system

Abstract

Provide a system. A recording device for a user to record their daily life; A means for uploading the recorded audio data to a cloud server; A means for converting the uploaded voice data into text data using voice recognition technology; A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords; a machine translation means for replacing the extracted text data with appropriate English expressions; A means for generating a 3D avatar video based on the replaced English expression; The system includes a means for transmitting the generated avatar video to a user's terminal.

Description

[Technical Field]

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

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

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

[0004] Today's non-native English speakers face the challenge of using existing English learning materials to learn in a way that is relevant to their daily lives and the conversations they actually use. This limits the efficiency and effectiveness of their learning, leaving many users struggling to improve their English communication skills. Additionally, it is difficult to learn conversational levels relevant to actual situations, such as formal, business casual, and casual. The present invention aims to solve these challenges and enable efficient and effective English learning by recording a user's daily life, analyzing it, and providing avatar videos that translate the conversations into English. [Means for solving the problem]

[0005] The present invention provides the following means.

[0006] The system includes a recording device for a user to record daily life, a means for uploading the recorded voice data to a cloud server, a means for converting the uploaded voice data into text data using voice recognition technology, a means for analyzing the converted text data using natural language processing and extracting the content of the conversation and keywords, a machine translation means for replacing the extracted text data with appropriate English expressions, a means for generating a 3D avatar video based on the replaced English expressions, and a means for transmitting the generated avatar video to the user's terminal.

[0007] It also includes means for inputting user comments and replies into the if function, means for analyzing the input new comments and replies and generating additional conversation scenes, and means for providing updated avatar videos.

[0008] Furthermore, by providing a means to generate narration for the generated avatar video using a voice synthesis engine and a means to select the expression level (formal, business casual, or casual), it becomes possible to learn English in a way that corresponds to a variety of expression scenes.

[0009] A "recording device" is a device for recording the user's voice.

[0010] A "cloud server" is a remote computer server that stores and processes data over the Internet.

[0011] "Voice recognition technology" is a technology that analyzes voice data and converts it into text data.

[0012] "Text data" refers to text information converted using voice recognition technology.

[0013] "Natural language processing" is a branch of artificial intelligence that analyzes text data to understand its meaning.

[0014] "Conversation content" refers to information indicating the gist and intention of the voice spoken by the user.

[0015] "Keywords" refer to particularly important words or phrases in text data.

[0016] "Machine translation means" is a technology that automatically converts text data in one language into another language.

[0017] "English expression" refers to a sentence that has been converted from Japanese text into English by machine translation means.

[0018] "3D avatar video" is a video of a three-dimensional character generated based on the user's recorded utterances.

[0019] The "if function" refers to the function that generates a new conversation scene in response to a new statement or reply entered by the user.

[0020] A "voice synthesis engine" is a technology that generates voices that mimic human voices based on text data.

[0021] "Level of expression" refers to the format and style of conversation, such as formal, business casual, or casual. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention relates to a system that records a user's actual daily life, analyzes the data, and generates avatar videos in which the data is translated into natural English.

[0044] Program processing overview

[0045] Audio recording and data upload

[0046] User: Wears a watch-type recording device and presses the recording start button. The device starts recording audio. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[0047] Device: Recording data is temporarily stored on the device and then uploaded to a cloud server via the internet once recording is complete.

[0048] Analysis of voice data and conversion to text

[0049] Server: The cloud server uses voice recognition technology to analyze the uploaded voice data and convert it into text data. The user's speech, "It's a nice day today. I have a meeting this afternoon," is converted into text data that reads, "It's a nice day today. I have a meeting this afternoon."

[0050] Server: The converted text data is analyzed using natural language processing technology to extract key conversational content and keywords. Keywords such as "nice weather" and "meeting" are extracted here.

[0051] Replace with appropriate English expressions

[0052] Server: Based on the extracted text data, the server uses machine translation to translate it into an appropriate English expression. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0053] Server: Applies formal, business casual, or casual presentation level based on user selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0054] Avatar video generation

[0055] Server: Based on the translated text data, a speech synthesis engine is used to generate narration, and a 3D avatar generation engine is used to create an avatar video with appropriate speaking style and facial expressions.

[0056] Server: The generated avatar video is sent to the user's device.

[0057] Customization with the if function

[0058] User: After watching the generated avatar video, the user can input another comment or reply. For example, in response to the comment "I have a meeting in the afternoon," the user can input "What happens if I miss the train?" using the if function.

[0059] Server: Generates additional dialogue scenes based on new input. For example, a new scene might be created such as "It's nice weather today. What if I miss the train?"

[0060] Server: The updated avatar video can be provided to the user again to extend the learning content.

[0061] In this way, this system provides a natural English learning environment based on the user's daily life and can support the learning of a variety of conversational expressions. Users can learn English expressions in real-life situations, realizing efficient and effective learning.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[0065] Step 2:

[0066] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[0067] Step 3:

[0068] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[0069] Step 4:

[0070] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0071] Step 5:

[0072] The server then analyzes the converted text data using natural language processing technology to extract key conversational content and keywords, such as "nice weather" and "meeting."

[0073] Step 6:

[0074] The server uses machine translation means to convert the extracted text data into appropriate English expressions.

[0075] Step 7:

[0076] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0077] Step 8:

[0078] The server generates narration voice using a voice synthesis engine based on the translated text data.

[0079] Step 9:

[0080] The server uses a 3D avatar generation engine to create an avatar video based on the narration voice and text data, and sets the avatar's movements, facial expressions, and speech content.

[0081] Step 10:

[0082] The server transmits the generated avatar animation to the user's terminal.

[0083] Step 11:

[0084] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0085] Step 12:

[0086] The device sends any new comments or replies that are entered to the server.

[0087] Step 13:

[0088] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0089] Step 14:

[0090] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0091] Step 15:

[0092] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0093] Through the above processing steps, an avatar video for English learning that is suited to the user's daily life is generated, and the learning content can also be customized.

[0094] Example 1

[0095] 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."

[0096] Conventional English learning systems have made it difficult for users to learn efficiently by incorporating the context of their own daily lives. They also lacked a means to convert recorded audio data into appropriate foreign language expressions and provide them to users in a natural format. Furthermore, the system's ability to expand learning content by inputting new utterances and replies was limited. The present invention aims to solve these problems by providing an environment in which users can learn a foreign language in a natural way within their daily lives, thereby enabling them to effectively learn a variety of conversational expressions.

[0097] 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.

[0098] In this invention, the server includes a recording device for recording the user's daily life, means for uploading the recorded voice data to a cloud provider, means for converting the uploaded voice data into text data using voice recognition, means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, means for replacing the extracted text data with appropriate foreign language expressions, means for generating a virtual character video based on the replaced foreign language expressions, means for transmitting the generated virtual character video to the user's device, means for applying an expression level according to a user's selection, and means for synchronizing the virtual character's facial expressions and movements with the voice data. This allows the user to incorporate the context of their own daily life into more natural and effective foreign language learning.

[0099] A "recording device" is a device for recording a user's daily life and has the function of temporarily storing audio data.

[0100] "Cloud provider" is a general term for services that provide remote servers that store and manage audio data uploaded from recording devices.

[0101] "Speech recognition" is a technology that analyzes recorded voice data and converts it into corresponding text data.

[0102] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[0103] "Translation means" refers to a method or technology for converting extracted text data into an appropriate foreign language expression.

[0104] "Virtual character video" is a video in which a 3D character speaking is generated based on translated foreign language expressions.

[0105] "Terminal" means a device operated by a user and used to receive and display virtual character videos.

[0106] "Levels of expression" is a way of distinguishing between different communication styles such as formal, business casual, casual, etc., as selected by the user.

[0107] The "conditional branching function" is a technology that dynamically generates and updates conversation scenes based on new user comments and responses.

[0108] A "speech synthesis engine" is a technology that converts text data into voice data, allowing virtual characters to speak naturally.

[0109] This invention is a system that records a user's daily life, analyzes the data, and generates a virtual character animation that translates it into natural foreign language. This system includes a wide range of technical elements, such as a recording device, speech recognition technology, natural language processing, translation into appropriate foreign language expressions, generation of a virtual character animation, a conditional branching function that inputs and analyzes the user's statements and responses, and a speech synthesis engine.

[0110] Recording devices and data upload

[0111] User: Wears a recording device and presses the start recording button to record sounds from everyday life. The recorded audio data is temporarily stored in the device.

[0112] Specifically, the user says, "It's a nice day today. I have a meeting this afternoon."

[0113] On your device: Once you finish recording, your device will upload the data via your internet connection to a cloud provider, which will then store and manage your audio data.

[0114] Speech Recognition and Natural Language Processing

[0115] Server: The voice data uploaded to the cloud provider is analyzed using speech recognition technology and converted into text data. For example, the Google® Cloud Speech-to-Text API is used. After the text conversion, the result is "It's a nice day today. I have a meeting this afternoon."

[0116] Server: The converted text data is analyzed using natural language processing technology to extract the conversation content and keywords. For example, OpenAI's GPT-3 (registered trademark) is used. Keywords such as "nice weather" and "meeting" are extracted.

[0117] Application of translation means and expression levels

[0118] Server: The extracted text data is replaced with an appropriate foreign language expression using machine translation. Specifically, DeepL or Google Translate is used. For example, "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon."

[0119] Server: Apply presentation level (formal, business casual, casual) based on user selection. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[0120] Virtual character video and voice synthesis

[0121] Server: Generates narration using a speech synthesis engine (e.g., Amazon Polly) based on the translated text data.

[0122] Server: Using a 3D avatar generation engine, a virtual character's animation is generated based on the narration audio. By synchronizing the virtual character's facial expressions and movements with the audio data, a character animation with natural speaking and movement is generated.

[0123] Server: The generated virtual character video is sent to the device and becomes available for viewing by the user.

[0124] Customization with conditional branching

[0125] User: After watching the generated virtual character video, the user can input different statements or responses using the conditional branching function. For example, in response to "I have a meeting in the afternoon," the user can add a question such as "What happens if I miss the train?"

[0126] Server: Generates additional conversation scenes based on new statements and replies, and sends the updated virtual character video back to the user's device.

[0127] An example prompt is:

[0128] User: I have a meeting this afternoon.

[0129] Server: If you miss the train, what will you do?

[0130] This allows users to incorporate the context of their daily lives, making foreign language learning more natural and effective.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] Audio recording

[0134] The user puts on the recording device and presses the start recording button.

[0135] Input: User's everyday voice.

[0136] What happens: The device's microphone captures audio and temporarily stores the audio data locally.

[0137] Output: Recorded audio data is obtained.

[0138] Step 2:

[0139] Uploading data

[0140] After the device finishes recording, it uploads the audio data to a cloud provider via its internet connection.

[0141] Input: Recorded audio data in the device.

[0142] What it does: Recordings are sent to a cloud provider via Wi-Fi or mobile data.

[0143] Output: Audio data uploaded to a cloud provider.

[0144] Step 3:

[0145] Voice Recognition

[0146] The server analyzes the voice data uploaded to the cloud provider using voice recognition technology.

[0147] Input: Audio data stored in the cloud.

[0148] Specific operation: A speech recognition engine (e.g., Google Cloud Speech-to-Text API) converts the voice data into text data.

[0149] Output: Text data such as "It's nice weather today. I have a meeting this afternoon."

[0150] Step 4:

[0151] Natural Language Processing

[0152] The server analyzes the converted text data using natural language processing technology and extracts key conversation content and keywords.

[0153] Input: Text data generated by speech recognition.

[0154] How it works: A natural language processing engine (e.g., OpenAI GPT-3) analyzes the meaning and structure of the text and extracts keywords such as "good weather" and "meeting."

[0155] Output: Extracted conversation content and keywords.

[0156] Step 5:

[0157] Machine Translation

[0158] The server uses machine translation means to convert the extracted text data into an appropriate foreign language expression.

[0159] Input: Extracted text data and keywords.

[0160] What happens: A translation engine (e.g., DeepL or Google Translate) translates "It's nice weather today. I have a meeting this afternoon." into "It's nice weather today. I have a meeting this afternoon."

[0161] Output: Text data converted into appropriate foreign language expressions.

[0162] Step 6:

[0163] Applying expression levels

[0164] The server applies an expression level (formal, business casual, casual) to the translated text data according to the user's selection.

[0165] Input: Translated text data.

[0166] Specific Behavior: Changes the presentation style of text data based on the user's settings. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[0167] Output: Text data with the appropriate representation level applied.

[0168] Step 7:

[0169] Speech synthesis

[0170] The server generates narration using a speech synthesis engine based on the translated text data.

[0171] Input: Text data with representation levels applied.

[0172] Specific operation: A speech synthesis engine (e.g., Amazon Polly) converts text data into speech.

[0173] Output: Narration audio data.

[0174] Step 8:

[0175] Virtual character video generation

[0176] The server generates a virtual character video using a 3D avatar generation engine based on the narration voice generated by voice synthesis.

[0177] Input: Narration audio data.

[0178] Specific operation: The 3D avatar generation engine synchronizes with the voice data to create the facial expressions and movements of the virtual character.

[0179] Output: Virtual character video data.

[0180] Step 9:

[0181] Sending videos

[0182] The server transmits the generated virtual character animation to the user's terminal.

[0183] Input: Virtual character video data.

[0184] Specific operation: Video data is transferred to the user's device via the Internet.

[0185] Output: Virtual character video sent to the user's device.

[0186] Step 10:

[0187] Customization with conditional branching

[0188] After viewing the generated virtual character video, the user can input different comments or replies using the conditional branching function.

[0189] Input: The user's new statement or reply.

[0190] Specific behavior: The user creates different scenarios by inputting new utterances through the application.

[0191] Output: New statements and reply data sent to the server.

[0192] Step 11:

[0193] Generate additional scenes

[0194] The server generates a conversation scene based on the new utterances and replies, and provides the updated virtual character animation to the user again.

[0195] Input: New utterances and response data.

[0196] What it does: Synthesizes new scenes and updates the virtual character.

[0197] Output: The updated virtual character animation data is sent to the user's device.

[0198] (Application example 1)

[0199] 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."

[0200] In conventional factories, it is difficult to communicate with international workers, and although multilingual support is required, there is a lack of appropriate translation and guidance, which makes it inefficient. Therefore, a system that enables efficient and natural communication is needed.

[0201] 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.

[0202] In this invention, the server includes a recording device for recording users' daily lives, a means for uploading the recorded voice data to a cloud server, a means for converting the uploaded voice data into text data using speech recognition technology, a means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, a machine translation means for replacing the extracted text data with appropriate English expressions, a means for generating a 3D avatar video based on the replaced English expressions, a means for outputting a voice-synthesized narration to a robot that supports multilingual communication with factory workers, and a means for transmitting the generated avatar video to a user's device, thereby enabling efficient and natural communication with multinational workers in a factory.

[0203] A "recording device" is a device for recording the sounds of a user's daily life or work in a factory.

[0204] A "cloud server" is a remote server that stores and analyzes recorded data via the Internet.

[0205] "Speech recognition technology" is a technology for analyzing recorded voice data and converting it into text data.

[0206] "Natural language processing" is a technology for analyzing text data and extracting conversation content and keywords.

[0207] "Machine translation means" refers to technology for converting extracted text data into appropriate English expressions.

[0208] "3D avatar video" is a video of an avatar in three-dimensional space, generated based on text data translated into English.

[0209] "Voice synthesis narration" is narration that uses voice synthesis technology and is added to 3D avatar videos.

[0210] A "robot that supports multilingual communication" is a robot that supports multilingual communication with workers within a factory.

[0211] A "user's terminal" is a device that can receive and play the generated avatar video.

[0212] The system for implementing the present invention is configured as follows.

[0213] First, a user uses a recording device to record the sounds of their daily life or work in a factory. This recording device captures the user's speech and temporarily stores it within the device. For example, a microphone (e.g., Shure MV88) is used.

[0214] The recorded audio data is then uploaded to a cloud server via the Internet. The cloud server is constructed using a remote server such as AWS (registered trademark) EC2. This server converts the uploaded audio data into text data using speech recognition technology. For speech recognition, the speech_recognition library or vosk library is used.

[0215] The converted text data is then analyzed using natural language processing technology to extract conversation content and keywords. This process requires software that uses natural language processing technology. The extracted text data is then converted into appropriate English expressions using the GoogleTrans library.

[0216] Next, a 3D avatar video is generated based on the converted English expressions. This video generation uses a 3D avatar generation engine and a speech synthesis engine (e.g., pyttsx3). This system displays the generated avatar video on factory robots, particularly to support smooth communication among multinational workers in factories. The use of a GPU (e.g., NVIDIA GeForce) enables real-time generation.

[0217] Finally, the generated avatar video is sent to the user's device, which can be a smartphone, tablet, or other device, and can play the avatar video.

[0218] For example:

[0219] If a factory has many foreign workers, the robot can record their conversations and provide appropriate instructions and information in English through an avatar. For example, if a worker asks, "Which process should I do next?", the robot can translate the recording into "What is the next process I should do?" and the avatar can respond appropriately.

[0220] Example prompt sentence:

[0221] When a user asks, "What is the next process I should do?", the program records the voice, converts it to text, and translates it as "What is the next process I should do?" The avatar then displays the appropriate answer.

[0222] As described above, the present invention provides a system that realizes efficient and natural communication with multinational workers in a factory.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] A user uses a recording device to record the sounds of work being done in a factory. The input is the user's speech, which is captured by the recording device. Specifically, the user presses the start recording button, and a microphone (e.g., Shure MV88) captures the sound. This generates audio data. The output is the recorded audio data.

[0226] Step 2:

[0227] The recorded audio data is uploaded to a cloud server via the Internet. The input is the audio data stored in the recording device. Specifically, the device transfers the audio data over the Internet to a remote server such as AWS EC2. The output is the audio data stored on the cloud server.

[0228] Step 3:

[0229] The server uses speech recognition technology to convert the uploaded voice data into text data. The input is voice data stored on the cloud server. Specifically, the server analyzes the voice data using the speech_recognition library and vosk library to generate text data. The output is the converted text data.

[0230] Step 4:

[0231] The server analyzes the converted text data using natural language processing technology to extract the conversation content and keywords. The input is text data generated using speech recognition technology. Specifically, it uses natural language processing software for text analysis to extract key keywords from the utterance, "Which step should I take next?" The output is the extracted keywords and the analysis results.

[0232] Step 5:

[0233] The server machine translates the extracted text data into appropriate English expressions. The inputs are the keywords extracted as analysis results and the text data. Specifically, it uses the googletrans library to translate the Japanese text "Which process should I do next?" into the English text "What is the next process I should do?" The output is the translated English text.

[0234] Step 6:

[0235] The server generates a 3D avatar video based on the translated English expressions. The input is the translated English text. Specifically, it generates a narration voice using a speech synthesis engine (e.g., pyttsx3) and creates an avatar video with appropriate dialogue using a 3D avatar generation engine. The output is the generated 3D avatar video.

[0236] Step 7:

[0237] The generated avatar video is sent to a factory robot, which displays the avatar video and outputs a voice-synthesized narration. The input is a 3D avatar video sent from the server. The robot's display and speaker play the avatar video and convey the narration to the user. The output is the avatar video provided to the user and the English narration.

[0238] Step 8:

[0239] By inputting the user's comments and replies into the if function, the new comments and replies are analyzed and additional conversation scenes are generated. The input is the user's new comments and replies. Specifically, the server re-analyzes the new text data and constructs the additional conversation scenes generated by the if function. The output is an updated avatar video.

[0240] 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.

[0241] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video.

[0242] Program processing overview

[0243] Audio recording and data upload

[0244] The user wears the watch-type recording device and presses the recording start button. The device then starts recording the surrounding sounds. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[0245] The device temporarily stores the recorded data within the device, and once recording is complete, uploads the audio data to a cloud server via the Internet.

[0246] Analysis of voice data and conversion to text

[0247] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0248] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[0249] Replace with appropriate English expressions

[0250] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0251] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0252] Recognizing user emotions with an emotion engine

[0253] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. For example, if a user says "It's a nice day today," the emotion is recognized as "joy."

[0254] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[0255] Adapting English expressions and avatar expressions according to emotions

[0256] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[0257] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[0258] Avatar video generation and provision

[0259] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[0260] The server transmits the generated avatar animation to the user's terminal.

[0261] Customization with the if function

[0262] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0263] The device sends any new comments or replies that are entered to the server.

[0264] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0265] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0266] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0267] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[0271] Step 2:

[0272] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[0273] Step 3:

[0274] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[0275] Step 4:

[0276] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0277] Step 5:

[0278] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[0279] Step 6:

[0280] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0281] Step 7:

[0282] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0283] Step 8:

[0284] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. If the user says happily, "It's a nice day today," the emotion is recognized as "joy."

[0285] Step 9:

[0286] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[0287] Step 10:

[0288] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[0289] Step 11:

[0290] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[0291] Step 12:

[0292] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[0293] Step 13:

[0294] The server transmits the generated avatar animation to the user's terminal.

[0295] Step 14:

[0296] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0297] Step 15:

[0298] The device sends any new comments or replies that are entered to the server.

[0299] Step 16:

[0300] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0301] Step 17:

[0302] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0303] Step 18:

[0304] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0305] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[0306] Example 2

[0307] 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."

[0308] In modern society, many people need to learn English, but it is difficult to efficiently acquire practical English conversation skills using traditional teaching methods. Furthermore, because they are unable to teach natural conversations that reflect the user's emotions and situation, they are not effective enough in actual communication. Furthermore, because it is difficult to customize the learning methods to meet the needs of individual learners, there is also the issue of a tendency for motivation to decrease.

[0309] 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.

[0310] In this invention, the server includes means for converting voice data into text data using voice recognition technology, means for analyzing the converted text data using natural language processing technology to extract conversation content and keywords, machine translation means for replacing the extracted text data with appropriate English expressions, emotion analysis means for analyzing the voice data and recognizing the user's emotions, means for adapting English expressions containing emotions and avatar expressions, means for generating 3D avatar video based on the replaced English expressions, and means for transmitting the generated 3D avatar video to the user's terminal. This allows the user to learn natural English conversation that is suited to their daily life, enabling flexible and practical learning that is tailored to the user's emotions and situations.

[0311] An "audio collection device" is a device that allows a user to record audio from their daily life, and includes wristwatch-type devices and dedicated recording devices.

[0312] "Via the network" refers to a method of transmitting audio data to a cloud server using the Internet or other communication networks.

[0313] A "cloud server" is a remote server that stores and processes data over the Internet.

[0314] "Speech recognition technology" is a technology that analyzes voice data and converts it into text data, and generally uses a voice recognition engine.

[0315] "Text data" refers to digital text information converted using voice recognition technology.

[0316] "Natural language processing technology" is a technology that analyzes the content of text data and extracts meaning and keywords.

[0317] "Machine translation means" is a technology for translating text data into another language, and generally uses a translation engine.

[0318] "Emotion analysis means" is a technology that recognizes a user's emotions from voice and text data.

[0319] An "emotion identification tag" is a tag that indicates the user's emotion, and includes an identifier such as "joy" or "anger."

[0320] "3D avatar video" is a three-dimensional character video generated based on the user's voice and text.

[0321] A "voice synthesis engine" is a technology for converting text data into voice data.

[0322] The "if function" allows the user to input a different statement or response and have it reflected in the system.

[0323] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the user's speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video. This system enables users to study English more realistically and effectively.

[0324] This system uses the following hardware and software: A wristwatch-type device or a dedicated recording device is used as the voice collection device used by the user. The voice data is transmitted over the Internet, and a common cloud storage service (e.g., Amazon Web Services' S3 bucket or Google Cloud Storage) is used as the cloud server.

[0325] Audio recording and data upload

[0326] A user puts on the audio collection device and starts recording. For example, the user might say, "It's a nice day today. I have a meeting this afternoon." The recording device captures this audio, and the device temporarily stores the recorded audio data. The device then uploads the audio data to a cloud server via an internet connection.

[0327] Analysis of voice data and conversion to text

[0328] The uploaded voice data is stored on a cloud server. The server then converts the voice data into text data using a voice recognition engine such as Google Cloud Speech-to-Text or IBM Watson (registered trademark). For example, a speech that says, "It's a nice day today. I have a meeting this afternoon" is converted into text format.

[0329] Text analysis using natural language processing

[0330] The server analyzes the text data using natural language processing (NLP) technology to extract the conversation content and keywords. This analysis can be performed using OpenAI's GPT-3 or SpaCy. For example, "good weather" and "meeting" are extracted as keywords.

[0331] Replace with appropriate English expressions

[0332] Based on the extracted text data, the server uses machine translation tools (such as Google Translate API or DeepL API) to translate the text into appropriate English expressions. For example, the text "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon." The server also applies expression levels such as formal, business casual, and casual according to the user's selection.

[0333] Recognizing user emotions with an emotion engine

[0334] The server analyzes the voice data using an emotion engine (such as Microsoft® Azure® Emotion API or AWS Comprehend) to recognize the user's emotion. For example, if a user says happily, "It's a nice day today," the emotion is recognized as "joy." Based on the recognized emotion, an emotion tag such as "joy" is assigned to the text data.

[0335] Adapting English expressions and avatar expressions according to emotions

[0336] The server adapts the English expressions and avatar facial expressions based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the server configures the avatar to speak with a smile. A speech synthesis engine (Amazon Polly or Google Text-to-Speech) is then used to generate a narration voice appropriate to the emotion.

[0337] Avatar video generation and provision

[0338] Based on this narration audio and text data, the server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video. The generated avatar video is then sent to the user's device, where the user can watch the video on their smartphone, tablet, or PC.

[0339] Customization with the if function

[0340] The user can use the if function to input a different statement or response. For example, they can input "What happens if I miss the train?" The device sends the new statement or response to the server, which analyzes it with a speech recognition engine and generates new text data. Based on this, additional conversation scenes are generated and the narration audio and avatar video are updated. The updated avatar video is then sent back to the user's device and can be viewed.

[0341] An example of a prompt is:

[0342] "Text extracted from everyday audio recordings: 'It's nice weather today. I have a meeting this afternoon.'"

[0343] "Example translation: 'It's nice weather today. I have a meeting this afternoon.'"

[0344] Examples include "Emotion tag: 'joy'".

[0345] In this way, the system generates avatar videos for English learning that are in line with the user's daily life and provides expressions that correspond to emotions, thereby realizing more practical and effective English learning.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1: Start recording and collect audio data

[0348] Input: User's everyday conversational voice

[0349] How it works: A user puts on a wristwatch-style audio collection device and presses the record button. The device begins collecting sounds from the surrounding area.

[0350] Data processing / calculation: Recording devices capture audio as digital data and temporarily store that data in their internal memory.

[0351] Output: Collected audio data

[0352] Step 2: Upload your audio data

[0353] Input: Collected audio data

[0354] How it works: The device establishes an internet connection and sends the audio data stored in its internal memory to a cloud server.

[0355] Data processing / calculation: Data compression and transfer

[0356] Output: Audio data stored on a cloud server

[0357] Step 3: Convert audio data to text

[0358] Input: Audio data on a cloud server

[0359] How it works: The server uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to analyze the audio data and convert it into text data.

[0360] Data processing / calculation: Analysis of voice signals and conversion to text information

[0361] Output: Converted text data (e.g. "It's a nice day today. I have a meeting this afternoon.")

[0362] Step 4: Analyzing text data and extracting keywords

[0363] Input: Converted text data

[0364] How it works: The server uses natural language processing (NLP) to analyze the text and extract key conversation topics and keywords (e.g., "nice weather" and "meeting").

[0365] Data processing / calculation: Text analysis and keyword extraction

[0366] Output: Extracted keywords

[0367] Step 5: Translating the text data

[0368] Input: Extracted text data

[0369] How it works: The server uses a machine translation engine (e.g., Google Translate API) to translate the extracted text data into appropriate English expressions.

[0370] Data processing / calculation: Translation of text data

[0371] Output: English text (e.g., "It's nice weather today. I have a meeting this afternoon.")

[0372] Step 6: Sentiment analysis and tagging

[0373] Input: Translated English text and original audio data

[0374] How it works: The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API) to recognize the user's emotion and assign an appropriate emotion tag (e.g., "joy").

[0375] Data processing / computation: sentiment analysis and tagging

[0376] Output: English text with sentiment tags

[0377] Step 7: Generate narration audio

[0378] Input: English text with sentiment tags

[0379] How it works: The server uses a speech synthesis engine (Amazon Polly or Google Text-to-Speech) to generate narration voice based on the emotion.

[0380] Data processing / calculation: Convert text data into audio data

[0381] Output: Generated narration audio

[0382] Step 8: Generate avatar video

[0383] Input: English text and narration audio

[0384] How it works: The server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video based on the text and audio. The avatar's movements and facial expressions are also set here.

[0385] Data processing / calculation: Avatar video generation

[0386] Output: Generated 3D avatar video

[0387] Step 9: Submit your avatar video

[0388] Input: Generated 3D avatar video

[0389] How it works: The server sends the generated avatar video to the user's device.

[0390] Data processing / calculation: Data compression and transfer

[0391] Output: Avatar video on user's device

[0392] Step 10: Customizing with the if function

[0393] Input: New user comments or responses

[0394] How it works: The user uses the if function to input a new comment or reply, and the device sends it to the server. The server then uses a speech recognition engine to analyze the new input and generate text data.

[0395] Data processing / calculation: generating and analyzing new text data

[0396] Output: New text data and updated avatar video

[0397] In this way, the system learns natural English conversation that is suited to the user's daily life, providing flexible and practical learning that is tailored to the user's emotions and circumstances.

[0398] (Application example 2)

[0399] 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."

[0400] Conventional online shopping sites require users to enter information such as the products they want, their budget, and preferences in a text-based format, making them difficult to use, especially for elderly users and those unfamiliar with technology. Furthermore, it is difficult to understand the user's emotions when searching for products, limiting the amount of personalized advice and suggestions they can provide. Furthermore, automated user support using voice data is also insufficient. To address these issues, a system is needed that analyzes users' voices and emotions and uses 3D avatars to provide advice and suggestions tailored to individual needs.

[0401] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0402] In this invention, the server includes a means for recognizing a user's emotion, a means for assigning an emotion tag based on the recognized emotion and generating a 3D avatar video based on the emotion tag, and a means for transmitting the generated avatar video to the user's device so that the avatar video can be viewed within a smartphone application, thereby enabling the user to receive personalized advice and suggestions based on their own emotions and needs.

[0403] A "recording device" is a device that allows a user to record their daily life.

[0404] A "cloud server" is a remote server for storing and processing data over the Internet.

[0405] "Speech recognition technology" is a technology that converts voice data into text data.

[0406] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[0407] "Machine translation means" refers to technology that automatically translates text data from one language to another.

[0408] "Emotion recognition means" is a technology that analyzes emotions from the user's voice and identifies those emotions.

[0409] An "emotion tag" is a tag that indicates an emotion identified by an emotion recognition means.

[0410] "3D avatar video" is a video of a three-dimensional person or character that responds to the user's conversation and emotions.

[0411] A "user terminal" is an information processing device such as a computer, smartphone, or tablet that is used by a user.

[0412] A "smartphone application" is a software program that runs on a smartphone.

[0413] The "if function" is a function that allows you to input user comments and responses and generate new scenarios.

[0414] A "speech synthesis engine" is a technology that converts text data into speech.

[0415] "Formal, business casual, and casual levels of expression" are styles of expression that can be selected according to different situations and uses.

[0416] The system for realizing this application example operates in the following steps.

[0417] Overview of program processing

[0418] 1. Audio recording and data upload

[0419] When a user starts recording their daily life, audio is recorded using a smartphone or a dedicated recording device. This audio data is then uploaded to a cloud server, which contains a database for temporarily storing the audio data. The audio data is uploaded via network communication.

[0420] 2. Analysis of voice data and conversion to text

[0421] The cloud server converts the uploaded voice data into text data using speech recognition technology. The Google Cloud Speech-to-Text API is used for speech recognition. This API has the ability to convert voice data into text data with high accuracy.

[0422] 3. Natural Language Processing and Machine Translation

[0423] The converted text data is analyzed using natural language processing technology to extract conversation content and keywords. This process uses a natural language processing (NLP) library. The extracted text data is then machine-translated into appropriate English expressions using the Google Translate API.

[0424] 4. Emotion Recognition and Emotion Tagging

[0425] The server uses the IBM Watson Tone Analyzer API to recognize the user's emotions from the voice data. This allows the server to assign an emotion tag based on what the user says. The emotion tag indicates a specific emotional state, such as "joy," "sadness," or "surprise."

[0426] 5. 3D avatar video generation and provision

[0427] Based on the recognized emotion tags, a 3D avatar video is generated based on the emotion. The 3D avatar is created using a 3D model generation engine such as Unity or Adobe Fuse. The voice in the avatar video is generated using a speech synthesis engine such as Amazon Polly.

[0428] 6. Video distribution to smartphone applications

[0429] The generated avatar video is delivered to the user's smartphone application via AWS CloudFront, where the user can watch the avatar's responses to their questions.

[0430] The hardware and software that runs the program

[0431] Smartphones or dedicated recording devices are used for the initial recording process. AWS S3 or a database is used to store and process the recorded data. Google Cloud Speech-to-Text API is used for speech recognition, NLP libraries and Google Translate API for natural language processing and machine translation. IBM Watson Tone Analyzer API is used for emotion recognition, Unity or Adobe Fuse for 3D avatar generation, and Amazon Polly for speech synthesis. AWS CloudFront is used for final video distribution.

[0432] Examples and prompts

[0433] For example, consider the case where a user says, "I want new shoes, but I'm not sure which ones to get." This voice data is recorded and uploaded to a cloud server. Then, using speech recognition technology, it is converted into text data: "I want new shoes, but I'm not sure which ones to get." This text data is analyzed using natural language processing, and keywords such as "new shoes" and "confused" are extracted. The text data is then translated into English using the Google Translate API, resulting in "I want new shoes, but I am confused about which one to choose." Next, the user's emotion is recognized as "confused" by IBM Watson Tone Analyzer, and that emotion tag is assigned. Based on the emotion tag "confused," a video is generated in which an avatar suggests in English, "Here are some popular shoes that might match your taste," and the video is delivered to the user's app via AWS CloudFront.

[0434] In this way, the system provides personalized shopping advice based on the user's voice input and emotion recognition.

[0435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0436] Step 1:

[0437] Users record sounds from their daily lives using a smartphone or a dedicated recording device. When the user presses the "Start Recording" button, the device begins to record the surrounding sounds. The input data is the audio data of the user's daily conversation, and this is temporarily saved on the device as output data.

[0438] Step 2:

[0439] When recording is complete, the device uploads the recorded audio data to the cloud server. When the user presses the "Stop Recording" button, the audio data temporarily stored on the device is sent to the cloud server via the Internet. The input data is the recorded audio data, which is then saved on the cloud server as output data.

[0440] Step 3:

[0441] The server receives the voice data uploaded to the cloud server and analyzes it using speech recognition technology. Specifically, it converts the voice data into text data using the Google Cloud Speech-to-Text API. The input data is the voice data on the cloud server, and the output data is the converted text data.

[0442] Step 4:

[0443] The server analyzes the converted text data using natural language processing technology to extract key conversational content and keywords. Specifically, it uses a natural language processing (NLP) library to identify keywords and important phrases. The input data is text data, and the output data is the extracted conversational content and keywords.

[0444] Step 5:

[0445] The server uses machine translation to convert the extracted text data into appropriate English expressions. Specifically, it uses the Google Translate API to convert Japanese text into English. The input data is Japanese text data, and the output data is the text data translated into English.

[0446] Step 6:

[0447] The server uses an emotion engine to recognize the user's emotion when analyzing the voice data. Specifically, it uses the IBM Watson Tone Analyzer API to identify the user's emotion from the text data. The input data is the voice data and text data, and the output data is the recognized emotion tag.

[0448] Step 7:

[0449] The server assigns appropriate emotion tags based on the emotion tags and generates a 3D avatar video based on the emotion tags. Specifically, Unity and Adobe Fuse are used to create a 3D avatar based on the user's emotion, and Amazon Polly is used to synthesize speech. The input data is text data translated into English and emotion tags, and the output data is the generated avatar video.

[0450] Step 8:

[0451] The server sends the generated avatar video to the user's device so that it can be viewed within the smartphone application. Specifically, the video is distributed using AWS CloudFront. The input data is the generated avatar video, and the output data is a video that can be viewed within the user's smartphone application.

[0452] 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.

[0453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] 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.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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. 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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."

[0468] The present invention relates to a system that records a user's actual daily life, analyzes the data, and generates avatar videos in which the data is translated into natural English.

[0469] Program processing overview

[0470] Audio recording and data upload

[0471] User: Wears a watch-type recording device and presses the recording start button. The device starts recording audio. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[0472] Device: Recording data is temporarily stored on the device and then uploaded to a cloud server via the internet once recording is complete.

[0473] Analysis of voice data and conversion to text

[0474] Server: The cloud server uses voice recognition technology to analyze the uploaded voice data and convert it into text data. The user's speech, "It's a nice day today. I have a meeting this afternoon," is converted into text data that reads, "It's a nice day today. I have a meeting this afternoon."

[0475] Server: The converted text data is analyzed using natural language processing technology to extract key conversational content and keywords. Keywords such as "nice weather" and "meeting" are extracted here.

[0476] Replace with appropriate English expressions

[0477] Server: Based on the extracted text data, the server uses machine translation to translate it into an appropriate English expression. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0478] Server: Applies formal, business casual, or casual presentation level based on user selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0479] Avatar video generation

[0480] Server: Based on the translated text data, a speech synthesis engine is used to generate narration, and a 3D avatar generation engine is used to create an avatar video with appropriate speaking style and facial expressions.

[0481] Server: The generated avatar video is sent to the user's device.

[0482] Customization with the if function

[0483] User: After watching the generated avatar video, the user can input another comment or reply. For example, in response to the comment "I have a meeting in the afternoon," the user can input "What happens if I miss the train?" using the if function.

[0484] Server: Generates additional dialogue scenes based on new input. For example, a new scene might be created such as "It's nice weather today. What if I miss the train?"

[0485] Server: The updated avatar video can be provided to the user again to extend the learning content.

[0486] In this way, this system provides a natural English learning environment based on the user's daily life and can support the learning of a variety of conversational expressions. Users can learn English expressions in real-life situations, realizing efficient and effective learning.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[0490] Step 2:

[0491] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[0492] Step 3:

[0493] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[0494] Step 4:

[0495] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0496] Step 5:

[0497] The server then analyzes the converted text data using natural language processing technology to extract key conversational content and keywords, such as "nice weather" and "meeting."

[0498] Step 6:

[0499] The server uses machine translation means to convert the extracted text data into appropriate English expressions.

[0500] Step 7:

[0501] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0502] Step 8:

[0503] The server generates narration voice using a voice synthesis engine based on the translated text data.

[0504] Step 9:

[0505] The server uses a 3D avatar generation engine to create an avatar video based on the narration voice and text data, and sets the avatar's movements, facial expressions, and speech content.

[0506] Step 10:

[0507] The server transmits the generated avatar animation to the user's terminal.

[0508] Step 11:

[0509] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0510] Step 12:

[0511] The device sends any new comments or replies that are entered to the server.

[0512] Step 13:

[0513] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0514] Step 14:

[0515] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0516] Step 15:

[0517] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0518] Through the above processing steps, an avatar video for English learning that is suited to the user's daily life is generated, and the learning content can also be customized.

[0519] Example 1

[0520] 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."

[0521] Conventional English learning systems have made it difficult for users to learn efficiently by incorporating the context of their own daily lives. They also lacked a means to convert recorded audio data into appropriate foreign language expressions and provide them to users in a natural format. Furthermore, the system's ability to expand learning content by inputting new utterances and replies was limited. The present invention aims to solve these problems by providing an environment in which users can learn a foreign language in a natural way within their daily lives, thereby enabling them to effectively learn a variety of conversational expressions.

[0522] 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.

[0523] In this invention, the server includes a recording device for recording the user's daily life, means for uploading the recorded voice data to a cloud provider, means for converting the uploaded voice data into text data using voice recognition, means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, means for replacing the extracted text data with appropriate foreign language expressions, means for generating a virtual character video based on the replaced foreign language expressions, means for transmitting the generated virtual character video to the user's device, means for applying an expression level according to a user's selection, and means for synchronizing the virtual character's facial expressions and movements with the voice data. This allows the user to incorporate the context of their own daily life into more natural and effective foreign language learning.

[0524] A "recording device" is a device for recording a user's daily life and has the function of temporarily storing audio data.

[0525] "Cloud provider" is a general term for services that provide remote servers that store and manage audio data uploaded from recording devices.

[0526] "Speech recognition" is a technology that analyzes recorded voice data and converts it into corresponding text data.

[0527] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[0528] "Translation means" refers to a method or technology for converting extracted text data into an appropriate foreign language expression.

[0529] "Virtual character video" is a video in which a 3D character speaking is generated based on translated foreign language expressions.

[0530] "Terminal" means a device operated by a user and used to receive and display virtual character videos.

[0531] "Levels of expression" is a way of distinguishing between different communication styles such as formal, business casual, casual, etc., as selected by the user.

[0532] The "conditional branching function" is a technology that dynamically generates and updates conversation scenes based on new user comments and responses.

[0533] A "speech synthesis engine" is a technology that converts text data into voice data, allowing virtual characters to speak naturally.

[0534] This invention is a system that records a user's daily life, analyzes the data, and generates a virtual character animation that translates it into natural foreign language. This system includes a wide range of technical elements, such as a recording device, speech recognition technology, natural language processing, translation into appropriate foreign language expressions, generation of a virtual character animation, a conditional branching function that inputs and analyzes the user's statements and responses, and a speech synthesis engine.

[0535] Recording devices and data upload

[0536] User: Wears a recording device and presses the start recording button to record sounds from everyday life. The recorded audio data is temporarily stored in the device.

[0537] Specifically, the user says, "It's a nice day today. I have a meeting this afternoon."

[0538] On your device: Once you finish recording, your device will upload the data via your internet connection to a cloud provider, which will then store and manage your audio data.

[0539] Speech Recognition and Natural Language Processing

[0540] Server: The voice data uploaded to the cloud provider is analyzed using speech recognition technology and converted into text data. For example, the Google Cloud Speech-to-Text API is used. After the text conversion, the result is "It's a nice day today. I have a meeting this afternoon."

[0541] Server: The converted text data is analyzed using natural language processing technology to extract the conversation content and keywords. For example, OpenAI's GPT-3 is used. Keywords such as "good weather" and "meeting" are extracted.

[0542] Application of translation means and expression levels

[0543] Server: The extracted text data is replaced with an appropriate foreign language expression using machine translation. Specifically, DeepL or Google Translate is used. For example, "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon."

[0544] Server: Apply presentation level (formal, business casual, casual) based on user selection. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[0545] Virtual character video and voice synthesis

[0546] Server: Generates narration using a speech synthesis engine (e.g., Amazon Polly) based on the translated text data.

[0547] Server: Using a 3D avatar generation engine, a virtual character's animation is generated based on the narration audio. By synchronizing the virtual character's facial expressions and movements with the audio data, a character animation with natural speaking and movement is generated.

[0548] Server: The generated virtual character video is sent to the device and becomes available for viewing by the user.

[0549] Customization with conditional branching

[0550] User: After watching the generated virtual character video, the user can input different statements or responses using the conditional branching function. For example, in response to "I have a meeting in the afternoon," the user can add a question such as "What happens if I miss the train?"

[0551] Server: Generates additional conversation scenes based on new statements and replies, and sends the updated virtual character video back to the user's device.

[0552] An example prompt is:

[0553] User: I have a meeting this afternoon.

[0554] Server: If you miss the train, what will you do?

[0555] This allows users to incorporate the context of their daily lives, making foreign language learning more natural and effective.

[0556] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0557] Step 1:

[0558] Audio recording

[0559] The user puts on the recording device and presses the start recording button.

[0560] Input: User's everyday voice.

[0561] What happens: The device's microphone captures audio and temporarily stores the audio data locally.

[0562] Output: Recorded audio data is obtained.

[0563] Step 2:

[0564] Uploading data

[0565] After the device finishes recording, it uploads the audio data to a cloud provider via its internet connection.

[0566] Input: Recorded audio data in the device.

[0567] What it does: Recordings are sent to a cloud provider via Wi-Fi or mobile data.

[0568] Output: Audio data uploaded to a cloud provider.

[0569] Step 3:

[0570] Voice Recognition

[0571] The server analyzes the voice data uploaded to the cloud provider using voice recognition technology.

[0572] Input: Audio data stored in the cloud.

[0573] Specific operation: A speech recognition engine (e.g., Google Cloud Speech-to-Text API) converts the voice data into text data.

[0574] Output: Text data such as "It's nice weather today. I have a meeting this afternoon."

[0575] Step 4:

[0576] Natural Language Processing

[0577] The server analyzes the converted text data using natural language processing technology and extracts key conversation content and keywords.

[0578] Input: Text data generated by speech recognition.

[0579] How it works: A natural language processing engine (e.g., OpenAI GPT-3) analyzes the meaning and structure of the text and extracts keywords such as "good weather" and "meeting."

[0580] Output: Extracted conversation content and keywords.

[0581] Step 5:

[0582] Machine Translation

[0583] The server uses machine translation means to convert the extracted text data into an appropriate foreign language expression.

[0584] Input: Extracted text data and keywords.

[0585] What happens: A translation engine (e.g., DeepL or Google Translate) translates "It's nice weather today. I have a meeting this afternoon." into "It's nice weather today. I have a meeting this afternoon."

[0586] Output: Text data converted into appropriate foreign language expressions.

[0587] Step 6:

[0588] Applying expression levels

[0589] The server applies an expression level (formal, business casual, casual) to the translated text data according to the user's selection.

[0590] Input: Translated text data.

[0591] Specific Behavior: Changes the presentation style of text data based on the user's settings. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[0592] Output: Text data with the appropriate representation level applied.

[0593] Step 7:

[0594] Speech synthesis

[0595] The server generates narration using a speech synthesis engine based on the translated text data.

[0596] Input: Text data with representation levels applied.

[0597] Specific operation: A speech synthesis engine (e.g., Amazon Polly) converts text data into speech.

[0598] Output: Narration audio data.

[0599] Step 8:

[0600] Virtual character video generation

[0601] The server generates a virtual character video using a 3D avatar generation engine based on the narration voice generated by voice synthesis.

[0602] Input: Narration audio data.

[0603] Specific operation: The 3D avatar generation engine synchronizes with the voice data to create the facial expressions and movements of the virtual character.

[0604] Output: Virtual character video data.

[0605] Step 9:

[0606] Sending videos

[0607] The server transmits the generated virtual character animation to the user's terminal.

[0608] Input: Virtual character video data.

[0609] Specific operation: Video data is transferred to the user's device via the Internet.

[0610] Output: Virtual character video sent to the user's device.

[0611] Step 10:

[0612] Customization with conditional branching

[0613] After viewing the generated virtual character video, the user can input different comments or replies using the conditional branching function.

[0614] Input: The user's new statement or reply.

[0615] Specific behavior: The user creates different scenarios by inputting new utterances through the application.

[0616] Output: New statements and reply data sent to the server.

[0617] Step 11:

[0618] Generate additional scenes

[0619] The server generates a conversation scene based on the new utterances and replies, and provides the updated virtual character animation to the user again.

[0620] Input: New utterances and response data.

[0621] What it does: Synthesizes new scenes and updates the virtual character.

[0622] Output: The updated virtual character animation data is sent to the user's device.

[0623] (Application example 1)

[0624] 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."

[0625] In conventional factories, it is difficult to communicate with international workers, and despite the need for multilingual support, there is a lack of appropriate translation and guidance, making it inefficient. Therefore, a system that enables efficient and natural communication is needed.

[0626] 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.

[0627] In this invention, the server includes a recording device for recording users' daily lives, a means for uploading the recorded voice data to a cloud server, a means for converting the uploaded voice data into text data using speech recognition technology, a means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, a machine translation means for replacing the extracted text data with appropriate English expressions, a means for generating a 3D avatar video based on the replaced English expressions, a means for outputting a voice-synthesized narration to a robot that supports multilingual communication with factory workers, and a means for transmitting the generated avatar video to the user's device, thereby enabling efficient and natural communication with multinational workers in a factory.

[0628] A "recording device" is a device for recording the sounds of a user's daily life or work in a factory.

[0629] A "cloud server" is a remote server that stores and analyzes recorded data via the Internet.

[0630] "Speech recognition technology" is a technology for analyzing recorded voice data and converting it into text data.

[0631] "Natural language processing" is a technology for analyzing text data and extracting conversation content and keywords.

[0632] "Machine translation means" refers to technology for converting extracted text data into appropriate English expressions.

[0633] "3D avatar video" is a video of an avatar in three-dimensional space, generated based on text data translated into English.

[0634] "Voice synthesis narration" is narration that uses voice synthesis technology and is added to 3D avatar videos.

[0635] A "robot that supports multilingual communication" is a robot that supports multilingual communication with workers within a factory.

[0636] A "user's terminal" is a device that can receive and play the generated avatar video.

[0637] The system for implementing the present invention is configured as follows.

[0638] First, a user uses a recording device to record the sounds of their daily life or work in a factory. This recording device captures the user's speech and temporarily stores it within the device. For example, a microphone (e.g., Shure MV88) is used.

[0639] The recorded audio data is then uploaded to a cloud server via the Internet. The cloud server is built using a remote server such as AWS EC2. This server converts the uploaded audio data into text using speech recognition technology. For speech recognition, the speech_recognition library or vosk library is used.

[0640] The converted text data is then analyzed using natural language processing technology to extract conversation content and keywords. This process requires software that uses natural language processing technology. The extracted text data is then converted into appropriate English expressions using the GoogleTrans library.

[0641] Next, a 3D avatar video is generated based on the converted English expressions. This video generation uses a 3D avatar generation engine and a speech synthesis engine (e.g., pyttsx3). This system displays the generated avatar video on factory robots, particularly to support smooth communication among multinational workers in factories. The use of a GPU (e.g., NVIDIA GeForce) enables real-time generation.

[0642] Finally, the generated avatar video is sent to the user's device, which can be a smartphone, tablet, or other device, and can play the avatar video.

[0643] For example:

[0644] If a factory has many foreign workers, the robot can record their conversations and provide appropriate instructions and information in English through an avatar. For example, if a worker asks, "Which process should I do next?", the robot can translate the recording into "What is the next process I should do?" and the avatar can respond appropriately.

[0645] Example prompt sentence:

[0646] When a user asks, "What is the next process I should do?", the program records the voice, converts it to text, and translates it as "What is the next process I should do?" The avatar then displays the appropriate answer.

[0647] As described above, the present invention provides a system that realizes efficient and natural communication with multinational workers in a factory.

[0648] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0649] Step 1:

[0650] A user uses a recording device to record the sounds of work being done in a factory. The input is the user's speech, which is captured by the recording device. Specifically, the user presses the start recording button, and a microphone (e.g., Shure MV88) captures the sound. This generates audio data. The output is the recorded audio data.

[0651] Step 2:

[0652] The recorded audio data is uploaded to a cloud server via the Internet. The input is the audio data stored in the recording device. Specifically, the device transfers the audio data over the Internet to a remote server such as AWS EC2. The output is the audio data stored on the cloud server.

[0653] Step 3:

[0654] The server uses speech recognition technology to convert the uploaded voice data into text data. The input is voice data stored on the cloud server. Specifically, the server analyzes the voice data using the speech_recognition library and vosk library to generate text data. The output is the converted text data.

[0655] Step 4:

[0656] The server analyzes the converted text data using natural language processing technology to extract the conversation content and keywords. The input is text data generated using speech recognition technology. Specifically, it uses natural language processing software for text analysis to extract key keywords from the utterance, "Which step should I take next?" The output is the extracted keywords and the analysis results.

[0657] Step 5:

[0658] The server machine translates the extracted text data into appropriate English expressions. The inputs are the keywords extracted as analysis results and the text data. Specifically, it uses the googletrans library to translate the Japanese text "Which process should I do next?" into the English text "What is the next process I should do?" The output is the translated English text.

[0659] Step 6:

[0660] The server generates a 3D avatar video based on the translated English expressions. The input is the translated English text. Specifically, it generates a narration voice using a speech synthesis engine (e.g., pyttsx3) and creates an avatar video with appropriate dialogue using a 3D avatar generation engine. The output is the generated 3D avatar video.

[0661] Step 7:

[0662] The generated avatar video is sent to a factory robot, which displays the avatar video and outputs a voice-synthesized narration. The input is a 3D avatar video sent from the server. The robot's display and speaker play the avatar video and convey the narration to the user. The output is the avatar video provided to the user and the English narration.

[0663] Step 8:

[0664] By inputting the user's comments and replies into the if function, the new comments and replies are analyzed and additional conversation scenes are generated. The input is the user's new comments and replies. Specifically, the server re-analyzes the new text data and constructs the additional conversation scenes generated by the if function. The output is an updated avatar video.

[0665] 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.

[0666] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video.

[0667] Program processing overview

[0668] Audio recording and data upload

[0669] The user wears the watch-type recording device and presses the recording start button. The device then starts recording the surrounding sounds. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[0670] The device temporarily stores the recorded data within the device, and once recording is complete, uploads the audio data to a cloud server via the Internet.

[0671] Analysis of voice data and conversion to text

[0672] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0673] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[0674] Replace with appropriate English expressions

[0675] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0676] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0677] Recognizing user emotions with an emotion engine

[0678] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. For example, if a user says "It's a nice day today," the emotion is recognized as "joy."

[0679] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[0680] Adapting English expressions and avatar expressions according to emotions

[0681] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[0682] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[0683] Avatar video generation and provision

[0684] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[0685] The server transmits the generated avatar animation to the user's terminal.

[0686] Customization with the if function

[0687] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0688] The device sends any new comments or replies that are entered to the server.

[0689] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0690] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0691] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0692] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[0693] The processing flow will be explained below.

[0694] Step 1:

[0695] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[0696] Step 2:

[0697] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[0698] Step 3:

[0699] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[0700] Step 4:

[0701] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0702] Step 5:

[0703] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[0704] Step 6:

[0705] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0706] Step 7:

[0707] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0708] Step 8:

[0709] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. If the user says happily, "It's a nice day today," the emotion is recognized as "joy."

[0710] Step 9:

[0711] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[0712] Step 10:

[0713] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[0714] Step 11:

[0715] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[0716] Step 12:

[0717] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[0718] Step 13:

[0719] The server transmits the generated avatar animation to the user's terminal.

[0720] Step 14:

[0721] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0722] Step 15:

[0723] The device sends any new comments or replies that are entered to the server.

[0724] Step 16:

[0725] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0726] Step 17:

[0727] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0728] Step 18:

[0729] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0730] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[0731] Example 2

[0732] 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."

[0733] In modern society, many people need to learn English, but it is difficult to efficiently acquire practical English conversation skills using traditional teaching methods. Furthermore, because they are unable to teach natural conversations that reflect the user's emotions and situation, they are not effective enough in actual communication. Furthermore, because it is difficult to customize the learning methods to meet the needs of individual learners, there is also the issue of a tendency for motivation to decrease.

[0734] 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.

[0735] In this invention, the server includes means for converting voice data into text data using voice recognition technology, means for analyzing the converted text data using natural language processing technology to extract conversation content and keywords, machine translation means for replacing the extracted text data with appropriate English expressions, emotion analysis means for analyzing the voice data and recognizing the user's emotions, means for adapting English expressions containing emotions and avatar expressions, means for generating 3D avatar video based on the replaced English expressions, and means for transmitting the generated 3D avatar video to the user's terminal. This allows the user to learn natural English conversation that is suited to their daily life, enabling flexible and practical learning that is tailored to the user's emotions and situations.

[0736] An "audio collection device" is a device that allows a user to record audio from their daily life, and includes wristwatch-type devices and dedicated recording devices.

[0737] "Via the network" refers to a method of transmitting audio data to a cloud server using the Internet or other communication networks.

[0738] A "cloud server" is a remote server that stores and processes data over the Internet.

[0739] "Speech recognition technology" is a technology that analyzes voice data and converts it into text data, and generally uses a voice recognition engine.

[0740] "Text data" refers to digital text information converted using voice recognition technology.

[0741] "Natural language processing technology" is a technology that analyzes the content of text data and extracts meaning and keywords.

[0742] "Machine translation means" is a technology for translating text data into another language, and generally uses a translation engine.

[0743] "Emotion analysis means" is a technology that recognizes a user's emotions from voice and text data.

[0744] An "emotion identification tag" is a tag that indicates the user's emotion, and includes an identifier such as "joy" or "anger."

[0745] "3D avatar video" is a three-dimensional character video generated based on the user's voice and text.

[0746] A "voice synthesis engine" is a technology for converting text data into voice data.

[0747] The "if function" allows the user to input a different statement or response and have it reflected in the system.

[0748] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the user's speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video. This system enables users to study English more realistically and effectively.

[0749] This system uses the following hardware and software: A wristwatch-type device or a dedicated recording device is used as the voice collection device used by the user. The voice data is transmitted over the Internet, and a common cloud storage service (e.g., Amazon Web Services' S3 bucket or Google Cloud Storage) is used as the cloud server.

[0750] Audio recording and data upload

[0751] A user puts on the audio collection device and starts recording. For example, the user might say, "It's a nice day today. I have a meeting this afternoon." The recording device captures this audio, and the device temporarily stores the recorded audio data. The device then uploads the audio data to a cloud server via an internet connection.

[0752] Analysis of voice data and conversion to text

[0753] The uploaded voice data is stored on a cloud server. The server then uses a speech recognition engine such as Google Cloud Speech-to-Text or IBM Watson to convert the voice data into text data. For example, a speech that says, "It's a nice day today. I have a meeting this afternoon" is converted into text format.

[0754] Text analysis using natural language processing

[0755] The server analyzes the text data using natural language processing (NLP) technology to extract the conversation content and keywords. This analysis can be performed using OpenAI's GPT-3 or SpaCy. For example, "good weather" and "meeting" are extracted as keywords.

[0756] Replace with appropriate English expressions

[0757] Based on the extracted text data, the server uses machine translation tools (such as Google Translate API or DeepL API) to translate the text into appropriate English expressions. For example, the text "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon." The server also applies expression levels such as formal, business casual, and casual according to the user's selection.

[0758] Recognizing user emotions with an emotion engine

[0759] The server analyzes the voice data using an emotion engine (such as Microsoft Azure's Emotion API or AWS's Comprehend) to recognize the user's emotion. For example, if a user says happily, "It's a nice day today," the emotion is recognized as "joy." Based on the recognized emotion, an emotion tag such as "joy" is assigned to the text data.

[0760] Adapting English expressions and avatar expressions according to emotions

[0761] The server adapts the English expressions and avatar facial expressions based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the server configures the avatar to speak with a smile. A speech synthesis engine (Amazon Polly or Google Text-to-Speech) is then used to generate a narration voice appropriate to the emotion.

[0762] Avatar video generation and provision

[0763] Based on this narration audio and text data, the server uses a 3D avatar generation engine (such as Unity or Unreal Engine) to generate an avatar video. The generated avatar video is then sent to the user's device, where the user can watch the video on their smartphone, tablet, or PC.

[0764] Customization with the if function

[0765] The user can use the if function to input a different statement or response. For example, they can input "What happens if I miss the train?" The device sends the new statement or response to the server, which analyzes it with a speech recognition engine and generates new text data. Based on this, additional conversation scenes are generated and the narration audio and avatar video are updated. The updated avatar video is then sent back to the user's device and can be viewed.

[0766] An example of a prompt is:

[0767] "Text extracted from everyday audio recordings: 'It's nice weather today. I have a meeting this afternoon.'"

[0768] "Example translation: 'It's nice weather today. I have a meeting this afternoon.'"

[0769] Examples include "Emotion tag: 'joy'".

[0770] In this way, the system generates avatar videos for English learning that are in line with the user's daily life and provides expressions that correspond to emotions, thereby realizing more practical and effective English learning.

[0771] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0772] Step 1: Start recording and collect audio data

[0773] Input: User's everyday conversational voice

[0774] How it works: A user puts on a wristwatch-style audio collection device and presses the record button. The device begins collecting sounds from the surrounding area.

[0775] Data processing / calculation: Recording devices capture audio as digital data and temporarily store that data in their internal memory.

[0776] Output: Collected audio data

[0777] Step 2: Upload your audio data

[0778] Input: Collected audio data

[0779] How it works: The device establishes an internet connection and sends the audio data stored in its internal memory to a cloud server.

[0780] Data processing / calculation: Data compression and transfer

[0781] Output: Audio data stored on a cloud server

[0782] Step 3: Convert audio data to text

[0783] Input: Audio data on a cloud server

[0784] How it works: The server uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to analyze the audio data and convert it into text data.

[0785] Data processing / calculation: Analysis of voice signals and conversion to text information

[0786] Output: Converted text data (e.g. "It's a nice day today. I have a meeting this afternoon.")

[0787] Step 4: Analyzing text data and extracting keywords

[0788] Input: Converted text data

[0789] How it works: The server uses natural language processing (NLP) to analyze the text and extract key conversation topics and keywords (e.g., "nice weather" and "meeting").

[0790] Data processing / calculation: Text analysis and keyword extraction

[0791] Output: Extracted keywords

[0792] Step 5: Translating the text data

[0793] Input: Extracted text data

[0794] How it works: The server uses a machine translation engine (e.g., Google Translate API) to translate the extracted text data into appropriate English expressions.

[0795] Data processing / calculation: Translation of text data

[0796] Output: English text (e.g., "It's nice weather today. I have a meeting this afternoon.")

[0797] Step 6: Sentiment analysis and tagging

[0798] Input: Translated English text and original audio data

[0799] How it works: The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API) to recognize the user's emotion and assign an appropriate emotion tag (e.g., "joy").

[0800] Data processing / computation: sentiment analysis and tagging

[0801] Output: English text with sentiment tags

[0802] Step 7: Generate narration audio

[0803] Input: English text with sentiment tags

[0804] How it works: The server uses a speech synthesis engine (Amazon Polly or Google Text-to-Speech) to generate narration voice based on the emotion.

[0805] Data processing / calculation: Convert text data into audio data

[0806] Output: Generated narration audio

[0807] Step 8: Generate avatar video

[0808] Input: English text and narration audio

[0809] How it works: The server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video based on the text and audio. The avatar's movements and facial expressions are also set here.

[0810] Data processing / calculation: Avatar video generation

[0811] Output: Generated 3D avatar video

[0812] Step 9: Submit your avatar video

[0813] Input: Generated 3D avatar video

[0814] How it works: The server sends the generated avatar video to the user's device.

[0815] Data processing / calculation: Data compression and transfer

[0816] Output: Avatar video on user's device

[0817] Step 10: Customizing with the if function

[0818] Input: New user comments or responses

[0819] How it works: The user uses the if function to input a new comment or reply, and the device sends it to the server. The server then uses a speech recognition engine to analyze the new input and generate text data.

[0820] Data processing / calculation: generating and analyzing new text data

[0821] Output: New text data and updated avatar video

[0822] In this way, the system learns natural English conversation that is suited to the user's daily life, providing flexible and practical learning that is tailored to the user's emotions and circumstances.

[0823] (Application example 2)

[0824] 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."

[0825] Conventional online shopping sites require users to enter information such as the products they want, their budget, and preferences in a text-based format, making them difficult to use, especially for elderly users and those unfamiliar with technology. Furthermore, it is difficult to understand the user's emotions when searching for products, limiting the amount of personalized advice and suggestions they can provide. Furthermore, automated user support using voice data is also insufficient. To address these issues, a system is needed that analyzes users' voices and emotions and uses 3D avatars to provide advice and suggestions tailored to individual needs.

[0826] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0827] In this invention, the server includes a means for recognizing a user's emotion, a means for assigning an emotion tag based on the recognized emotion and generating a 3D avatar video based on the emotion tag, and a means for transmitting the generated avatar video to the user's device so that the avatar video can be viewed within a smartphone application, thereby enabling the user to receive personalized advice and suggestions based on their own emotions and needs.

[0828] A "recording device" is a device that allows a user to record their daily life.

[0829] A "cloud server" is a remote server for storing and processing data over the Internet.

[0830] "Speech recognition technology" is a technology that converts voice data into text data.

[0831] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[0832] "Machine translation means" refers to technology that automatically translates text data from one language to another.

[0833] "Emotion recognition means" is a technology that analyzes emotions from the user's voice and identifies those emotions.

[0834] An "emotion tag" is a tag that indicates an emotion identified by an emotion recognition means.

[0835] "3D avatar video" is a video of a three-dimensional person or character that responds to the user's conversation and emotions.

[0836] A "user terminal" is an information processing device such as a computer, smartphone, or tablet that is used by a user.

[0837] A "smartphone application" is a software program that runs on a smartphone.

[0838] The "if function" is a function that allows you to input user comments and responses and generate new scenarios.

[0839] A "speech synthesis engine" is a technology that converts text data into speech.

[0840] "Formal, business casual, and casual levels of expression" are styles of expression that can be selected according to different situations and uses.

[0841] The system for realizing this application example operates in the following steps.

[0842] Overview of program processing

[0843] 1. Audio recording and data upload

[0844] When a user starts recording their daily life, audio is recorded using a smartphone or a dedicated recording device. This audio data is then uploaded to a cloud server, which contains a database for temporarily storing the audio data. The audio data is uploaded via network communication.

[0845] 2. Analysis of voice data and conversion to text

[0846] The cloud server converts the uploaded voice data into text data using speech recognition technology. The Google Cloud Speech-to-Text API is used for speech recognition. This API has the ability to convert voice data into text data with high accuracy.

[0847] 3. Natural Language Processing and Machine Translation

[0848] The converted text data is analyzed using natural language processing technology to extract conversation content and keywords. This process uses a natural language processing (NLP) library. The extracted text data is then machine-translated into appropriate English expressions using the Google Translate API.

[0849] 4. Emotion Recognition and Emotion Tagging

[0850] The server uses the IBM Watson Tone Analyzer API to recognize the user's emotions from the voice data. This allows the server to assign an emotion tag based on what the user says. The emotion tag indicates a specific emotional state, such as "joy," "sadness," or "surprise."

[0851] 5. 3D avatar video generation and provision

[0852] Based on the recognized emotion tags, a 3D avatar video is generated based on the emotion. The 3D avatar is created using a 3D model generation engine such as Unity or Adobe Fuse. The voice in the avatar video is generated using a speech synthesis engine such as Amazon Polly.

[0853] 6. Video distribution to smartphone applications

[0854] The generated avatar video is delivered to the user's smartphone application via AWS CloudFront, where the user can watch the avatar's responses to their questions.

[0855] The hardware and software that runs the program

[0856] Smartphones or dedicated recording devices are used for the initial recording process. AWS S3 or a database is used to store and process the recorded data. Google Cloud Speech-to-Text API is used for speech recognition, NLP libraries and Google Translate API for natural language processing and machine translation. IBM Watson Tone Analyzer API is used for emotion recognition, Unity or Adobe Fuse for 3D avatar generation, and Amazon Polly for speech synthesis. AWS CloudFront is used for final video distribution.

[0857] Examples and prompts

[0858] For example, consider the case where a user says, "I want new shoes, but I'm not sure which ones to get." This voice data is recorded and uploaded to a cloud server. Then, using speech recognition technology, it is converted into text data: "I want new shoes, but I'm not sure which ones to get." This text data is analyzed using natural language processing, and keywords such as "new shoes" and "confused" are extracted. The text data is then translated into English using the Google Translate API, resulting in "I want new shoes, but I am confused about which one to choose." Next, the user's emotion is recognized as "confused" by IBM Watson Tone Analyzer, and that emotion tag is assigned. Based on the emotion tag "confused," a video is generated in which an avatar suggests in English, "Here are some popular shoes that might match your taste," and the video is delivered to the user's app via AWS CloudFront.

[0859] In this way, the system provides personalized shopping advice based on the user's voice input and emotion recognition.

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Step 1:

[0862] Users record sounds from their daily lives using a smartphone or a dedicated recording device. When the user presses the "Start Recording" button, the device begins to record the surrounding sounds. The input data is the audio data of the user's daily conversation, and this is temporarily saved on the device as output data.

[0863] Step 2:

[0864] When recording is complete, the device uploads the recorded audio data to the cloud server. When the user presses the "Stop Recording" button, the audio data temporarily stored on the device is sent to the cloud server via the Internet. The input data is the recorded audio data, which is then saved on the cloud server as output data.

[0865] Step 3:

[0866] The server receives the voice data uploaded to the cloud server and analyzes it using speech recognition technology. Specifically, it converts the voice data into text data using the Google Cloud Speech-to-Text API. The input data is the voice data on the cloud server, and the output data is the converted text data.

[0867] Step 4:

[0868] The server analyzes the converted text data using natural language processing technology to extract key conversational content and keywords. Specifically, it uses a natural language processing (NLP) library to identify keywords and important phrases. The input data is text data, and the output data is the extracted conversational content and keywords.

[0869] Step 5:

[0870] The server uses machine translation to convert the extracted text data into appropriate English expressions. Specifically, it uses the Google Translate API to convert Japanese text into English. The input data is Japanese text data, and the output data is the text data translated into English.

[0871] Step 6:

[0872] The server uses an emotion engine to recognize the user's emotion when analyzing the voice data. Specifically, it uses the IBM Watson Tone Analyzer API to identify the user's emotion from the text data. The input data is the voice data and text data, and the output data is the recognized emotion tag.

[0873] Step 7:

[0874] The server assigns appropriate emotion tags based on the emotion tags and generates a 3D avatar video based on the emotion tags. Specifically, Unity and Adobe Fuse are used to create a 3D avatar based on the user's emotion, and Amazon Polly is used to synthesize speech. The input data is text data translated into English and emotion tags, and the output data is the generated avatar video.

[0875] Step 8:

[0876] The server sends the generated avatar video to the user's device so that it can be viewed within the smartphone application. Specifically, the video is distributed using AWS CloudFront. The input data is the generated avatar video, and the output data is a video that can be viewed within the user's smartphone application.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] [Third embodiment]

[0881] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0882] 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.

[0883] 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).

[0884] 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.

[0885] 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.

[0886] 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).

[0887] 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. 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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."

[0893] The present invention relates to a system that records a user's actual daily life, analyzes the data, and generates avatar videos in which the data is translated into natural English.

[0894] Program processing overview

[0895] Audio recording and data upload

[0896] User: Wears a watch-type recording device and presses the recording start button. The device starts recording audio. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[0897] Device: Recording data is temporarily stored on the device and then uploaded to a cloud server via the internet once recording is complete.

[0898] Analysis of voice data and conversion to text

[0899] Server: The cloud server uses voice recognition technology to analyze the uploaded voice data and convert it into text data. The user's speech, "It's a nice day today. I have a meeting this afternoon," is converted into text data that reads, "It's a nice day today. I have a meeting this afternoon."

[0900] Server: The converted text data is analyzed using natural language processing technology to extract key conversational content and keywords. Keywords such as "nice weather" and "meeting" are extracted here.

[0901] Replace with appropriate English expressions

[0902] Server: Based on the extracted text data, the server uses machine translation to translate it into an appropriate English expression. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[0903] Server: Applies formal, business casual, or casual presentation level based on user selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0904] Avatar video generation

[0905] Server: Based on the translated text data, a speech synthesis engine is used to generate narration, and a 3D avatar generation engine is used to create an avatar video with appropriate speaking style and facial expressions.

[0906] Server: The generated avatar video is sent to the user's device.

[0907] Customization with the if function

[0908] User: After watching the generated avatar video, the user can input another comment or reply. For example, in response to the comment "I have a meeting in the afternoon," the user can input "What happens if I miss the train?" using the if function.

[0909] Server: Generates additional dialogue scenes based on new input. For example, a new scene might be created such as "It's nice weather today. What if I miss the train?"

[0910] Server: The updated avatar video can be provided to the user again to extend the learning content.

[0911] In this way, this system provides a natural English learning environment based on the user's daily life and can support the learning of a variety of conversational expressions. Users can learn English expressions in real-life situations, realizing efficient and effective learning.

[0912] The processing flow will be explained below.

[0913] Step 1:

[0914] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[0915] Step 2:

[0916] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[0917] Step 3:

[0918] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[0919] Step 4:

[0920] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[0921] Step 5:

[0922] The server then analyzes the converted text data using natural language processing technology to extract key conversational content and keywords, such as "nice weather" and "meeting."

[0923] Step 6:

[0924] The server uses machine translation means to convert the extracted text data into appropriate English expressions.

[0925] Step 7:

[0926] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[0927] Step 8:

[0928] The server generates narration voice using a voice synthesis engine based on the translated text data.

[0929] Step 9:

[0930] The server uses a 3D avatar generation engine to create an avatar video based on the narration voice and text data, and sets the avatar's movements, facial expressions, and speech content.

[0931] Step 10:

[0932] The server transmits the generated avatar animation to the user's terminal.

[0933] Step 11:

[0934] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[0935] Step 12:

[0936] The device sends any new comments or replies that are entered to the server.

[0937] Step 13:

[0938] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[0939] Step 14:

[0940] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[0941] Step 15:

[0942] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[0943] Through the above processing steps, an avatar video for English learning that is suited to the user's daily life is generated, and the learning content can also be customized.

[0944] Example 1

[0945] 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."

[0946] Conventional English learning systems have made it difficult for users to learn efficiently by incorporating the context of their own daily lives. They also lacked a means to convert recorded audio data into appropriate foreign language expressions and provide them to users in a natural format. Furthermore, the system's ability to expand learning content by inputting new utterances and replies was limited. The present invention aims to solve these problems by providing an environment in which users can learn a foreign language in a natural way within their daily lives, thereby enabling them to effectively learn a variety of conversational expressions.

[0947] 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.

[0948] In this invention, the server includes a recording device for recording the user's daily life, means for uploading the recorded voice data to a cloud provider, means for converting the uploaded voice data into text data using voice recognition, means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, means for replacing the extracted text data with appropriate foreign language expressions, means for generating a virtual character video based on the replaced foreign language expressions, means for transmitting the generated virtual character video to the user's device, means for applying an expression level according to a user's selection, and means for synchronizing the virtual character's facial expressions and movements with the voice data. This allows the user to incorporate the context of their own daily life into more natural and effective foreign language learning.

[0949] A "recording device" is a device for recording a user's daily life and has the function of temporarily storing audio data.

[0950] "Cloud provider" is a general term for services that provide remote servers that store and manage audio data uploaded from recording devices.

[0951] "Speech recognition" is a technology that analyzes recorded voice data and converts it into corresponding text data.

[0952] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[0953] "Translation means" refers to a method or technology for converting extracted text data into an appropriate foreign language expression.

[0954] "Virtual character video" is a video in which a 3D character speaking is generated based on translated foreign language expressions.

[0955] "Terminal" means a device operated by a user and used to receive and display virtual character videos.

[0956] "Levels of expression" is a way of distinguishing between different communication styles such as formal, business casual, casual, etc., as selected by the user.

[0957] The "conditional branching function" is a technology that dynamically generates and updates conversation scenes based on new user comments and responses.

[0958] A "speech synthesis engine" is a technology that converts text data into voice data, allowing virtual characters to speak naturally.

[0959] This invention is a system that records a user's daily life, analyzes the data, and generates a virtual character animation that translates it into natural foreign language. This system includes a wide range of technical elements, such as a recording device, speech recognition technology, natural language processing, translation into appropriate foreign language expressions, generation of a virtual character animation, a conditional branching function that inputs and analyzes the user's statements and responses, and a speech synthesis engine.

[0960] Recording devices and data upload

[0961] User: Wears a recording device and presses the start recording button to record sounds from everyday life. The recorded audio data is temporarily stored in the device.

[0962] Specifically, the user says, "It's a nice day today. I have a meeting this afternoon."

[0963] On your device: Once you finish recording, your device will upload the data via your internet connection to a cloud provider, which will then store and manage your audio data.

[0964] Speech Recognition and Natural Language Processing

[0965] Server: The voice data uploaded to the cloud provider is analyzed using speech recognition technology and converted into text data. For example, the Google Cloud Speech-to-Text API is used. After the text conversion, the result is "It's a nice day today. I have a meeting this afternoon."

[0966] Server: The converted text data is analyzed using natural language processing technology to extract the conversation content and keywords. For example, OpenAI's GPT-3 is used. Keywords such as "good weather" and "meeting" are extracted.

[0967] Application of translation means and expression levels

[0968] Server: The extracted text data is replaced with an appropriate foreign language expression using machine translation. Specifically, DeepL or Google Translate is used. For example, "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon."

[0969] Server: Apply presentation level (formal, business casual, casual) based on user selection. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[0970] Virtual character video and voice synthesis

[0971] Server: Generates narration using a speech synthesis engine (e.g., Amazon Polly) based on the translated text data.

[0972] Server: Using a 3D avatar generation engine, a virtual character's animation is generated based on the narration audio. By synchronizing the virtual character's facial expressions and movements with the audio data, a character animation with natural speaking and movement is generated.

[0973] Server: The generated virtual character video is sent to the device and becomes available for viewing by the user.

[0974] Customization with conditional branching

[0975] User: After watching the generated virtual character video, the user can input different statements or responses using the conditional branching function. For example, in response to "I have a meeting in the afternoon," the user can add a question such as "What happens if I miss the train?"

[0976] Server: Generates additional conversation scenes based on new statements and replies, and sends the updated virtual character video back to the user's device.

[0977] An example prompt is:

[0978] User: I have a meeting this afternoon.

[0979] Server: If you miss the train, what will you do?

[0980] This allows users to incorporate the context of their daily lives, making foreign language learning more natural and effective.

[0981] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0982] Step 1:

[0983] Audio recording

[0984] The user puts on the recording device and presses the start recording button.

[0985] Input: User's everyday voice.

[0986] What happens: The device's microphone captures audio and temporarily stores the audio data locally.

[0987] Output: Recorded audio data is obtained.

[0988] Step 2:

[0989] Uploading data

[0990] After the device finishes recording, it uploads the audio data to a cloud provider via its internet connection.

[0991] Input: Recorded audio data in the device.

[0992] What it does: Recordings are sent to a cloud provider via Wi-Fi or mobile data.

[0993] Output: Audio data uploaded to a cloud provider.

[0994] Step 3:

[0995] Voice Recognition

[0996] The server analyzes the voice data uploaded to the cloud provider using voice recognition technology.

[0997] Input: Audio data stored in the cloud.

[0998] Specific operation: A speech recognition engine (e.g., Google Cloud Speech-to-Text API) converts the voice data into text data.

[0999] Output: Text data such as "It's nice weather today. I have a meeting this afternoon."

[1000] Step 4:

[1001] Natural Language Processing

[1002] The server analyzes the converted text data using natural language processing technology and extracts key conversation content and keywords.

[1003] Input: Text data generated by speech recognition.

[1004] How it works: A natural language processing engine (e.g., OpenAI GPT-3) analyzes the meaning and structure of the text and extracts keywords such as "good weather" and "meeting."

[1005] Output: Extracted conversation content and keywords.

[1006] Step 5:

[1007] Machine Translation

[1008] The server uses machine translation means to convert the extracted text data into an appropriate foreign language expression.

[1009] Input: Extracted text data and keywords.

[1010] What happens: A translation engine (e.g., DeepL or Google Translate) translates "It's nice weather today. I have a meeting this afternoon." into "It's nice weather today. I have a meeting this afternoon."

[1011] Output: Text data converted into appropriate foreign language expressions.

[1012] Step 6:

[1013] Applying expression levels

[1014] The server applies an expression level (formal, business casual, casual) to the translated text data according to the user's selection.

[1015] Input: Translated text data.

[1016] Specific Behavior: Changes the presentation style of text data based on the user's settings. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[1017] Output: Text data with the appropriate representation level applied.

[1018] Step 7:

[1019] Speech synthesis

[1020] The server generates narration using a speech synthesis engine based on the translated text data.

[1021] Input: Text data with representation levels applied.

[1022] Specific operation: A speech synthesis engine (e.g., Amazon Polly) converts text data into speech.

[1023] Output: Narration audio data.

[1024] Step 8:

[1025] Virtual character video generation

[1026] The server generates a virtual character video using a 3D avatar generation engine based on the narration voice generated by voice synthesis.

[1027] Input: Narration audio data.

[1028] Specific operation: The 3D avatar generation engine synchronizes with the voice data to create the facial expressions and movements of the virtual character.

[1029] Output: Virtual character video data.

[1030] Step 9:

[1031] Sending videos

[1032] The server transmits the generated virtual character animation to the user's terminal.

[1033] Input: Virtual character video data.

[1034] Specific operation: Video data is transferred to the user's device via the Internet.

[1035] Output: Virtual character video sent to the user's device.

[1036] Step 10:

[1037] Customization with conditional branching

[1038] After viewing the generated virtual character video, the user can input different comments or replies using the conditional branching function.

[1039] Input: The user's new statement or reply.

[1040] Specific behavior: The user creates different scenarios by inputting new utterances through the application.

[1041] Output: New statements and reply data sent to the server.

[1042] Step 11:

[1043] Generate additional scenes

[1044] The server generates a conversation scene based on the new utterances and replies, and provides the updated virtual character animation to the user again.

[1045] Input: New utterances and response data.

[1046] What it does: Synthesizes new scenes and updates the virtual character.

[1047] Output: The updated virtual character animation data is sent to the user's device.

[1048] (Application example 1)

[1049] 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."

[1050] In conventional factories, it is difficult to communicate with international workers, and despite the need for multilingual support, there is a lack of appropriate translation and guidance, making it inefficient. Therefore, a system that enables efficient and natural communication is needed.

[1051] 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.

[1052] In this invention, the server includes a recording device for recording users' daily lives, a means for uploading the recorded voice data to a cloud server, a means for converting the uploaded voice data into text data using speech recognition technology, a means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, a machine translation means for replacing the extracted text data with appropriate English expressions, a means for generating a 3D avatar video based on the replaced English expressions, a means for outputting a voice-synthesized narration to a robot that supports multilingual communication with factory workers, and a means for transmitting the generated avatar video to the user's device, thereby enabling efficient and natural communication with multinational workers in a factory.

[1053] A "recording device" is a device for recording the sounds of a user's daily life or work in a factory.

[1054] A "cloud server" is a remote server that stores and analyzes recorded data via the Internet.

[1055] "Speech recognition technology" is a technology for analyzing recorded voice data and converting it into text data.

[1056] "Natural language processing" is a technology for analyzing text data and extracting conversation content and keywords.

[1057] "Machine translation means" refers to technology for converting extracted text data into appropriate English expressions.

[1058] "3D avatar video" is a video of an avatar in three-dimensional space, generated based on text data translated into English.

[1059] "Voice synthesis narration" is narration that uses voice synthesis technology and is added to 3D avatar videos.

[1060] A "robot that supports multilingual communication" is a robot that supports multilingual communication with workers within a factory.

[1061] A "user's terminal" is a device that can receive and play the generated avatar video.

[1062] The system for implementing the present invention is configured as follows.

[1063] First, a user uses a recording device to record the sounds of their daily life or work in a factory. This recording device captures the user's speech and temporarily stores it within the device. For example, a microphone (e.g., Shure MV88) is used.

[1064] The recorded audio data is then uploaded to a cloud server via the Internet. The cloud server is built using a remote server such as AWS EC2. This server converts the uploaded audio data into text using speech recognition technology. For speech recognition, the speech_recognition library or vosk library is used.

[1065] The converted text data is then analyzed using natural language processing technology to extract conversation content and keywords. This process requires software that uses natural language processing technology. The extracted text data is then converted into appropriate English expressions using the GoogleTrans library.

[1066] Next, a 3D avatar video is generated based on the converted English expressions. This video generation uses a 3D avatar generation engine and a speech synthesis engine (e.g., pyttsx3). This system displays the generated avatar video on factory robots, particularly to support smooth communication among multinational workers in factories. The use of a GPU (e.g., NVIDIA GeForce) enables real-time generation.

[1067] Finally, the generated avatar video is sent to the user's device, which can be a smartphone, tablet, or other device, and can play the avatar video.

[1068] For example:

[1069] If a factory has many foreign workers, the robot can record their conversations and provide appropriate instructions and information in English through an avatar. For example, if a worker asks, "Which process should I do next?", the robot can translate the recording into "What is the next process I should do?" and the avatar can respond appropriately.

[1070] Example prompt sentence:

[1071] When a user asks, "What is the next process I should do?", the program records the voice, converts it to text, and translates it as "What is the next process I should do?" The avatar then displays the appropriate answer.

[1072] As described above, the present invention provides a system that realizes efficient and natural communication with multinational workers in a factory.

[1073] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1074] Step 1:

[1075] A user uses a recording device to record the sounds of work being done in a factory. The input is the user's speech, which is captured by the recording device. Specifically, the user presses the start recording button, and a microphone (e.g., Shure MV88) captures the sound. This generates audio data. The output is the recorded audio data.

[1076] Step 2:

[1077] The recorded audio data is uploaded to a cloud server via the Internet. The input is the audio data stored in the recording device. Specifically, the device transfers the audio data over the Internet to a remote server such as AWS EC2. The output is the audio data stored on the cloud server.

[1078] Step 3:

[1079] The server uses speech recognition technology to convert the uploaded voice data into text data. The input is voice data stored on the cloud server. Specifically, the server analyzes the voice data using the speech_recognition library and vosk library to generate text data. The output is the converted text data.

[1080] Step 4:

[1081] The server analyzes the converted text data using natural language processing technology to extract the conversation content and keywords. The input is text data generated using speech recognition technology. Specifically, it uses natural language processing software for text analysis to extract key keywords from the utterance, "Which step should I take next?" The output is the extracted keywords and the analysis results.

[1082] Step 5:

[1083] The server machine translates the extracted text data into appropriate English expressions. The inputs are the keywords extracted as analysis results and the text data. Specifically, it uses the googletrans library to translate the Japanese text "Which process should I do next?" into the English text "What is the next process I should do?" The output is the translated English text.

[1084] Step 6:

[1085] The server generates a 3D avatar video based on the translated English expressions. The input is the translated English text. Specifically, it generates a narration voice using a speech synthesis engine (e.g., pyttsx3) and creates an avatar video with appropriate dialogue using a 3D avatar generation engine. The output is the generated 3D avatar video.

[1086] Step 7:

[1087] The generated avatar video is sent to a factory robot, which displays the avatar video and outputs a voice-synthesized narration. The input is a 3D avatar video sent from the server. The robot's display and speaker play the avatar video and convey the narration to the user. The output is the avatar video provided to the user and the English narration.

[1088] Step 8:

[1089] By inputting the user's comments and replies into the if function, the new comments and replies are analyzed and additional conversation scenes are generated. The input is the user's new comments and replies. Specifically, the server re-analyzes the new text data and constructs the additional conversation scenes generated by the if function. The output is an updated avatar video.

[1090] 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.

[1091] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video.

[1092] Program processing overview

[1093] Audio recording and data upload

[1094] The user wears the watch-type recording device and presses the recording start button. The device then starts recording the surrounding sounds. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[1095] The device temporarily stores the recorded data within the device, and once recording is complete, uploads the audio data to a cloud server via the Internet.

[1096] Analysis of voice data and conversion to text

[1097] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[1098] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[1099] Replace with appropriate English expressions

[1100] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[1101] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1102] Recognizing user emotions with an emotion engine

[1103] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. For example, if a user says "It's a nice day today," the emotion is recognized as "joy."

[1104] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[1105] Adapting English expressions and avatar expressions according to emotions

[1106] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[1107] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[1108] Avatar video generation and provision

[1109] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[1110] The server transmits the generated avatar animation to the user's terminal.

[1111] Customization with the if function

[1112] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[1113] The device sends any new comments or replies that are entered to the server.

[1114] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[1115] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[1116] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[1117] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[1121] Step 2:

[1122] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[1123] Step 3:

[1124] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[1125] Step 4:

[1126] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[1127] Step 5:

[1128] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[1129] Step 6:

[1130] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[1131] Step 7:

[1132] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1133] Step 8:

[1134] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. If the user says happily, "It's a nice day today," the emotion is recognized as "joy."

[1135] Step 9:

[1136] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[1137] Step 10:

[1138] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[1139] Step 11:

[1140] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[1141] Step 12:

[1142] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[1143] Step 13:

[1144] The server transmits the generated avatar animation to the user's terminal.

[1145] Step 14:

[1146] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[1147] Step 15:

[1148] The device sends any new comments or replies that are entered to the server.

[1149] Step 16:

[1150] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[1151] Step 17:

[1152] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[1153] Step 18:

[1154] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[1155] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[1156] Example 2

[1157] 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."

[1158] In modern society, many people need to learn English, but it is difficult to efficiently acquire practical English conversation skills using traditional teaching methods. Furthermore, because they are unable to teach natural conversations that reflect the user's emotions and situation, they are not effective enough in actual communication. Furthermore, because it is difficult to customize the learning methods to meet the needs of individual learners, there is also the issue of a tendency for motivation to decrease.

[1159] 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.

[1160] In this invention, the server includes means for converting voice data into text data using voice recognition technology, means for analyzing the converted text data using natural language processing technology to extract conversation content and keywords, machine translation means for replacing the extracted text data with appropriate English expressions, emotion analysis means for analyzing the voice data and recognizing the user's emotions, means for adapting English expressions containing emotions and avatar expressions, means for generating 3D avatar video based on the replaced English expressions, and means for transmitting the generated 3D avatar video to the user's terminal. This allows the user to learn natural English conversation that is suited to their daily life, enabling flexible and practical learning that is tailored to the user's emotions and situations.

[1161] An "audio collection device" is a device that allows a user to record audio from their daily life, and includes wristwatch-type devices and dedicated recording devices.

[1162] "Via the network" refers to a method of transmitting audio data to a cloud server using the Internet or other communication networks.

[1163] A "cloud server" is a remote server that stores and processes data over the Internet.

[1164] "Speech recognition technology" is a technology that analyzes voice data and converts it into text data, and generally uses a voice recognition engine.

[1165] "Text data" refers to digital text information converted using voice recognition technology.

[1166] "Natural language processing technology" is a technology that analyzes the content of text data and extracts meaning and keywords.

[1167] "Machine translation means" is a technology for translating text data into another language, and generally uses a translation engine.

[1168] "Emotion analysis means" is a technology that recognizes a user's emotions from voice and text data.

[1169] An "emotion identification tag" is a tag that indicates the user's emotion, and includes an identifier such as "joy" or "anger."

[1170] "3D avatar video" is a three-dimensional character video generated based on the user's voice and text.

[1171] A "voice synthesis engine" is a technology for converting text data into voice data.

[1172] The "if function" allows the user to input a different statement or response and have it reflected in the system.

[1173] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the user's speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video. This system enables users to study English more realistically and effectively.

[1174] This system uses the following hardware and software: A wristwatch-type device or a dedicated recording device is used as the voice collection device used by the user. The voice data is transmitted over the Internet, and a common cloud storage service (e.g., Amazon Web Services' S3 bucket or Google Cloud Storage) is used as the cloud server.

[1175] Audio recording and data upload

[1176] A user puts on the audio collection device and starts recording. For example, the user might say, "It's a nice day today. I have a meeting this afternoon." The recording device captures this audio, and the device temporarily stores the recorded audio data. The device then uploads the audio data to a cloud server via an internet connection.

[1177] Analysis of voice data and conversion to text

[1178] The uploaded voice data is stored on a cloud server. The server then uses a speech recognition engine such as Google Cloud Speech-to-Text or IBM Watson to convert the voice data into text data. For example, a speech that says, "It's a nice day today. I have a meeting this afternoon" is converted into text format.

[1179] Text analysis using natural language processing

[1180] The server analyzes the text data using natural language processing (NLP) technology to extract the conversation content and keywords. This analysis can be performed using OpenAI's GPT-3 or SpaCy. For example, "good weather" and "meeting" are extracted as keywords.

[1181] Replace with appropriate English expressions

[1182] Based on the extracted text data, the server uses machine translation tools (such as Google Translate API or DeepL API) to translate the text into appropriate English expressions. For example, the text "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon." The server also applies expression levels such as formal, business casual, and casual according to the user's selection.

[1183] Recognizing user emotions with an emotion engine

[1184] The server analyzes the voice data using an emotion engine (such as Microsoft Azure's Emotion API or AWS's Comprehend) to recognize the user's emotion. For example, if a user says happily, "It's a nice day today," the emotion is recognized as "joy." Based on the recognized emotion, an emotion tag such as "joy" is assigned to the text data.

[1185] Adapting English expressions and avatar expressions according to emotions

[1186] The server adapts the English expressions and avatar facial expressions based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the server configures the avatar to speak with a smile. A speech synthesis engine (Amazon Polly or Google Text-to-Speech) is then used to generate a narration voice appropriate to the emotion.

[1187] Avatar video generation and provision

[1188] Based on this narration audio and text data, the server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video. The generated avatar video is then sent to the user's device, where the user can watch the video on their smartphone, tablet, or PC.

[1189] Customization with the if function

[1190] The user can use the if function to input a different statement or response. For example, they can input "What happens if I miss the train?" The device sends the new statement or response to the server, which analyzes it with a speech recognition engine and generates new text data. Based on this, additional conversation scenes are generated and the narration audio and avatar video are updated. The updated avatar video is then sent back to the user's device and can be viewed.

[1191] An example of a prompt is:

[1192] "Text extracted from everyday audio recordings: 'It's nice weather today. I have a meeting this afternoon.'"

[1193] "Example translation: 'It's nice weather today. I have a meeting this afternoon.'"

[1194] Examples include "Emotion tag: 'joy'".

[1195] In this way, the system generates avatar videos for English learning that are in line with the user's daily life and provides expressions that correspond to emotions, thereby realizing more practical and effective English learning.

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

[1197] Step 1: Start recording and collect audio data

[1198] Input: User's everyday conversational voice

[1199] How it works: A user puts on a wristwatch-style audio collection device and presses the record button. The device begins collecting sounds from the surrounding area.

[1200] Data processing / calculation: Recording devices capture audio as digital data and temporarily store that data in their internal memory.

[1201] Output: Collected audio data

[1202] Step 2: Upload your audio data

[1203] Input: Collected audio data

[1204] How it works: The device establishes an internet connection and sends the audio data stored in its internal memory to a cloud server.

[1205] Data processing / calculation: Data compression and transfer

[1206] Output: Audio data stored on a cloud server

[1207] Step 3: Convert audio data to text

[1208] Input: Audio data on a cloud server

[1209] How it works: The server uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to analyze the audio data and convert it into text data.

[1210] Data processing / calculation: Analysis of voice signals and conversion to text information

[1211] Output: Converted text data (e.g. "It's a nice day today. I have a meeting this afternoon.")

[1212] Step 4: Analyzing text data and extracting keywords

[1213] Input: Converted text data

[1214] How it works: The server uses natural language processing (NLP) to analyze the text and extract key conversation topics and keywords (e.g., "nice weather" and "meeting").

[1215] Data processing / calculation: Text analysis and keyword extraction

[1216] Output: Extracted keywords

[1217] Step 5: Translating the text data

[1218] Input: Extracted text data

[1219] How it works: The server uses a machine translation engine (e.g., Google Translate API) to translate the extracted text data into appropriate English expressions.

[1220] Data processing / calculation: Translation of text data

[1221] Output: English text (e.g., "It's nice weather today. I have a meeting this afternoon.")

[1222] Step 6: Sentiment analysis and tagging

[1223] Input: Translated English text and original audio data

[1224] How it works: The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API) to recognize the user's emotion and assign an appropriate emotion tag (e.g., "joy").

[1225] Data processing / computation: sentiment analysis and tagging

[1226] Output: English text with sentiment tags

[1227] Step 7: Generate narration audio

[1228] Input: English text with sentiment tags

[1229] How it works: The server uses a speech synthesis engine (Amazon Polly or Google Text-to-Speech) to generate narration voice based on the emotion.

[1230] Data processing / calculation: Convert text data into audio data

[1231] Output: Generated narration audio

[1232] Step 8: Generate avatar video

[1233] Input: English text and narration audio

[1234] How it works: The server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video based on the text and audio. The avatar's movements and facial expressions are also set here.

[1235] Data processing / calculation: Avatar video generation

[1236] Output: Generated 3D avatar video

[1237] Step 9: Submit your avatar video

[1238] Input: Generated 3D avatar video

[1239] How it works: The server sends the generated avatar video to the user's device.

[1240] Data processing / calculation: Data compression and transfer

[1241] Output: Avatar video on user's device

[1242] Step 10: Customizing with the if function

[1243] Input: New user comments or responses

[1244] How it works: The user uses the if function to input a new comment or reply, and the device sends it to the server. The server then uses a speech recognition engine to analyze the new input and generate text data.

[1245] Data processing / calculation: generating and analyzing new text data

[1246] Output: New text data and updated avatar video

[1247] In this way, the system learns natural English conversation that is suited to the user's daily life, providing flexible and practical learning that is tailored to the user's emotions and circumstances.

[1248] (Application example 2)

[1249] 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."

[1250] Conventional online shopping sites require users to enter information such as the products they want, their budget, and preferences in a text-based format, making them difficult to use, especially for elderly users and those unfamiliar with technology. Furthermore, it is difficult to understand the user's emotions when searching for products, limiting the amount of personalized advice and suggestions they can provide. Furthermore, automated user support using voice data is also insufficient. To address these issues, a system is needed that analyzes users' voices and emotions and uses 3D avatars to provide advice and suggestions tailored to individual needs.

[1251] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1252] In this invention, the server includes a means for recognizing a user's emotion, a means for assigning an emotion tag based on the recognized emotion and generating a 3D avatar video based on the emotion tag, and a means for transmitting the generated avatar video to the user's device so that the avatar video can be viewed within a smartphone application, thereby enabling the user to receive personalized advice and suggestions based on their own emotions and needs.

[1253] A "recording device" is a device that allows a user to record their daily life.

[1254] A "cloud server" is a remote server for storing and processing data over the Internet.

[1255] "Speech recognition technology" is a technology that converts voice data into text data.

[1256] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[1257] "Machine translation means" refers to technology that automatically translates text data from one language to another.

[1258] "Emotion recognition means" is a technology that analyzes emotions from the user's voice and identifies those emotions.

[1259] An "emotion tag" is a tag that indicates an emotion identified by an emotion recognition means.

[1260] "3D avatar video" is a video of a three-dimensional person or character that responds to the user's conversation and emotions.

[1261] A "user terminal" is an information processing device such as a computer, smartphone, or tablet that is used by a user.

[1262] A "smartphone application" is a software program that runs on a smartphone.

[1263] The "if function" is a function that allows you to input user comments and responses and generate new scenarios.

[1264] A "speech synthesis engine" is a technology that converts text data into speech.

[1265] "Formal, business casual, and casual levels of expression" are styles of expression that can be selected according to different situations and uses.

[1266] The system for realizing this application example operates in the following steps.

[1267] Overview of program processing

[1268] 1. Audio recording and data upload

[1269] When a user starts recording their daily life, audio is recorded using a smartphone or a dedicated recording device. This audio data is then uploaded to a cloud server, which contains a database for temporarily storing the audio data. The audio data is uploaded via network communication.

[1270] 2. Analysis of voice data and conversion to text

[1271] The cloud server converts the uploaded voice data into text data using speech recognition technology. The Google Cloud Speech-to-Text API is used for speech recognition. This API has the ability to convert voice data into text data with high accuracy.

[1272] 3. Natural Language Processing and Machine Translation

[1273] The converted text data is analyzed using natural language processing technology to extract conversation content and keywords. This process uses a natural language processing (NLP) library. The extracted text data is then machine-translated into appropriate English expressions using the Google Translate API.

[1274] 4. Emotion Recognition and Emotion Tagging

[1275] The server uses the IBM Watson Tone Analyzer API to recognize the user's emotions from the voice data. This allows the server to assign an emotion tag based on what the user says. The emotion tag indicates a specific emotional state, such as "joy," "sadness," or "surprise."

[1276] 5. 3D avatar video generation and provision

[1277] Based on the recognized emotion tags, a 3D avatar video is generated based on the emotion. The 3D avatar is created using a 3D model generation engine such as Unity or Adobe Fuse. The voice in the avatar video is generated using a speech synthesis engine such as Amazon Polly.

[1278] 6. Video distribution to smartphone applications

[1279] The generated avatar video is delivered to the user's smartphone application via AWS CloudFront, where the user can watch the avatar's responses to their questions.

[1280] The hardware and software that runs the program

[1281] Smartphones or dedicated recording devices are used for the initial recording process. AWS S3 or a database is used to store and process the recorded data. Google Cloud Speech-to-Text API is used for speech recognition, NLP libraries and Google Translate API for natural language processing and machine translation. IBM Watson Tone Analyzer API is used for emotion recognition, Unity or Adobe Fuse for 3D avatar generation, and Amazon Polly for speech synthesis. AWS CloudFront is used for final video distribution.

[1282] Examples and prompts

[1283] For example, consider the case where a user says, "I want new shoes, but I'm not sure which ones to get." This voice data is recorded and uploaded to a cloud server. Then, using speech recognition technology, it is converted into text data: "I want new shoes, but I'm not sure which ones to get." This text data is analyzed using natural language processing, and keywords such as "new shoes" and "confused" are extracted. The text data is then translated into English using the Google Translate API, resulting in "I want new shoes, but I am confused about which one to choose." Next, the user's emotion is recognized as "confused" by IBM Watson Tone Analyzer, and that emotion tag is assigned. Based on the emotion tag "confused," a video is generated in which an avatar suggests in English, "Here are some popular shoes that might match your taste," and the video is delivered to the user's app via AWS CloudFront.

[1284] In this way, the system provides personalized shopping advice based on the user's voice input and emotion recognition.

[1285] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1286] Step 1:

[1287] Users record sounds from their daily lives using a smartphone or a dedicated recording device. When the user presses the "Start Recording" button, the device begins to record the surrounding sounds. The input data is the audio data of the user's daily conversation, and this is temporarily saved on the device as output data.

[1288] Step 2:

[1289] When recording is complete, the device uploads the recorded audio data to the cloud server. When the user presses the "Stop Recording" button, the audio data temporarily stored on the device is sent to the cloud server via the Internet. The input data is the recorded audio data, which is then saved on the cloud server as output data.

[1290] Step 3:

[1291] The server receives the voice data uploaded to the cloud server and analyzes it using speech recognition technology. Specifically, it converts the voice data into text data using the Google Cloud Speech-to-Text API. The input data is the voice data on the cloud server, and the output data is the converted text data.

[1292] Step 4:

[1293] The server analyzes the converted text data using natural language processing technology to extract key conversational content and keywords. Specifically, it uses a natural language processing (NLP) library to identify keywords and important phrases. The input data is text data, and the output data is the extracted conversational content and keywords.

[1294] Step 5:

[1295] The server uses machine translation to convert the extracted text data into appropriate English expressions. Specifically, it uses the Google Translate API to convert Japanese text into English. The input data is Japanese text data, and the output data is the text data translated into English.

[1296] Step 6:

[1297] The server uses an emotion engine to recognize the user's emotion when analyzing the voice data. Specifically, it uses the IBM Watson Tone Analyzer API to identify the user's emotion from the text data. The input data is the voice data and text data, and the output data is the recognized emotion tag.

[1298] Step 7:

[1299] The server assigns appropriate emotion tags based on the emotion tags and generates a 3D avatar video based on the emotion tags. Specifically, Unity and Adobe Fuse are used to create a 3D avatar based on the user's emotion, and Amazon Polly is used to synthesize speech. The input data is text data translated into English and emotion tags, and the output data is the generated avatar video.

[1300] Step 8:

[1301] The server sends the generated avatar video to the user's device so that it can be viewed within the smartphone application. Specifically, the video is distributed using AWS CloudFront. The input data is the generated avatar video, and the output data is a video that can be viewed within the user's smartphone application.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] [Fourth embodiment]

[1306] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1307] 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.

[1308] 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).

[1309] 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.

[1310] 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.

[1311] 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).

[1312] 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. 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.

[1313] 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.

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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."

[1319] The present invention relates to a system that records a user's actual daily life, analyzes the data, and generates avatar videos in which the data is translated into natural English.

[1320] Program processing overview

[1321] Audio recording and data upload

[1322] User: Wears a watch-type recording device and presses the recording start button. The device starts recording audio. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[1323] Device: Recording data is temporarily stored on the device and then uploaded to a cloud server via the internet once recording is complete.

[1324] Analysis of voice data and conversion to text

[1325] Server: The cloud server uses voice recognition technology to analyze the uploaded voice data and convert it into text data. The user's speech, "It's a nice day today. I have a meeting this afternoon," is converted into text data that reads, "It's a nice day today. I have a meeting this afternoon."

[1326] Server: The converted text data is analyzed using natural language processing technology to extract key conversational content and keywords. Keywords such as "nice weather" and "meeting" are extracted here.

[1327] Replace with appropriate English expressions

[1328] Server: Based on the extracted text data, the server uses machine translation to translate it into an appropriate English expression. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[1329] Server: Applies formal, business casual, or casual presentation level based on user selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1330] Avatar video generation

[1331] Server: Based on the translated text data, a speech synthesis engine is used to generate narration, and a 3D avatar generation engine is used to create an avatar video with appropriate speaking style and facial expressions.

[1332] Server: The generated avatar video is sent to the user's device.

[1333] Customization with the if function

[1334] User: After watching the generated avatar video, the user can input another comment or reply. For example, in response to the comment "I have a meeting in the afternoon," the user can input "What happens if I miss the train?" using the if function.

[1335] Server: Generates additional dialogue scenes based on new input. For example, a new scene might be created such as "It's nice weather today. What if I miss the train?"

[1336] Server: The updated avatar video can be provided to the user again to extend the learning content.

[1337] In this way, this system provides a natural English learning environment based on the user's daily life and can support the learning of a variety of conversational expressions. Users can learn English expressions in real-life situations, realizing efficient and effective learning.

[1338] The processing flow will be explained below.

[1339] Step 1:

[1340] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[1341] Step 2:

[1342] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[1343] Step 3:

[1344] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[1345] Step 4:

[1346] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[1347] Step 5:

[1348] The server then analyzes the converted text data using natural language processing technology to extract key conversational content and keywords, such as "nice weather" and "meeting."

[1349] Step 6:

[1350] The server uses machine translation means to convert the extracted text data into appropriate English expressions.

[1351] Step 7:

[1352] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1353] Step 8:

[1354] The server generates narration voice using a voice synthesis engine based on the translated text data.

[1355] Step 9:

[1356] The server uses a 3D avatar generation engine to create an avatar video based on the narration voice and text data, and sets the avatar's movements, facial expressions, and speech content.

[1357] Step 10:

[1358] The server transmits the generated avatar animation to the user's terminal.

[1359] Step 11:

[1360] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[1361] Step 12:

[1362] The device sends any new comments or replies that are entered to the server.

[1363] Step 13:

[1364] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[1365] Step 14:

[1366] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[1367] Step 15:

[1368] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[1369] Through the above processing steps, an avatar video for English learning that is suited to the user's daily life is generated, and the learning content can also be customized.

[1370] Example 1

[1371] 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."

[1372] Conventional English learning systems have made it difficult for users to learn efficiently by incorporating the context of their own daily lives. They also lacked a means to convert recorded audio data into appropriate foreign language expressions and provide them to users in a natural format. Furthermore, the system's ability to expand learning content by inputting new utterances and replies was limited. The present invention aims to solve these problems by providing an environment in which users can learn a foreign language in a natural way within their daily lives, thereby enabling them to effectively learn a variety of conversational expressions.

[1373] 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.

[1374] In this invention, the server includes a recording device for recording the user's daily life, means for uploading the recorded voice data to a cloud provider, means for converting the uploaded voice data into text data using voice recognition, means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, means for replacing the extracted text data with appropriate foreign language expressions, means for generating a virtual character video based on the replaced foreign language expressions, means for transmitting the generated virtual character video to the user's device, means for applying an expression level according to a user's selection, and means for synchronizing the virtual character's facial expressions and movements with the voice data. This allows the user to incorporate the context of their own daily life into more natural and effective foreign language learning.

[1375] A "recording device" is a device for recording a user's daily life and has the function of temporarily storing audio data.

[1376] "Cloud provider" is a general term for services that provide remote servers that store and manage audio data uploaded from recording devices.

[1377] "Speech recognition" is a technology that analyzes recorded voice data and converts it into corresponding text data.

[1378] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[1379] "Translation means" refers to a method or technology for converting extracted text data into an appropriate foreign language expression.

[1380] "Virtual character video" is a video in which a 3D character speaking is generated based on translated foreign language expressions.

[1381] "Terminal" means a device operated by a user and used to receive and display virtual character videos.

[1382] "Levels of expression" is a way of distinguishing between different communication styles such as formal, business casual, casual, etc., as selected by the user.

[1383] The "conditional branching function" is a technology that dynamically generates and updates conversation scenes based on new user comments and responses.

[1384] A "speech synthesis engine" is a technology that converts text data into voice data, allowing virtual characters to speak naturally.

[1385] This invention is a system that records a user's daily life, analyzes the data, and generates a virtual character animation that translates it into natural foreign language. This system includes a wide range of technical elements, such as a recording device, speech recognition technology, natural language processing, translation into appropriate foreign language expressions, generation of a virtual character animation, a conditional branching function that inputs and analyzes the user's statements and responses, and a speech synthesis engine.

[1386] Recording devices and data upload

[1387] User: Wears a recording device and presses the start recording button to record sounds from everyday life. The recorded audio data is temporarily stored in the device.

[1388] Specifically, the user says, "It's a nice day today. I have a meeting this afternoon."

[1389] On your device: Once you finish recording, your device will upload the data via your internet connection to a cloud provider, which will then store and manage your audio data.

[1390] Speech Recognition and Natural Language Processing

[1391] Server: The voice data uploaded to the cloud provider is analyzed using speech recognition technology and converted into text data. For example, the Google Cloud Speech-to-Text API is used. After the text conversion, the result is "It's a nice day today. I have a meeting this afternoon."

[1392] Server: The converted text data is analyzed using natural language processing technology to extract the conversation content and keywords. For example, OpenAI's GPT-3 is used. Keywords such as "good weather" and "meeting" are extracted.

[1393] Application of translation means and expression levels

[1394] Server: The extracted text data is replaced with an appropriate foreign language expression using machine translation. Specifically, DeepL or Google Translate is used. For example, "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon."

[1395] Server: Apply presentation level (formal, business casual, casual) based on user selection. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[1396] Virtual character video and voice synthesis

[1397] Server: Generates narration using a speech synthesis engine (e.g., Amazon Polly) based on the translated text data.

[1398] Server: Using a 3D avatar generation engine, a virtual character's animation is generated based on the narration audio. By synchronizing the virtual character's facial expressions and movements with the audio data, a character animation with natural speaking and movement is generated.

[1399] Server: The generated virtual character video is sent to the device and becomes available for viewing by the user.

[1400] Customization with conditional branching

[1401] User: After watching the generated virtual character video, the user can input different statements or responses using the conditional branching function. For example, in response to "I have a meeting in the afternoon," the user can add a question such as "What happens if I miss the train?"

[1402] Server: Generates additional conversation scenes based on new statements and replies, and sends the updated virtual character video back to the user's device.

[1403] An example prompt is:

[1404] User: I have a meeting this afternoon.

[1405] Server: If you miss the train, what will you do?

[1406] This allows users to incorporate the context of their daily lives, making foreign language learning more natural and effective.

[1407] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1408] Step 1:

[1409] Audio recording

[1410] The user puts on the recording device and presses the start recording button.

[1411] Input: User's everyday voice.

[1412] What happens: The device's microphone captures audio and temporarily stores the audio data locally.

[1413] Output: Recorded audio data is obtained.

[1414] Step 2:

[1415] Uploading data

[1416] After the device finishes recording, it uploads the audio data to a cloud provider via its internet connection.

[1417] Input: Recorded audio data in the device.

[1418] What it does: Recordings are sent to a cloud provider via Wi-Fi or mobile data.

[1419] Output: Audio data uploaded to a cloud provider.

[1420] Step 3:

[1421] Voice Recognition

[1422] The server analyzes the voice data uploaded to the cloud provider using voice recognition technology.

[1423] Input: Audio data stored in the cloud.

[1424] Specific operation: A speech recognition engine (e.g., Google Cloud Speech-to-Text API) converts the voice data into text data.

[1425] Output: Text data such as "It's nice weather today. I have a meeting this afternoon."

[1426] Step 4:

[1427] Natural Language Processing

[1428] The server analyzes the converted text data using natural language processing technology and extracts key conversation content and keywords.

[1429] Input: Text data generated by speech recognition.

[1430] How it works: A natural language processing engine (e.g., OpenAI GPT-3) analyzes the meaning and structure of the text and extracts keywords such as "good weather" and "meeting."

[1431] Output: Extracted conversation content and keywords.

[1432] Step 5:

[1433] Machine Translation

[1434] The server uses machine translation means to convert the extracted text data into an appropriate foreign language expression.

[1435] Input: Extracted text data and keywords.

[1436] What happens: A translation engine (e.g., DeepL or Google Translate) translates "It's nice weather today. I have a meeting this afternoon." into "It's nice weather today. I have a meeting this afternoon."

[1437] Output: Text data converted into appropriate foreign language expressions.

[1438] Step 6:

[1439] Applying expression levels

[1440] The server applies an expression level (formal, business casual, casual) to the translated text data according to the user's selection.

[1441] Input: Translated text data.

[1442] Specific Behavior: Changes the presentation style of text data based on the user's settings. If business casual is selected, "It's nice weather today. I have a meeting this afternoon." is used.

[1443] Output: Text data with the appropriate representation level applied.

[1444] Step 7:

[1445] Speech synthesis

[1446] The server generates narration using a speech synthesis engine based on the translated text data.

[1447] Input: Text data with representation levels applied.

[1448] Specific operation: A speech synthesis engine (e.g., Amazon Polly) converts text data into speech.

[1449] Output: Narration audio data.

[1450] Step 8:

[1451] Virtual character video generation

[1452] The server generates a virtual character video using a 3D avatar generation engine based on the narration voice generated by voice synthesis.

[1453] Input: Narration audio data.

[1454] Specific operation: The 3D avatar generation engine synchronizes with the voice data to create the facial expressions and movements of the virtual character.

[1455] Output: Virtual character video data.

[1456] Step 9:

[1457] Sending videos

[1458] The server transmits the generated virtual character animation to the user's terminal.

[1459] Input: Virtual character video data.

[1460] Specific operation: Video data is transferred to the user's device via the Internet.

[1461] Output: Virtual character video sent to the user's device.

[1462] Step 10:

[1463] Customization with conditional branching

[1464] After viewing the generated virtual character video, the user can input different comments or replies using the conditional branching function.

[1465] Input: The user's new statement or reply.

[1466] Specific behavior: The user creates different scenarios by inputting new utterances through the application.

[1467] Output: New statements and reply data sent to the server.

[1468] Step 11:

[1469] Generate additional scenes

[1470] The server generates a conversation scene based on the new utterances and replies, and provides the updated virtual character animation to the user again.

[1471] Input: New utterances and response data.

[1472] What it does: Synthesizes new scenes and updates the virtual character.

[1473] Output: The updated virtual character animation data is sent to the user's device.

[1474] (Application example 1)

[1475] 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."

[1476] In conventional factories, it is difficult to communicate with international workers, and despite the need for multilingual support, there is a lack of appropriate translation and guidance, making it inefficient. Therefore, a system that enables efficient and natural communication is needed.

[1477] 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.

[1478] In this invention, the server includes a recording device for recording users' daily lives, a means for uploading the recorded voice data to a cloud server, a means for converting the uploaded voice data into text data using speech recognition technology, a means for analyzing the converted text data using natural language processing and extracting conversation content and keywords, a machine translation means for replacing the extracted text data with appropriate English expressions, a means for generating a 3D avatar video based on the replaced English expressions, a means for outputting a voice-synthesized narration to a robot that supports multilingual communication with factory workers, and a means for transmitting the generated avatar video to a user's device, thereby enabling efficient and natural communication with multinational workers in a factory.

[1479] A "recording device" is a device for recording the sounds of a user's daily life or work in a factory.

[1480] A "cloud server" is a remote server that stores and analyzes recorded data via the Internet.

[1481] "Speech recognition technology" is a technology for analyzing recorded voice data and converting it into text data.

[1482] "Natural language processing" is a technology for analyzing text data and extracting conversation content and keywords.

[1483] "Machine translation means" refers to technology for converting extracted text data into appropriate English expressions.

[1484] "3D avatar video" is a video of an avatar in three-dimensional space, generated based on text data translated into English.

[1485] "Voice synthesis narration" is narration that uses voice synthesis technology and is added to 3D avatar videos.

[1486] A "robot that supports multilingual communication" is a robot that supports multilingual communication with workers within a factory.

[1487] A "user's terminal" is a device that can receive and play the generated avatar video.

[1488] The system for implementing the present invention is configured as follows.

[1489] First, a user uses a recording device to record the sounds of their daily life or work in a factory. This recording device captures the user's speech and temporarily stores it within the device. For example, a microphone (e.g., Shure MV88) is used.

[1490] The recorded audio data is then uploaded to a cloud server via the Internet. The cloud server is built using a remote server such as AWS EC2. This server converts the uploaded audio data into text using speech recognition technology. For speech recognition, the speech_recognition library or vosk library is used.

[1491] The converted text data is then analyzed using natural language processing technology to extract conversation content and keywords. This process requires software that uses natural language processing technology. The extracted text data is then converted into appropriate English expressions using the GoogleTrans library.

[1492] Next, a 3D avatar video is generated based on the converted English expressions. This video generation uses a 3D avatar generation engine and a speech synthesis engine (e.g., pyttsx3). This system displays the generated avatar video on factory robots, particularly to support smooth communication among multinational workers in factories. The use of a GPU (e.g., NVIDIA GeForce) enables real-time generation.

[1493] Finally, the generated avatar video is sent to the user's device, which can be a smartphone, tablet, or other device, and can play the avatar video.

[1494] For example:

[1495] If a factory has many foreign workers, the robot can record their conversations and provide appropriate instructions and information in English through an avatar. For example, if a worker asks, "Which process should I do next?", the robot can translate the recording into "What is the next process I should do?" and the avatar can respond appropriately.

[1496] Example prompt sentence:

[1497] When a user asks, "What is the next process I should do?", the program records the voice, converts it to text, and translates it as "What is the next process I should do?" The avatar then displays the appropriate answer.

[1498] As described above, the present invention provides a system that realizes efficient and natural communication with multinational workers in a factory.

[1499] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1500] Step 1:

[1501] A user uses a recording device to record the sounds of work being done in a factory. The input is the user's speech, which is captured by the recording device. Specifically, the user presses the start recording button, and a microphone (e.g., Shure MV88) captures the sound. This generates audio data. The output is the recorded audio data.

[1502] Step 2:

[1503] The recorded audio data is uploaded to a cloud server via the Internet. The input is the audio data stored in the recording device. Specifically, the device transfers the audio data over the Internet to a remote server such as AWS EC2. The output is the audio data stored on the cloud server.

[1504] Step 3:

[1505] The server uses speech recognition technology to convert the uploaded voice data into text data. The input is voice data stored on the cloud server. Specifically, the server analyzes the voice data using the speech_recognition library and vosk library to generate text data. The output is the converted text data.

[1506] Step 4:

[1507] The server analyzes the converted text data using natural language processing technology to extract the conversation content and keywords. The input is text data generated using speech recognition technology. Specifically, it uses natural language processing software for text analysis to extract key keywords from the utterance, "Which step should I take next?" The output is the extracted keywords and the analysis results.

[1508] Step 5:

[1509] The server machine translates the extracted text data into appropriate English expressions. The inputs are the keywords extracted as analysis results and the text data. Specifically, it uses the googletrans library to translate the Japanese text "Which process should I do next?" into the English text "What is the next process I should do?" The output is the translated English text.

[1510] Step 6:

[1511] The server generates a 3D avatar video based on the translated English expressions. The input is the translated English text. Specifically, it generates a narration voice using a speech synthesis engine (e.g., pyttsx3) and creates an avatar video with appropriate dialogue using a 3D avatar generation engine. The output is the generated 3D avatar video.

[1512] Step 7:

[1513] The generated avatar video is sent to a factory robot, which displays the avatar video and outputs a voice-synthesized narration. The input is a 3D avatar video sent from the server. The robot's display and speaker play the avatar video and convey the narration to the user. The output is the avatar video provided to the user and the English narration.

[1514] Step 8:

[1515] By inputting the user's comments and replies into the if function, the new comments and replies are analyzed and additional conversation scenes are generated. The input is the user's new comments and replies. Specifically, the server re-analyzes the new text data and constructs the additional conversation scenes generated by the if function. The output is an updated avatar video.

[1516] 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.

[1517] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video.

[1518] Program processing overview

[1519] Audio recording and data upload

[1520] The user wears the watch-type recording device and presses the recording start button. The device then starts recording the surrounding sounds. For example, the user might say, "It's a nice day today. I have a meeting this afternoon."

[1521] The device temporarily stores the recorded data within the device, and once recording is complete, uploads the audio data to a cloud server via the Internet.

[1522] Analysis of voice data and conversion to text

[1523] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[1524] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[1525] Replace with appropriate English expressions

[1526] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[1527] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1528] Recognizing user emotions with an emotion engine

[1529] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. For example, if a user says "It's a nice day today," the emotion is recognized as "joy."

[1530] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[1531] Adapting English expressions and avatar expressions according to emotions

[1532] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[1533] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[1534] Avatar video generation and provision

[1535] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[1536] The server transmits the generated avatar animation to the user's terminal.

[1537] Customization with the if function

[1538] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[1539] The device sends any new comments or replies that are entered to the server.

[1540] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[1541] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[1542] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[1543] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[1544] The processing flow will be explained below.

[1545] Step 1:

[1546] The user wears the watch-type recording device and presses the start recording button, which causes the device to begin recording the surrounding sounds.

[1547] Step 2:

[1548] The device temporarily stores the recording, for example, if a user says, "It's a nice day today. I have a meeting this afternoon."

[1549] Step 3:

[1550] Once recording is complete, the device uploads the audio data to a cloud server via the Internet.

[1551] Step 4:

[1552] The server receives the voice data uploaded to the cloud server and analyzes it using voice recognition technology, which converts the voice data into text data.

[1553] Step 5:

[1554] The server then uses natural language processing technology to analyze the converted text data and extract key conversational content and keywords. For example, from an utterance such as "It's nice weather today. I have a meeting this afternoon," the keywords "nice weather" and "meeting" are extracted.

[1555] Step 6:

[1556] The server uses machine translation to translate the extracted text data into appropriate English expressions. For example, "It's nice weather today. I have a meeting this afternoon." is translated into "It's nice weather today. I have a meeting this afternoon."

[1557] Step 7:

[1558] The server applies the following levels of formal, business casual, and casual depending on the user's selection. For business casual, "It's nice weather today. I have a meeting this afternoon." is used.

[1559] Step 8:

[1560] The server uses an emotion engine to analyze the voice data and recognize the user's emotion. If the user says happily, "It's a nice day today," the emotion is recognized as "joy."

[1561] Step 9:

[1562] The server assigns an appropriate emotion tag based on the recognized emotion. For example, if "joy" is recognized, the emotion tag "joy" is assigned to the text data.

[1563] Step 10:

[1564] The server adapts the English expressions and facial expressions of the avatar based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the avatar will be set to speak with a smile.

[1565] Step 11:

[1566] The server again uses the voice synthesis engine to generate a narration voice according to the emotion.

[1567] Step 12:

[1568] The server uses a 3D avatar generation engine to create an avatar video based on the text data and narration audio, and sets the avatar's movements, facial expressions, and speech content.

[1569] Step 13:

[1570] The server transmits the generated avatar animation to the user's terminal.

[1571] Step 14:

[1572] The user watches the received avatar video, and if they want to try a different statement or response, they can use the if function to input a new statement or response, for example, "What happens if I miss the train?"

[1573] Step 15:

[1574] The device sends any new comments or replies that are entered to the server.

[1575] Step 16:

[1576] The server analyzes new statements and responses using a voice recognition engine and converts them into text data.

[1577] Step 17:

[1578] The server generates additional conversation scenes based on the new text data and updates the narration audio and avatar video.

[1579] Step 18:

[1580] The server transmits the updated avatar video to the user's terminal so that the user can view it.

[1581] In this way, this system generates avatar videos for English learning that are in line with the user's daily life, recognizes the user's emotions, and adapts expressions accordingly, providing a more realistic and practical English learning experience.

[1582] Example 2

[1583] 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."

[1584] In modern society, many people need to learn English, but it is difficult to efficiently acquire practical English conversation skills using traditional teaching methods. Furthermore, because they are unable to teach natural conversations that reflect the user's emotions and situation, they are not effective enough in actual communication. Furthermore, because it is difficult to customize the learning methods to meet the needs of individual learners, there is also the issue of a tendency for motivation to decrease.

[1585] 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.

[1586] In this invention, the server includes means for converting voice data into text data using voice recognition technology, means for analyzing the converted text data using natural language processing technology to extract conversation content and keywords, machine translation means for replacing the extracted text data with appropriate English expressions, emotion analysis means for analyzing the voice data and recognizing the user's emotions, means for adapting English expressions containing emotions and avatar expressions, means for generating 3D avatar video based on the replaced English expressions, and means for transmitting the generated 3D avatar video to the user's terminal. This allows the user to learn natural English conversation that is suited to their daily life, enabling flexible and practical learning that is tailored to the user's emotions and situations.

[1587] An "audio collection device" is a device that allows a user to record audio from their daily life, and includes wristwatch-type devices and dedicated recording devices.

[1588] "Via the network" refers to a method of transmitting audio data to a cloud server using the Internet or other communication networks.

[1589] A "cloud server" is a remote server that stores and processes data over the Internet.

[1590] "Speech recognition technology" is a technology that analyzes voice data and converts it into text data, and generally uses a voice recognition engine.

[1591] "Text data" refers to digital text information converted using voice recognition technology.

[1592] "Natural language processing technology" is a technology that analyzes the content of text data and extracts meaning and keywords.

[1593] "Machine translation means" is a technology for translating text data into another language, and generally uses a translation engine.

[1594] "Emotion analysis means" is a technology that recognizes a user's emotions from voice and text data.

[1595] An "emotion identification tag" is a tag that indicates the user's emotion, and includes an identifier such as "joy" or "anger."

[1596] "3D avatar video" is a three-dimensional character video generated based on the user's voice and text.

[1597] A "voice synthesis engine" is a technology for converting text data into voice data.

[1598] The "if function" allows the user to input a different statement or response and have it reflected in the system.

[1599] The present invention relates to a system that records a user's actual daily life, analyzes the data, generates an avatar video in which the user's speech is translated into natural English, and further recognizes the user's emotions and adapts the content of the avatar video. This system enables users to study English more realistically and effectively.

[1600] This system uses the following hardware and software: A wristwatch-type device or a dedicated recording device is used as the voice collection device used by the user. The voice data is transmitted over the Internet, and a common cloud storage service (e.g., Amazon Web Services' S3 bucket or Google Cloud Storage) is used as the cloud server.

[1601] Audio recording and data upload

[1602] A user puts on the audio collection device and starts recording. For example, the user might say, "It's a nice day today. I have a meeting this afternoon." The recording device captures this audio, and the device temporarily stores the recorded audio data. The device then uploads the audio data to a cloud server via an internet connection.

[1603] Analysis of voice data and conversion to text

[1604] The uploaded voice data is stored on a cloud server. The server then uses a speech recognition engine such as Google Cloud Speech-to-Text or IBM Watson to convert the voice data into text data. For example, a speech that says, "It's a nice day today. I have a meeting this afternoon" is converted into text format.

[1605] Text analysis using natural language processing

[1606] The server analyzes the text data using natural language processing (NLP) technology to extract the conversation content and keywords. This analysis can be performed using OpenAI's GPT-3 or SpaCy. For example, "good weather" and "meeting" are extracted as keywords.

[1607] Replace with appropriate English expressions

[1608] Based on the extracted text data, the server uses machine translation tools (such as Google Translate API or DeepL API) to translate the text into appropriate English expressions. For example, the text "It's nice weather today. I have a meeting this afternoon" is translated into "It's nice weather today. I have a meeting this afternoon." The server also applies expression levels such as formal, business casual, and casual according to the user's selection.

[1609] Recognizing user emotions with an emotion engine

[1610] The server analyzes the voice data using an emotion engine (such as Microsoft Azure's Emotion API or AWS's Comprehend) to recognize the user's emotion. For example, if a user says happily, "It's a nice day today," the emotion is recognized as "joy." Based on the recognized emotion, an emotion tag such as "joy" is assigned to the text data.

[1611] Adapting English expressions and avatar expressions according to emotions

[1612] The server adapts the English expressions and avatar facial expressions based on the emotion tag. For example, if "It's nice weather today. I have a meeting this afternoon" is tagged with the emotion "joy," the server configures the avatar to speak with a smile. A speech synthesis engine (Amazon Polly or Google Text-to-Speech) is then used to generate a narration voice appropriate to the emotion.

[1613] Avatar video generation and provision

[1614] Based on this narration audio and text data, the server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video. The generated avatar video is then sent to the user's device, where the user can watch the video on their smartphone, tablet, or PC.

[1615] Customization with the if function

[1616] The user can use the if function to input a different statement or response. For example, they can input "What happens if I miss the train?" The device sends the new statement or response to the server, which analyzes it with a speech recognition engine and generates new text data. Based on this, additional conversation scenes are generated and the narration audio and avatar video are updated. The updated avatar video is then sent back to the user's device and can be viewed.

[1617] An example of a prompt is:

[1618] "Text extracted from everyday audio recordings: 'It's nice weather today. I have a meeting this afternoon.'"

[1619] "Example translation: 'It's nice weather today. I have a meeting this afternoon.'"

[1620] Examples include "Emotion tag: 'joy'".

[1621] In this way, the system generates avatar videos for English learning that are in line with the user's daily life and provides expressions that correspond to emotions, thereby realizing more practical and effective English learning.

[1622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1623] Step 1: Start recording and collect audio data

[1624] Input: User's everyday conversational voice

[1625] How it works: A user puts on a wristwatch-style audio collection device and presses the record button. The device begins collecting sounds from the surrounding area.

[1626] Data processing / calculation: Recording devices capture audio as digital data and temporarily store that data in their internal memory.

[1627] Output: Collected audio data

[1628] Step 2: Upload your audio data

[1629] Input: Collected audio data

[1630] How it works: The device establishes an internet connection and sends the audio data stored in its internal memory to a cloud server.

[1631] Data processing / calculation: Data compression and transfer

[1632] Output: Audio data stored on a cloud server

[1633] Step 3: Convert audio data to text

[1634] Input: Audio data on a cloud server

[1635] How it works: The server uses a speech recognition engine (e.g., Google Cloud Speech-to-Text) to analyze the audio data and convert it into text data.

[1636] Data processing / calculation: Analysis of voice signals and conversion to text information

[1637] Output: Converted text data (e.g. "It's a nice day today. I have a meeting this afternoon.")

[1638] Step 4: Analyzing text data and extracting keywords

[1639] Input: Converted text data

[1640] How it works: The server uses natural language processing (NLP) to analyze the text and extract key conversation topics and keywords (e.g., "nice weather" and "meeting").

[1641] Data processing / calculation: Text analysis and keyword extraction

[1642] Output: Extracted keywords

[1643] Step 5: Translating the text data

[1644] Input: Extracted text data

[1645] How it works: The server uses a machine translation engine (e.g., Google Translate API) to translate the extracted text data into appropriate English expressions.

[1646] Data processing / calculation: Translation of text data

[1647] Output: English text (e.g., "It's nice weather today. I have a meeting this afternoon.")

[1648] Step 6: Sentiment analysis and tagging

[1649] Input: Translated English text and original audio data

[1650] How it works: The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API) to recognize the user's emotion and assign an appropriate emotion tag (e.g., "joy").

[1651] Data processing / computation: sentiment analysis and tagging

[1652] Output: English text with sentiment tags

[1653] Step 7: Generate narration audio

[1654] Input: English text with sentiment tags

[1655] How it works: The server uses a speech synthesis engine (Amazon Polly or Google Text-to-Speech) to generate narration voice based on the emotion.

[1656] Data processing / calculation: Convert text data into audio data

[1657] Output: Generated narration audio

[1658] Step 8: Generate avatar video

[1659] Input: English text and narration audio

[1660] How it works: The server uses a 3D avatar generation engine (Unity or Unreal Engine) to generate an avatar video based on the text and audio. The avatar's movements and facial expressions are also set here.

[1661] Data processing / calculation: Avatar video generation

[1662] Output: Generated 3D avatar video

[1663] Step 9: Submit your avatar video

[1664] Input: Generated 3D avatar video

[1665] How it works: The server sends the generated avatar video to the user's device.

[1666] Data processing / calculation: Data compression and transfer

[1667] Output: Avatar video on user's device

[1668] Step 10: Customizing with the if function

[1669] Input: New user comments or responses

[1670] How it works: The user uses the if function to input a new comment or reply, and the device sends it to the server. The server then uses a speech recognition engine to analyze the new input and generate text data.

[1671] Data processing / calculation: generating and analyzing new text data

[1672] Output: New text data and updated avatar video

[1673] In this way, the system learns natural English conversation that is suited to the user's daily life, providing flexible and practical learning that is tailored to the user's emotions and circumstances.

[1674] (Application example 2)

[1675] 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."

[1676] Conventional online shopping sites require users to enter information such as the products they want, their budget, and preferences in a text-based format, making them difficult to use, especially for elderly users and those unfamiliar with technology. Furthermore, it is difficult to understand the user's emotions when searching for products, limiting the amount of personalized advice and suggestions they can provide. Furthermore, automated user support using voice data is also insufficient. To address these issues, a system is needed that analyzes users' voices and emotions and uses 3D avatars to provide advice and suggestions tailored to individual needs.

[1677] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1678] In this invention, the server includes a means for recognizing a user's emotion, a means for assigning an emotion tag based on the recognized emotion and generating a 3D avatar video based on the emotion tag, and a means for transmitting the generated avatar video to the user's device so that the avatar video can be viewed within a smartphone application, thereby enabling the user to receive personalized advice and suggestions based on their own emotions and needs.

[1679] A "recording device" is a device that allows a user to record their daily life.

[1680] A "cloud server" is a remote server for storing and processing data over the Internet.

[1681] "Speech recognition technology" is a technology that converts voice data into text data.

[1682] "Natural language processing" is a technology that analyzes text data and extracts conversation content and keywords.

[1683] "Machine translation means" refers to technology that automatically translates text data from one language to another.

[1684] "Emotion recognition means" is a technology that analyzes emotions from the user's voice and identifies those emotions.

[1685] An "emotion tag" is a tag that indicates an emotion identified by an emotion recognition means.

[1686] "3D avatar video" is a video of a three-dimensional person or character that responds to the user's conversation and emotions.

[1687] A "user terminal" is an information processing device such as a computer, smartphone, or tablet that is used by a user.

[1688] A "smartphone application" is a software program that runs on a smartphone.

[1689] The "if function" is a function that allows you to input user comments and responses and generate new scenarios.

[1690] A "speech synthesis engine" is a technology that converts text data into speech.

[1691] "Formal, business casual, and casual levels of expression" are styles of expression that can be selected according to different situations and uses.

[1692] The system for realizing this application example operates in the following steps.

[1693] Overview of program processing

[1694] 1. Audio recording and data upload

[1695] When a user starts recording their daily life, audio is recorded using a smartphone or a dedicated recording device. This audio data is then uploaded to a cloud server, which contains a database for temporarily storing the audio data. The audio data is uploaded via network communication.

[1696] 2. Analysis of voice data and conversion to text

[1697] The cloud server converts the uploaded voice data into text data using speech recognition technology. The Google Cloud Speech-to-Text API is used for speech recognition. This API has the ability to convert voice data into text data with high accuracy.

[1698] 3. Natural Language Processing and Machine Translation

[1699] The converted text data is analyzed using natural language processing technology to extract conversation content and keywords. This process uses a natural language processing (NLP) library. The extracted text data is then machine-translated into appropriate English expressions using the Google Translate API.

[1700] 4. Emotion Recognition and Emotion Tagging

[1701] The server uses the IBM Watson Tone Analyzer API to recognize the user's emotions from the voice data. This allows the server to assign an emotion tag based on what the user says. The emotion tag indicates a specific emotional state, such as "joy," "sadness," or "surprise."

[1702] 5. 3D avatar video generation and provision

[1703] Based on the recognized emotion tags, a 3D avatar video is generated based on the emotion. The 3D avatar is created using a 3D model generation engine such as Unity or Adobe Fuse. The voice in the avatar video is generated using a speech synthesis engine such as Amazon Polly.

[1704] 6. Video distribution to smartphone applications

[1705] The generated avatar video is delivered to the user's smartphone application via AWS CloudFront, where the user can watch the avatar's responses to their questions.

[1706] The hardware and software that runs the program

[1707] Smartphones or dedicated recording devices are used for the initial recording process. AWS S3 or a database is used to store and process the recorded data. Google Cloud Speech-to-Text API is used for speech recognition, NLP libraries and Google Translate API for natural language processing and machine translation. IBM Watson Tone Analyzer API is used for emotion recognition, Unity or Adobe Fuse for 3D avatar generation, and Amazon Polly for speech synthesis. AWS CloudFront is used for final video distribution.

[1708] Examples and prompts

[1709] For example, consider the case where a user says, "I want new shoes, but I'm not sure which ones to get." This voice data is recorded and uploaded to a cloud server. Then, using speech recognition technology, it is converted into text data: "I want new shoes, but I'm not sure which ones to get." This text data is analyzed using natural language processing, and keywords such as "new shoes" and "confused" are extracted. The text data is then translated into English using the Google Translate API, resulting in "I want new shoes, but I am confused about which one to choose." Next, the user's emotion is recognized as "confused" by IBM Watson Tone Analyzer, and that emotion tag is assigned. Based on the emotion tag "confused," a video is generated in which an avatar suggests in English, "Here are some popular shoes that might match your taste," and the video is delivered to the user's app via AWS CloudFront.

[1710] In this way, the system provides personalized shopping advice based on the user's voice input and emotion recognition.

[1711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1712] Step 1:

[1713] Users record sounds from their daily lives using a smartphone or a dedicated recording device. When the user presses the "Start Recording" button, the device begins to record the surrounding sounds. The input data is the audio data of the user's daily conversation, and this is temporarily saved on the device as output data.

[1714] Step 2:

[1715] When recording is complete, the device uploads the recorded audio data to the cloud server. When the user presses the "Stop Recording" button, the audio data temporarily stored on the device is sent to the cloud server via the Internet. The input data is the recorded audio data, which is then saved on the cloud server as output data.

[1716] Step 3:

[1717] The server receives the voice data uploaded to the cloud server and analyzes it using speech recognition technology. Specifically, it converts the voice data into text data using the Google Cloud Speech-to-Text API. The input data is the voice data on the cloud server, and the output data is the converted text data.

[1718] Step 4:

[1719] The server analyzes the converted text data using natural language processing technology to extract key conversational content and keywords. Specifically, it uses a natural language processing (NLP) library to identify keywords and important phrases. The input data is text data, and the output data is the extracted conversational content and keywords.

[1720] Step 5:

[1721] The server uses machine translation to convert the extracted text data into appropriate English expressions. Specifically, it uses the Google Translate API to convert Japanese text into English. The input data is Japanese text data, and the output data is the text data translated into English.

[1722] Step 6:

[1723] The server uses an emotion engine to recognize the user's emotion when analyzing the voice data. Specifically, it uses the IBM Watson Tone Analyzer API to identify the user's emotion from the text data. The input data is the voice data and text data, and the output data is the recognized emotion tag.

[1724] Step 7:

[1725] The server assigns appropriate emotion tags based on the emotion tags and generates a 3D avatar video based on the emotion tags. Specifically, Unity and Adobe Fuse are used to create a 3D avatar based on the user's emotion, and Amazon Polly is used to synthesize speech. The input data is text data translated into English and emotion tags, and the output data is the generated avatar video.

[1726] Step 8:

[1727] The server sends the generated avatar video to the user's device so that it can be viewed within the smartphone application. Specifically, the video is distributed using AWS CloudFront. The input data is the generated avatar video, and the output data is a video that can be viewed within the user's smartphone application.

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] FIG. 9 illustrates 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 behaviors 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.

[1733] 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.

[1734] 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).

[1735] 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.

[1736] 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."

[1737] 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.

[1738] 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).

[1739] 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.

[1740] 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.

[1741] 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.

[1742] 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.

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] The following is further disclosed regarding the above embodiment.

[1750] (Claim 1)

[1751] a recording device for users to record their daily lives;

[1752] A means for uploading the recorded audio data to a cloud server;

[1753] A means for converting the uploaded voice data into text data using voice recognition technology;

[1754] A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords;

[1755] a machine translation means for replacing the extracted text data with appropriate English expressions;

[1756] A means for generating a 3D avatar video based on the replaced English expression;

[1757] The system includes a means for transmitting the generated avatar video to a user's terminal.

[1758] (Claim 2)

[1759] A means of inputting user comments and responses into the if function,

[1760] A means for analyzing input new utterances and replies and generating additional conversation scenes;

[1761] 10. The system of claim 1, further comprising: means for providing updated avatar animations.

[1762] (Claim 3)

[1763] a means for generating a narration for the generated avatar video using a voice synthesis engine;

[1764] 10. The system of claim 1, further comprising means for selecting an appearance level from formal, business casual, and casual.

[1765] "Example 1"

[1766] (Claim 1)

[1767] a recording device for a user to record daily life;

[1768] a means for uploading the recorded audio data to a cloud provider;

[1769] A means for converting the uploaded voice data into text data by voice recognition;

[1770] A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords;

[1771] a translation means for replacing the extracted text data with an appropriate foreign language expression;

[1772] A means for generating a virtual character video based on the replaced foreign language expression;

[1773] means for transmitting the generated virtual character video to a user's terminal;

[1774] means for applying a representation level in response to a user selection;

[1775] The system includes means for synchronizing the facial expressions and movements of a virtual character with audio data.

[1776] (Claim 2)

[1777] A means for inputting user comments and responses into the conditional branching function;

[1778] A means for analyzing input new utterances and replies and generating additional conversation scenes;

[1779] 10. The system of claim 1, further comprising: means for providing updated virtual character animation.

[1780] (Claim 3)

[1781] means for generating a narration for the generated virtual character video using a voice synthesis engine;

[1782] 10. The system of claim 1, further comprising means for selecting a representation level.

[1783] "Application Example 1"

[1784] (Claim 1)

[1785] a recording device for users to record their daily lives;

[1786] A means for uploading the recorded audio data to a cloud server;

[1787] A means for converting the uploaded voice data into text data using voice recognition technology;

[1788] A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords;

[1789] a machine translation means for replacing the extracted text data with appropriate English expressions;

[1790] A means for generating a 3D avatar video based on the replaced English expression;

[1791] a means for outputting a voice synthesis narration to a robot that assists in multilingual communication with factory workers;

[1792] The system includes a means for transmitting the generated avatar video to a user's terminal.

[1793] (Claim 2)

[1794] A means of inputting user comments and responses into the if function,

[1795] A means for analyzing input new utterances and replies and generating additional conversation scenes;

[1796] 10. The system of claim 1, further comprising: means for providing updated avatar animations.

[1797] (Claim 3)

[1798] a means for generating a narration for the generated avatar video using a voice synthesis engine;

[1799] 10. The system of claim 1, further comprising means for selecting an appearance level from formal, business casual, and casual.

[1800] "Example 2: Combining Emotion Engines"

[1801] (Claim 1)

[1802] a voice collection device for a user to record their daily life;

[1803] A means for transmitting the collected voice data to a cloud server via a network;

[1804] A means for converting the transmitted voice data into text data using voice recognition technology;

[1805] A means for analyzing the converted text data using natural language processing technology and extracting the conversation content and keywords;

[1806] a machine translation means for replacing the extracted text data with appropriate English expressions;

[1807] emotion analysis means for the server to analyze the voice data and recognize the emotion of the user;

[1808] A means for adapting English expressions and avatar expressions including emotions;

[1809] A means for generating a 3D avatar video based on the replaced English expression;

[1810] The system includes a means for transmitting the generated 3D avatar video to a user's terminal.

[1811] (Claim 2)

[1812] A means of inputting user comments and responses into the if function,

[1813] A means for analyzing input new utterances and replies and generating additional conversation scenes;

[1814] 10. The system of claim 1, further comprising: means for providing updated avatar animations.

[1815] (Claim 3)

[1816] a means for generating a narration for the generated avatar video using a voice synthesis engine;

[1817] A means to choose the level of expression: formal, business casual, or casual;

[1818] 2. The system according to claim 1, further comprising means for assigning an appropriate emotion identification tag according to the emotion of the user.

[1819] "Application example 2 when combining emotion engines"

[1820] (Claim 1)

[1821] a recording device for users to record their daily lives;

[1822] A means for uploading the recorded audio data to a cloud server;

[1823] A means for converting the uploaded voice data into text data using voice recognition technology;

[1824] A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords;

[1825] a machine translation means for replacing the extracted text data with appropriate English expressions;

[1826] means for recognizing a user's emotion;

[1827] A means for assigning emotion tags based on the recognized emotions and generating a 3D avatar video based on the emotion tags;

[1828] The system includes a means for transmitting the generated avatar video to a user's device so that it can be viewed within a smartphone application.

[1829] (Claim 2)

[1830] A means of inputting user comments and responses into the if function,

[1831] A means for analyzing input new utterances and replies and generating additional conversation scenes;

[1832] 10. The system of claim 1, further comprising: means for providing updated avatar animations.

[1833] (Claim 3)

[1834] a means for generating a narration for the generated avatar video using a voice synthesis engine;

[1835] 10. The system of claim 1, further comprising means for selecting an appearance level from formal, business casual, and casual. [Explanation of symbols]

[1836] 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 recording device for users to record their daily lives; A means for uploading the recorded audio data to a cloud server; A means for converting the uploaded voice data into text data using voice recognition technology; A means for analyzing the converted text data using natural language processing and extracting the conversation content and keywords; a machine translation means for replacing the extracted text data with appropriate English expressions; A means for generating a 3D avatar video based on the replaced English expression; The system includes a means for transmitting the generated avatar video to a user's terminal.

2. A means of inputting user comments and responses into the if function, A means for analyzing input new utterances and replies and generating additional conversation scenes; The system of claim 1 further comprising means for providing updated avatar animations.

3. a means for generating a narration for the generated avatar video using a voice synthesis engine; 10. The system of claim 1, further comprising means for selecting an appearance level from formal, business casual, and casual.

Images