPT-4). For example, "This wine pairs particularly well with red meat dishes and pasta."

[1282] Output: Generated answer text.

[1283] Step 7:

[1284] Adjusting responses based on emotions

[1285] Input: Generated response text and sentiment analysis results

[1286] How it works: The server uses an emotion engine to adjust its responses based on the user's emotional state. For example, if the user is confused, it might prepare a gentle response such as, "Please calm down. This wine pairs especially well with red meat dishes and pasta."

[1287] Output: Adaptive response text that responds to emotions.

[1288] Step 8:

[1289] Convert the answer into audio data.

[1290] Input: Emotionally adaptive response text

[1291] Operation: The server uses a text-to-speech engine (e.g., Google Text-to-Speech API) to convert the response text into audio data.

[1292] Output: Converted audio data.

[1293] Step 9:

[1294] Send audio and text data to the device.

[1295] Input: Converted audio data and response text data

[1296] Operation: The server transmits voice and text data to the mobile device over the network.

[1297] Output: Data received on the terminal side.

[1298] Step 10:

[1299] Providing answers to users

[1300] Input: Audio and text data received by the device

[1301] Operation: The device plays audio data and displays text data on the screen. For example, it might play the response "This wine pairs particularly well with red meat dishes and pasta" as audio and simultaneously display it on the screen.

[1302] Output: Users can verify the answer visually and aurally.

[1303] The above outlines the specific processing steps of the system program that implements the application example. This allows users to receive appropriate answers in real time and support tailored to their emotional state.

[1304] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1305] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1306] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1307] [Fourth Embodiment]

[1308] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1309] As shown in Figure 7, the 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.

[1310] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1311] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1312] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1313] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1314] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1315] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1316] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1317] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1318] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1319] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1320] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1321] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[1322] System Configuration

[1323] 1. Mobile device

[1324] These are electronic devices such as smartphones and tablets that users carry with them.

[1325] It is equipped with means for voice input and text input.

[1326] It has communication capabilities to process input data and send it to the server.

[1327] It has the function of converting voice input into text using speech recognition technology.

[1328] 2. Server

[1329] This refers to a computing system installed on the cloud or on-premises.

[1330] It is equipped with a natural language processing engine and analyzes the received text data.

[1331] The AI ​​model (e.g., machine learning or deep learning algorithms) is used to generate the answer.

[1332] A speech synthesis engine is used to convert text responses into audio data.

[1333] 3. Network

[1334] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[1335] Program processing

[1336] Overall flow

[1337] The overall operation of this system consists of a series of steps, starting with user input and culminating in the provision of a response to the user. The specific processing flow is described below in natural language.

[1338] 1. User input of question

[1339] Users input questions about how to use their smartphones using their mobile devices. Questions can be entered via voice or text. For example, a user might ask, "How do I take a screenshot?" using voice.

[1340] 2. Input data acquisition and preprocessing

[1341] The mobile device acquires user input data. In the case of voice input, it uses a microphone to acquire voice data and converts it into text data using speech recognition technology. In the case of text input, it is treated as text data as is.

[1342] 3. Sending queries to the server

[1343] The mobile device sends the acquired text data to the server. The server then prepares to perform the next processing based on the received text data.

[1344] 4. Question Analysis and Intent Understanding

[1345] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the meaning of the question "How to take a screenshot" and extracts information to generate an appropriate answer.

[1346] 5. Generating the answer

[1347] The server uses an AI model to generate the best answer to a question. In this step, the AI ​​model generates the text of the answer based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[1348] 6. Execute speech synthesis.

[1349] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[1350] 7. Send the response to the device.

[1351] The server generates audio and text data and sends it to the mobile device. This is how the final output is displayed on the user's device.

[1352] 8. Presenting answers to the user

[1353] The mobile device provides the user with received audio and text data. The audio data is played through the speaker, and the text data is displayed on the screen. This allows the user to obtain specific answers to their questions.

[1354] Specific example

[1355] Consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit a photo?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine and generates an answer using an AI model, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data using a speech synthesis engine and sent back to the mobile device. Finally, the mobile device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[1356] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[1357] The following describes the processing flow.

[1358] Step 1:

[1359] The user uses a mobile device to input a question via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[1360] Step 2:

[1361] The device acquires voice input via the microphone, or text input from a field.

[1362] Step 3:

[1363] The device uses speech recognition technology to convert the voice data into text data. The resulting text might be something like, "Tell me how to take a screenshot."

[1364] Step 4:

[1365] The terminal sends the acquired text data to the server. The data is transferred to the server via the network.

[1366] Step 5:

[1367] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information.

[1368] Step 6:

[1369] The server uses an AI model to generate the best answer to a question. For example, it might generate an answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[1370] Step 7:

[1371] The server generates text responses, which are then passed to a speech synthesis engine to produce audio data. The generated audio data allows users to hear the responses even if they cannot visually verify them.

[1372] Step 8:

[1373] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[1374] Step 9:

[1375] The device plays back received audio data and displays text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button simultaneously," both audibly and as text.

[1376] In this way, users can get immediate and appropriate answers to their questions. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means.

[1377] (Example 1)

[1378] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1379] With the widespread adoption of modern smartphones and mobile devices, there is a growing demand for systems that can resolve user questions about device usage in real time. Senior users and tech-savvy users, in particular, often struggle to understand how to operate their devices, making a system that provides quick and accurate instructions essential. However, conventional systems have struggled to provide appropriate answers to user questions in real time, and their low accuracy in speech recognition and natural language processing has made them unuser-friendly. This invention aims to solve these problems.

[1380] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1381] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative artificial intelligence model, and means for using a speech synthesis engine when generating audio data. This makes it possible for users to input questions about how to use smartphones or mobile devices in real time, and for the system to acquire and analyze audio or text data to provide a quick and appropriate answer.

[1382] A "user" refers to a person who operates the system and enters questions.

[1383] "Personal information terminals" refer to portable electronic devices such as smartphones and tablets.

[1384] A "question" refers to the content that a user inputs using a mobile device, and which the system then uses to generate an answer.

[1385] "Speech recognition technology" refers to the technology that converts speech data into text data.

[1386] A "natural language processing engine" refers to software that analyzes text data and understands its meaning.

[1387] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that generates answers based on past data and context.

[1388] A "speech synthesis engine" refers to a technology used to convert text data into speech data.

[1389] A "server" refers to a remote computer system that performs data processing.

[1390] "Network" refers to the communication channel that connects a mobile device to a server.

[1391] "Text data" refers to voice input converted by speech recognition technology or strings of characters entered directly.

[1392] "Audio data" refers to digital audio information generated by a speech synthesis engine based on text generated by speech recognition technology.

[1393] This invention is a system that provides real-time answers to questions from users regarding the use of smartphones via their mobile devices. The system includes mobile devices, a server, and a network connecting them.

[1394] System Configuration

[1395] 1. Mobile device

[1396] These are electronic devices such as smartphones and tablets that users carry with them.

[1397] It is equipped with means for voice input and text input.

[1398] It has communication capabilities to process input data and send it to the server.

[1399] It has the functionality to convert voice input into text using speech recognition technology (for example, Google Speech-to-Text API).

[1400] 2. Server

[1401] This refers to a computing system installed on the cloud or on-premises.

[1402] It is equipped with a natural language processing engine (such as Python's NLTK library or SpaCy) to analyze the received text data.

[1403] The system generates answers using generative artificial intelligence models (e.g., GPT-3 or BERT).

[1404] Convert text responses into audio data using a speech synthesis engine (e.g., Google Text-to-Speech API).

[1405] 3. Network

[1406] This refers to a communication channel that connects a mobile device to a server, and includes the internet and mobile networks.

[1407] Program processing

[1408] The user enters a question about how to use their smartphone using a mobile device. The question can be entered by voice or text. For example, consider a case where the user asks by voice, "How do I take a screenshot?" In this case, the mobile device acquires the voice data and converts it into text data, "How do I take a screenshot?", using voice recognition technology.

[1409] Next, this text data is sent to the server. The server uses a natural language processing engine to analyze the text data and understand the intent of the question. For example, it might identify "how to take a screenshot" and generate an appropriate answer.

[1410] The server uses a generative artificial intelligence model to generate the best possible answer to a question. The model generates the answer text based on past data and context. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button at the same time."

[1411] Next, the server passes the generated text of the response to a speech synthesis engine to generate audio data. This allows the user to hear the response even if they cannot visually confirm it. The generated audio and text data are sent to the mobile device, which reads the response aloud and displays it as text on the screen.

[1412] Specific example

[1413] Consider a scenario where a user asks a voice question using a mobile device: "How do I edit a photo?" The device acquires the voice data and converts it into text data, "How do I edit a photo?", using speech recognition technology. Next, the text data is sent to a server, which analyzes the question using a natural language processing engine. An AI model generates the answer, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." The generated answer is converted into voice data by a speech synthesis engine and sent back to the mobile device. The device reads the answer aloud, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," and displays it as text on the screen.

[1414] Example of a prompt

[1415] Here are some examples of prompt messages:

[1416] "How do I take a screenshot?"

[1417] "How do I lower the volume on my smartphone?"

[1418] "Please tell me how to edit photos."

[1419] In this way, the system provides users with quick and appropriate answers to their questions about how to use their smartphones.

[1420] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1421] Step 1:

[1422] The user enters a question using a mobile device. The input method is either voice input or text input. Specifically, the user asks a question by voice into the device, such as "Tell me how to take a screenshot." In this process, the mobile device uses its microphone to acquire voice data and receives it as input data.

[1423] Step 2:

[1424] The device acquires the user's voice data and converts it into text data using speech recognition technology. Specifically, the device sends the acquired voice data to a cloud-based speech recognition service (for example, Google Speech-to-Text API), which then converts the voice data into text data and returns it. The output of this process is the text data obtained by speech recognition technology: "Tell me how to take a screenshot."

[1425] Step 3:

[1426] The terminal sends the acquired text data to the server. In this process, the terminal uses the HTTPS protocol over the internet to send the text data to the server as a POST request. The input is text data, and the output is the transmission of data to the server.

[1427] Step 4:

[1428] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. Specifically, the server tokenizes the text data, extracts important keywords, and analyzes the context. The input is the text data "Tell me how to take a screenshot," and the output is the understood intent of the question, "How to take a screenshot."

[1429] Step 5:

[1430] The server uses a generative artificial intelligence model to generate the best answer to a question. In this step, the server passes the prompt "How do I take a screenshot?" to the generative AI model, which outputs the answer "To take a screenshot, press the side button and the volume up button at the same time." The input is the understood intent of the question, and the output is the generated answer text "To take a screenshot, press the side button and the volume up button at the same time."

[1431] Step 6:

[1432] The server generates the text response, which is then passed to a text-to-speech engine to produce audio data. In this process, the server sends the text data to a text-to-speech service such as the Google Text-to-Speech API, which generates and receives the audio data (e.g., an MP3 file). The input is the generated text response, and the output is the generated audio data.

[1433] Step 7:

[1434] The server generates audio and text data and sends it to the mobile device. In this process, the server again uses the HTTPS protocol to send the data to the device. The input is audio and text data, and the output is the transmission of data to the device.

[1435] Step 8:

[1436] The device provides the user with the audio and text data it receives. Specifically, the device plays the audio data and displays the text data on the screen. The input is the audio and text data received from the server, and the output is audio playback and text display to the user.

[1437] The above outlines the specific processing steps of this system's program.

[1438] (Application Example 1)

[1439] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1440] Conventional technologies had limitations in how users could input questions using digital information terminals and receive answers in real time. In particular, there was a lack of systems capable of providing efficient and effective support when using smartphones. Furthermore, it was difficult to quickly generate accurate answers to a wide range of user questions. This resulted in reduced user convenience and hindered the smooth use of digital services.

[1441] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1442] In this invention, the server includes means for analyzing text data using a natural language processing engine to understand the intent of a question, means for generating an answer based on the text data using a generative AI model, and means for appropriately processing information using prompt sentences to generate an answer. As a result, when a user inputs a question using an information terminal, the server can generate a quick and accurate answer, thereby improving user convenience and enabling smooth use of digital services.

[1443] An "information terminal" refers to an electronic device such as a smartphone or tablet that a user carries with them.

[1444] A "natural language processing engine" is a software technology that analyzes text data to understand the meaning of sentences and the intent of questions.

[1445] A "generative AI model" is an artificial intelligence program that uses machine learning and deep learning algorithms to make predictions and generate information based on input data.

[1446] A "prompt sentence" is an input sentence given to an AI model, and it is an instruction sentence that generates an appropriate answer to a specific question or task.

[1447] A "speech synthesis engine" is a technology for converting text data into speech data, and is software that enables speech output.

[1448] "Text data" refers to data that represents user-entered questions, server-generated answers, and other information as text.

[1449] "Voice data" refers to data generated by a speech synthesis engine or recorded from user input.

[1450] Modes for carrying out the invention

[1451] System Overview

[1452] This invention is a system for users to input questions using an information terminal and receive answers in real time. The system includes an information terminal, a server, and a network connecting the two. The system of this invention is designed to efficiently provide user support, particularly in content distribution services.

[1453] System Configuration

[1454] 1. Information terminal

[1455] These are electronic devices such as smartphones and tablets that users carry with them.

[1456] It is equipped with means for voice input and text input.

[1457] It has communication capabilities to process input data and send it to the server.

[1458] It has the function of converting voice input into text data using speech recognition technology.

[1459] 2. Server

[1460] This refers to a computing system installed on the cloud or on-premises.

[1461] It is equipped with a natural language processing engine and analyzes the received text data.

[1462] The system generates answers using generative AI models (e.g., machine learning or deep learning algorithms).

[1463] Use prompt statements to properly process the intent of the question and generate an answer.

[1464] A speech synthesis engine is used to convert text responses into audio data.

[1465] 3. Network

[1466] This refers to a communication channel that connects information terminals and servers, such as the internet and mobile networks.

[1467] Program processing details

[1468] The system operates as follows: When a user enters a question using an information terminal, the data is sent to the server. The server analyzes the text data using a natural language processing engine and generates the optimal answer using a generative AI model. During this process, prompts are used to improve the accuracy of the answer. The generated answer is converted into audio data by a speech synthesis engine and sent back to the information terminal.

[1469] Specific example

[1470] For example, consider a case where a user inputs the question, "What are some of the latest dramas you recommend?". In this case, the information terminal acquires the voice data and converts it into text data, "What are some of the latest dramas you recommend?", using speech recognition technology. Next, the text data is sent to the server, which analyzes the question using a natural language processing engine. Then, a generative AI model generates an answer using the following prompt sentence.

[1471] Example of a prompt

[1472] "What are some of the latest dramas you recommend?"

[1473] Based on this prompt, the server generates a response such as "The current recommended drama is 'XX Drama'," and converts it into audio data using a speech synthesis engine. Finally, this audio data and text data are sent to the information terminal and provided to the user.

[1474] In this way, the system is designed to allow users to obtain quick and accurate answers to their questions. This improves user convenience and enables smoother use of the content delivery service.

[1475] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1476] Detailed program processing steps

[1477] Step 1:

[1478] The user enters a question using an information terminal. Input can be via voice or text. For example, the user might voice-input the question, "What are some recommended new dramas?" The information terminal acquires the voice data through its microphone and uses speech recognition technology to convert this voice data into text data. The input is voice data, and the output is text data.

[1479] Step 2:

[1480] The information terminal sends the converted text data to the server. Here, the information terminal uses a network (Internet or mobile network) to send the text data to the server as a POST request. The input is text data, and the output is the query text delivered to the server.

[1481] Step 3:

[1482] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. In this step, the input text data is subjected to morphological and contextual analysis to identify the subject and meaning of the question. The input is the received text data, and the output is the analyzed intent of the question.

[1483] Step 4:

[1484] The server uses a generative AI model to generate answers based on the analyzed question intent. In this process, prompts are used to provide clear instructions to the AI ​​model, enabling it to produce appropriate answers. The input consists of the analyzed question intent and prompts, while the output is the generated answer text.

[1485] Step 5:

[1486] The server passes the generated response text to the speech synthesis engine, which converts the text data into speech data. In this step, the speech synthesis engine converts the text data into a speech waveform, making it a format that is easy for humans to understand. The input is the response text, and the output is the generated speech data.

[1487] Step 6:

[1488] The server sends the generated audio and text data to the information terminal. Here, the generated data is retransmitted to the information terminal via the network. The input is the audio and text data, and the output is the data sent to the information terminal.

[1489] Step 7:

[1490] The information terminal plays the received audio data and displays the text data on the screen. This allows the user to confirm the answer through both sight and sound. Specifically, it plays the audio data using the speaker and displays the text data on the display. The input is the received audio data and text data, and the output is the played audio and the displayed text.

[1491] Step 8:

[1492] The user confirms that they have received an answer to their question by listening to voice instructions from the device and confirming the text displayed on the screen. This resolves the user's doubts and completes the information retrieval through the system. The input is the played audio and displayed text, and the output is the user's understanding and confirmation.

[1493] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1494] This invention is a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers according to the user's emotional state. This system includes a mobile device, a server, and a network connecting the two.

[1495] System Configuration

[1496] 1. Mobile device

[1497] These are electronic devices such as smartphones and tablets that users can carry with them.

[1498] It is equipped with means for voice input and text input, and has a function to acquire input data.

[1499] It has the ability to convert voice input into text data using speech recognition technology.

[1500] It has the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to the server.

[1501] 2. Server

[1502] This refers to a computing system installed on the cloud or on-premises.

[1503] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[1504] Using AI models (e.g., machine learning or deep learning algorithms), we generate appropriate answers to user questions.

[1505] It has the functionality to analyze the user's emotional state using an emotion engine and generate adaptive responses that correspond to those emotions.

[1506] Convert the text response generated using a speech synthesis engine into audio data.

[1507] 3. Network

[1508] This includes the internet and mobile networks as communication channels connecting mobile devices and servers.

[1509] Program processing

[1510] The program's processing is explained below in natural language.

[1511] Overall flow

[1512] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer.

[1513] 1. User input of question

[1514] The user uses a mobile device to input a question via voice or text. For example, consider the case where the user asks a question by voice, "How do I take a screenshot?"

[1515] 2. Input data acquisition and preprocessing

[1516] The device acquires user input data. In the case of voice input, voice data is acquired through the microphone and converted into text data using speech recognition technology. In the case of text input, it is processed as text data as is.

[1517] 3. Emotion analysis

[1518] The device analyzes the user's voice data through an emotion engine to determine their emotions. For example, it identifies the user's emotional state, such as being excited, calm, or irritated.

[1519] 4. Sending queries to the server

[1520] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[1521] 5. Question Analysis and Intent Understanding

[1522] The server uses a natural language processing engine to analyze the received text data and understand the intent of the question. For example, it identifies the specific steps for "how to take a screenshot."

[1523] 6. Generating the answer

[1524] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[1525] 7. Adjusting responses to emotions

[1526] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it will generate text that explains things in a gentle tone.

[1527] 8. Execute speech synthesis

[1528] The generated text of the response is passed to a speech synthesis engine to produce audio data. This audio data is intended to allow users to hear the response even if they cannot visually confirm it.

[1529] 9. Sending the response to the device

[1530] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[1531] 10. Presenting answers to the user

[1532] The device plays the received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," and simultaneously display it as text.

[1533] Specific example

[1534] For example, consider a scenario where a user uses a mobile device to ask a voice question, "How do I edit photos?" In this case, the device uses voice recognition technology to convert the voice data into text data, "How do I edit photos?", while simultaneously analyzing the user's emotions using an emotion engine. The text data, along with the analysis results, is then sent to the server.

[1535] The server uses a natural language processing engine to understand the intent of the question and generates a response such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, it generates a response such as, "Please calm down. Now, open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," which is then converted into audio data using a speech synthesis engine and sent to the device.

[1536] The mobile device plays back received audio data and simultaneously displays text data on the screen. Users can confirm information through both sight and sound, and receive appropriate support tailored to their emotions.

[1537] In this way, the system can provide quick and appropriate answers to user questions, and further enhance the user experience using sentiment analysis.

[1538] The following describes the processing flow.

[1539] Step 1:

[1540] The user inputs the question via voice or text using a mobile device. For example, the user might input "How do I take a screenshot?" via voice.

[1541] Step 2:

[1542] The device acquires voice input via the microphone, or text input from a field.

[1543] Step 3:

[1544] The device uses speech recognition technology to convert voice data into text data. For example, the voice "Tell me how to take a screenshot" is converted into the text "Tell me how to take a screenshot".

[1545] Step 4:

[1546] The device uses an emotion engine to analyze the user's emotions from their voice data. For example, the emotion engine analyzes the tone, speed, and volume of the user's voice to identify their emotional state, such as whether they are excited or calm.

[1547] Step 5:

[1548] The device sends the acquired text data and sentiment analysis results to the server. The data is transferred to the server via the network.

[1549] Step 6:

[1550] The server analyzes the received text data using a natural language processing engine. Through this analysis, it understands the intent of the question and extracts the necessary information. For example, it identifies the specific steps involved in a question like "How to take a screenshot."

[1551] Step 7:

[1552] The server uses an AI model to generate the best answer to a question. For example, it might generate a text answer like, "To take a screenshot, press the side button and the volume up button at the same time."

[1553] Step 8:

[1554] The server uses an emotion engine to generate adaptive responses that correspond to the user's emotional state. For example, if the user is irritated, it might generate a gentle response such as, "Please calm down. Now, to take a screenshot, press the side button and the volume up button at the same time."

[1555] Step 9:

[1556] The server passes the generated text response to the speech synthesis engine, which then generates audio data. For example, it might generate audio data saying, "To take a screenshot, press the side button and the volume up button at the same time."

[1557] Step 10:

[1558] The server generates audio and text data and sends it to the terminal. The data is transferred to the terminal via the network.

[1559] Step 11:

[1560] The device plays back received audio data and displays the text data on the screen. For example, it might say, "To take a screenshot, press the side button and the volume up button at the same time," while simultaneously displaying the text on the screen.

[1561] In this way, users can receive appropriate answers to their questions immediately. Furthermore, by providing information in both audio and text formats, users can receive information through both visual and auditory means. Additionally, sentiment analysis is used to provide appropriate responses tailored to the user's emotions, thus improving the user experience.

[1562] (Example 2)

[1563] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1564] Traditional question-answering systems often provided uniform answers without considering the user's emotional state. As a result, they failed to provide appropriate support, especially to frustrated or confused users, leading to a poor user experience. Furthermore, delays in providing answers, both verbally and text-based, resulted in insufficient problem-solving in situations requiring quick responses.

[1565] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1566] In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for adjusting the generated answer based on the sentiment analysis results. This enables the provision of adaptive answers that correspond to the user's emotional state, allowing for a quick and appropriate response.

[1567] A "user" is an individual who uses the system to input questions and receive answers.

[1568] A "personal digital assistant" (PDA) refers to an electronic device that a user can carry with them, such as a smartphone or tablet.

[1569] "Audio data" refers to the digital representation of an audio signal acquired through the microphone of a mobile device.

[1570] "Text data" refers to speech recognition results from audio data or directly entered text information.

[1571] "Emotional analysis" is the process of analyzing a user's emotional state from their voice or text.

[1572] A "server" is a computing system used to analyze questions and generate answers.

[1573] A "natural language processing engine" is a software engine that analyzes text data to understand its meaning and intent.

[1574] A "generative AI model" is a model that uses machine learning and deep learning algorithms to generate responses based on natural language.

[1575] A "speech synthesis engine" is a software engine used to convert text data into speech data.

[1576] "Emotional analysis results" refer to data that indicates the user's emotional state, obtained through emotional analysis.

[1577] "Response adjustment" refers to the process of modifying the content and tone of generated responses to better suit the user's emotional state.

[1578] A "network" refers to the communication infrastructure used for data communication between mobile devices and servers.

[1579] A "protocol" is a set of communication rules used to exchange data between a terminal and a server.

[1580] Modes for carrying out the invention

[1581] This invention provides a system in which a user inputs a question via a mobile device and receives an appropriate answer to that question in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is intended to generate adaptive answers that correspond to the user's emotional state. This system uses a mobile device, a server, and a network connecting the two.

[1582] System Configuration

[1583] 1. Mobile device

[1584] These are electronic devices such as smartphones and tablets that users can carry with them. The devices are equipped with means of voice input and text input, and have the function of acquiring input data. They also have the function of converting voice input into text data using speech recognition technology. Specifically, Google Cloud Speech-to-Text is used. Furthermore, they have the function of analyzing the user's emotional state in real time through an emotion engine and sending the analysis results to a server. IBM Watson's emotion analysis API is used for emotion analysis.

[1585] 2. Server

[1586] This is a computing system located in the cloud or on-premises. The server is equipped with a natural language processing engine and uses tools such as Google Cloud Natural Language API and spaCy to analyze incoming text data and understand the intent of the user's questions. It also uses a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate answers to the user's questions. Furthermore, it can use an emotion engine to analyze the user's emotional state and generate adaptive answers that correspond to those emotions. The generated answers are converted into speech data using a speech synthesis engine (e.g., Amazon Polly or Google Cloud Text-to-Speech).

[1587] 3. Network

[1588] This includes the internet and mobile networks as communication channels connecting mobile devices and servers. HTTP or HTTPS protocols are used for communication.

[1589] Program processing

[1590] The system's operation begins with the user inputting a question and progresses through a series of steps, including sentiment analysis, to ultimately provide the user with an answer. The following details each process of the system and the technologies used.

[1591] 1. User input of question

[1592] Users input questions using their mobile devices via voice or text. For example, they might ask a voice question like, "How do I take a screenshot?"

[1593] 2. Input data acquisition and preprocessing

[1594] The device acquires the user's voice data through the microphone. The acquired voice data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text). In the case of text input, it is acquired as text data as is.

[1595] 3. Emotion analysis

[1596] The device's built-in emotion engine is used to analyze the user's emotional state from voice or text data. For example, IBM Watson's emotion analysis API can be used to identify emotional states such as "excited," "calm," or "irritated." In some cases, the analysis may determine that the user is slightly confused.

[1597] 4. Sending queries to the server

[1598] The device sends the acquired text data and sentiment analysis results to the server. Communication takes place via the HTTP or HTTPS protocol over the internet or mobile network.

[1599] 5. Question Analysis and Intent Understanding

[1600] The server uses a natural language processing engine (NLP) to analyze the received text data and uses tools such as Google Cloud Natural Language API and spaCy to understand the intent of the question. For example, it can recognize the specific steps for "how to take a screenshot."

[1601] 6. Generating the answer

[1602] The server uses a generated AI model (e.g., OpenAI's GPT-3) to generate the best possible answer to the user's question. Specifically, it might generate text such as, "To take a screenshot, press the side button and the volume up button simultaneously."

[1603] 7. Adjusting responses to emotions

[1604] The server uses sentiment analysis results to generate adaptive responses. For example, if the user is frustrated, it might generate a response in a gentle tone such as, "I know you're in a hurry, but don't worry, to take a screenshot, just press the side button and the volume up button at the same time."

[1605] 8. Execute speech synthesis

[1606] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. This audio data allows users to verify the answers through means other than sight.

[1607] 9. Sending the response to the device

[1608] The server sends the generated audio and text data to the terminal. This is also done via the internet or mobile network, using the HTTP or HTTPS protocol.

[1609] 10. Presenting answers to the user

[1610] The device plays the received audio data and simultaneously displays the text data on the screen. The user hears an audio message saying, "To take a screenshot, press the side button and the volume up button at the same time," and can also visually confirm this in text.

[1611] Specific example

[1612] For example, consider a scenario where a user asks a question by voice to their mobile device: "Tell me how to edit photos." The device uses voice recognition technology to convert the voice data into text data, "Tell me how to edit photos," and an emotion engine analyzes the user's emotions. The text data, along with the analysis results, is then sent to the server.

[1613] The server understands the intent of the question through a natural language processing engine and generates an answer such as, "Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner." Furthermore, based on the sentiment analysis results, if a gentler tone is needed, a response such as, "Please calm down. Open the Photos app, select the photo you want to edit, and tap the edit button in the upper right corner," is generated and converted into speech data by a speech synthesis engine.

[1614] The mobile device plays the received audio data and simultaneously displays the message "Open the photo app, select the photo you want to edit, and tap the edit button in the upper right corner" on the screen. The user can confirm the specific steps through both sight and sound. In this way, the system provides quick and appropriate answers to the user's questions and can further enhance the user experience using sentiment analysis.

[1615] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1616] Step 1: The user enters the question using a mobile device.

[1617] The user inputs a question by voice using the microphone on their smartphone or tablet. For example, they might voice the question, "How do I take a screenshot?" The input data is an audio signal, which then becomes the input for the next step.

[1618] Step 2: The terminal acquires the audio data and performs preprocessing.

[1619] The device acquires the user's voice data through the microphone. The acquired voice data is processed as a digital signal and passed to the speech recognition engine. For example, the Google Cloud Speech-to-Text engine is used to convert this voice data into text data. The voice signal is the input data, and the converted text data is the output.

[1620] Step 3: The device performs emotion analysis.

[1621] The device receives text data and uses an emotion engine to analyze the user's emotional state. For example, it uses IBM Watson's emotion analysis API to identify emotions such as "irritated" from the text data. The input data is text data, and the emotion analysis results are the output.

[1622] Step 4: The device sends text data and sentiment analysis results to the server.

[1623] The terminal sends the acquired text data and sentiment analysis results to the server. HTTP or HTTPS protocols are used for communication, and the data is sent to the server over the network. The input data consists of text data and sentiment analysis results, and the output of this step is the success of the data transmission to the server.

[1624] Step 5: The server analyzes the question and understands its intent.

[1625] The server analyzes the received text data using a natural language processing engine to understand the intent of the question. For example, it uses the Google Cloud Natural Language API or spaCy to identify "how to take a screenshot." The input data is text data, and the output is the analysis result that identifies the intent of the question.

[1626] Step 6: The server generates an answer using the generated AI model.

[1627] The server uses a generative AI model (e.g., OpenAI's GPT-3) based on the analysis results to generate the best answer to the question. For example, it might generate the answer, "To take a screenshot, press the side button and the volume up button simultaneously." The input data is the analysis results used to identify the intent of the question, and the generated answer (text data) is the output.

[1628] Step 7: The server adjusts the response based on emotion.

[1629] The server uses sentiment analysis results to generate adaptive responses that match the user's emotional state. For example, if the user is frustrated, it will generate a gentle response such as, "You're in a hurry, aren't you? But don't worry, to take a screenshot, press the side button and the volume up button at the same time." The input data consists of the generated response and the sentiment analysis results, and the adjusted response is the output.

[1630] Step 8: The server converts the data into speech data using a speech synthesis engine.

[1631] The server uses a text-to-speech engine (e.g., Amazon Polly or Google Cloud Text-to-Speech) to convert the generated text responses into audio data. The input data is the text response, and the output is the converted audio data.

[1632] Step 9: The server sends the response to the terminal.

[1633] The server sends the generated audio and text data to the terminal. The data is then transmitted to the terminal over the network using the HTTP or HTTPS protocol. The input data consists of audio and text data, and the output of this step is the success of the data transmission to the terminal.

[1634] Step 10: The device presents the answer to the user.

[1635] The device plays the received audio data while simultaneously displaying text data on the screen. The user hears specific instructions, such as "To take a screenshot, press the side button and the volume up button simultaneously," through audio and can visually confirm them through text. The input data consists of audio and text data, and the output is the response presented to the user.

[1636] (Application Example 2)

[1637] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1638] Conventional question-answering systems using mobile devices generate answers without considering the user's emotional state, resulting in a limited user experience and often failing to provide appropriate support. Furthermore, in in-store purchasing support, simply providing text-based answers is insufficient; it's necessary to respond to the user's real-time emotional changes. Therefore, the challenge lies in realizing a system that analyzes user emotions and provides adaptive support tailored to those emotions.

[1639] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing text data using a natural language processing engine and understanding the intent of the question, means for generating an answer based on the text data using a generative AI model, and means for analyzing the user's emotional state using an emotion engine and generating an adaptive answer corresponding to the emotion. This makes it possible to provide a quick and appropriate answer to the user's question and to improve the user experience using emotion analysis.

[1640] A "user" refers to a person who uses a mobile device to input questions and receive answers.

[1641] A "personal digital assistant" (PDA) is an electronic device that a user can carry with them, such as a smartphone or tablet.

[1642] "Voice data" refers to the user's voice information acquired using a microphone.

[1643] "Text data" refers to character information converted from audio data or character information entered by the user.

[1644] A "server" is a computing system that performs data analysis and response generation.

[1645] A "natural language processing engine" is a technology that analyzes text data and understands the intent behind a question.

[1646] A "generative AI model" is a system that uses machine learning and deep learning algorithms to generate the optimal answer to a question.

[1647] An "emotion engine" is a technology that analyzes a user's emotional state from their voice and text data.

[1648] A "speech synthesis engine" is a technology that converts text data into speech data.

[1649] "Network" is a general term for the communication lines and infrastructure that connect mobile devices and servers.

[1650] "Speech recognition technology" is a technology that converts speech data into text data.

[1651] An "adaptive response" refers to a response that is adjusted according to the user's emotional state.

[1652] This invention is a system in which a user inputs a question using a mobile device and receives an appropriate answer in real time. Furthermore, the system aims to analyze the user's emotions and generate adaptive answers that correspond to those emotions. The system includes a mobile device, a server, and a network connecting them.

[1653] 1. Mobile device

[1654] Personal digital assistants (PDAs) are electronic devices that users can carry with them, such as smartphones and tablets. These devices have the following functions:

[1655] A means of enabling voice input and text input.

[1656] A means of converting voice input into text data using speech recognition technology.

[1657] A means of analyzing a user's emotional state using an emotion engine and sending the analysis results to a server.

[1658] 2. Server

[1659] A server is a computing system that performs data analysis and response generation. The server has the following functions:

[1660] Equipped with a natural language processing engine, it analyzes received text data to understand the intent behind the user's question.

[1661] A means of generating the optimal response based on text data using a generative AI model.

[1662] A means of analyzing a user's emotional state using an emotion engine and generating adaptive responses that correspond to those emotions.

[1663] A method for converting text responses generated using a speech synthesis engine into speech data.

[1664] Means for transmitting voice data and text data to a mobile information terminal

[1665] 3. Network

[1666] A network is a general term for communication lines and infrastructure used to connect mobile devices and servers. This includes the internet and mobile networks. Various types of data are exchanged between servers and devices through this network.

[1667] Processing flow

[1668] 1. The user enters their question via voice or text using a mobile device. For example, they might ask, "What does this wine pair well with?"

[1669] 2. The device uses speech recognition technology to convert speech data into text data, and an emotion engine analyzes the user's emotional state.

[1670] 3. The analysis results, along with the text data, are sent to the server.

[1671] 4. The server uses a natural language processing engine to understand the intent of the question and generates the best answer using a generative AI model.

[1672] 5. An emotion engine is used to prepare adaptive responses that correspond to the user's emotional state.

[1673] 6. The text response generated by the speech synthesis engine is converted into audio data.

[1674] 7. The response data is sent to the mobile device, which plays the audio data and displays the text data.

[1675] Specific example

[1676] For example, consider a scenario where a user asks a question about wine in a physical store. The user uses their smartphone to ask a question by voice, "What does this wine pair well with?" The smartphone converts the voice into text and simultaneously analyzes the user's emotions. When this information is sent to the server, the server analyzes the intent of the question and generates an answer such as, "This wine pairs particularly well with red meat dishes and pasta." If the server analyzes that the user is confused, it generates a gentler response such as, "Please calm down. This wine pairs particularly well with red meat dishes and pasta," converts it into voice data, and sends it to the smartphone.

[1677] Example of a prompt

[1678] User question: "What does this wine pair well with?"

[1679] System response: "This wine pairs particularly well with red meat dishes and pasta. Is there anything else you'd like to order?"

[1680] This system allows users to receive appropriate answers in real time, even in physical stores, and to receive support tailored to their emotional state.

[1681] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1682] Step 1:

[1683] The user enters a question.

[1684] Input: The user enters the question by voice using the microphone on their mobile device, or by typing text using the keyboard.

[1685] Action: The user asks a voice question: "What does this wine pair well with?"

[1686] Output: Audio data or text data.

[1687] Step 2:

[1688] Convert audio data to text data

[1689] Input: Audio data

[1690] Operation: The device uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the audio data into text data.

[1691] Output: Converted text data (e.g., "What does this wine pair well with?").

[1692] Step 3:

[1693] Analysis of emotional states

[1694] Input: Converted text data

[1695] Operation: The device uses an emotion engine (e.g., Microsoft Azure Text Analytics) to analyze the user's emotional state. The analysis takes into account the user's tone of voice and text content.

[1696] Output: Sentiment analysis results (e.g., interesting, confused, etc.).

[1697] Step 4:

[1698] Send text data and sentiment analysis results to the server.

[1699] Input: Converted text data and sentiment analysis results

[1700] Operation: The device sends text data and sentiment analysis results to the server via the network.

[1701] Output: Data received on the server side.

[1702] Step 5:

[1703] Analyze the intent of the question

[1704] Input: Received text data

[1705] Operation: The server uses a natural language processing engine (e.g., NLTK or spaCy) to analyze text data and understand the intent of the question. For example, the question "What does this wine pair well with?" is interpreted as an attempt to find out which wines pair well with food.

[1706] Output: Analysis results that understand the intent of the question.

[1707] Step 6:

[1708] Generate an answer

[1709] Input: Analysis results that understand the intent of the question

[1710] Operation: The server generates the optimal answer using an AI model (e.g., GPT-4). For example, "This wine pairs particularly well with red meat dishes and pasta."

[1711] Output: Generated answer text.

[1712] Step 7:

[1713] Adjusting responses based on emotions

[1714] Input: Generated response text and sentiment analysis results

[1715] How it works: The server uses an emotion engine to adjust its responses based on the user's emotional state. For example, if the user is confused, it might prepare a gentle response such as, "Please calm down. This wine pairs especially well with red meat dishes and pasta."

[1716] Output: Adaptive response text that responds to emotions.

[1717] Step 8:

[1718] Convert the answer into audio data.

[1719] Input: Emotionally adaptive response text

[1720] Operation: The server uses a text-to-speech engine (e.g., Google Text-to-Speech API) to convert the response text into audio data.

[1721] Output: Converted audio data.

[1722] Step 9:

[1723] Send audio and text data to the device.

[1724] Input: Converted audio data and response text data

[1725] Operation: The server transmits voice and text data to the mobile device over the network.

[1726] Output: Data received on the terminal side.

[1727] Step 10:

[1728] Providing answers to users

[1729] Input: Audio and text data received by the device

[1730] Operation: The device plays audio data and displays text data on the screen. For example, it might play the response "This wine pairs particularly well with red meat dishes and pasta" as audio and simultaneously display it on the screen.

[1731] Output: Users can verify the answer visually and aurally.

[1732] The above outlines the specific processing steps of the system program that implements the application example. This allows users to receive appropriate answers in real time and support tailored to their emotional state.

[1733] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1734] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1735] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1736] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1737] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1738] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1739] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1740] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1741] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1742] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1743] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1744] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1745] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1746] 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.

[1747] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1748] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1749] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1750] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1751] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1752] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1753] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1754] The following is further disclosed regarding the embodiments described above.

[1755] (Claim 1)

[1756] A means by which the user enters a question using a mobile device,

[1757] A means by which a mobile information terminal acquires voice or text data,

[1758] A means by which a mobile device converts voice data into text,

[1759] A means by which a mobile device sends text data to a server,

[1760] The server uses a natural language processing engine to analyze text data and understand the intent of the question.

[1761] A server that uses an AI model to generate responses based on text data,

[1762] A means of converting the text response generated by the server into audio data,

[1763] A means for the server to transmit voice data and text data to a mobile information terminal,

[1764] A means for a mobile information terminal to play audio data and display text data,

[1765] A system that includes this.

[1766] (Claim 2)

[1767] The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating speech data.

[1768] (Claim 3)

[1769] The system according to claim 1, characterized in that a mobile information terminal acquires voice input from a user and converts the voice into text data using speech recognition technology.

[1770] "Example 1"

[1771] (Claim 1)

[1772] A means by which the user enters a question using a mobile device,

[1773] A means by which a mobile information terminal acquires voice or text data,

[1774] A means by which a mobile device converts voice data into text,

[1775] A means by which a mobile device sends text data to a server,

[1776] The server uses a natural language processing engine to analyze text data and understand the intent of the question.

[1777] A means for generating responses based on text data using a server-generated artificial intelligence model,

[1778] A means of converting the text response generated by the server into audio data,

[1779] A means for the server to transmit voice data and text data to a mobile information terminal,

[1780] A means for a mobile information terminal to play audio data and display text data,

[1781] A system that includes this.

[1782] (Claim 2)

[1783] The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating speech data.

[1784] (Claim 3)

[1785] The system according to claim 1, characterized in that a mobile information terminal acquires voice input from a user and converts the voice into text data using speech recognition technology.

[1786] That's all.

[1787] "Application Example 1"

[1788] (Claim 1)

[1789] A means by which the user enters a question using an information terminal,

[1790] A means by which an information terminal acquires voice or text data,

[1791] A means by which an information terminal converts voice data into text,

[1792] A means by which an information terminal sends text data to a server,

[1793] The server uses a natural language processing engine to analyze text data and understand the intent of the question.

[1794] A means by which a server generates answers based on text data using a generated AI model,

[1795] A means of converting the text response generated by the server into audio data,

[1796] A means for the server to transmit voice data and text data to an information terminal,

[1797] A means by which an information terminal plays audio data and displays text data,

[1798] A system that includes this.

[1799] (Claim 2)

[1800] The system according to claim 1, characterized in that the server appropriately processes information using prompt statements and generates a response.

[1801] (Claim 3)

[1802] The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating speech data.

[1803] "Example 2 of combining an emotion engine"

[1804] (Claim 1)

[1805] A means by which the user enters a question using a mobile device,

[1806] A means by which a mobile information terminal acquires voice or text data,

[1807] A means by which a mobile device converts voice data into text,

[1808] A means for a mobile device to perform emotion analysis,

[1809] A means by which a mobile information terminal transmits text data and sentiment analysis results to a server,

[1810] The server uses a natural language processing engine to analyze text data and understand the intent of the question.

[1811] A means by which a server generates answers based on text data using a generated AI model,

[1812] A means for adjusting the response generated by the server based on the sentiment analysis results,

[1813] A means of converting the text response generated by the server into audio data,

[1814] A means for the server to transmit voice data and text data to a mobile information terminal,

[1815] A means for a mobile information terminal to play audio data and display text data,

[1816] A system that includes this.

[1817] (Claim 2)

[1818] The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating speech data.

[1819] (Claim 3)

[1820] The system according to claim 1, characterized in that a mobile information terminal acquires voice input from a user and converts the voice into text data using speech recognition technology.

[1821] "Application example 2 when combining with an emotional engine"

[1822] (Claim 1)

[1823] A means by which the user enters a question using a mobile device,

[1824] A means by which a mobile information terminal acquires voice or text data,

[1825] A means by which a mobile device converts voice data into text,

[1826] A means by which a mobile device sends text data to a server,

[1827] The server uses a natural language processing engine to analyze text data and understand the intent of the question.

[1828] A means by which a server generates answers based on text data using a generated AI model,

[1829] A means by which a server uses an emotion engine to analyze the user's emotional state and generate an adaptive response corresponding to that emotion,

[1830] A means of converting the text response generated by the server into audio data,

[1831] A means for the server to transmit voice data and text data to a mobile information terminal,

[1832] A means for a mobile information terminal to play audio data and display text data,

[1833] A system that includes this.

[1834] (Claim 2)

[1835] The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating audio data, and the generated response is provided in text or audio that is appropriate to the emotional state.

[1836] (Claim 3)

[1837] The system according to claim 1, characterized in that a mobile information terminal acquires voice input from a user, converts the voice into text data using speech recognition technology, and performs sentiment analysis. [Explanation of Symbols]

[1838] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means by which the user enters a question using a mobile device, A means by which a mobile information terminal acquires voice or text data, A means by which a mobile device converts voice data into text, A means by which a mobile device sends text data to a server, The server uses a natural language processing engine to analyze text data and understand the intent of the question. A server that uses an AI model to generate responses based on text data, A means of converting the text response generated by the server into audio data, A means for the server to transmit voice data and text data to a mobile information terminal, A means for a mobile information terminal to play audio data and display text data, A system that includes this.

2. The system according to claim 1, characterized in that the server uses a speech synthesis engine when generating speech data.

3. The system according to claim 1, characterized in that a mobile information terminal acquires voice input from a user and converts the voice into text data using speech recognition technology.

Images