System

Abstract

A system is provided.SOLUTION: A system comprising: means for converting a speech of a user into text using a speech recognition engine; means for transmitting the converted text to a server; means for analyzing the text using natural language processing and identifying an intention of the user; means for acquiring current screen information and transmitting the screen information to the server; means for generating an action based on the screen information and an analysis result; and means for transmitting the generated action to the terminal and providing assistance content to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Elderly people and IT novices who are not good at using smartphones often find themselves unable to do what they want because they don't know what to do. Furthermore, they don't know how to respond to messages about app updates or authentication, which makes it even more difficult to use. Even if they ask how to operate a smartphone by means other than face-to-face communication, they are unable to effectively communicate the screen status and have difficulty understanding the intention of the person explaining. The objective of this invention is to resolve these difficulties. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. A system is constructed that includes means for converting a user's speech into text using a voice recognition engine, means for sending the converted text to a server, means for the server to analyze the text using natural language processing and identify the user's intention, means for the terminal to acquire current screen information and send it to the server, means for the server to generate an action based on the screen information and the analysis results, and means for the server to send the generated action to the terminal, which then provides assistance content to the user. This allows users to use smartphones and apps without hesitation.

[0006] "User speech" refers to the speech spoken by the smartphone user.

[0007] "Speech Recognition Engine" means a technical device or software that converts speech into text.

[0008] "Text" refers to character data converted by a speech recognition engine.

[0009] A "server" refers to a computer system that provides a particular service over a network.

[0010] "Natural language processing (NLP)" refers to the technology that enables computers to understand and analyze human language.

[0011] "User intent" refers to the operation the user wants to perform or the information they are looking for.

[0012] "Screen information" refers to the general content displayed on a smartphone, including currently open apps and displayed messages.

[0013] "Action" refers to the specific operations or responses that a user performs on a smartphone or app.

[0014] "Speech synthesis engine" means a technical device or software that converts text data into speech.

[0015] "Assistance content" refers to the guidance and instructions provided to help users operate their smartphones and apps correctly. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[0038] This system supports user operations by having the smartphone device, server, and user work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[0039] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[0040] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or application status. The server generates appropriate actions based on this screen information and the analysis results. Specifically, it generates voice guidance based on the contents of the message displayed on the screen.

[0041] The server sends the generated action to the device, and the device provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message, telling the user, for example, "The message you are seeing says that you should install the latest update."

[0042] As a concrete example, consider the following scenario.

[0043] Example 1: Reading a message

[0044] When a user says to their smartphone, "Read me the message I'm currently viewing."

[0045] The user says, "Read the message I'm currently viewing."

[0046] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0047] The device sends this text to the server.

[0048] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0049] The device acquires the current screen information and sends it to the server.

[0050] The server analyzes the screen information and generates the displayed message content as guidance.

[0051] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[0052] Example 2: Downloading an app

[0053] When a user speaks to their smartphone saying, "I want to download this app."

[0054] The user says, "I want to download this app."

[0055] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0056] The device sends this text to the server.

[0057] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0058] The device acquires the current screen information and sends it to the server.

[0059] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0060] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[0061] In this way, the system of the present invention provides appropriate operation guidance so that the user can use the smartphone without any confusion.

[0062] The processing flow will be explained below.

[0063] Program processing flow

[0064] Example 1: Reading a message

[0065] Step 1:

[0066] The user speaks into the smartphone.

[0067] The user says, "Read the message that is currently displayed."

[0068] Step 2:

[0069] The device converts speech into text using a speech recognition engine.

[0070] The device converts the speech into text that reads "Read the message currently being displayed."

[0071] Step 3:

[0072] The terminal transmits the text data to the server.

[0073] The terminal sends the converted text to a server over the Internet.

[0074] Step 4:

[0075] The server parses the received text.

[0076] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[0077] Step 5:

[0078] The device acquires the current screen information and sends it to the server.

[0079] The terminal acquires the currently displayed message information and sends it to the server.

[0080] Step 6:

[0081] The server generates appropriate actions based on the screen information and analysis results.

[0082] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[0083] Step 7:

[0084] The server sends the generated action to the terminal.

[0085] The server transmits the generated guidance content to the terminal.

[0086] Step 8:

[0087] The terminal plays back audio guidance and provides feedback to the user.

[0088] The device uses a speech synthesis engine to read the message content aloud.

[0089] Example 2: Downloading an app

[0090] Step 1:

[0091] The user speaks into the smartphone.

[0092] The user says, "I want to download this app."

[0093] Step 2:

[0094] The device converts speech into text using a speech recognition engine.

[0095] The device converts the speech into text: "I want to download this app."

[0096] Step 3:

[0097] The terminal transmits the text data to the server.

[0098] The terminal sends the converted text to a server over the Internet.

[0099] Step 4:

[0100] The server parses the received text.

[0101] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[0102] Step 5:

[0103] The device acquires the current screen information and sends it to the server.

[0104] The device retrieves current screen information and sends it to the server, for example, whether a specific app page is displayed.

[0105] Step 6:

[0106] The server generates appropriate actions based on the screen information and analysis results.

[0107] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[0108] Step 7:

[0109] The server sends the generated action to the terminal.

[0110] The server transmits the generated guidance content to the terminal.

[0111] Step 8:

[0112] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[0113] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[0114] This series of steps allows users to operate their smartphones and apps without any confusion.

[0115] Example 1

[0116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0117] In modern society, the use of smartphones is common, but they are often difficult to operate for the elderly and IT novices. Furthermore, the text-based instructions provided as operation guides place a heavy visual burden on users, making them particularly difficult to use for people with impaired eyesight. Furthermore, when complex operations are required, users can become confused and unable to understand the operations. Given this situation, there is a need to provide a means for users to easily understand and use smartphone operations appropriately.

[0118] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0119] In this invention, the server includes means for converting a user's speech into text using a speech recognition means, means for transmitting the converted text to a network device, means for the network device to analyze the text using natural language processing technology and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the network device, means for the network device to generate an action based on the screen information and the analysis result, and means for the network device to transmit the generated action to the terminal, and the terminal to provide assistance content to the user. This makes it possible to provide operation guidance quickly and accurately based on the user's speech.

[0120] A "user" is a person who operates an information system or device.

[0121] An "utterance" is a spoken instruction or request made orally by a user.

[0122] A "voice recognition means" is a technique or device that converts a voice signal into text data.

[0123] "Text" is character information converted by a speech recognition means.

[0124] A "network device" is a computer system that transmits, receives, and processes data.

[0125] "Natural language processing technology" is a computational technology for analyzing text data and understanding its meaning and intent.

[0126] "Screen information" is information about the current display content of the device and the state of the application.

[0127] An "action" is a specific operation or guidance that is executed in response to a user's input or request.

[0128] "Speech synthesis means" refers to a technology or device that converts text information into speech and outputs it.

[0129] "Assistance content" refers to information or instructions provided to assist the user in performing operations.

[0130] This invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people and IT novices who are not good at operating smartphones. This system supports user operations by working in cooperation with the smartphone terminal, server, and user.

[0131] This system uses the following hardware and software:

[0132] Speech recognition method: Uses speech recognition technology such as Google Speech-to-Text API.

[0133] Network device: A server for sending, receiving, and analyzing data.

[0134] Natural language processing technology: Uses AI models such as the BERT model.

[0135] Speech synthesis method: Use a speech synthesis engine such as Amazon Polly.

[0136] System Operation Overview

[0137] When a user speaks to a smartphone, the following series of processes take place:

[0138] First, the user speaks to the smartphone. For example, they say, "Read my message." The terminal uses a voice recognition means to convert this speech into text data. In this case, it is converted into the text "Read my message." Next, the terminal transmits the converted text data to the network device.

[0139] The server analyzes the received text data using natural language processing technology to identify the user's intent. This analysis identifies that the user wants to know the content of the displayed message. The terminal then acquires the current screen information and sends it to the network device. This screen information includes the currently displayed message and the application status.

[0140] The server generates an appropriate action based on the received screen information and analysis results. For example, it creates a voice prompt based on the displayed message. The generated action is then sent to the device, which then uses a voice synthesis means to read it aloud to the user. For example, it tells the user, "The displayed message says to install the latest update."

[0141] Specific examples

[0142] Example 1: Reading a message

[0143] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[0144] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0145] The device sends this text to the server.

[0146] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0147] The device acquires the current screen information and sends it to the server.

[0148] The server analyzes the screen information and generates the displayed message content as guidance.

[0149] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[0150] Example 2: Downloading an app

[0151] The user speaks to their smartphone saying, "I want to download this app."

[0152] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0153] The device sends this text to the server.

[0154] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0155] The device acquires the current screen information and sends it to the server.

[0156] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0157] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[0158] Prompt Sentence Examples

[0159] "Read the displayed message"

[0160] I want to download this app

[0161] "I want to connect to a new Wi-Fi network."

[0162] In this way, the system provides appropriate operational guidance to help users use their smartphones easily.

[0163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0164] Step 1:

[0165] The user speaks into the smartphone. For example, they say, "Read the message aloud." The user's speech is captured as voice data by the device's microphone.

[0166] Input: User's spoken utterance

[0167] Output: Audio data

[0168] Step 2:

[0169] The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the acquired voice data into text. In this process, the voice waveform is analyzed and the corresponding text data is generated. Specifically, the voice data is converted into the text "Read message aloud."

[0170] Input: Audio data

[0171] Output: Text data (e.g. "Read message aloud")

[0172] Step 3:

[0173] The terminal transmits the generated text data to a network device (server), and an operation of transmitting the text data is performed using an HTTP request.

[0174] Input: Text data (e.g. "Read message aloud")

[0175] Output: Sends text data to the server

[0176] Step 4:

[0177] The text data received by the server is analyzed using natural language processing technology (e.g., BERT model). This analysis allows the meaning of the text data to be understood and the user's intent to be identified. Specifically, the intent is analyzed as "I want to know the contents of the message."

[0178] Input: Text data (e.g. "Read message aloud")

[0179] Output: User intent (e.g. "I want to know the contents of this message")

[0180] Step 5:

[0181] The device retrieves current screen information, including displayed messages and application state. This information is collected from the smartphone's screen capture and active apps.

[0182] Input: None (internal sensor data)

[0183] Output: Screen information (e.g. "Install the latest updates" message)

[0184] Step 6:

[0185] The screen information acquired by the device is sent to the server, also using an HTTP request.

[0186] Input: Screen Information

[0187] Output: Sending screen information to the server

[0188] Step 7:

[0189] The server generates an appropriate action based on the screen information received and the analyzed user intent. Specifically, it generates voice guidance based on the displayed message. For example, it creates guidance such as "The displayed message asks you to install the latest update."

[0190] Input: Screen information, user intent

[0191] Output: Generated action (e.g., voice guidance)

[0192] Step 8:

[0193] The server sends the generated action details to the terminal, which are also sent as an HTTP response.

[0194] Input: The generated action (e.g., voice prompt)

[0195] Output: Sends the action to the terminal.

[0196] Step 9:

[0197] The device uses a speech synthesis engine (e.g., Amazon Polly) to convert the received guidance content into voice and read it aloud to the user. Specifically, the device tells the user, "The message you are seeing tells you to install the latest update."

[0198] Input: The generated action (e.g., voice prompt)

[0199] Output: Providing audio guidance to the user

[0200] (Application example 1)

[0201] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0202] For elderly people who are not good at using smartphones or those who are new to IT, it is not easy to respond quickly and accurately in an emergency. In particular, when people are in a panic, it becomes difficult to perform complex operations or make appropriate reports. For this reason, there is a need for a system that allows users to easily make emergency reports through speech and encourages appropriate responses.

[0203] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0204] In this invention, the server includes means for converting a user's speech into text using a voice recognition engine, means for transmitting the converted text to the server, means for the server to analyze the text using natural language processing and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the server, means for the server to generate an action based on the screen information and the analysis result, means for the server to transmit the generated action to the terminal and the terminal to provide assistance content to the user, and means for recognizing that the user's intention is to make an emergency call and transmitting an appropriate emergency signal to an external network. This allows the user to make an emergency call using only voice utterances and respond quickly and accurately.

[0205] "User utterance" refers to a voice instruction input via a smartphone or smart glasses.

[0206] A "speech recognition engine" is a software or hardware technology that converts voice data into text.

[0207] "Text" is character information converted from a user's speech using a voice recognition engine.

[0208] A "server" is a computer system for processing and analyzing data over a network.

[0209] "Natural language processing" is a field of computer science that is the technology for analyzing and understanding natural language.

[0210] "User intent" refers to what the user wants to operate or confirm through their smartphone or smart glasses.

[0211] "Current screen information" is information that indicates the content and status currently displayed on a smartphone or smart glasses.

[0212] An "action" is a specific operation or instruction that is generated on the server and executed by the terminal based on the user's intention.

[0213] "Emergency signal" means an electrical or electronic signal intended to notify external emergency services of an emergency.

[0214] "External network" refers to communication means outside the system, such as the Internet or emergency service networks.

[0215] "Location information" is geographical data that indicates the user's current location.

[0216] This invention is a system that allows elderly people who are not good at operating smartphones or people new to IT to easily make emergency calls by speaking. This system is composed of the following elements.

[0217] System Configuration

[0218] Hardware configuration:

[0219] User device: smartphone or smart glasses

[0220] Server: A computer system that processes data and returns analysis results to the user's terminal.

[0221] Software configuration:

[0222] Speech recognition engine: converts user speech into text

[0223] Natural language processing engine: Analyzes text and identifies user intent

[0224] Speech synthesis engine: provides text to the user as speech

[0225] Network communication: Communication technology for exchanging data between servers

[0226] Operation overview

[0227] 1. Speech Recognition:

[0228] The user speaks into their smartphone or smart glasses, saying things like "Call the police" or "Help me." This speech is converted into text by a speech recognition engine and sent to the server.

[0229] 2. Natural Language Processing:

[0230] The server analyzes the received text using a natural language processing engine to identify the user's intent. For example, if the spoken content is "Call the police," the server recognizes that this refers to an emergency call.

[0231] 3. Get screen information:

[0232] The user's device acquires the current screen information and sends it to the server, which allows the server to grasp the current situation, such as which application the user is using.

[0233] 4. Emergency signal generation and transmission:

[0234] The server generates an emergency signal based on the analysis results and the screen information. This signal includes the user's location information and is transmitted to an external network (e.g., an emergency service network).

[0235] 5. User Feedback:

[0236] The user device uses a speech synthesis engine to provide information to the user based on the action received from the server, such as a message such as "Emergency call completed."

[0237] Specific examples

[0238] Scenario 1: A suspicious person breaks into a home while the user is at home, and the user utters "Help me." The smartphone recognizes this utterance, the server analyzes it using natural language processing, and an emergency call is made. The user receives voice feedback saying, "The police have been called."

[0239] Scenario 2: A user encounters an accident while out and says, "Call the police." The smart glasses recognize this, the server analyzes it, and makes an emergency call. The user is notified by voice that "the emergency call has been completed."

[0240] Prompt Sentence Examples

[0241] Example prompt for a generative AI model:

[0242] I'd like to develop an emergency call application using voice recognition. This application will recognize user-uttered phrases such as "help" or "call the police" and automatically make the appropriate emergency call. How should I implement this?

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] A user speaks into a smartphone or smart glasses. The input is the user's voice, and the output is captured as audio data by a microphone.

[0246] Step 2:

[0247] The device uses a voice recognition engine to convert the captured voice data into text.

[0248] The input is the user's voice data, which is analyzed by the voice recognition engine and output as text data. Specifically, the voice recognition engine breaks down the voice into phonemes and phrases and converts them into a string of characters.

[0249] Step 3:

[0250] The terminal sends the converted text to the server.

[0251] The input is text data converted by a speech recognition engine, and the output is text data sent to a server via network communication.

[0252] Step 4:

[0253] The server analyzes the received text data using a natural language processing engine to identify the user's intent.

[0254] The input is text data sent from the device, and the natural language processing engine analyzes the text content to identify the user's intention (e.g., emergency call) and outputs it. Specifically, the natural language processing engine extracts important keywords from the text and classifies the user's intention based on them.

[0255] Step 5:

[0256] The user terminal acquires the current screen information and sends it to the server.

[0257] The input is the screen information of the user's device (e.g., open applications and displayed content), and the output is the data that sends that information to the server. Specifically, the device's screen capture function or data acquisition API is used to obtain the current screen information, which is then sent to the server as digital data.

[0258] Step 6:

[0259] The server generates appropriate actions based on the screen information and analysis results.

[0260] The input is the user's intention and the screen information, and the output is the corresponding action (e.g., generating an emergency call signal). Specifically, the server runs an algorithm that compares the user's intention with the screen information and determines the action based on that.

[0261] Step 7:

[0262] The server sends the generated action to the terminal.

[0263] The input is the action data generated by the server, and the output is the information that the data is sent to the terminal via network communication.

[0264] Step 8:

[0265] The terminal provides the user with assistance content based on the action received from the server.

[0266] The input is the action data sent from the server, and the output is feedback to the user (e.g., voice guidance). Specifically, a speech synthesis engine is used to convert text data into voice, and a message such as "Emergency call completed" is conveyed to the user.

[0267] Step 9:

[0268] The server recognizes the user's intent to call an emergency service and transmits the appropriate emergency signal to the external network.

[0269] The input is the user's intention to make an emergency call and their location information, and the output is the call information to the emergency service. Specifically, the server obtains the user's current location from GPS data and sends the emergency call message in an appropriate format to the external emergency service.

[0270] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0271] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[0272] This system supports user operations by having the smartphone device, server, and emotion engine that analyzes the user's emotions work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[0273] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[0274] Furthermore, the emotion engine analyzes the user's speech to recognize emotions. For example, if the user says "I don't know what to do" in an anxious voice, the emotion engine will recognize the emotion as anxiety or confusion.

[0275] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or the state of the application. The server generates the appropriate action based on this screen information and the analysis results.

[0276] The server further adjusts the content of the action depending on the user's emotion recognized by the emotion engine. For example, if the user is feeling anxious, the server generates more detailed guidance.

[0277] The server sends the generated action to the device, which then provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message and provide feedback based on the user's emotions. For example, the device tells the user, "The message you see is telling you to install the latest update. Don't worry, it's easy to do."

[0278] As a concrete example, consider the following scenario.

[0279] Example 1: Message reading and emotional response

[0280] When a user says to their smartphone, "Read me the message I'm currently viewing."

[0281] The user says, "Read the message I'm currently viewing."

[0282] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0283] The device sends this text to the server.

[0284] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0285] The emotion engine analyzes the user's speech and recognizes emotions, such as anxiety or confusion.

[0286] The device acquires the current screen information and sends it to the server.

[0287] The server analyzes the screen information and generates the displayed message content as guidance.

[0288] The server reflects the results of the emotion engine and provides feedback in a gentler tone.

[0289] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud: "The message you're seeing says, 'Please install the latest update.' Don't worry, everything's fine."

[0290] Example 2: App downloads and emotional responses

[0291] When a user speaks to their smartphone saying, "I want to download this app."

[0292] The user says, "I want to download this app."

[0293] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0294] The device sends this text to the server.

[0295] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0296] The emotion engine analyzes user utterances and recognizes emotions, such as anxiety or lack of confidence.

[0297] The device acquires the current screen information and sends it to the server.

[0298] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0299] The server reflects the results of the emotion engine and adds encouraging words and detailed explanations.

[0300] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud and, if necessary, displays an icon indicating a download button. "Press the download button at the bottom right of the screen. Don't worry, it's easy."

[0301] In this way, the system of the present invention provides appropriate operational guidance so that users can operate their smartphones and apps without hesitation while receiving support that is tailored to their emotions.

[0302] The processing flow will be explained below.

[0303] Example 1: Message reading and emotional response

[0304] Step 1:

[0305] The user speaks into the smartphone.

[0306] The user says, "Read the message that is currently displayed."

[0307] Step 2:

[0308] The device converts speech into text using a speech recognition engine.

[0309] The device converts the speech into text that reads "Read the message currently being displayed."

[0310] Step 3:

[0311] The terminal transmits the text data to the server.

[0312] The terminal sends the converted text to a server over the Internet.

[0313] Step 4:

[0314] The server parses the received text.

[0315] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[0316] Step 5:

[0317] The emotion engine analyzes the user's speech and recognizes emotions.

[0318] The emotion engine performs voice analysis and recognizes emotions such as anxiety or confusion from the tone and rate of the user's voice.

[0319] Step 6:

[0320] The device acquires the current screen information and sends it to the server.

[0321] The terminal acquires the currently displayed message information and sends it to the server.

[0322] Step 7:

[0323] The server generates appropriate actions based on the screen information and analysis results.

[0324] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[0325] Step 8:

[0326] The server adjusts the action content by reflecting the results of the emotion engine.

[0327] The server takes into account the user's feelings and adds encouragement or further guidance as needed.

[0328] Step 9:

[0329] The server sends the generated action to the terminal.

[0330] The server then sends the generated guidance to the device, such as "The message you're seeing tells you to install the latest update. Don't worry, it's fine."

[0331] Step 10:

[0332] The terminal plays back audio guidance and provides feedback to the user.

[0333] The device uses a speech synthesis engine to read aloud the message content and emotionally sensitive feedback.

[0334] Example 2: App downloads and emotional responses

[0335] Step 1:

[0336] The user speaks into the smartphone.

[0337] The user says, "I want to download this app."

[0338] Step 2:

[0339] The device converts speech into text using a speech recognition engine.

[0340] The device converts the speech into text: "I want to download this app."

[0341] Step 3:

[0342] The terminal transmits the text data to the server.

[0343] The terminal sends the converted text to a server over the Internet.

[0344] Step 4:

[0345] The server parses the received text.

[0346] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[0347] Step 5:

[0348] The emotion engine analyzes the user's speech and recognizes emotions.

[0349] The emotion engine performs voice analysis and recognizes emotions such as anxiety or lack of confidence from the user's tone and rate of voice.

[0350] Step 6:

[0351] The device acquires the current screen information and sends it to the server.

[0352] The device checks whether the download page for a specific app is displayed and sends the screen information to the server.

[0353] Step 7:

[0354] The server generates appropriate actions based on the screen information and analysis results.

[0355] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[0356] Step 8:

[0357] The server adjusts the action content by reflecting the results of the emotion engine.

[0358] The server adds encouraging words and detailed explanations based on the emotion engine.

[0359] Step 9:

[0360] The server sends the generated action to the terminal.

[0361] The server then sends the generated guidance to the device, such as "Please press the download button at the bottom right of the screen. It's easy, so don't worry."

[0362] Step 10:

[0363] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[0364] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[0365] This series of steps allows users to operate their smartphones and apps without hesitation while receiving emotional support.

[0366] Example 2

[0367] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] In recent years, with the spread of smartphones, operation has become more complex, and there are more and more situations where elderly people and IT novices find it difficult to use. In particular, when users do not know how to operate a device or when an error message is displayed, they often become confused and anxious. To solve this problem, a system is needed that can accurately understand the user's intention from their speech and provide appropriate operation guidance that takes their emotions into consideration.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0370] In this invention, the server includes means for converting a user's speech into text using a speech recognition engine, means for analyzing the text using natural language processing to identify the user's intention, and means for recognizing the emotion of the user's speech using an emotion engine. This makes it possible to accurately grasp the user's intention and emotion from the user's speech and provide emotion-conscious operation guidance in real time.

[0371] A "speech recognition engine" is software or a system that converts a user's speech into text data in real time.

[0372] A "server" is a computer system that receives, analyzes, and processes data via a network.

[0373] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0374] An "emotion engine" is a system that recognizes and analyzes emotions from the content of a user's speech and vocal expressions.

[0375] "Text data" is character string data that represents the content of a user's speech, converted by a voice recognition engine.

[0376] "Screen information" is data that indicates the content displayed on the terminal and the current state of the application.

[0377] An "action" refers to a specific operation or instruction generated by the server based on the user's intentions and emotions.

[0378] A "speech synthesis engine" is a system that converts text data into speech and allows the user to listen.

[0379] "Assistance content" refers to operational guidance and information provided to the user as a result of an action generated by the server.

[0380] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for implementing the present invention are described below.

[0381] This system supports user operations by having the smartphone device, server, and emotion engine work together. Specifically, when the user speaks to the smartphone, the device converts the speech into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0382] For example, if the user says "Read my message," the device converts this utterance into text "Read my message." The device then transmits the converted text data to the server.

[0383] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to determine the user's intent. In this example, the server interprets the user as wanting to know the content of the displayed message.

[0384] Additionally, an emotion engine (e.g., Microsoft Azure Text Analytics) runs on the server and recognizes emotions from the user's spoken text. For example, if a user says "I don't know what to do" in an anxious voice, the emotion engine will recognize anxiety and confusion.

[0385] Next, the device acquires the current screen information (displayed messages and application status) and sends it to the server. The server generates appropriate actions based on this screen information and analysis results. The server further adjusts the content of the action according to the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, the server will generate more detailed guidance.

[0386] Finally, the server sends the generated action to the device, and the device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the action details to the user as voice. For example, the device might say something like, "The message displayed tells you to install the latest update. Don't worry, it's easy to do."

[0387] Specific examples

[0388] Consider the following scenario:

[0389] Example 1: Message reading and emotional response

[0390] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[0391] The device converts speech into text using Google Cloud Speech-to-Text.

[0392] The device sends this text to the server.

[0393] The server uses Google Cloud Natural Language to analyze the text and interpret the user's intent as "I want to know the contents of the message."

[0394] The sentiment engine uses Microsoft Azure Text Analytics to recognise emotions and detect anxiety or confusion.

[0395] The device acquires the current screen information and sends it to the server.

[0396] The server analyzes the screen information, determines that the message content is "Please install the latest update," and generates this as guidance.

[0397] The server adds feedback such as "Don't worry, it's easy to use" based on the results of the emotion engine.

[0398] The server sends the guidance back to the device, which then uses Google Cloud Text-to-Speech to read it aloud: "The message you see is telling you to install the latest update. Don't worry, it's easy."

[0399] Prompt Sentence Examples

[0400] "When a user speaks to their smartphone, the system uses a speech recognition engine to convert the speech into text, which is then sent to a server for analysis. Based on the results of analyzing the text and emotions, appropriate operational guidance is generated and read aloud using a speech synthesis engine. For example, if a user says, 'Read the message currently being displayed,' the system will read the message aloud and add words of reassurance."

[0401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0402] Step 1:

[0403] The user speaks.

[0404] The user speaks to the smartphone to instruct specific operations or ask questions. For example, they say, "Read aloud a message." The input is the user's voice, and the output is voice data.

[0405] Step 2:

[0406] The device converts the voice data into text.

[0407] The device uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the user's speech into text data in real time. The input is voice data, and the output is text data saying "Read message aloud."

[0408] Step 3:

[0409] The terminal transmits the text data to the server.

[0410] The terminal sends the converted text data to the server. The input is the text data, and the output is a network transmission containing it.

[0411] Step 4:

[0412] The server analyzes the text data and identifies the user's intent.

[0413] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to identify the user's intent. The input is the text data, and the output is the analyzed intent. In this example, the user's intent is to have the displayed message read aloud.

[0414] Step 5:

[0415] The emotion engine recognizes the user's emotions.

[0416] An emotion engine on the server (e.g., Microsoft Azure Text Analytics) analyzes the user's spoken text and recognizes emotions. The input is the spoken text, and the output is the recognized emotion (e.g., anxiety, confusion).

[0417] Step 6:

[0418] The device sends the screen information to the server.

[0419] This function obtains the screen information currently displayed on the device (e.g., message content, application status) and sends it to the server. The input is the screen information of the device, and the output is a network transmission containing it.

[0420] Step 7:

[0421] The server analyzes the screen information and generates appropriate actions.

[0422] The server analyzes the screen information sent and generates the action the user wants. The input is the screen information and the analyzed intent, and the output is the generated action (e.g., preparing to read the message content).

[0423] Step 8:

[0424] The server adjusts the action content based on the emotion.

[0425] The server reflects the results of the emotion engine and corrects and complements the action content. The input is the generated action and emotion recognition result, and the output is the adjusted action content. For example, if the user is feeling anxious, a detailed explanation is added.

[0426] Step 9:

[0427] The server sends the final guidance to the terminal.

[0428] The server sends the final guidance content back to the terminal. The input is the adjusted action content, and the output is a network transmission containing the guidance content.

[0429] Step 10:

[0430] The terminal provides guidance to the user.

[0431] The device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the guidance sent from the server to the user as audio. The input is the guidance content, and the output is audio output (e.g., "The message displayed tells you to install the latest update. Don't worry, it's easy to do.").

[0432] (Application example 2)

[0433] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0434] Conventional smartphone operation support systems recognize users' speech and provide operational guidance, but the operation methods and on-screen information are often difficult to intuitively understand, especially for elderly people and IT novices. Furthermore, providing information one-way without considering the user's emotions or psychological state can leave users feeling confused and anxious. This leads to a poor user experience and a tendency for users to avoid using the system.

[0435] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for converting a user's utterance into text using a voice recognition engine; means for transmitting the converted text to the data processing device; means for the data processing device to analyze the text using natural language processing and identify the user's intention; means for the terminal to acquire current display information and transmit it to the data processing device; means for the data processing device to generate an action based on the display information and the analysis result; means for the data processing device to transmit the generated action to the terminal and provide assistance content to the user; emotion analysis means for the terminal to analyze the user's emotion; and means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means. This makes it possible to provide appropriate and gentle guidance while taking into account the user's intention as well as their psychological state.

[0436] "Means for converting user speech into text using a speech recognition engine" is a function that converts the speech information spoken by the user into character data using speech recognition technology.

[0437] The "means for transmitting the converted text to a data processing device" is a function for transferring character data generated by speech recognition to a device that processes data via a network.

[0438] "Means for the data processing device to analyze text using natural language processing and identify the user's intent" is a function that uses natural language processing technology to analyze received text data and identify the user's requests and wishes.

[0439] The "means for the terminal to acquire the currently displayed information and transmit it to the data processing device" is a function that captures the content displayed on the screen of the terminal and transmits it to the data processing device.

[0440] The "means for the data processing device to generate an action based on the display information and the analysis result" is a function that generates an appropriate response or operation guidance based on the display content and the result of analyzing the user's intention.

[0441] "Means for transmitting the action generated by the data processing device to the terminal, and the terminal providing assistance content to the user" is a function for transferring the generated instruction content back to the terminal, and the terminal providing that content to the user as guidance.

[0442] "Emotion analysis means for the terminal to analyze the user's emotions" is a function that recognizes and analyzes emotions from the user's speech and attitude.

[0443] "Means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means" is a function that reflects the results of the emotion analysis and adjusts the action to appropriate content according to the user's psychological state.

[0444] The system embodying the present invention analyzes the user's voice input and provides the necessary guidance, a process carried out by the cooperation of multiple hardware and software components.

[0445] The system mainly consists of a smartphone (hereinafter referred to as the terminal), a data processing device (hereinafter referred to as the server), an emotion analysis means, a speech synthesis engine, a natural language processing engine, and a speech recognition engine.

[0446] It starts when a user speaks to a terminal in a store to ask a question about a product or service. A specific example is when a user asks, "Where is the cosmetics counter?"

[0447] First, the device converts the user's speech into text using a speech recognition engine, using the speech_recognition library, and then sends the converted text to the server.

[0448] The server analyzes the received text using a natural language processing engine to determine the user's intent. A natural language processing model for a specific purpose is used for natural language processing. Based on the analysis results, it is determined that the information the user is looking for is "the location of the cosmetics counter."

[0449] In parallel, the device uses an emotion analysis tool to analyze the user's emotions during speech. The emotion_recognition library is used for emotion analysis, and emotions such as anxiety and confusion are identified. The device also transmits this emotion information to the server.

[0450] Next, the server generates an appropriate action based on the displayed information, the results of intent analysis, and the results of emotion analysis, in response to the user's question. This action can be structured as, for example, "The cosmetics counter is on the third floor."

[0451] If the user's emotions indicate anxiety or confusion, the server generates additional reassuring feedback, such as an encouraging message like, "It's on the third floor, so take your time and look around."

[0452] The generated actions are sent back to the device, which uses a speech synthesis engine to provide voice guidance to the user. This voice guidance is generated in real time using the GTTS library.

[0453] Specific examples

[0454] If a user asks, "Where is the cosmetics counter?":

[0455] The device uses a voice recognition engine to convert the question into text.

[0456] The text is sent to a server and analyzed by a natural language processing engine.

[0457] The server identifies the user's intent and determines that the question is about the location of the cosmetics section.

[0458] At the same time, the terminal analyzes the user's emotions using an emotion analysis means and determines that the user is feeling anxious.

[0459] The server generates an action saying, "The cosmetics department is on the third floor," and adds the feedback, "Don't worry, take your time and look around."

[0460] The generated information is sent to the terminal, and a voice synthesis engine provides voice guidance to the user.

[0461] Prompt Sentence Examples

[0462] "User Question: Is this product cheap?"

[0463] "Answer: This product is currently on sale at a special price. Please purchase with confidence."

[0464] "Emotion: Security. Use the word 'special' correctly to emphasize the low price."

[0465] In this way, the system provides appropriate guidance that takes into account the psychological state of the user.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] The user speaks to the smartphone (device). For example, they ask, "Where is the cosmetics counter?" At this point, the user's voice becomes input to the system.

[0469] Step 2:

[0470] The device uses a speech recognition engine (speech_recognition library) to convert the user's speech into text. The input is the user's voice, and the output is the converted text data. The converted text will be "Where is the cosmetics counter?"

[0471] Step 3:

[0472] The terminal sends the converted text to the server. The input here is the converted text data, and the output is the data sent to the server. Specifically, the text data is sent to the server via an HTTP request using a library such as requests.

[0473] Step 4:

[0474] The server receives the text data and analyzes it using a natural language processing engine (a natural language processing model for limited purposes). The input is the received text data, and the output is the analysis result. The server determines that the user is asking about the location of the cosmetics counter and identifies the user's intent.

[0475] Step 5:

[0476] The device uses an emotion analysis means (emotion_recognition library) to analyze the user's emotions. The input is the user's speech data, and the output is the recognized emotion data. The emotion analysis means identifies the emotion "anxiety."

[0477] Step 6:

[0478] The device sends the emotion analysis results to the server. The input here is the recognized emotion data, and the output is the data sent to the server. Specifically, it is sent to the server as an HTTP request, just like text data.

[0479] Step 7:

[0480] The server generates appropriate actions based on the display information, analysis results, and emotion analysis results. The input is the display information, the user's intention, and emotion data, and the output is the generated action data. The server adds a psychological sense of security to the basic action of "The cosmetics counter is on the third floor," by adding "Take your time and look around."

[0481] Step 8:

[0482] The server sends the generated action to the terminal, where the input is the generated action data and the output is the data sent to the terminal.

[0483] Step 9:

[0484] The device uses a speech synthesis engine (GTTS library) to convert the instructions sent from the server into voice and provides the user with assistance. The input is the action data sent from the server, and the output is audible audio that the user can hear. Specifically, the speech synthesis engine converts the text into an audio file and plays it back from the speaker. The guidance provided is, "The cosmetics department is on the third floor. Don't worry, take your time and look around."

[0485] In this way, the system, in which each step works in conjunction with the other, starts with the user's voice input and provides appropriate guidance by voice.

[0486] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0488] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0489] [Second embodiment]

[0490] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0491] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0492] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0493] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0494] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0495] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0496] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0497] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0498] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0499] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0500] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0501] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0502] The present invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[0503] This system supports user operations by having the smartphone device, server, and user work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[0504] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[0505] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or application status. The server generates appropriate actions based on this screen information and the analysis results. Specifically, it generates voice guidance based on the contents of the message displayed on the screen.

[0506] The server sends the generated action to the device, and the device provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message, telling the user, for example, "The message you are seeing says that you should install the latest update."

[0507] As a concrete example, consider the following scenario.

[0508] Example 1: Reading a message

[0509] When a user says to their smartphone, "Read me the message I'm currently viewing."

[0510] The user says, "Read the message I'm currently viewing."

[0511] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0512] The device sends this text to the server.

[0513] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0514] The device acquires the current screen information and sends it to the server.

[0515] The server analyzes the screen information and generates the displayed message content as guidance.

[0516] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[0517] Example 2: Downloading an app

[0518] When a user speaks to their smartphone saying, "I want to download this app."

[0519] The user says, "I want to download this app."

[0520] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0521] The device sends this text to the server.

[0522] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0523] The device acquires the current screen information and sends it to the server.

[0524] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0525] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[0526] In this way, the system of the present invention provides appropriate operation guidance so that the user can use the smartphone without any confusion.

[0527] The processing flow will be explained below.

[0528] Program processing flow

[0529] Example 1: Reading a message

[0530] Step 1:

[0531] The user speaks into the smartphone.

[0532] The user says, "Read the message that is currently displayed."

[0533] Step 2:

[0534] The device converts speech into text using a speech recognition engine.

[0535] The device converts the speech into text that reads "Read the message currently being displayed."

[0536] Step 3:

[0537] The terminal transmits the text data to the server.

[0538] The terminal sends the converted text to a server over the Internet.

[0539] Step 4:

[0540] The server parses the received text.

[0541] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[0542] Step 5:

[0543] The device acquires the current screen information and sends it to the server.

[0544] The terminal acquires the currently displayed message information and sends it to the server.

[0545] Step 6:

[0546] The server generates appropriate actions based on the screen information and analysis results.

[0547] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[0548] Step 7:

[0549] The server sends the generated action to the terminal.

[0550] The server transmits the generated guidance content to the terminal.

[0551] Step 8:

[0552] The terminal plays back audio guidance and provides feedback to the user.

[0553] The device uses a speech synthesis engine to read the message content aloud.

[0554] Example 2: Downloading an app

[0555] Step 1:

[0556] The user speaks into the smartphone.

[0557] The user says, "I want to download this app."

[0558] Step 2:

[0559] The device converts speech into text using a speech recognition engine.

[0560] The device converts the speech into text: "I want to download this app."

[0561] Step 3:

[0562] The terminal transmits the text data to the server.

[0563] The terminal sends the converted text to a server over the Internet.

[0564] Step 4:

[0565] The server parses the received text.

[0566] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[0567] Step 5:

[0568] The device acquires the current screen information and sends it to the server.

[0569] The device retrieves current screen information and sends it to the server, for example, whether a specific app page is displayed.

[0570] Step 6:

[0571] The server generates appropriate actions based on the screen information and analysis results.

[0572] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[0573] Step 7:

[0574] The server sends the generated action to the terminal.

[0575] The server transmits the generated guidance content to the terminal.

[0576] Step 8:

[0577] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[0578] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[0579] This series of steps allows users to operate their smartphones and apps without any confusion.

[0580] Example 1

[0581] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0582] In modern society, the use of smartphones is common, but they are often difficult to operate for the elderly and IT novices. Furthermore, the text-based instructions provided as operation guides place a heavy visual burden on users, making them particularly difficult to use for people with impaired eyesight. Furthermore, when complex operations are required, users can become confused and unable to understand the operations. Given this situation, there is a need to provide a means for users to easily understand and use smartphone operations appropriately.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0584] In this invention, the server includes means for converting a user's speech into text using a speech recognition means, means for transmitting the converted text to a network device, means for the network device to analyze the text using natural language processing technology and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the network device, means for the network device to generate an action based on the screen information and the analysis result, and means for the network device to transmit the generated action to the terminal, and the terminal to provide assistance content to the user. This makes it possible to provide operation guidance quickly and accurately based on the user's speech.

[0585] A "user" is a person who operates an information system or device.

[0586] An "utterance" is a spoken instruction or request made orally by a user.

[0587] A "voice recognition means" is a technique or device that converts a voice signal into text data.

[0588] "Text" is character information converted by a speech recognition means.

[0589] A "network device" is a computer system that transmits, receives, and processes data.

[0590] "Natural language processing technology" is a computational technology for analyzing text data and understanding its meaning and intent.

[0591] "Screen information" is information about the current display content of the device and the state of the application.

[0592] An "action" is a specific operation or guidance that is executed in response to a user's input or request.

[0593] "Speech synthesis means" refers to a technology or device that converts text information into speech and outputs it.

[0594] "Assistance content" refers to information or instructions provided to assist the user in performing operations.

[0595] This invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people and IT novices who are not good at operating smartphones. This system supports user operations by working in cooperation with the smartphone terminal, server, and user.

[0596] This system uses the following hardware and software:

[0597] Speech recognition method: Uses speech recognition technology such as Google Speech-to-Text API.

[0598] Network device: A server for sending, receiving, and analyzing data.

[0599] Natural language processing technology: Uses AI models such as the BERT model.

[0600] Speech synthesis method: Use a speech synthesis engine such as Amazon Polly.

[0601] System Operation Overview

[0602] When a user speaks to a smartphone, the following series of processes take place:

[0603] First, the user speaks to the smartphone. For example, they say, "Read my message." The terminal uses a voice recognition means to convert this speech into text data. In this case, it is converted into the text "Read my message." Next, the terminal transmits the converted text data to the network device.

[0604] The server analyzes the received text data using natural language processing technology to identify the user's intent. This analysis identifies that the user wants to know the content of the displayed message. The terminal then acquires the current screen information and sends it to the network device. This screen information includes the currently displayed message and the application status.

[0605] The server generates an appropriate action based on the received screen information and analysis results. For example, it creates a voice prompt based on the displayed message. The generated action is then sent to the device, which then uses a voice synthesis means to read it aloud to the user. For example, it tells the user, "The displayed message says to install the latest update."

[0606] Specific examples

[0607] Example 1: Reading a message

[0608] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[0609] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0610] The device sends this text to the server.

[0611] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0612] The device acquires the current screen information and sends it to the server.

[0613] The server analyzes the screen information and generates the displayed message content as guidance.

[0614] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[0615] Example 2: Downloading an app

[0616] The user speaks to their smartphone saying, "I want to download this app."

[0617] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0618] The device sends this text to the server.

[0619] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0620] The device acquires the current screen information and sends it to the server.

[0621] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0622] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[0623] Prompt Sentence Examples

[0624] "Read the displayed message"

[0625] I want to download this app

[0626] "I want to connect to a new Wi-Fi network."

[0627] In this way, the system provides appropriate operational guidance to help users use their smartphones easily.

[0628] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0629] Step 1:

[0630] The user speaks into the smartphone. For example, they say, "Read the message aloud." The user's speech is captured as voice data by the device's microphone.

[0631] Input: User's spoken utterance

[0632] Output: Audio data

[0633] Step 2:

[0634] The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the acquired voice data into text. In this process, the voice waveform is analyzed and the corresponding text data is generated. Specifically, the voice data is converted into the text "Read message aloud."

[0635] Input: Audio data

[0636] Output: Text data (e.g. "Read message aloud")

[0637] Step 3:

[0638] The terminal transmits the generated text data to a network device (server), and an operation of transmitting the text data is performed using an HTTP request.

[0639] Input: Text data (e.g. "Read message aloud")

[0640] Output: Sends text data to the server

[0641] Step 4:

[0642] The text data received by the server is analyzed using natural language processing technology (e.g., BERT model). This analysis allows the meaning of the text data to be understood and the user's intent to be identified. Specifically, the intent is analyzed as "I want to know the contents of the message."

[0643] Input: Text data (e.g. "Read message aloud")

[0644] Output: User intent (e.g. "I want to know the contents of this message")

[0645] Step 5:

[0646] The device retrieves current screen information, including displayed messages and application state. This information is collected from the smartphone's screen capture and active apps.

[0647] Input: None (internal sensor data)

[0648] Output: Screen information (e.g. "Install the latest updates" message)

[0649] Step 6:

[0650] The screen information acquired by the device is sent to the server, also using an HTTP request.

[0651] Input: Screen Information

[0652] Output: Sending screen information to the server

[0653] Step 7:

[0654] The server generates an appropriate action based on the screen information received and the analyzed user intent. Specifically, it generates voice guidance based on the displayed message. For example, it creates guidance such as "The displayed message asks you to install the latest update."

[0655] Input: Screen information, user intent

[0656] Output: Generated action (e.g., voice guidance)

[0657] Step 8:

[0658] The server sends the generated action details to the terminal, which are also sent as an HTTP response.

[0659] Input: The generated action (e.g., voice prompt)

[0660] Output: Sends the action to the terminal.

[0661] Step 9:

[0662] The device uses a speech synthesis engine (e.g., Amazon Polly) to convert the received guidance content into voice and read it aloud to the user. Specifically, the device tells the user, "The message you are seeing tells you to install the latest update."

[0663] Input: The generated action (e.g., voice prompt)

[0664] Output: Providing audio guidance to the user

[0665] (Application example 1)

[0666] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0667] For elderly people who are not good at using smartphones or those who are new to IT, it is not easy to respond quickly and accurately in an emergency. In particular, when people are in a panic, it becomes difficult to perform complex operations or make appropriate reports. For this reason, there is a need for a system that allows users to easily make emergency reports through speech and encourages appropriate responses.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0669] In this invention, the server includes means for converting a user's speech into text using a voice recognition engine, means for transmitting the converted text to the server, means for the server to analyze the text using natural language processing and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the server, means for the server to generate an action based on the screen information and the analysis result, means for the server to transmit the generated action to the terminal and the terminal to provide assistance content to the user, and means for recognizing that the user's intention is to make an emergency call and transmitting an appropriate emergency signal to an external network. This allows the user to make an emergency call using only voice utterances and respond quickly and accurately.

[0670] "User utterance" refers to a voice instruction input via a smartphone or smart glasses.

[0671] A "speech recognition engine" is a software or hardware technology that converts voice data into text.

[0672] "Text" is character information converted from a user's speech using a voice recognition engine.

[0673] A "server" is a computer system for processing and analyzing data over a network.

[0674] "Natural language processing" is a field of computer science that is the technology for analyzing and understanding natural language.

[0675] "User intent" refers to what the user wants to operate or confirm through their smartphone or smart glasses.

[0676] "Current screen information" is information that indicates the content and status currently displayed on a smartphone or smart glasses.

[0677] An "action" is a specific operation or instruction that is generated on the server and executed by the terminal based on the user's intention.

[0678] "Emergency signal" means an electrical or electronic signal intended to notify external emergency services of an emergency.

[0679] "External network" refers to communication means outside the system, such as the Internet or emergency service networks.

[0680] "Location information" is geographical data that indicates the user's current location.

[0681] This invention is a system that allows elderly people who are not good at operating smartphones or people new to IT to easily make emergency calls by speaking. This system is composed of the following elements.

[0682] System Configuration

[0683] Hardware configuration:

[0684] User device: smartphone or smart glasses

[0685] Server: A computer system that processes data and returns analysis results to the user's terminal.

[0686] Software configuration:

[0687] Speech recognition engine: converts user speech into text

[0688] Natural language processing engine: Analyzes text and identifies user intent

[0689] Speech synthesis engine: provides text to the user as speech

[0690] Network communication: Communication technology for exchanging data between servers

[0691] Operation overview

[0692] 1. Speech Recognition:

[0693] The user speaks into their smartphone or smart glasses, saying things like "Call the police" or "Help me." This speech is converted into text by a speech recognition engine and sent to the server.

[0694] 2. Natural Language Processing:

[0695] The server analyzes the received text using a natural language processing engine to identify the user's intent. For example, if the spoken content is "Call the police," the server recognizes that this refers to an emergency call.

[0696] 3. Get screen information:

[0697] The user's device acquires the current screen information and sends it to the server, which allows the server to grasp the current situation, such as which application the user is using.

[0698] 4. Emergency signal generation and transmission:

[0699] The server generates an emergency signal based on the analysis results and the screen information. This signal includes the user's location information and is transmitted to an external network (e.g., an emergency service network).

[0700] 5. User Feedback:

[0701] The user device uses a speech synthesis engine to provide information to the user based on the action received from the server, such as a message such as "Emergency call completed."

[0702] Specific examples

[0703] Scenario 1: A suspicious person breaks into a home while the user is at home, and the user utters "Help me." The smartphone recognizes this utterance, the server analyzes it using natural language processing, and an emergency call is made. The user receives voice feedback saying, "The police have been called."

[0704] Scenario 2: A user encounters an accident while out and says, "Call the police." The smart glasses recognize this, the server analyzes it, and makes an emergency call. The user is notified by voice that "the emergency call has been completed."

[0705] Prompt Sentence Examples

[0706] Example prompt for a generative AI model:

[0707] I'd like to develop an emergency call application using voice recognition. This application will recognize user-uttered phrases such as "help" or "call the police" and automatically make the appropriate emergency call. How should I implement this?

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] A user speaks into a smartphone or smart glasses. The input is the user's voice, and the output is captured as audio data by a microphone.

[0711] Step 2:

[0712] The device uses a voice recognition engine to convert the captured voice data into text.

[0713] The input is the user's voice data, which is analyzed by the voice recognition engine and output as text data. Specifically, the voice recognition engine breaks down the voice into phonemes and phrases and converts them into a string of characters.

[0714] Step 3:

[0715] The terminal sends the converted text to the server.

[0716] The input is text data converted by a speech recognition engine, and the output is text data sent to a server via network communication.

[0717] Step 4:

[0718] The server analyzes the received text data using a natural language processing engine to identify the user's intent.

[0719] The input is text data sent from the device, and the natural language processing engine analyzes the text content to identify the user's intention (e.g., emergency call) and outputs it. Specifically, the natural language processing engine extracts important keywords from the text and classifies the user's intention based on them.

[0720] Step 5:

[0721] The user terminal acquires the current screen information and sends it to the server.

[0722] The input is the screen information of the user's device (e.g., open applications and displayed content), and the output is the data that sends that information to the server. Specifically, the device's screen capture function or data acquisition API is used to obtain the current screen information, which is then sent to the server as digital data.

[0723] Step 6:

[0724] The server generates appropriate actions based on the screen information and analysis results.

[0725] The input is the user's intention and the screen information, and the output is the corresponding action (e.g., generating an emergency call signal). Specifically, the server runs an algorithm that compares the user's intention with the screen information and determines the action based on that.

[0726] Step 7:

[0727] The server sends the generated action to the terminal.

[0728] The input is the action data generated by the server, and the output is the information that the data is sent to the terminal via network communication.

[0729] Step 8:

[0730] The terminal provides the user with assistance content based on the action received from the server.

[0731] The input is the action data sent from the server, and the output is feedback to the user (e.g., voice guidance). Specifically, a speech synthesis engine is used to convert text data into voice, and a message such as "Emergency call completed" is conveyed to the user.

[0732] Step 9:

[0733] The server recognizes the user's intent to call an emergency service and transmits the appropriate emergency signal to the external network.

[0734] The input is the user's intention to make an emergency call and their location information, and the output is the call information to the emergency service. Specifically, the server obtains the user's current location from GPS data and sends the emergency call message in an appropriate format to the external emergency service.

[0735] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0736] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[0737] This system supports user operations by having the smartphone device, server, and emotion engine that analyzes the user's emotions work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[0738] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[0739] Furthermore, the emotion engine analyzes the user's speech to recognize emotions. For example, if the user says "I don't know what to do" in an anxious voice, the emotion engine will recognize the emotion as anxiety or confusion.

[0740] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or the state of the application. The server generates the appropriate action based on this screen information and the analysis results.

[0741] The server further adjusts the content of the action depending on the user's emotion recognized by the emotion engine. For example, if the user is feeling anxious, the server generates more detailed guidance.

[0742] The server sends the generated action to the device, which then provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message and provide feedback based on the user's emotions. For example, the device tells the user, "The message you see is telling you to install the latest update. Don't worry, it's easy to do."

[0743] As a concrete example, consider the following scenario.

[0744] Example 1: Message reading and emotional response

[0745] When a user says to their smartphone, "Read me the message I'm currently viewing."

[0746] The user says, "Read the message I'm currently viewing."

[0747] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0748] The device sends this text to the server.

[0749] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0750] The emotion engine analyzes the user's speech and recognizes emotions, such as anxiety or confusion.

[0751] The device acquires the current screen information and sends it to the server.

[0752] The server analyzes the screen information and generates the displayed message content as guidance.

[0753] The server reflects the results of the emotion engine and provides feedback in a gentler tone.

[0754] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud: "The message you're seeing says, 'Please install the latest update.' Don't worry, everything's fine."

[0755] Example 2: App downloads and emotional responses

[0756] When a user speaks to their smartphone saying, "I want to download this app."

[0757] The user says, "I want to download this app."

[0758] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0759] The device sends this text to the server.

[0760] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0761] The emotion engine analyzes user utterances and recognizes emotions, such as anxiety or lack of confidence.

[0762] The device acquires the current screen information and sends it to the server.

[0763] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0764] The server reflects the results of the emotion engine and adds encouraging words and detailed explanations.

[0765] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud and, if necessary, displays an icon indicating a download button. "Press the download button at the bottom right of the screen. Don't worry, it's easy."

[0766] In this way, the system of the present invention provides appropriate operational guidance so that users can operate their smartphones and apps without hesitation while receiving support that is tailored to their emotions.

[0767] The processing flow will be explained below.

[0768] Example 1: Message reading and emotional response

[0769] Step 1:

[0770] The user speaks into the smartphone.

[0771] The user says, "Read the message that is currently displayed."

[0772] Step 2:

[0773] The device converts speech into text using a speech recognition engine.

[0774] The device converts the speech into text that reads "Read the message currently being displayed."

[0775] Step 3:

[0776] The terminal transmits the text data to the server.

[0777] The terminal sends the converted text to a server over the Internet.

[0778] Step 4:

[0779] The server parses the received text.

[0780] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[0781] Step 5:

[0782] The emotion engine analyzes the user's speech and recognizes emotions.

[0783] The emotion engine performs voice analysis and recognizes emotions such as anxiety or confusion from the tone and rate of the user's voice.

[0784] Step 6:

[0785] The device acquires the current screen information and sends it to the server.

[0786] The terminal acquires the currently displayed message information and sends it to the server.

[0787] Step 7:

[0788] The server generates appropriate actions based on the screen information and analysis results.

[0789] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[0790] Step 8:

[0791] The server adjusts the action content by reflecting the results of the emotion engine.

[0792] The server takes into account the user's feelings and adds encouragement or further guidance as needed.

[0793] Step 9:

[0794] The server sends the generated action to the terminal.

[0795] The server then sends the generated guidance to the device, such as "The message you're seeing tells you to install the latest update. Don't worry, it's fine."

[0796] Step 10:

[0797] The terminal plays back audio guidance and provides feedback to the user.

[0798] The device uses a speech synthesis engine to read aloud the message content and emotionally sensitive feedback.

[0799] Example 2: App downloads and emotional responses

[0800] Step 1:

[0801] The user speaks into the smartphone.

[0802] The user says, "I want to download this app."

[0803] Step 2:

[0804] The device converts speech into text using a speech recognition engine.

[0805] The device converts the speech into text: "I want to download this app."

[0806] Step 3:

[0807] The terminal transmits the text data to the server.

[0808] The terminal sends the converted text to a server over the Internet.

[0809] Step 4:

[0810] The server parses the received text.

[0811] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[0812] Step 5:

[0813] The emotion engine analyzes the user's speech and recognizes emotions.

[0814] The emotion engine performs voice analysis and recognizes emotions such as anxiety or lack of confidence from the user's tone and rate of voice.

[0815] Step 6:

[0816] The device acquires the current screen information and sends it to the server.

[0817] The device checks whether the download page for a specific app is displayed and sends the screen information to the server.

[0818] Step 7:

[0819] The server generates appropriate actions based on the screen information and analysis results.

[0820] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[0821] Step 8:

[0822] The server adjusts the action content by reflecting the results of the emotion engine.

[0823] The server adds encouraging words and detailed explanations based on the emotion engine.

[0824] Step 9:

[0825] The server sends the generated action to the terminal.

[0826] The server then sends the generated guidance to the device, such as "Please press the download button at the bottom right of the screen. It's easy, so don't worry."

[0827] Step 10:

[0828] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[0829] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[0830] This series of steps allows users to operate their smartphones and apps without hesitation while receiving emotional support.

[0831] Example 2

[0832] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0833] In recent years, with the spread of smartphones, operation has become more complex, and there are more and more situations where elderly people and IT novices find it difficult to use. In particular, when users do not know how to operate a device or when an error message is displayed, they often become confused and anxious. To solve this problem, a system is needed that can accurately understand the user's intention from their speech and provide appropriate operation guidance that takes their emotions into consideration.

[0834] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0835] In this invention, the server includes means for converting a user's speech into text using a speech recognition engine, means for analyzing the text using natural language processing to identify the user's intention, and means for recognizing the emotion of the user's speech using an emotion engine. This makes it possible to accurately grasp the user's intention and emotion from the user's speech and provide emotion-conscious operation guidance in real time.

[0836] A "speech recognition engine" is software or a system that converts a user's speech into text data in real time.

[0837] A "server" is a computer system that receives, analyzes, and processes data via a network.

[0838] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0839] An "emotion engine" is a system that recognizes and analyzes emotions from the content of a user's speech and vocal expressions.

[0840] "Text data" is character string data that represents the content of a user's speech, converted by a voice recognition engine.

[0841] "Screen information" is data that indicates the content displayed on the terminal and the current state of the application.

[0842] An "action" refers to a specific operation or instruction generated by the server based on the user's intentions and emotions.

[0843] A "speech synthesis engine" is a system that converts text data into speech and allows the user to listen.

[0844] "Assistance content" refers to operational guidance and information provided to the user as a result of an action generated by the server.

[0845] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for implementing the present invention are described below.

[0846] This system supports user operations by having the smartphone device, server, and emotion engine work together. Specifically, when the user speaks to the smartphone, the device converts the speech into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0847] For example, if the user says "Read my message," the device converts this utterance into text "Read my message." The device then transmits the converted text data to the server.

[0848] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to determine the user's intent. In this example, the server interprets the user as wanting to know the content of the displayed message.

[0849] Additionally, an emotion engine (e.g., Microsoft Azure Text Analytics) runs on the server and recognizes emotions from the user's spoken text. For example, if a user says "I don't know what to do" in an anxious voice, the emotion engine will recognize anxiety and confusion.

[0850] Next, the device acquires the current screen information (displayed messages and application status) and sends it to the server. The server generates appropriate actions based on this screen information and analysis results. The server further adjusts the content of the action according to the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, the server will generate more detailed guidance.

[0851] Finally, the server sends the generated action to the device, and the device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the action details to the user as voice. For example, the device might say something like, "The message displayed tells you to install the latest update. Don't worry, it's easy to do."

[0852] Specific examples

[0853] Consider the following scenario:

[0854] Example 1: Message reading and emotional response

[0855] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[0856] The device converts speech into text using Google Cloud Speech-to-Text.

[0857] The device sends this text to the server.

[0858] The server uses Google Cloud Natural Language to analyze the text and interpret the user's intent as "I want to know the contents of the message."

[0859] The sentiment engine uses Microsoft Azure Text Analytics to recognise emotions and detect anxiety or confusion.

[0860] The device acquires the current screen information and sends it to the server.

[0861] The server analyzes the screen information, determines that the message content is "Please install the latest update," and generates this as guidance.

[0862] The server adds feedback such as "Don't worry, it's easy to use" based on the results of the emotion engine.

[0863] The server sends the guidance back to the device, which then uses Google Cloud Text-to-Speech to read it aloud: "The message you see is telling you to install the latest update. Don't worry, it's easy."

[0864] Prompt Sentence Examples

[0865] "When a user speaks to their smartphone, the system uses a speech recognition engine to convert the speech into text, which is then sent to a server for analysis. Based on the results of analyzing the text and emotions, appropriate operational guidance is generated and read aloud using a speech synthesis engine. For example, if a user says, 'Read the message currently being displayed,' the system will read the message aloud and add words of reassurance."

[0866] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0867] Step 1:

[0868] The user speaks.

[0869] The user speaks to the smartphone to instruct specific operations or ask questions. For example, they say, "Read aloud a message." The input is the user's voice, and the output is voice data.

[0870] Step 2:

[0871] The device converts the voice data into text.

[0872] The device uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the user's speech into text data in real time. The input is voice data, and the output is text data saying "Read message aloud."

[0873] Step 3:

[0874] The terminal transmits the text data to the server.

[0875] The terminal sends the converted text data to the server. The input is the text data, and the output is a network transmission containing it.

[0876] Step 4:

[0877] The server analyzes the text data and identifies the user's intent.

[0878] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to identify the user's intent. The input is the text data, and the output is the analyzed intent. In this example, the user's intent is to have the displayed message read aloud.

[0879] Step 5:

[0880] The emotion engine recognizes the user's emotions.

[0881] An emotion engine on the server (e.g., Microsoft Azure Text Analytics) analyzes the user's spoken text and recognizes emotions. The input is the spoken text, and the output is the recognized emotion (e.g., anxiety, confusion).

[0882] Step 6:

[0883] The device sends the screen information to the server.

[0884] This function obtains the screen information currently displayed on the device (e.g., message content, application status) and sends it to the server. The input is the screen information of the device, and the output is a network transmission containing it.

[0885] Step 7:

[0886] The server analyzes the screen information and generates appropriate actions.

[0887] The server analyzes the screen information sent and generates the action the user wants. The input is the screen information and the analyzed intent, and the output is the generated action (e.g., preparing to read the message content).

[0888] Step 8:

[0889] The server adjusts the action content based on the emotion.

[0890] The server reflects the results of the emotion engine and corrects and complements the action content. The input is the generated action and emotion recognition result, and the output is the adjusted action content. For example, if the user is feeling anxious, a detailed explanation is added.

[0891] Step 9:

[0892] The server sends the final guidance to the terminal.

[0893] The server sends the final guidance content back to the terminal. The input is the adjusted action content, and the output is a network transmission containing the guidance content.

[0894] Step 10:

[0895] The terminal provides guidance to the user.

[0896] The device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the guidance sent from the server to the user as audio. The input is the guidance content, and the output is audio output (e.g., "The message displayed tells you to install the latest update. Don't worry, it's easy to do.").

[0897] (Application example 2)

[0898] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0899] Conventional smartphone operation support systems recognize users' speech and provide operational guidance, but the operation methods and on-screen information are often difficult to intuitively understand, especially for elderly people and IT novices. Furthermore, providing information one-way without considering the user's emotions or psychological state can leave users feeling confused and anxious. This leads to a poor user experience and a tendency for users to avoid using the system.

[0900] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for converting a user's utterance into text using a voice recognition engine; means for transmitting the converted text to the data processing device; means for the data processing device to analyze the text using natural language processing and identify the user's intention; means for the terminal to acquire current display information and transmit it to the data processing device; means for the data processing device to generate an action based on the display information and the analysis result; means for the data processing device to transmit the generated action to the terminal and provide assistance content to the user; emotion analysis means for the terminal to analyze the user's emotion; and means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means. This makes it possible to provide appropriate and gentle guidance while taking into account the user's intention as well as their psychological state.

[0901] "Means for converting user speech into text using a speech recognition engine" is a function that converts the speech information spoken by the user into character data using speech recognition technology.

[0902] The "means for transmitting the converted text to a data processing device" is a function for transferring character data generated by speech recognition to a device that processes data via a network.

[0903] "Means for the data processing device to analyze text using natural language processing and identify the user's intent" is a function that uses natural language processing technology to analyze received text data and identify the user's requests and wishes.

[0904] The "means for the terminal to acquire the currently displayed information and transmit it to the data processing device" is a function that captures the content displayed on the screen of the terminal and transmits it to the data processing device.

[0905] The "means for the data processing device to generate an action based on the display information and the analysis result" is a function that generates an appropriate response or operation guidance based on the display content and the result of analyzing the user's intention.

[0906] "Means for transmitting the action generated by the data processing device to the terminal, and the terminal providing assistance content to the user" is a function for transferring the generated instruction content back to the terminal, and the terminal providing that content to the user as guidance.

[0907] "Emotion analysis means for the terminal to analyze the user's emotions" is a function that recognizes and analyzes emotions from the user's speech and attitude.

[0908] "Means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means" is a function that reflects the results of the emotion analysis and adjusts the action to appropriate content according to the user's psychological state.

[0909] The system embodying the present invention analyzes the user's voice input and provides the necessary guidance, a process carried out by the cooperation of multiple hardware and software components.

[0910] The system mainly consists of a smartphone (hereinafter referred to as the terminal), a data processing device (hereinafter referred to as the server), an emotion analysis means, a speech synthesis engine, a natural language processing engine, and a speech recognition engine.

[0911] It starts when a user speaks to a terminal in a store to ask a question about a product or service. A specific example is when a user asks, "Where is the cosmetics counter?"

[0912] First, the device converts the user's speech into text using a speech recognition engine, using the speech_recognition library, and then sends the converted text to the server.

[0913] The server analyzes the received text using a natural language processing engine to determine the user's intent. A natural language processing model for a specific purpose is used for natural language processing. Based on the analysis results, it is determined that the information the user is looking for is "the location of the cosmetics counter."

[0914] In parallel, the device uses an emotion analysis tool to analyze the user's emotions during speech. The emotion_recognition library is used for emotion analysis, and emotions such as anxiety and confusion are identified. The device also transmits this emotion information to the server.

[0915] Next, the server generates an appropriate action based on the displayed information, the results of intent analysis, and the results of emotion analysis, in response to the user's question. This action can be structured as, for example, "The cosmetics counter is on the third floor."

[0916] If the user's emotions indicate anxiety or confusion, the server generates additional reassuring feedback, such as an encouraging message like, "It's on the third floor, so take your time and look around."

[0917] The generated actions are sent back to the device, which uses a speech synthesis engine to provide voice guidance to the user. This voice guidance is generated in real time using the GTTS library.

[0918] Specific examples

[0919] If a user asks, "Where is the cosmetics counter?":

[0920] The device uses a voice recognition engine to convert the question into text.

[0921] The text is sent to a server and analyzed by a natural language processing engine.

[0922] The server identifies the user's intent and determines that the question is about the location of the cosmetics section.

[0923] At the same time, the terminal analyzes the user's emotions using an emotion analysis means and determines that the user is feeling anxious.

[0924] The server generates an action saying, "The cosmetics department is on the third floor," and adds the feedback, "Don't worry, take your time and look around."

[0925] The generated information is sent to the terminal, and a voice synthesis engine provides voice guidance to the user.

[0926] Prompt Sentence Examples

[0927] "User Question: Is this product cheap?"

[0928] "Answer: This product is currently on sale at a special price. Please purchase with confidence."

[0929] "Emotion: Security. Use the word 'special' correctly to emphasize the low price."

[0930] In this way, the system provides appropriate guidance that takes into account the psychological state of the user.

[0931] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0932] Step 1:

[0933] The user speaks to the smartphone (device). For example, they ask, "Where is the cosmetics counter?" At this point, the user's voice becomes input to the system.

[0934] Step 2:

[0935] The device uses a speech recognition engine (speech_recognition library) to convert the user's speech into text. The input is the user's voice, and the output is the converted text data. The converted text will be "Where is the cosmetics counter?"

[0936] Step 3:

[0937] The terminal sends the converted text to the server. The input here is the converted text data, and the output is the data sent to the server. Specifically, the text data is sent to the server via an HTTP request using a library such as requests.

[0938] Step 4:

[0939] The server receives the text data and analyzes it using a natural language processing engine (a natural language processing model for limited purposes). The input is the received text data, and the output is the analysis result. The server determines that the user is asking about the location of the cosmetics counter and identifies the user's intent.

[0940] Step 5:

[0941] The device uses an emotion analysis means (emotion_recognition library) to analyze the user's emotions. The input is the user's speech data, and the output is the recognized emotion data. The emotion analysis means identifies the emotion "anxiety."

[0942] Step 6:

[0943] The device sends the emotion analysis results to the server. The input here is the recognized emotion data, and the output is the data sent to the server. Specifically, it is sent to the server as an HTTP request, just like text data.

[0944] Step 7:

[0945] The server generates appropriate actions based on the display information, analysis results, and emotion analysis results. The input is the display information, the user's intention, and emotion data, and the output is the generated action data. The server adds a psychological sense of security to the basic action of "The cosmetics counter is on the third floor," by adding "Take your time and look around."

[0946] Step 8:

[0947] The server sends the generated action to the terminal, where the input is the generated action data and the output is the data sent to the terminal.

[0948] Step 9:

[0949] The device uses a speech synthesis engine (GTTS library) to convert the instructions sent from the server into voice and provides the user with assistance. The input is the action data sent from the server, and the output is audible audio that the user can hear. Specifically, the speech synthesis engine converts the text into an audio file and plays it back from the speaker. The guidance provided is, "The cosmetics department is on the third floor. Don't worry, take your time and look around."

[0950] In this way, the system, in which each step works in conjunction with the other, starts with the user's voice input and provides appropriate guidance by voice.

[0951] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0952] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0953] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0954] [Third embodiment]

[0955] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0956] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0957] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0958] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0959] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0960] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0961] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0962] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0963] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0964] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0965] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0966] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0967] The present invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[0968] This system supports user operations by having the smartphone device, server, and user work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[0969] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[0970] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or application status. The server generates appropriate actions based on this screen information and the analysis results. Specifically, it generates voice guidance based on the contents of the message displayed on the screen.

[0971] The server sends the generated action to the device, and the device provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message, telling the user, for example, "The message you are seeing says that you should install the latest update."

[0972] As a concrete example, consider the following scenario.

[0973] Example 1: Reading a message

[0974] When a user says to their smartphone, "Read me the message I'm currently viewing."

[0975] The user says, "Read the message I'm currently viewing."

[0976] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[0977] The device sends this text to the server.

[0978] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[0979] The device acquires the current screen information and sends it to the server.

[0980] The server analyzes the screen information and generates the displayed message content as guidance.

[0981] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[0982] Example 2: Downloading an app

[0983] When a user speaks to their smartphone saying, "I want to download this app."

[0984] The user says, "I want to download this app."

[0985] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[0986] The device sends this text to the server.

[0987] The server analyzes the text and interprets the user's intent as "I want to download the app."

[0988] The device acquires the current screen information and sends it to the server.

[0989] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[0990] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[0991] In this way, the system of the present invention provides appropriate operation guidance so that the user can use the smartphone without any confusion.

[0992] The processing flow will be explained below.

[0993] Program processing flow

[0994] Example 1: Reading a message

[0995] Step 1:

[0996] The user speaks into the smartphone.

[0997] The user says, "Read the message that is currently displayed."

[0998] Step 2:

[0999] The device converts speech into text using a speech recognition engine.

[1000] The device converts the speech into text that reads "Read the message currently being displayed."

[1001] Step 3:

[1002] The terminal transmits the text data to the server.

[1003] The terminal sends the converted text to a server over the Internet.

[1004] Step 4:

[1005] The server parses the received text.

[1006] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[1007] Step 5:

[1008] The device acquires the current screen information and sends it to the server.

[1009] The terminal acquires the currently displayed message information and sends it to the server.

[1010] Step 6:

[1011] The server generates appropriate actions based on the screen information and analysis results.

[1012] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[1013] Step 7:

[1014] The server sends the generated action to the terminal.

[1015] The server transmits the generated guidance content to the terminal.

[1016] Step 8:

[1017] The terminal plays back audio guidance and provides feedback to the user.

[1018] The device uses a speech synthesis engine to read the message content aloud.

[1019] Example 2: Downloading an app

[1020] Step 1:

[1021] The user speaks into the smartphone.

[1022] The user says, "I want to download this app."

[1023] Step 2:

[1024] The device converts speech into text using a speech recognition engine.

[1025] The device converts the speech into text: "I want to download this app."

[1026] Step 3:

[1027] The terminal transmits the text data to the server.

[1028] The terminal sends the converted text to a server over the Internet.

[1029] Step 4:

[1030] The server parses the received text.

[1031] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[1032] Step 5:

[1033] The device acquires the current screen information and sends it to the server.

[1034] The device retrieves current screen information and sends it to the server, for example, whether a specific app page is displayed.

[1035] Step 6:

[1036] The server generates appropriate actions based on the screen information and analysis results.

[1037] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[1038] Step 7:

[1039] The server sends the generated action to the terminal.

[1040] The server transmits the generated guidance content to the terminal.

[1041] Step 8:

[1042] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[1043] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[1044] This series of steps allows users to operate their smartphones and apps without any confusion.

[1045] Example 1

[1046] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1047] In modern society, the use of smartphones is common, but they are often difficult to operate for the elderly and IT novices. Furthermore, the text-based instructions provided as operation guides place a heavy visual burden on users, making them particularly difficult to use for people with impaired eyesight. Furthermore, when complex operations are required, users can become confused and unable to understand the operations. Given this situation, there is a need to provide a means for users to easily understand and use smartphone operations appropriately.

[1048] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1049] In this invention, the server includes means for converting a user's speech into text using a speech recognition means, means for transmitting the converted text to a network device, means for the network device to analyze the text using natural language processing technology and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the network device, means for the network device to generate an action based on the screen information and the analysis result, and means for the network device to transmit the generated action to the terminal, and the terminal to provide assistance content to the user. This makes it possible to provide operation guidance quickly and accurately based on the user's speech.

[1050] A "user" is a person who operates an information system or device.

[1051] An "utterance" is a spoken instruction or request made orally by a user.

[1052] A "voice recognition means" is a technique or device that converts a voice signal into text data.

[1053] "Text" is character information converted by a speech recognition means.

[1054] A "network device" is a computer system that transmits, receives, and processes data.

[1055] "Natural language processing technology" is a computational technology for analyzing text data and understanding its meaning and intent.

[1056] "Screen information" is information about the current display content of the device and the state of the application.

[1057] An "action" is a specific operation or guidance that is executed in response to a user's input or request.

[1058] "Speech synthesis means" refers to a technology or device that converts text information into speech and outputs it.

[1059] "Assistance content" refers to information or instructions provided to assist the user in performing operations.

[1060] This invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people and IT novices who are not good at operating smartphones. This system supports user operations by working in cooperation with the smartphone terminal, server, and user.

[1061] This system uses the following hardware and software:

[1062] Speech recognition method: Uses speech recognition technology such as Google Speech-to-Text API.

[1063] Network device: A server for sending, receiving, and analyzing data.

[1064] Natural language processing technology: Uses AI models such as the BERT model.

[1065] Speech synthesis method: Use a speech synthesis engine such as Amazon Polly.

[1066] System Operation Overview

[1067] When a user speaks to a smartphone, the following series of processes take place:

[1068] First, the user speaks to the smartphone. For example, they say, "Read my message." The terminal uses a voice recognition means to convert this speech into text data. In this case, it is converted into the text "Read my message." Next, the terminal transmits the converted text data to the network device.

[1069] The server analyzes the received text data using natural language processing technology to identify the user's intent. This analysis identifies that the user wants to know the content of the displayed message. The terminal then acquires the current screen information and sends it to the network device. This screen information includes the currently displayed message and the application status.

[1070] The server generates an appropriate action based on the received screen information and analysis results. For example, it creates a voice prompt based on the displayed message. The generated action is then sent to the device, which then uses a voice synthesis means to read it aloud to the user. For example, it tells the user, "The displayed message says to install the latest update."

[1071] Specific examples

[1072] Example 1: Reading a message

[1073] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[1074] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[1075] The device sends this text to the server.

[1076] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[1077] The device acquires the current screen information and sends it to the server.

[1078] The server analyzes the screen information and generates the displayed message content as guidance.

[1079] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[1080] Example 2: Downloading an app

[1081] The user speaks to their smartphone saying, "I want to download this app."

[1082] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[1083] The device sends this text to the server.

[1084] The server analyzes the text and interprets the user's intent as "I want to download the app."

[1085] The device acquires the current screen information and sends it to the server.

[1086] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[1087] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[1088] Prompt Sentence Examples

[1089] "Read the displayed message"

[1090] I want to download this app

[1091] "I want to connect to a new Wi-Fi network."

[1092] In this way, the system provides appropriate operational guidance to help users use their smartphones easily.

[1093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1094] Step 1:

[1095] The user speaks into the smartphone. For example, they say, "Read the message aloud." The user's speech is captured as voice data by the device's microphone.

[1096] Input: User's spoken utterance

[1097] Output: Audio data

[1098] Step 2:

[1099] The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the acquired voice data into text. In this process, the voice waveform is analyzed and the corresponding text data is generated. Specifically, the voice data is converted into the text "Read message aloud."

[1100] Input: Audio data

[1101] Output: Text data (e.g. "Read message aloud")

[1102] Step 3:

[1103] The terminal transmits the generated text data to a network device (server), and an operation of transmitting the text data is performed using an HTTP request.

[1104] Input: Text data (e.g. "Read message aloud")

[1105] Output: Sends text data to the server

[1106] Step 4:

[1107] The text data received by the server is analyzed using natural language processing technology (e.g., BERT model). This analysis allows the meaning of the text data to be understood and the user's intent to be identified. Specifically, the intent is analyzed as "I want to know the contents of the message."

[1108] Input: Text data (e.g. "Read message aloud")

[1109] Output: User intent (e.g. "I want to know the contents of this message")

[1110] Step 5:

[1111] The device retrieves current screen information, including displayed messages and application state. This information is collected from the smartphone's screen capture and active apps.

[1112] Input: None (internal sensor data)

[1113] Output: Screen information (e.g. "Install the latest updates" message)

[1114] Step 6:

[1115] The screen information acquired by the device is sent to the server, also using an HTTP request.

[1116] Input: Screen Information

[1117] Output: Sending screen information to the server

[1118] Step 7:

[1119] The server generates an appropriate action based on the screen information received and the analyzed user intent. Specifically, it generates voice guidance based on the displayed message. For example, it creates guidance such as "The displayed message asks you to install the latest update."

[1120] Input: Screen information, user intent

[1121] Output: Generated action (e.g., voice guidance)

[1122] Step 8:

[1123] The server sends the generated action details to the terminal, which are also sent as an HTTP response.

[1124] Input: The generated action (e.g., voice prompt)

[1125] Output: Sends the action to the terminal.

[1126] Step 9:

[1127] The device uses a speech synthesis engine (e.g., Amazon Polly) to convert the received guidance content into voice and read it aloud to the user. Specifically, the device tells the user, "The message you are seeing tells you to install the latest update."

[1128] Input: The generated action (e.g., voice prompt)

[1129] Output: Providing audio guidance to the user

[1130] (Application example 1)

[1131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1132] For elderly people who are not good at using smartphones or those who are new to IT, it is not easy to respond quickly and accurately in an emergency. In particular, when people are in a panic, it becomes difficult to perform complex operations or make appropriate reports. For this reason, there is a need for a system that allows users to easily make emergency reports through speech and encourages appropriate responses.

[1133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1134] In this invention, the server includes means for converting a user's speech into text using a voice recognition engine, means for transmitting the converted text to the server, means for the server to analyze the text using natural language processing and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the server, means for the server to generate an action based on the screen information and the analysis result, means for the server to transmit the generated action to the terminal and the terminal to provide assistance content to the user, and means for recognizing that the user's intention is to make an emergency call and transmitting an appropriate emergency signal to an external network. This allows the user to make an emergency call using only voice utterances and respond quickly and accurately.

[1135] "User utterance" refers to a voice instruction input via a smartphone or smart glasses.

[1136] A "speech recognition engine" is a software or hardware technology that converts voice data into text.

[1137] "Text" is character information converted from a user's speech using a voice recognition engine.

[1138] A "server" is a computer system for processing and analyzing data over a network.

[1139] "Natural language processing" is a field of computer science that is the technology for analyzing and understanding natural language.

[1140] "User intent" refers to what the user wants to operate or confirm through their smartphone or smart glasses.

[1141] "Current screen information" is information that indicates the content and status currently displayed on a smartphone or smart glasses.

[1142] An "action" is a specific operation or instruction that is generated on the server and executed by the terminal based on the user's intention.

[1143] "Emergency signal" means an electrical or electronic signal intended to notify external emergency services of an emergency.

[1144] "External network" refers to communication means outside the system, such as the Internet or emergency service networks.

[1145] "Location information" is geographical data that indicates the user's current location.

[1146] This invention is a system that allows elderly people who are not good at operating smartphones or people new to IT to easily make emergency calls by speaking. This system is composed of the following elements.

[1147] System Configuration

[1148] Hardware configuration:

[1149] User device: smartphone or smart glasses

[1150] Server: A computer system that processes data and returns analysis results to the user's terminal.

[1151] Software configuration:

[1152] Speech recognition engine: converts user speech into text

[1153] Natural language processing engine: Analyzes text and identifies user intent

[1154] Speech synthesis engine: provides text to the user as speech

[1155] Network communication: Communication technology for exchanging data between servers

[1156] Operation overview

[1157] 1. Speech Recognition:

[1158] The user speaks into their smartphone or smart glasses, saying things like "Call the police" or "Help me." This speech is converted into text by a speech recognition engine and sent to the server.

[1159] 2. Natural Language Processing:

[1160] The server analyzes the received text using a natural language processing engine to identify the user's intent. For example, if the spoken content is "Call the police," the server recognizes that this refers to an emergency call.

[1161] 3. Get screen information:

[1162] The user's device acquires the current screen information and sends it to the server, which allows the server to grasp the current situation, such as which application the user is using.

[1163] 4. Emergency signal generation and transmission:

[1164] The server generates an emergency signal based on the analysis results and the screen information. This signal includes the user's location information and is transmitted to an external network (e.g., an emergency service network).

[1165] 5. User Feedback:

[1166] The user device uses a speech synthesis engine to provide information to the user based on the action received from the server, such as a message such as "Emergency call completed."

[1167] Specific examples

[1168] Scenario 1: A suspicious person breaks into a home while the user is at home, and the user utters "Help me." The smartphone recognizes this utterance, the server analyzes it using natural language processing, and an emergency call is made. The user receives voice feedback saying, "The police have been called."

[1169] Scenario 2: A user encounters an accident while out and says, "Call the police." The smart glasses recognize this, the server analyzes it, and makes an emergency call. The user is notified by voice that "the emergency call has been completed."

[1170] Prompt Sentence Examples

[1171] Example prompt for a generative AI model:

[1172] I'd like to develop an emergency call application using voice recognition. This application will recognize user-uttered phrases such as "help" or "call the police" and automatically make the appropriate emergency call. How should I implement this?

[1173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1174] Step 1:

[1175] A user speaks into a smartphone or smart glasses. The input is the user's voice, and the output is captured as audio data by a microphone.

[1176] Step 2:

[1177] The device uses a voice recognition engine to convert the captured voice data into text.

[1178] The input is the user's voice data, which is analyzed by the voice recognition engine and output as text data. Specifically, the voice recognition engine breaks down the voice into phonemes and phrases and converts them into a string of characters.

[1179] Step 3:

[1180] The terminal sends the converted text to the server.

[1181] The input is text data converted by a speech recognition engine, and the output is text data sent to a server via network communication.

[1182] Step 4:

[1183] The server analyzes the received text data using a natural language processing engine to identify the user's intent.

[1184] The input is text data sent from the device, and the natural language processing engine analyzes the text content to identify the user's intention (e.g., emergency call) and outputs it. Specifically, the natural language processing engine extracts important keywords from the text and classifies the user's intention based on them.

[1185] Step 5:

[1186] The user terminal acquires the current screen information and sends it to the server.

[1187] The input is the screen information of the user's device (e.g., open applications and displayed content), and the output is the data that sends that information to the server. Specifically, the device's screen capture function or data acquisition API is used to obtain the current screen information, which is then sent to the server as digital data.

[1188] Step 6:

[1189] The server generates appropriate actions based on the screen information and analysis results.

[1190] The input is the user's intention and the screen information, and the output is the corresponding action (e.g., generating an emergency call signal). Specifically, the server runs an algorithm that compares the user's intention with the screen information and determines the action based on that.

[1191] Step 7:

[1192] The server sends the generated action to the terminal.

[1193] The input is the action data generated by the server, and the output is the information that the data is sent to the terminal via network communication.

[1194] Step 8:

[1195] The terminal provides the user with assistance content based on the action received from the server.

[1196] The input is the action data sent from the server, and the output is feedback to the user (e.g., voice guidance). Specifically, a speech synthesis engine is used to convert text data into voice, and a message such as "Emergency call completed" is conveyed to the user.

[1197] Step 9:

[1198] The server recognizes the user's intent to call an emergency service and transmits the appropriate emergency signal to the external network.

[1199] The input is the user's intention to make an emergency call and their location information, and the output is the call information to the emergency service. Specifically, the server obtains the user's current location from GPS data and sends the emergency call message in an appropriate format to the external emergency service.

[1200] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1201] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[1202] This system supports user operations by having the smartphone device, server, and emotion engine that analyzes the user's emotions work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[1203] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[1204] Furthermore, the emotion engine analyzes the user's speech to recognize emotions. For example, if the user says "I don't know what to do" in an anxious voice, the emotion engine will recognize the emotion as anxiety or confusion.

[1205] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or the state of the application. The server generates the appropriate action based on this screen information and the analysis results.

[1206] The server further adjusts the content of the action depending on the user's emotion recognized by the emotion engine. For example, if the user is feeling anxious, the server generates more detailed guidance.

[1207] The server sends the generated action to the device, which then provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message and provide feedback based on the user's emotions. For example, the device tells the user, "The message you see is telling you to install the latest update. Don't worry, it's easy to do."

[1208] As a concrete example, consider the following scenario.

[1209] Example 1: Message reading and emotional response

[1210] When a user says to their smartphone, "Read me the message I'm currently viewing."

[1211] The user says, "Read the message I'm currently viewing."

[1212] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[1213] The device sends this text to the server.

[1214] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[1215] The emotion engine analyzes the user's speech and recognizes emotions, such as anxiety or confusion.

[1216] The device acquires the current screen information and sends it to the server.

[1217] The server analyzes the screen information and generates the displayed message content as guidance.

[1218] The server reflects the results of the emotion engine and provides feedback in a gentler tone.

[1219] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud: "The message you're seeing says, 'Please install the latest update.' Don't worry, everything's fine."

[1220] Example 2: App downloads and emotional responses

[1221] When a user speaks to their smartphone saying, "I want to download this app."

[1222] The user says, "I want to download this app."

[1223] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[1224] The device sends this text to the server.

[1225] The server analyzes the text and interprets the user's intent as "I want to download the app."

[1226] The emotion engine analyzes user utterances and recognizes emotions, such as anxiety or lack of confidence.

[1227] The device acquires the current screen information and sends it to the server.

[1228] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[1229] The server reflects the results of the emotion engine and adds encouraging words and detailed explanations.

[1230] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud and, if necessary, displays an icon indicating a download button. "Press the download button at the bottom right of the screen. Don't worry, it's easy."

[1231] In this way, the system of the present invention provides appropriate operational guidance so that users can operate their smartphones and apps without hesitation while receiving support that is tailored to their emotions.

[1232] The processing flow will be explained below.

[1233] Example 1: Message reading and emotional response

[1234] Step 1:

[1235] The user speaks into the smartphone.

[1236] The user says, "Read the message that is currently displayed."

[1237] Step 2:

[1238] The device converts speech into text using a speech recognition engine.

[1239] The device converts the speech into text that reads "Read the message currently being displayed."

[1240] Step 3:

[1241] The terminal transmits the text data to the server.

[1242] The terminal sends the converted text to a server over the Internet.

[1243] Step 4:

[1244] The server parses the received text.

[1245] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[1246] Step 5:

[1247] The emotion engine analyzes the user's speech and recognizes emotions.

[1248] The emotion engine performs voice analysis and recognizes emotions such as anxiety or confusion from the tone and rate of the user's voice.

[1249] Step 6:

[1250] The device acquires the current screen information and sends it to the server.

[1251] The terminal acquires the currently displayed message information and sends it to the server.

[1252] Step 7:

[1253] The server generates appropriate actions based on the screen information and analysis results.

[1254] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[1255] Step 8:

[1256] The server adjusts the action content by reflecting the results of the emotion engine.

[1257] The server takes into account the user's feelings and adds encouragement or further guidance as needed.

[1258] Step 9:

[1259] The server sends the generated action to the terminal.

[1260] The server then sends the generated guidance to the device, such as "The message you're seeing tells you to install the latest update. Don't worry, it's fine."

[1261] Step 10:

[1262] The terminal plays back audio guidance and provides feedback to the user.

[1263] The device uses a speech synthesis engine to read aloud the message content and emotionally sensitive feedback.

[1264] Example 2: App downloads and emotional responses

[1265] Step 1:

[1266] The user speaks into the smartphone.

[1267] The user says, "I want to download this app."

[1268] Step 2:

[1269] The device converts speech into text using a speech recognition engine.

[1270] The device converts the speech into text: "I want to download this app."

[1271] Step 3:

[1272] The terminal transmits the text data to the server.

[1273] The terminal sends the converted text to a server over the Internet.

[1274] Step 4:

[1275] The server parses the received text.

[1276] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[1277] Step 5:

[1278] The emotion engine analyzes the user's speech and recognizes emotions.

[1279] The emotion engine performs voice analysis and recognizes emotions such as anxiety or lack of confidence from the user's tone and rate of voice.

[1280] Step 6:

[1281] The device acquires the current screen information and sends it to the server.

[1282] The device checks whether the download page for a specific app is displayed and sends the screen information to the server.

[1283] Step 7:

[1284] The server generates appropriate actions based on the screen information and analysis results.

[1285] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[1286] Step 8:

[1287] The server adjusts the action content by reflecting the results of the emotion engine.

[1288] The server adds encouraging words and detailed explanations based on the emotion engine.

[1289] Step 9:

[1290] The server sends the generated action to the terminal.

[1291] The server then sends the generated guidance to the device, such as "Please press the download button at the bottom right of the screen. It's easy, so don't worry."

[1292] Step 10:

[1293] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[1294] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[1295] This series of steps allows users to operate their smartphones and apps without hesitation while receiving emotional support.

[1296] Example 2

[1297] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1298] In recent years, with the spread of smartphones, operation has become more complex, and there are more and more situations where elderly people and IT novices find it difficult to use. In particular, when users do not know how to operate a device or when an error message is displayed, they often become confused and anxious. To solve this problem, a system is needed that can accurately understand the user's intention from their speech and provide appropriate operation guidance that takes their emotions into consideration.

[1299] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1300] In this invention, the server includes means for converting a user's speech into text using a speech recognition engine, means for analyzing the text using natural language processing to identify the user's intention, and means for recognizing the emotion of the user's speech using an emotion engine. This makes it possible to accurately grasp the user's intention and emotion from the user's speech and provide emotion-conscious operation guidance in real time.

[1301] A "speech recognition engine" is software or a system that converts a user's speech into text data in real time.

[1302] A "server" is a computer system that receives, analyzes, and processes data via a network.

[1303] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1304] An "emotion engine" is a system that recognizes and analyzes emotions from the content of a user's speech and vocal expressions.

[1305] "Text data" is character string data that represents the content of a user's speech, converted by a voice recognition engine.

[1306] "Screen information" is data that indicates the content displayed on the terminal and the current state of the application.

[1307] An "action" refers to a specific operation or instruction generated by the server based on the user's intentions and emotions.

[1308] A "speech synthesis engine" is a system that converts text data into speech and allows the user to listen.

[1309] "Assistance content" refers to operational guidance and information provided to the user as a result of an action generated by the server.

[1310] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for implementing the present invention are described below.

[1311] This system supports user operations by having the smartphone device, server, and emotion engine work together. Specifically, when the user speaks to the smartphone, the device converts the speech into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1312] For example, if the user says "Read my message," the device converts this utterance into text "Read my message." The device then transmits the converted text data to the server.

[1313] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to determine the user's intent. In this example, the server interprets the user as wanting to know the content of the displayed message.

[1314] Additionally, an emotion engine (e.g., Microsoft Azure Text Analytics) runs on the server and recognizes emotions from the user's spoken text. For example, if a user says "I don't know what to do" in an anxious voice, the emotion engine will recognize anxiety and confusion.

[1315] Next, the device acquires the current screen information (displayed messages and application status) and sends it to the server. The server generates appropriate actions based on this screen information and analysis results. The server further adjusts the content of the action according to the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, the server will generate more detailed guidance.

[1316] Finally, the server sends the generated action to the device, and the device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the action details to the user as voice. For example, the device might say something like, "The message displayed tells you to install the latest update. Don't worry, it's easy to do."

[1317] Specific examples

[1318] Consider the following scenario:

[1319] Example 1: Message reading and emotional response

[1320] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[1321] The device converts speech into text using Google Cloud Speech-to-Text.

[1322] The device sends this text to the server.

[1323] The server uses Google Cloud Natural Language to analyze the text and interpret the user's intent as "I want to know the contents of the message."

[1324] The sentiment engine uses Microsoft Azure Text Analytics to recognise emotions and detect anxiety or confusion.

[1325] The device acquires the current screen information and sends it to the server.

[1326] The server analyzes the screen information, determines that the message content is "Please install the latest update," and generates this as guidance.

[1327] The server adds feedback such as "Don't worry, it's easy to use" based on the results of the emotion engine.

[1328] The server sends the guidance back to the device, which then uses Google Cloud Text-to-Speech to read it aloud: "The message you see is telling you to install the latest update. Don't worry, it's easy."

[1329] Prompt Sentence Examples

[1330] "When a user speaks to their smartphone, the system uses a speech recognition engine to convert the speech into text, which is then sent to a server for analysis. Based on the results of analyzing the text and emotions, appropriate operational guidance is generated and read aloud using a speech synthesis engine. For example, if a user says, 'Read the message currently being displayed,' the system will read the message aloud and add words of reassurance."

[1331] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1332] Step 1:

[1333] The user speaks.

[1334] The user speaks to the smartphone to instruct specific operations or ask questions. For example, they say, "Read aloud a message." The input is the user's voice, and the output is voice data.

[1335] Step 2:

[1336] The device converts the voice data into text.

[1337] The device uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the user's speech into text data in real time. The input is voice data, and the output is text data saying "Read message aloud."

[1338] Step 3:

[1339] The terminal transmits the text data to the server.

[1340] The terminal sends the converted text data to the server. The input is the text data, and the output is a network transmission containing it.

[1341] Step 4:

[1342] The server analyzes the text data and identifies the user's intent.

[1343] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to identify the user's intent. The input is the text data, and the output is the analyzed intent. In this example, the user's intent is to have the displayed message read aloud.

[1344] Step 5:

[1345] The emotion engine recognizes the user's emotions.

[1346] An emotion engine on the server (e.g., Microsoft Azure Text Analytics) analyzes the user's spoken text and recognizes emotions. The input is the spoken text, and the output is the recognized emotion (e.g., anxiety, confusion).

[1347] Step 6:

[1348] The device sends the screen information to the server.

[1349] This function obtains the screen information currently displayed on the device (e.g., message content, application status) and sends it to the server. The input is the screen information of the device, and the output is a network transmission containing it.

[1350] Step 7:

[1351] The server analyzes the screen information and generates appropriate actions.

[1352] The server analyzes the screen information sent and generates the action the user wants. The input is the screen information and the analyzed intent, and the output is the generated action (e.g., preparing to read the message content).

[1353] Step 8:

[1354] The server adjusts the action content based on the emotion.

[1355] The server reflects the results of the emotion engine and corrects and complements the action content. The input is the generated action and emotion recognition result, and the output is the adjusted action content. For example, if the user is feeling anxious, a detailed explanation is added.

[1356] Step 9:

[1357] The server sends the final guidance to the terminal.

[1358] The server sends the final guidance content back to the terminal. The input is the adjusted action content, and the output is a network transmission containing the guidance content.

[1359] Step 10:

[1360] The terminal provides guidance to the user.

[1361] The device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the guidance sent from the server to the user as audio. The input is the guidance content, and the output is audio output (e.g., "The message displayed tells you to install the latest update. Don't worry, it's easy to do.").

[1362] (Application example 2)

[1363] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1364] Conventional smartphone operation support systems recognize users' speech and provide operational guidance, but the operation methods and on-screen information are often difficult to intuitively understand, especially for elderly people and IT novices. Furthermore, providing information one-way without considering the user's emotions or psychological state can leave users feeling confused and anxious. This leads to a poor user experience and a tendency for users to avoid using the system.

[1365] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for converting a user's utterance into text using a voice recognition engine; means for transmitting the converted text to the data processing device; means for the data processing device to analyze the text using natural language processing and identify the user's intention; means for the terminal to acquire current display information and transmit it to the data processing device; means for the data processing device to generate an action based on the display information and the analysis result; means for the data processing device to transmit the generated action to the terminal and provide assistance content to the user; emotion analysis means for the terminal to analyze the user's emotion; and means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means. This makes it possible to provide appropriate and gentle guidance while taking into account the user's intention as well as their psychological state.

[1366] "Means for converting user speech into text using a speech recognition engine" is a function that converts the speech information spoken by the user into character data using speech recognition technology.

[1367] The "means for transmitting the converted text to a data processing device" is a function for transferring character data generated by speech recognition to a device that processes data via a network.

[1368] "Means for the data processing device to analyze text using natural language processing and identify the user's intent" is a function that uses natural language processing technology to analyze received text data and identify the user's requests and wishes.

[1369] The "means for the terminal to acquire the currently displayed information and transmit it to the data processing device" is a function that captures the content displayed on the screen of the terminal and transmits it to the data processing device.

[1370] The "means for the data processing device to generate an action based on the display information and the analysis result" is a function that generates an appropriate response or operation guidance based on the display content and the result of analyzing the user's intention.

[1371] "Means for transmitting the action generated by the data processing device to the terminal, and the terminal providing assistance content to the user" is a function for transferring the generated instruction content back to the terminal, and the terminal providing that content to the user as guidance.

[1372] "Emotion analysis means for the terminal to analyze the user's emotions" is a function that recognizes and analyzes emotions from the user's speech and attitude.

[1373] "Means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means" is a function that reflects the results of the emotion analysis and adjusts the action to appropriate content according to the user's psychological state.

[1374] The system embodying the present invention analyzes the user's voice input and provides the necessary guidance, a process carried out by the cooperation of multiple hardware and software components.

[1375] The system mainly consists of a smartphone (hereinafter referred to as the terminal), a data processing device (hereinafter referred to as the server), an emotion analysis means, a speech synthesis engine, a natural language processing engine, and a speech recognition engine.

[1376] It starts when a user speaks to a terminal in a store to ask a question about a product or service. A specific example is when a user asks, "Where is the cosmetics counter?"

[1377] First, the device converts the user's speech into text using a speech recognition engine, using the speech_recognition library, and then sends the converted text to the server.

[1378] The server analyzes the received text using a natural language processing engine to determine the user's intent. A natural language processing model for a specific purpose is used for natural language processing. Based on the analysis results, it is determined that the information the user is looking for is "the location of the cosmetics counter."

[1379] In parallel, the device uses an emotion analysis tool to analyze the user's emotions during speech. The emotion_recognition library is used for emotion analysis, and emotions such as anxiety and confusion are identified. The device also transmits this emotion information to the server.

[1380] Next, the server generates an appropriate action based on the displayed information, the results of intent analysis, and the results of emotion analysis, in response to the user's question. This action can be structured as, for example, "The cosmetics counter is on the third floor."

[1381] If the user's emotions indicate anxiety or confusion, the server generates additional reassuring feedback, such as an encouraging message like, "It's on the third floor, so take your time and look around."

[1382] The generated actions are sent back to the device, which uses a speech synthesis engine to provide voice guidance to the user. This voice guidance is generated in real time using the GTTS library.

[1383] Specific examples

[1384] If a user asks, "Where is the cosmetics counter?":

[1385] The device uses a voice recognition engine to convert the question into text.

[1386] The text is sent to a server and analyzed by a natural language processing engine.

[1387] The server identifies the user's intent and determines that the question is about the location of the cosmetics section.

[1388] At the same time, the terminal analyzes the user's emotions using an emotion analysis means and determines that the user is feeling anxious.

[1389] The server generates an action saying, "The cosmetics department is on the third floor," and adds the feedback, "Don't worry, take your time and look around."

[1390] The generated information is sent to the terminal, and a voice synthesis engine provides voice guidance to the user.

[1391] Prompt Sentence Examples

[1392] "User Question: Is this product cheap?"

[1393] "Answer: This product is currently on sale at a special price. Please purchase with confidence."

[1394] "Emotion: Security. Use the word 'special' correctly to emphasize the low price."

[1395] In this way, the system provides appropriate guidance that takes into account the psychological state of the user.

[1396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1397] Step 1:

[1398] The user speaks to the smartphone (device). For example, they ask, "Where is the cosmetics counter?" At this point, the user's voice becomes input to the system.

[1399] Step 2:

[1400] The device uses a speech recognition engine (speech_recognition library) to convert the user's speech into text. The input is the user's voice, and the output is the converted text data. The converted text will be "Where is the cosmetics counter?"

[1401] Step 3:

[1402] The terminal sends the converted text to the server. The input here is the converted text data, and the output is the data sent to the server. Specifically, the text data is sent to the server via an HTTP request using a library such as requests.

[1403] Step 4:

[1404] The server receives the text data and analyzes it using a natural language processing engine (a natural language processing model for limited purposes). The input is the received text data, and the output is the analysis result. The server determines that the user is asking about the location of the cosmetics counter and identifies the user's intent.

[1405] Step 5:

[1406] The device uses an emotion analysis means (emotion_recognition library) to analyze the user's emotions. The input is the user's speech data, and the output is the recognized emotion data. The emotion analysis means identifies the emotion "anxiety."

[1407] Step 6:

[1408] The device sends the emotion analysis results to the server. The input here is the recognized emotion data, and the output is the data sent to the server. Specifically, it is sent to the server as an HTTP request, just like text data.

[1409] Step 7:

[1410] The server generates appropriate actions based on the display information, analysis results, and emotion analysis results. The input is the display information, the user's intention, and emotion data, and the output is the generated action data. The server adds a psychological sense of security to the basic action of "The cosmetics counter is on the third floor," by adding "Take your time and look around."

[1411] Step 8:

[1412] The server sends the generated action to the terminal, where the input is the generated action data and the output is the data sent to the terminal.

[1413] Step 9:

[1414] The device uses a speech synthesis engine (GTTS library) to convert the instructions sent from the server into voice and provides the user with assistance. The input is the action data sent from the server, and the output is audible audio that the user can hear. Specifically, the speech synthesis engine converts the text into an audio file and plays it back from the speaker. The guidance provided is, "The cosmetics department is on the third floor. Don't worry, take your time and look around."

[1415] In this way, the system, in which each step works in conjunction with the other, starts with the user's voice input and provides appropriate guidance by voice.

[1416] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1418] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1419] [Fourth embodiment]

[1420] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1421] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1423] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1427] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1428] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1429] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1430] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1431] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1432] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1433] The present invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[1434] This system supports user operations by having the smartphone device, server, and user work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[1435] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[1436] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or application status. The server generates appropriate actions based on this screen information and the analysis results. Specifically, it generates voice guidance based on the contents of the message displayed on the screen.

[1437] The server sends the generated action to the device, and the device provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message, telling the user, for example, "The message you are seeing says that you should install the latest update."

[1438] As a concrete example, consider the following scenario.

[1439] Example 1: Reading a message

[1440] When a user says to their smartphone, "Read me the message I'm currently viewing."

[1441] The user says, "Read the message I'm currently viewing."

[1442] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[1443] The device sends this text to the server.

[1444] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[1445] The device acquires the current screen information and sends it to the server.

[1446] The server analyzes the screen information and generates the displayed message content as guidance.

[1447] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[1448] Example 2: Downloading an app

[1449] When a user speaks to their smartphone saying, "I want to download this app."

[1450] The user says, "I want to download this app."

[1451] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[1452] The device sends this text to the server.

[1453] The server analyzes the text and interprets the user's intent as "I want to download the app."

[1454] The device acquires the current screen information and sends it to the server.

[1455] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[1456] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[1457] In this way, the system of the present invention provides appropriate operation guidance so that the user can use the smartphone without any confusion.

[1458] The processing flow will be explained below.

[1459] Program processing flow

[1460] Example 1: Reading a message

[1461] Step 1:

[1462] The user speaks into the smartphone.

[1463] The user says, "Read the message that is currently displayed."

[1464] Step 2:

[1465] The device converts speech into text using a speech recognition engine.

[1466] The device converts the speech into text that reads "Read the message currently being displayed."

[1467] Step 3:

[1468] The terminal transmits the text data to the server.

[1469] The terminal sends the converted text to a server over the Internet.

[1470] Step 4:

[1471] The server parses the received text.

[1472] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[1473] Step 5:

[1474] The device acquires the current screen information and sends it to the server.

[1475] The terminal acquires the currently displayed message information and sends it to the server.

[1476] Step 6:

[1477] The server generates appropriate actions based on the screen information and analysis results.

[1478] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[1479] Step 7:

[1480] The server sends the generated action to the terminal.

[1481] The server transmits the generated guidance content to the terminal.

[1482] Step 8:

[1483] The terminal plays back audio guidance and provides feedback to the user.

[1484] The device uses a speech synthesis engine to read the message content aloud.

[1485] Example 2: Downloading an app

[1486] Step 1:

[1487] The user speaks into the smartphone.

[1488] The user says, "I want to download this app."

[1489] Step 2:

[1490] The device converts speech into text using a speech recognition engine.

[1491] The device converts the speech into text: "I want to download this app."

[1492] Step 3:

[1493] The terminal transmits the text data to the server.

[1494] The terminal sends the converted text to a server over the Internet.

[1495] Step 4:

[1496] The server parses the received text.

[1497] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[1498] Step 5:

[1499] The device acquires the current screen information and sends it to the server.

[1500] The device retrieves current screen information and sends it to the server, for example, whether a specific app page is displayed.

[1501] Step 6:

[1502] The server generates appropriate actions based on the screen information and analysis results.

[1503] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[1504] Step 7:

[1505] The server sends the generated action to the terminal.

[1506] The server transmits the generated guidance content to the terminal.

[1507] Step 8:

[1508] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[1509] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[1510] This series of steps allows users to operate their smartphones and apps without any confusion.

[1511] Example 1

[1512] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1513] In modern society, the use of smartphones is common, but they are often difficult to operate for the elderly and IT novices. Furthermore, the text-based instructions provided as operation guides place a heavy visual burden on users, making them particularly difficult to use for people with impaired eyesight. Furthermore, when complex operations are required, users can become confused and unable to understand the operations. Given this situation, there is a need to provide a means for users to easily understand and use smartphone operations appropriately.

[1514] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1515] In this invention, the server includes means for converting a user's speech into text using a speech recognition means, means for transmitting the converted text to a network device, means for the network device to analyze the text using natural language processing technology and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the network device, means for the network device to generate an action based on the screen information and the analysis result, and means for the network device to transmit the generated action to the terminal, and the terminal to provide assistance content to the user. This makes it possible to provide operation guidance quickly and accurately based on the user's speech.

[1516] A "user" is a person who operates an information system or device.

[1517] An "utterance" is a spoken instruction or request made orally by a user.

[1518] A "voice recognition means" is a technique or device that converts a voice signal into text data.

[1519] "Text" is character information converted by a speech recognition means.

[1520] A "network device" is a computer system that transmits, receives, and processes data.

[1521] "Natural language processing technology" is a computational technology for analyzing text data and understanding its meaning and intent.

[1522] "Screen information" is information about the current display content of the device and the state of the application.

[1523] An "action" is a specific operation or guidance that is executed in response to a user's input or request.

[1524] "Speech synthesis means" refers to a technology or device that converts text information into speech and outputs it.

[1525] "Assistance content" refers to information or instructions provided to assist the user in performing operations.

[1526] This invention is a system that recognizes user utterances and provides appropriate operational guidance based on the user's intentions, targeted at elderly people and IT novices who are not good at operating smartphones. This system supports user operations by working in cooperation with the smartphone terminal, server, and user.

[1527] This system uses the following hardware and software:

[1528] Speech recognition method: Uses speech recognition technology such as Google Speech-to-Text API.

[1529] Network device: A server for sending, receiving, and analyzing data.

[1530] Natural language processing technology: Uses AI models such as the BERT model.

[1531] Speech synthesis method: Use a speech synthesis engine such as Amazon Polly.

[1532] System Operation Overview

[1533] When a user speaks to a smartphone, the following series of processes take place:

[1534] First, the user speaks to the smartphone. For example, they say, "Read my message." The terminal uses a voice recognition means to convert this speech into text data. In this case, it is converted into the text "Read my message." Next, the terminal transmits the converted text data to the network device.

[1535] The server analyzes the received text data using natural language processing technology to identify the user's intent. This analysis identifies that the user wants to know the content of the displayed message. The terminal then acquires the current screen information and sends it to the network device. This screen information includes the currently displayed message and the application status.

[1536] The server generates an appropriate action based on the received screen information and analysis results. For example, it creates a voice prompt based on the displayed message. The generated action is then sent to the device, which then uses a voice synthesis means to read it aloud to the user. For example, it tells the user, "The displayed message says to install the latest update."

[1537] Specific examples

[1538] Example 1: Reading a message

[1539] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[1540] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[1541] The device sends this text to the server.

[1542] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[1543] The device acquires the current screen information and sends it to the server.

[1544] The server analyzes the screen information and generates the displayed message content as guidance.

[1545] The server sends the guidance content back to the terminal, and the terminal reads the content aloud using a voice synthesis engine.

[1546] Example 2: Downloading an app

[1547] The user speaks to their smartphone saying, "I want to download this app."

[1548] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[1549] The device sends this text to the server.

[1550] The server analyzes the text and interprets the user's intent as "I want to download the app."

[1551] The device acquires the current screen information and sends it to the server.

[1552] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[1553] The server sends the guidance content back to the terminal, which then uses a voice synthesis engine to read the content aloud and, if necessary, displays an icon indicating a download button.

[1554] Prompt Sentence Examples

[1555] "Read the displayed message"

[1556] I want to download this app

[1557] "I want to connect to a new Wi-Fi network."

[1558] In this way, the system provides appropriate operational guidance to help users use their smartphones easily.

[1559] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1560] Step 1:

[1561] The user speaks into the smartphone. For example, they say, "Read the message aloud." The user's speech is captured as voice data by the device's microphone.

[1562] Input: User's spoken utterance

[1563] Output: Audio data

[1564] Step 2:

[1565] The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the acquired voice data into text. In this process, the voice waveform is analyzed and the corresponding text data is generated. Specifically, the voice data is converted into the text "Read message aloud."

[1566] Input: Audio data

[1567] Output: Text data (e.g. "Read message aloud")

[1568] Step 3:

[1569] The terminal transmits the generated text data to a network device (server), and an operation of transmitting the text data is performed using an HTTP request.

[1570] Input: Text data (e.g. "Read message aloud")

[1571] Output: Sends text data to the server

[1572] Step 4:

[1573] The text data received by the server is analyzed using natural language processing technology (e.g., BERT model). This analysis allows the meaning of the text data to be understood and the user's intent to be identified. Specifically, the intent is analyzed as "I want to know the contents of the message."

[1574] Input: Text data (e.g. "Read message aloud")

[1575] Output: User intent (e.g. "I want to know the contents of this message")

[1576] Step 5:

[1577] The device retrieves current screen information, including displayed messages and application state. This information is collected from the smartphone's screen capture and active apps.

[1578] Input: None (internal sensor data)

[1579] Output: Screen information (e.g. "Please install the latest updates" message)

[1580] Step 6:

[1581] The screen information acquired by the device is sent to the server, also using an HTTP request.

[1582] Input: Screen Information

[1583] Output: Sending screen information to the server

[1584] Step 7:

[1585] The server generates an appropriate action based on the screen information received and the analyzed user intent. Specifically, it generates voice guidance based on the displayed message. For example, it creates guidance such as "The displayed message asks you to install the latest update."

[1586] Input: Screen information, user intent

[1587] Output: Generated action (e.g., voice guidance)

[1588] Step 8:

[1589] The server sends the generated action details to the terminal, which are also sent as an HTTP response.

[1590] Input: The generated action (e.g., voice prompt)

[1591] Output: Sends the action to the terminal.

[1592] Step 9:

[1593] The device uses a speech synthesis engine (e.g., Amazon Polly) to convert the received guidance content into voice and read it aloud to the user. Specifically, the device tells the user, "The message you are seeing tells you to install the latest update."

[1594] Input: The generated action (e.g., voice prompt)

[1595] Output: Providing audio guidance to the user

[1596] (Application example 1)

[1597] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1598] For elderly people who are not good at using smartphones or those who are new to IT, it is not easy to respond quickly and accurately in an emergency. In particular, when people are in a panic, it becomes difficult to perform complex operations or make appropriate reports. For this reason, there is a need for a system that allows users to easily make emergency reports through speech and encourages appropriate responses.

[1599] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1600] In this invention, the server includes means for converting a user's speech into text using a voice recognition engine, means for transmitting the converted text to the server, means for the server to analyze the text using natural language processing and identify the user's intention, means for the terminal to acquire current screen information and transmit it to the server, means for the server to generate an action based on the screen information and the analysis result, means for the server to transmit the generated action to the terminal and the terminal to provide assistance content to the user, and means for recognizing that the user's intention is to make an emergency call and transmitting an appropriate emergency signal to an external network. This allows the user to make an emergency call using only voice utterances and respond quickly and accurately.

[1601] "User utterance" refers to a voice instruction input via a smartphone or smart glasses.

[1602] A "speech recognition engine" is a software or hardware technology that converts voice data into text.

[1603] "Text" is character information converted from a user's speech using a voice recognition engine.

[1604] A "server" is a computer system for processing and analyzing data over a network.

[1605] "Natural language processing" is a field of computer science that is the technology for analyzing and understanding natural language.

[1606] "User intent" refers to what the user wants to operate or confirm through their smartphone or smart glasses.

[1607] "Current screen information" is information that indicates the content and status currently displayed on a smartphone or smart glasses.

[1608] An "action" is a specific operation or instruction that is generated on the server and executed by the terminal based on the user's intention.

[1609] "Emergency signal" means an electrical or electronic signal intended to notify external emergency services of an emergency.

[1610] "External network" refers to communication means outside the system, such as the Internet or emergency service networks.

[1611] "Location information" is geographical data that indicates the user's current location.

[1612] This invention is a system that allows elderly people who are not good at operating smartphones or people new to IT to easily make emergency calls by speaking. This system is composed of the following elements.

[1613] System Configuration

[1614] Hardware configuration:

[1615] User device: smartphone or smart glasses

[1616] Server: A computer system that processes data and returns analysis results to the user's terminal.

[1617] Software configuration:

[1618] Speech recognition engine: converts user speech into text

[1619] Natural language processing engine: Analyzes text and identifies user intent

[1620] Speech synthesis engine: provides text to the user as speech

[1621] Network communication: Communication technology for exchanging data between servers

[1622] Operation overview

[1623] 1. Speech Recognition:

[1624] The user speaks into their smartphone or smart glasses, saying things like "Call the police" or "Help me." This speech is converted into text by a speech recognition engine and sent to the server.

[1625] 2. Natural Language Processing:

[1626] The server analyzes the received text using a natural language processing engine to identify the user's intent. For example, if the spoken content is "Call the police," the server recognizes that this refers to an emergency call.

[1627] 3. Get screen information:

[1628] The user's device acquires the current screen information and sends it to the server, which allows the server to grasp the current situation, such as which application the user is using.

[1629] 4. Emergency signal generation and transmission:

[1630] The server generates an emergency signal based on the analysis results and the screen information. This signal includes the user's location information and is transmitted to an external network (e.g., an emergency service network).

[1631] 5. User Feedback:

[1632] The user device uses a speech synthesis engine to provide information to the user based on the action received from the server, such as a message such as "Emergency call completed."

[1633] Specific examples

[1634] Scenario 1: A suspicious person breaks into a home while the user is at home, and the user utters "Help me." The smartphone recognizes this utterance, the server analyzes it using natural language processing, and an emergency call is made. The user receives voice feedback saying, "The police have been called."

[1635] Scenario 2: A user encounters an accident while out and says, "Call the police." The smart glasses recognize this, the server analyzes it, and makes an emergency call. The user is notified by voice that "the emergency call has been completed."

[1636] Prompt Sentence Examples

[1637] Example prompt for a generative AI model:

[1638] I'd like to develop an emergency call application using voice recognition. This application will recognize user-uttered phrases such as "help" or "call the police" and automatically make the appropriate emergency call. How should I implement this?

[1639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1640] Step 1:

[1641] A user speaks into a smartphone or smart glasses. The input is the user's voice, and the output is captured as audio data by a microphone.

[1642] Step 2:

[1643] The device uses a voice recognition engine to convert the captured voice data into text.

[1644] The input is the user's voice data, which is analyzed by the voice recognition engine and output as text data. Specifically, the voice recognition engine breaks down the voice into phonemes and phrases and converts them into a string of characters.

[1645] Step 3:

[1646] The terminal sends the converted text to the server.

[1647] The input is text data converted by a speech recognition engine, and the output is text data sent to a server via network communication.

[1648] Step 4:

[1649] The server analyzes the received text data using a natural language processing engine to identify the user's intent.

[1650] The input is text data sent from the device, and the natural language processing engine analyzes the text content to identify the user's intention (e.g., emergency call) and outputs it. Specifically, the natural language processing engine extracts important keywords from the text and classifies the user's intention based on them.

[1651] Step 5:

[1652] The user terminal acquires the current screen information and sends it to the server.

[1653] The input is the screen information of the user's device (e.g., open applications and displayed content), and the output is the data that sends that information to the server. Specifically, the device's screen capture function or data acquisition API is used to obtain the current screen information, which is then sent to the server as digital data.

[1654] Step 6:

[1655] The server generates appropriate actions based on the screen information and analysis results.

[1656] The input is the user's intention and the screen information, and the output is the corresponding action (e.g., generating an emergency call signal). Specifically, the server runs an algorithm that compares the user's intention with the screen information and determines the action based on that.

[1657] Step 7:

[1658] The server sends the generated action to the terminal.

[1659] The input is the action data generated by the server, and the output is the information that the data is sent to the terminal via network communication.

[1660] Step 8:

[1661] The terminal provides the user with assistance content based on the action received from the server.

[1662] The input is the action data sent from the server, and the output is feedback to the user (e.g., voice guidance). Specifically, a speech synthesis engine is used to convert text data into voice, and a message such as "Emergency call completed" is conveyed to the user.

[1663] Step 9:

[1664] The server recognizes the user's intent to call an emergency service and transmits the appropriate emergency signal to the external network.

[1665] The input is the user's intention to make an emergency call and their location information, and the output is the call information to the emergency service. Specifically, the server obtains the user's current location from GPS data and sends the emergency call message in an appropriate format to the external emergency service.

[1666] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1667] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for carrying out the present invention are described below.

[1668] This system supports user operations by having the smartphone device, server, and emotion engine that analyzes the user's emotions work together. When the user speaks to the smartphone, the device converts the speech into text using a speech recognition engine. For example, if the user says "Read me a message," the device converts this speech into the text "Read me a message."

[1669] The device then sends the converted text data to the server, which uses natural language processing to analyze the received text and determine the user's intent. In this example, the server determines that the user wants to know the content of the displayed message.

[1670] Furthermore, the emotion engine analyzes the user's speech to recognize emotions. For example, if the user says "I don't know what to do" in an anxious voice, the emotion engine will recognize the emotion as anxiety or confusion.

[1671] Next, the device acquires the current screen information and sends it to the server. Screen information refers to, for example, the currently displayed message or the state of the application. The server generates the appropriate action based on this screen information and the analysis results.

[1672] The server further adjusts the content of the action depending on the user's emotion recognized by the emotion engine. For example, if the user is feeling anxious, the server generates more detailed guidance.

[1673] The server sends the generated action to the device, which then provides assistance to the user. In this case, the device uses a speech synthesis engine to read out the message and provide feedback based on the user's emotions. For example, the device tells the user, "The message you see is telling you to install the latest update. Don't worry, it's easy to do."

[1674] As a concrete example, consider the following scenario.

[1675] Example 1: Message reading and emotional response

[1676] When a user says to their smartphone, "Read me the message I'm currently viewing."

[1677] The user says, "Read the message I'm currently viewing."

[1678] The device uses a voice recognition engine to convert the speech into the text "Read the currently displayed message aloud."

[1679] The device sends this text to the server.

[1680] The server analyzes the text and interprets the user's intent as "I want to know the contents of the message."

[1681] The emotion engine analyzes the user's speech and recognizes emotions, such as anxiety or confusion.

[1682] The device acquires the current screen information and sends it to the server.

[1683] The server analyzes the screen information and generates the displayed message content as guidance.

[1684] The server reflects the results of the emotion engine and provides feedback in a gentler tone.

[1685] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud: "The message you're seeing says, 'Please install the latest update.' Don't worry, everything's fine."

[1686] Example 2: App downloads and emotional responses

[1687] When a user speaks to their smartphone saying, "I want to download this app."

[1688] The user says, "I want to download this app."

[1689] The device uses a voice recognition engine to convert the speech into the text "I want to download this app."

[1690] The device sends this text to the server.

[1691] The server analyzes the text and interprets the user's intent as "I want to download the app."

[1692] The emotion engine analyzes user utterances and recognizes emotions, such as anxiety or lack of confidence.

[1693] The device acquires the current screen information and sends it to the server.

[1694] The server analyzes the screen information and generates guidance including the location of the download button and operation procedures.

[1695] The server reflects the results of the emotion engine and adds encouraging words and detailed explanations.

[1696] The server sends the guidance back to the device, which then uses a speech synthesis engine to read it out loud and, if necessary, displays an icon indicating a download button. "Press the download button at the bottom right of the screen. Don't worry, it's easy."

[1697] In this way, the system of the present invention provides appropriate operational guidance so that users can operate their smartphones and apps without hesitation while receiving support that is tailored to their emotions.

[1698] The processing flow will be explained below.

[1699] Example 1: Message reading and emotional response

[1700] Step 1:

[1701] The user speaks into the smartphone.

[1702] The user says, "Read the message that is currently displayed."

[1703] Step 2:

[1704] The device converts speech into text using a speech recognition engine.

[1705] The device converts the speech into text that reads "Read the message currently being displayed."

[1706] Step 3:

[1707] The terminal transmits the text data to the server.

[1708] The terminal sends the converted text to a server over the Internet.

[1709] Step 4:

[1710] The server parses the received text.

[1711] The server uses natural language processing (NLP) to analyze "read message" as the user's intent.

[1712] Step 5:

[1713] The emotion engine analyzes the user's speech and recognizes emotions.

[1714] The emotion engine performs voice analysis and recognizes emotions such as anxiety or confusion from the tone and rate of the user's voice.

[1715] Step 6:

[1716] The device acquires the current screen information and sends it to the server.

[1717] The terminal acquires the currently displayed message information and sends it to the server.

[1718] Step 7:

[1719] The server generates appropriate actions based on the screen information and analysis results.

[1720] The server analyzes the screen information and generates the contents of the displayed message as voice guidance.

[1721] Step 8:

[1722] The server adjusts the action content by reflecting the results of the emotion engine.

[1723] The server takes into account the user's feelings and adds encouragement or further guidance as needed.

[1724] Step 9:

[1725] The server sends the generated action to the terminal.

[1726] The server then sends the generated guidance to the device, such as "The message you're seeing tells you to install the latest update. Don't worry, it's fine."

[1727] Step 10:

[1728] The terminal plays back audio guidance and provides feedback to the user.

[1729] The device uses a speech synthesis engine to read aloud the message content and emotionally sensitive feedback.

[1730] Example 2: App downloads and emotional responses

[1731] Step 1:

[1732] The user speaks into the smartphone.

[1733] The user says, "I want to download this app."

[1734] Step 2:

[1735] The device converts speech into text using a speech recognition engine.

[1736] The device converts the speech into text: "I want to download this app."

[1737] Step 3:

[1738] The terminal transmits the text data to the server.

[1739] The terminal sends the converted text to a server over the Internet.

[1740] Step 4:

[1741] The server parses the received text.

[1742] The server uses natural language processing (NLP) to analyze "download app" as the user's intent.

[1743] Step 5:

[1744] The emotion engine analyzes the user's speech and recognizes emotions.

[1745] The emotion engine performs voice analysis and recognizes emotions such as anxiety or lack of confidence from the tone and rate of the user's voice.

[1746] Step 6:

[1747] The device acquires the current screen information and sends it to the server.

[1748] The device checks whether the download page for a specific app is displayed and sends the screen information to the server.

[1749] Step 7:

[1750] The server generates appropriate actions based on the screen information and analysis results.

[1751] The server analyzes the screen information and determines the position of the download button displayed to the user and the operation procedure.

[1752] Step 8:

[1753] The server adjusts the action content by reflecting the results of the emotion engine.

[1754] The server adds encouraging words and detailed explanations based on the emotion engine.

[1755] Step 9:

[1756] The server sends the generated action to the terminal.

[1757] The server then sends the generated guidance to the device, such as "Please press the download button at the bottom right of the screen. It's easy, so don't worry."

[1758] Step 10:

[1759] The terminal plays back audio guidance and visual guidance to provide feedback to the user.

[1760] The device uses a speech synthesis engine to tell the user to press the download button, and displays a prompt icon on the screen if necessary.

[1761] This series of steps allows users to operate their smartphones and apps without hesitation while receiving emotional support.

[1762] Example 2

[1763] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1764] In recent years, with the spread of smartphones, operation has become more complex, and there are more and more situations where elderly people and IT novices find it difficult to use. In particular, when users do not know how to operate a device or when an error message is displayed, they often become confused and anxious. To solve this problem, a system is needed that can accurately understand the user's intention from their speech and provide appropriate operation guidance that takes their emotions into consideration.

[1765] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1766] In this invention, the server includes means for converting a user's speech into text using a speech recognition engine, means for analyzing the text using natural language processing to identify the user's intention, and means for recognizing the emotion of the user's speech using an emotion engine. This makes it possible to accurately grasp the user's intention and emotion from the user's speech and provide emotion-conscious operation guidance in real time.

[1767] A "speech recognition engine" is software or a system that converts a user's speech into text data in real time.

[1768] A "server" is a computer system that receives, analyzes, and processes data via a network.

[1769] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1770] An "emotion engine" is a system that recognizes and analyzes emotions from the content of a user's speech and vocal expressions.

[1771] "Text data" is character string data that represents the content of a user's speech, converted by a voice recognition engine.

[1772] "Screen information" is data that indicates the content displayed on the terminal and the current state of the application.

[1773] An "action" refers to a specific operation or instruction generated by the server based on the user's intentions and emotions.

[1774] A "speech synthesis engine" is a system that converts text data into speech and allows the user to listen.

[1775] "Assistance content" refers to operational guidance and information provided to the user as a result of an action generated by the server.

[1776] The present invention is a system that recognizes user utterances and provides appropriate operation guidance based on the user's intentions and emotions, targeted at elderly people who are not good at operating smartphones and IT novices. Specific embodiments for implementing the present invention are described below.

[1777] This system supports user operations by having the smartphone device, server, and emotion engine work together. Specifically, when the user speaks to the smartphone, the device converts the speech into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1778] For example, if the user says "Read my message," the device converts this utterance into text "Read my message." The device then transmits the converted text data to the server.

[1779] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to determine the user's intent. In this example, the server interprets the user as wanting to know the content of the displayed message.

[1780] Additionally, an emotion engine (e.g., Microsoft Azure Text Analytics) runs on the server and recognizes emotions from the user's spoken text. For example, if a user says "I don't know what to do" in an anxious voice, the emotion engine will recognize anxiety and confusion.

[1781] Next, the device acquires the current screen information (displayed messages and application status) and sends it to the server. The server generates appropriate actions based on this screen information and analysis results. The server further adjusts the content of the action according to the user's emotions recognized by the emotion engine. For example, if the user is feeling anxious, the server will generate more detailed guidance.

[1782] Finally, the server sends the generated action to the device, and the device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the action details to the user as voice. For example, the device might say something like, "The message displayed tells you to install the latest update. Don't worry, it's easy to do."

[1783] Specific examples

[1784] Consider the following scenario:

[1785] Example 1: Message reading and emotional response

[1786] The user speaks to the smartphone, saying, "Read out the message currently being displayed."

[1787] The device converts speech into text using Google Cloud Speech-to-Text.

[1788] The device sends this text to the server.

[1789] The server uses Google Cloud Natural Language to analyze the text and interpret the user's intent as "I want to know the contents of the message."

[1790] The sentiment engine uses Microsoft Azure Text Analytics to recognise emotions and detect anxiety or confusion.

[1791] The device acquires the current screen information and sends it to the server.

[1792] The server analyzes the screen information, determines that the message content is "Please install the latest update," and generates this as guidance.

[1793] The server adds feedback such as "Don't worry, it's easy to use" based on the results of the emotion engine.

[1794] The server sends the guidance back to the device, which then uses Google Cloud Text-to-Speech to read it aloud: "The message you see is telling you to install the latest update. Don't worry, it's easy."

[1795] Prompt Sentence Examples

[1796] "When a user speaks to their smartphone, the system uses a speech recognition engine to convert the speech into text, which is then sent to a server for analysis. Based on the results of analyzing the text and emotions, appropriate operational guidance is generated and read aloud using a speech synthesis engine. For example, if a user says, 'Read the message currently being displayed,' the system will read the message aloud and add words of reassurance."

[1797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1798] Step 1:

[1799] The user speaks.

[1800] The user speaks to the smartphone to instruct specific operations or ask questions. For example, they say, "Read aloud a message." The input is the user's voice, and the output is voice data.

[1801] Step 2:

[1802] The device converts the voice data into text.

[1803] The device uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the user's speech into text data in real time. The input is voice data, and the output is text data saying "Read message aloud."

[1804] Step 3:

[1805] The terminal transmits the text data to the server.

[1806] The terminal sends the converted text data to the server. The input is the text data, and the output is a network transmission containing it.

[1807] Step 4:

[1808] The server analyzes the text data and identifies the user's intent.

[1809] The server analyzes the received text data using natural language processing technology (e.g., Google Cloud Natural Language) to identify the user's intent. The input is the text data, and the output is the analyzed intent. In this example, the user's intent is to have the displayed message read aloud.

[1810] Step 5:

[1811] The emotion engine recognizes the user's emotions.

[1812] An emotion engine on the server (e.g., Microsoft Azure Text Analytics) analyzes the user's spoken text and recognizes emotions. The input is the spoken text, and the output is the recognized emotion (e.g., anxiety, confusion).

[1813] Step 6:

[1814] The device sends the screen information to the server.

[1815] This function obtains the screen information currently displayed on the device (e.g., message content, application status) and sends it to the server. The input is the screen information of the device, and the output is a network transmission containing it.

[1816] Step 7:

[1817] The server analyzes the screen information and generates appropriate actions.

[1818] The server analyzes the screen information sent and generates the action the user wants. The input is the screen information and the analyzed intent, and the output is the generated action (e.g., preparing to read the message content).

[1819] Step 8:

[1820] The server adjusts the action content based on the emotion.

[1821] The server reflects the results of the emotion engine and corrects and complements the action content. The input is the generated action and emotion recognition result, and the output is the adjusted action content. For example, if the user is feeling anxious, a detailed explanation is added.

[1822] Step 9:

[1823] The server sends the final guidance to the terminal.

[1824] The server sends the final guidance content back to the terminal. The input is the adjusted action content, and the output is a network transmission containing the guidance content.

[1825] Step 10:

[1826] The terminal provides guidance to the user.

[1827] The device uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to provide the guidance sent from the server to the user as audio. The input is the guidance content, and the output is audio output (e.g., "The message displayed tells you to install the latest update. Don't worry, it's easy to do.").

[1828] (Application example 2)

[1829] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1830] Conventional smartphone operation support systems recognize users' speech and provide operational guidance, but the operation methods and on-screen information are often difficult to intuitively understand, especially for elderly people and IT novices. Furthermore, providing information one-way without considering the user's emotions or psychological state can leave users feeling confused and anxious. This leads to a poor user experience and a tendency for users to avoid using the system.

[1831] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for converting a user's utterance into text using a voice recognition engine; means for transmitting the converted text to the data processing device; means for the data processing device to analyze the text using natural language processing and identify the user's intention; means for the terminal to acquire current display information and transmit it to the data processing device; means for the data processing device to generate an action based on the display information and the analysis result; means for the data processing device to transmit the generated action to the terminal and provide assistance content to the user; emotion analysis means for the terminal to analyze the user's emotion; and means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means. This makes it possible to provide appropriate and gentle guidance while taking into account the user's intention as well as their psychological state.

[1832] "Means for converting user speech into text using a speech recognition engine" is a function that converts the speech information spoken by the user into character data using speech recognition technology.

[1833] The "means for transmitting the converted text to a data processing device" is a function for transferring character data generated by speech recognition to a device that processes data via a network.

[1834] "Means for the data processing device to analyze text using natural language processing and identify the user's intent" is a function that uses natural language processing technology to analyze received text data and identify the user's requests and wishes.

[1835] The "means for the terminal to acquire the currently displayed information and transmit it to the data processing device" is a function that captures the content displayed on the screen of the terminal and transmits it to the data processing device.

[1836] The "means for the data processing device to generate an action based on the display information and the analysis result" is a function that generates an appropriate response or operation guidance based on the display content and the result of analyzing the user's intention.

[1837] "Means for transmitting the action generated by the data processing device to the terminal, and the terminal providing assistance content to the user" is a function for transferring the generated instruction content back to the terminal, and the terminal providing that content to the user as guidance.

[1838] "Emotion analysis means for the terminal to analyze the user's emotions" is a function that recognizes and analyzes emotions from the user's speech and attitude.

[1839] "Means for the data processing device to adjust the content of the action according to the user's emotion recognized by the emotion analysis means" is a function that reflects the results of the emotion analysis and adjusts the action to appropriate content according to the user's psychological state.

[1840] The system embodying the present invention analyzes the user's voice input and provides the necessary guidance, a process carried out by the cooperation of multiple hardware and software components.

[1841] The system mainly consists of a smartphone (hereinafter referred to as the terminal), a data processing device (hereinafter referred to as the server), an emotion analysis means, a speech synthesis engine, a natural language processing engine, and a speech recognition engine.

[1842] It starts when a user speaks to a terminal in a store to ask a question about a product or service. A specific example is when a user asks, "Where is the cosmetics counter?"

[1843] First, the device converts the user's speech into text using a speech recognition engine, using the speech_recognition library, and then sends the converted text to the server.

[1844] The server analyzes the received text using a natural language processing engine to determine the user's intent. A natural language processing model for a specific purpose is used for natural language processing. Based on the analysis results, it is determined that the information the user is looking for is "the location of the cosmetics counter."

[1845] In parallel, the device uses an emotion analysis tool to analyze the user's emotions during speech. The emotion_recognition library is used for emotion analysis, and emotions such as anxiety and confusion are identified. The device also transmits this emotion information to the server.

[1846] Next, the server generates an appropriate action based on the displayed information, the results of intent analysis, and the results of emotion analysis, in response to the user's question. This action can be structured as, for example, "The cosmetics counter is on the third floor."

[1847] If the user's emotions indicate anxiety or confusion, the server generates additional reassuring feedback, such as an encouraging message like, "It's on the third floor, so take your time and look around."

[1848] The generated actions are sent back to the device, which uses a speech synthesis engine to provide voice guidance to the user. This voice guidance is generated in real time using the GTTS library.

[1849] Specific examples

[1850] If a user asks, "Where is the cosmetics counter?":

[1851] The device uses a voice recognition engine to convert the question into text.

[1852] The text is sent to a server and analyzed by a natural language processing engine.

[1853] The server identifies the user's intent and determines that the question is about the location of the cosmetics section.

[1854] At the same time, the terminal analyzes the user's emotions using an emotion analysis means and determines that the user is feeling anxious.

[1855] The server generates an action saying, "The cosmetics department is on the third floor," and adds the feedback, "Don't worry, take your time and look around."

[1856] The generated information is sent to the terminal, and a voice synthesis engine provides voice guidance to the user.

[1857] Prompt Sentence Examples

[1858] "User Question: Is this product cheap?"

[1859] "Answer: This product is currently on sale at a special price. Please purchase with confidence."

[1860] "Emotion: Security. Use the word 'special' correctly to emphasize the low price."

[1861] In this way, the system provides appropriate guidance that takes into account the psychological state of the user.

[1862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1863] Step 1:

[1864] The user speaks to the smartphone (device). For example, they ask, "Where is the cosmetics counter?" At this point, the user's voice becomes input to the system.

[1865] Step 2:

[1866] The device uses a speech recognition engine (speech_recognition library) to convert the user's speech into text. The input is the user's voice, and the output is the converted text data. The converted text will be "Where is the cosmetics counter?"

[1867] Step 3:

[1868] The terminal sends the converted text to the server. The input here is the converted text data, and the output is the data sent to the server. Specifically, the text data is sent to the server via an HTTP request using a library such as requests.

[1869] Step 4:

[1870] The server receives the text data and analyzes it using a natural language processing engine (a natural language processing model for limited purposes). The input is the received text data, and the output is the analysis result. The server determines that the user is asking about the location of the cosmetics counter and identifies the user's intent.

[1871] Step 5:

[1872] The device uses an emotion analysis means (emotion_recognition library) to analyze the user's emotions. The input is the user's speech data, and the output is the recognized emotion data. The emotion analysis means identifies the emotion "anxiety."

[1873] Step 6:

[1874] The device sends the emotion analysis results to the server. The input here is the recognized emotion data, and the output is the data sent to the server. Specifically, it is sent to the server as an HTTP request, just like text data.

[1875] Step 7:

[1876] The server generates appropriate actions based on the display information, analysis results, and emotion analysis results. The input is the display information, the user's intention, and emotion data, and the output is the generated action data. The server adds a psychological sense of security to the basic action of "The cosmetics counter is on the third floor," by adding "Take your time and look around."

[1877] Step 8:

[1878] The server sends the generated action to the terminal, where the input is the generated action data and the output is the data sent to the terminal.

[1879] Step 9:

[1880] The device uses a speech synthesis engine (GTTS library) to convert the instructions sent from the server into voice and provides the user with assistance. The input is the action data sent from the server, and the output is audible audio that the user can hear. Specifically, the speech synthesis engine converts the text into an audio file and plays it back from the speaker. The guidance provided is, "The cosmetics department is on the third floor. Don't worry, take your time and look around."

[1881] In this way, the system, in which each step works in conjunction with the other, starts with the user's voice input and provides appropriate guidance by voice.

[1882] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1883] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1884] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1885] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1886] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1887] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1888] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1889] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1890] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1891] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1892] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1893] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1894] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1895] 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.

[1896] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1897] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1898] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1899] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1900] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1901] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1902] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1903] The following is further disclosed regarding the above embodiment.

[1904] (Claim 1)

[1905] A means for converting a user's speech into text using a speech recognition engine;

[1906] means for transmitting the converted text to a server;

[1907] a means for the server to analyze the text using natural language processing to identify the user's intent;

[1908] A means for the terminal to acquire current screen information and transmit it to the server;

[1909] A means for the server to generate actions based on the screen information and analysis results,

[1910] a means for transmitting the generated action to the terminal, and for the terminal to provide assistance content to the user;

[1911] A system including:

[1912] (Claim 2)

[1913] 2. The system according to claim 1, wherein the server generates the content of the displayed message as voice guidance based on the user's intention.

[1914] (Claim 3)

[1915] 2. The system according to claim 1, wherein the terminal uses a speech synthesis engine to read out the instructions sent from the server.

[1916] "Example 1"

[1917] (Claim 1)

[1918] means for converting a user's speech into text using speech recognition means;

[1919] means for transmitting the converted text to a network device;

[1920] a means for the network device to analyze the text using natural language processing technology and identify the user's intent;

[1921] A means for the terminal to acquire current screen information and transmit it to the network device;

[1922] A means for the network device to generate an action based on the screen information and the analysis result;

[1923] a means for transmitting the action generated by the network device to the terminal, and for the terminal to provide assistance content to the user;

[1924] A system including:

[1925] (Claim 2)

[1926] 2. The system according to claim 1, wherein the network device generates the content of the displayed message as voice guidance based on the user's intention.

[1927] (Claim 3)

[1928] 2. The system according to claim 1, wherein the terminal uses a voice synthesis means to read out instructions sent from the network device.

[1929] "Application Example 1"

[1930] (Claim 1)

[1931] A means for converting a user's speech into text using a speech recognition engine;

[1932] means for transmitting the converted text to a server;

[1933] a means for the server to analyze the text using natural language processing to identify the user's intent;

[1934] A means for the terminal to acquire current screen information and transmit it to the server;

[1935] A means for the server to generate actions based on the screen information and analysis results,

[1936] a means for transmitting the generated action to the terminal, and for the terminal to provide assistance content to the user;

[1937] means for recognizing that the user's intent is to make an emergency call and transmitting an appropriate emergency signal to an external network;

[1938] A system including:

[1939] (Claim 2)

[1940] 2. The system according to claim 1, wherein the server generates the content of the displayed message as voice guidance based on the user's intention.

[1941] (Claim 3)

[1942] 2. The system according to claim 1, wherein the terminal uses a speech synthesis engine to read out the instructions sent from the server.

[1943] (Claim 4)

[1944] 2. The system according to claim 1, wherein when an emergency signal is transmitted, the user's location information is included in the transmitted information and transmitted to the external network.

[1945] "Example 2: Combining Emotion Engines"

[1946] (Claim 1)

[1947] A means for converting a user's speech into text using a speech recognition engine;

[1948] means for transmitting the converted text to a server;

[1949] a means for the server to analyze the text using natural language processing to identify the user's intent;

[1950] A means for the server to recognize emotions in user utterances using an emotion engine;

[1951] A means for the terminal to acquire current screen information and transmit it to the server;

[1952] The server generates actions based on the screen information and analysis results, and adjusts the content of the actions based on the emotions.

[1953] a means for transmitting the generated action to the terminal, and for the terminal to provide assistance content to the user;

[1954] A system including:

[1955] (Claim 2)

[1956] 2. The system according to claim 1, wherein the server generates the content of the displayed message as voice guidance according to the user's emotion based on the user's intention.

[1957] (Claim 3)

[1958] 2. The system according to claim 1, wherein the terminal uses a speech synthesis engine to read out instructions sent from the server in a tone of voice based on emotion.

[1959] "Application example 2 when combining emotion engines"

[1960] (Claim 1)

[1961] A means for converting a user's speech into text using a speech recognition engine;

[1962] means for transmitting the converted text to a data processing device;

[1963] means for the data processing device to analyze the text using natural language processing to identify the user's intent;

[1964] means for the terminal to acquire and transmit current display information to the data processing device;

[1965] a means for generating an action based on the display information and the analysis result in the data processing device;

[1966] means for transmitting the action generated by the data processing device to the terminal, and for the terminal to provide assistance content to the user;

[1967] emotion analysis means for the terminal to analyze the emotion of the user;

[1968] a means for adjusting the content of an action in accordance with the user's emotion recognized by the emotion analysis means;

[1969] A system including:

[1970] (Claim 2)

[1971] 2. The system according to claim 1, wherein the data processing device generates the content of the displayed information as voice guidance based on the user's intention.

[1972] (Claim 3)

[1973] 2. The system according to claim 1, wherein the terminal uses a speech synthesis engine to read out instructions sent from the data processing device. [Explanation of symbols]

[1974] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for converting a user's speech into text using a speech recognition engine; means for transmitting the converted text to a server; a means for the server to analyze the text using natural language processing to identify the user's intent; A means for the terminal to acquire current screen information and transmit it to the server; A means for the server to generate actions based on the screen information and analysis results, a means for transmitting the generated action to the terminal, and for the terminal to provide assistance content to the user; A system including:

2. 2. The system according to claim 1, wherein the server generates the content of the displayed message as a voice guidance based on the user's intention.

3. 2. The system according to claim 1, wherein the terminal uses a speech synthesis engine to read out the instructions sent from the server.

Images