system

Abstract

We provide the system. [Solution] A speech recognition means that acquires voice input and converts the voice data into text data, A method for generating English content based on text data acquired using generative artificial intelligence, A presentation means for presenting the generated English content to the user audibly or visually, A progress management system that monitors and analyzes the user's learning progress, A feedback generation means that provides feedback based on learning progress, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, there is a need for means to efficiently learn English as a second language and be able to use it naturally. However, conventional English learning methods have time and location limitations and it is difficult to provide an environment where one can efficiently and continuously be exposed to English. For this reason, there is a need for an innovative system that allows users to naturally learn English in their daily lives and continue learning while checking their progress.

Means for Solving the Problems

[0005] This invention provides a system to support English language learning in daily life. Specifically, it acquires user voice input using speech recognition means and converts it into text data. Next, it includes means for generating English content based on the acquired text data using generative artificial intelligence. Furthermore, it provides an environment in which the user can naturally be exposed to English by presenting the generated English content to the user either audibly or visually. In addition, it constructs a system that supports continuous learning by including progress management means for monitoring and analyzing the user's learning progress and feedback generation means for providing feedback based on the learning progress.

[0006] "Voice recognition means" refers to a function that acquires the user's voice input and converts that voice data into text data.

[0007] "Generative artificial intelligence" refers to a technology that generates natural language from given data based on pre-programmed algorithms.

[0008] "English content" refers to information and materials provided to users for learning English, and can be in text or audio format.

[0009] "Presentation method" refers to a function for presenting the generated English content to the user in an audio or visual manner.

[0010] "Progress management means" refers to functions for monitoring and analyzing a user's learning progress and understanding their learning status.

[0011] "Feedback generation means" refers to functions that provide useful information and suggestions based on the user's learning progress to support learning. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention implements a system that effectively supports users' English language learning in their daily lives by combining smart glasses and artificial intelligence. This system has functions for speech recognition, presentation of generated English content, monitoring of learning progress, and provision of feedback.

[0034] Speech recognition and English content generation

[0035] The device accepts voice commands from the user. For example, suppose the user says, "Tell me today's news," using voice input. The device then converts this command into text data using voice recognition.

[0036] The converted text is sent to a server, where a generating artificial intelligence generates appropriate English news based on this text information. The generated content is selected through access to the latest news database.

[0037] English content presentation

[0038] The device plays the generated English news content to the user as audio or displays it as text on the smart glasses' display. For example, "Today's main news is about developments in the foreign exchange market." This allows the user to be exposed to English both visually and aurally.

[0039] Learning progress management and feedback

[0040] The device temporarily stores a history of the user's conversations and the content they listen to, and periodically sends it to the server.

[0041] The server analyzes this data to track the user's improvement in English skills. For example, it focuses on aspects such as pronunciation, grammar, and vocabulary frequency.

[0042] Based on the analysis results, the server provides feedback to the user. For example, it might say, "Your pronunciation has improved since yesterday; keep up the good work!"

[0043] This format allows users to learn English interactively anytime, anywhere, and to efficiently progress while monitoring their own progress. This system reduces the burden of learning while realizing practical and sustainable English education.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user wears smart glasses and gives voice commands in English to request information. For example, they might say, "Tell me today's news."

[0047] Step 2:

[0048] The device captures the user's voice through its built-in microphone. Using speech recognition technology, the voice is converted into text data. This converted text accurately represents the instructions.

[0049] Step 3:

[0050] The device sends text data to the server along with contextual information such as the user's location and time. This enables more personalized responses.

[0051] Step 4:

[0052] The server analyzes the received text data and uses generative artificial intelligence to generate appropriate English content. For example, it accesses a database of the latest news, selects relevant news articles, and generates text in natural language format.

[0053] Step 5:

[0054] The server formats the generated English content in a way that is easy for the user to understand and sends it to the terminal. This content includes both audio and text data.

[0055] Step 6:

[0056] The device presents the generated content to the user. By using the voice output function to convey the news content to the user and simultaneously displaying it as text on the smart glasses' display, it promotes learning through both visual and auditory means.

[0057] Step 7:

[0058] The device monitors user responses and further interactions, and may send this information to the server as feedback. This data is used for progress management.

[0059] Step 8:

[0060] The server analyzes the learning data and generates feedback based on the user's progress. This feedback is sent periodically to the device, providing the user with encouragement such as "persistence pays off" and suggestions for improvement.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Existing English learning systems lack sufficient personalized learning support based on users' progress and learning history. Furthermore, their limited ability to efficiently analyze voice-input information and generate and present relevant content makes it difficult to maximize learning effectiveness. Additionally, the inability to utilize learning history long-term makes it challenging to provide continuous learning support to users.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes a voice input conversion means, a generation means, and a presentation means. This makes it possible to efficiently convert the user's voice input into text information and generate and present personalized content based on that information. Furthermore, by managing learning progress and providing feedback, it is possible to realize continuous and effective learning support and improve the efficiency of the user's English learning.

[0066] "Voice input conversion means" refers to a technology that analyzes voice information and converts it into text information, and involves obtaining the user's utterance as a string of characters through speech recognition.

[0067] "Generation method" refers to a technology that creates new information content using generative artificial intelligence based on acquired textual information.

[0068] "Presentation means" refers to technologies for conveying generated information content to users visually or aurally, and is a means of dynamically displaying or playing information audibly.

[0069] "Learning progress management methods" refer to technologies that quantitatively grasp the progress of skill improvement by temporarily saving and analyzing a user's learning history.

[0070] A "feedback generation method" is a technology that creates information to communicate areas for improvement and changes to users based on analysis results, with the aim of providing individualized learning support.

[0071] "Data storage methods" refer to technologies that build databases to store learning history over the long term and use it for future learning.

[0072] "Personalization" refers to providing a more effective learning experience by adjusting learning content and feedback according to the user's characteristics and history.

[0073] This invention is a system that combines speech input conversion technology and generation technology to facilitate language acquisition in the user's daily life. The system aims to analyze the user's speech input, generate English content using a generation AI model, manage learning progress, and provide feedback.

[0074] The terminal has the ability to receive voice commands from the user and uses existing voice recognition software (e.g., a voice recognition API) to perform voice recognition. After converting the voice input into text information, it uses an internet connection and API communication technology to send the text information to the server.

[0075] The server utilizes generative AI models (e.g., natural language processing models) to generate appropriate English content based on the received text information. Specifically, it can access external information sources (e.g., news APIs) to provide the latest news and educational content. This generated content is tailored to the user's interests and incorporates features to keep them engaged in learning.

[0076] The device presents the generated English content to the user either as audio or text. Audio output uses text-to-speech technology (e.g., a text-to-speech API). Visual presentation is achieved by displaying text on smart glasses or a mobile device screen. This allows the user to engage with English through both auditory and visual means.

[0077] This system temporarily stores the user's activity history and conversation content to monitor their learning progress and analyze their progress. This data, periodically sent to the server, is used to analyze the user's learning performance. Based on this analysis, the user receives feedback such as, "Your pronunciation has improved since yesterday. Keep up the good work!" This allows users to continue learning while keeping track of their own progress.

[0078] For example, if a user gives a voice command such as "Tell me yesterday's sports news in English," the content is converted into text, a generative AI model on the server generates relevant English news, and it is presented to the user via the device. This prompt format allows users to use topics they are interested in on a daily basis, making language learning enjoyable.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The device accepts voice input from the user. When the user says, "Tell me yesterday's sports news in English," this voice becomes the input. The device uses voice recognition software to convert the voice data into text data. As a result, the text data is output.

[0082] Step 2:

[0083] The terminal sends the converted character data to the server. Secure communication is performed using HTTPS, and the character data is provided to the server as input. The server receives this data and can then perform the following processing.

[0084] Step 3:

[0085] The server activates a generative AI model and analyzes the received text data. This analysis determines what kind of content is required. Based on this text data, the server retrieves relevant information from the latest news API and generates relevant English news content. The generated English content becomes the output.

[0086] Step 4:

[0087] The device receives pre-generated English content sent from the server. Based on this, it performs actions to present the content to the user visually or aurally. Specifically, it displays text on the smart glasses' display or presents it to the user as audio using synthesized speech technology. As a result, the user can access English news content.

[0088] Step 5:

[0089] The device records user activity and temporarily stores learning progress. Data on which content the user watched or listened to and for how long is used as input, and this data is recorded to understand learning trends. This data is later sent to the server.

[0090] Step 6:

[0091] The server analyzes the learning data received from the device. Detailed data, including learning history and pronunciation evaluations, is used as input to check the user's skill improvement. Based on this analysis, the server generates feedback and outputs a feedback message to the user. This message, such as "Your pronunciation has improved since yesterday," is conveyed to the user via the device.

[0092] (Application Example 1)

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

[0094] This invention aims to provide efficient learning support in users' daily lives, and in particular, to provide continuous and effective support for English language learning. Many learning support tools currently on the market struggle to adequately meet the individual needs of users and offer limited interactive learning experiences. To address these challenges, this invention aims to provide a learning system that seamlessly integrates into the user's daily life.

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

[0096] In this invention, the server includes data conversion means for acquiring voice input and converting the voice data into text data, generation means for generating information content based on the acquired text data using generative artificial intelligence, and output means for presenting the generated information content to the user audibly or visually. This allows users to naturally acquire learning opportunities in their daily lives. Furthermore, the efficient learning experience is enhanced by the provision of appropriate information presentation and feedback.

[0097] A "data conversion means that acquires voice input and converts voice data into text data" is a function that receives voice information and converts it into corresponding character information using a language model.

[0098] "Generative means for generating information content based on text data acquired using generative artificial intelligence" refers to a function that uses knowledge databases and learning models to create appropriate information based on given text information.

[0099] "Output means for presenting generated information content to the user in audio or visual form" refers to a function for providing the generated information to the user using display on a screen or speech synthesis functionality.

[0100] "An evaluation management system that monitors and analyzes users' learning progress" refers to a function that records users' learning activities, analyzes the data, and evaluates their learning progress.

[0101] A "feedback generation method that provides feedback based on learning progress" is a function that presents advice and areas for improvement according to the user's progress during the learning process.

[0102] "An information storage method that records user behavior history and builds a long-term learning database" refers to a function that collects user activity data and builds learning history and trends over time.

[0103] "A means of communication that obtains information from external resources via an internet connection" refers to a function that accesses data and services existing externally through a network and obtains the necessary information.

[0104] "Activity coordination means that provide information in a timely manner based on the user's daily activities" refers to a function that adjusts to provide information at the optimal timing in accordance with the user's daily actions.

[0105] The system for implementing this invention is constructed using smart devices (primarily smart glasses) and network connectivity. The system's components and operation are described below.

[0106] First, the user gives instructions using the voice input function of their smart device. This voice data is converted into text data using speech recognition technology. High-precision language models are used for speech recognition, such as the Google® Cloud Speech-to-Text API.

[0107] Subsequently, the server retrieves the converted text data and generates appropriate information content using generative artificial intelligence (generative AI model). This generative AI model, for example, uses OpenAI's GPT model to generate news and learning content tailored to user requests. During the generation process, necessary data is obtained from the latest external information sources via the internet, and content is created based on that data.

[0108] The generated information content is sent from the server to a smart device and output to the user either visually or audibly. Visually, text is displayed on the smart glasses' screen, and audibly, information is provided to the user in an audible form using a speech synthesis system (such as Amazon Polly).

[0109] Simultaneously, the device monitors the user's learning progress, and the server collects and analyzes the progress data. Learning history and behavioral data are stored in a long-term learning database, and the server generates feedback based on this data and sends it to the smart device. This feedback helps to improve the quality of the user's learning.

[0110] For example, if a user says, "Tell me the main news stories this morning," speech recognition converts this instruction into text, and the server uses a generative AI model to generate the latest news. The generated news is displayed visually on the smart glasses and played aloud. Feedback is provided, such as, "You have learned more vocabulary related to the news than yesterday."

[0111] Example of a prompt:

[0112] User request: "What are the main news stories this morning?"

[0113] Prompt to the generative AI model: "Search for the latest news and provide concise English news articles on key topics."

[0114] This configuration allows users to continue learning efficiently and naturally at various moments in their daily lives.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The user provides voice input through a smart device. The input voice data is captured through the device's microphone. In this process, the user's voice commands are reproduced and recorded as digital voice data.

[0118] Step 2:

[0119] The device sends the captured audio data to a speech recognition engine, which converts it into text data. The input is audio data, and the output is the corresponding text data. The speech recognition engine uses an advanced language model (e.g., Google Cloud Speech-to-Text) to analyze the audio data and accurately convert it into text.

[0120] Step 3:

[0121] The server receives text data sent from the terminal and generates informational content using a generative AI model. The input is text data, and the output is the generated informational content. Specifically, the server sends prompts to the OpenAI GPT model to retrieve and generate the latest news information, etc.

[0122] Step 4:

[0123] The server transmits the generated information content to the terminal, which then presents it to the user via a smart device. The input is the generated information content, and the output is the visual or audio information presented to the user. The terminal displays text on its screen and also uses a speech synthesis engine to play the information aloud.

[0124] Step 5:

[0125] The device collects user learning progress data and reports it periodically to the server. Input is user usage data (e.g., viewing time, interaction content), and output is a log sent to the server as progress data. This data is important for recording learning outcomes and habits.

[0126] Step 6:

[0127] The server analyzes accumulated user progress data and generates feedback. The input is the accumulated data, and the output is a feedback message for the user. The server queries the database and generates advice based on the user's learning patterns and progress.

[0128] Step 7:

[0129] Feedback is sent to the user via the device. The input is feedback from the server, and the output is feedback information presented to the user. The device enhances the user's motivation to learn by clearly presenting the feedback content through displays and audio.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention is a system that realizes a more personalized English learning experience by incorporating an emotion engine to recognize the user's emotional state and provide English content that is appropriate to that state. By utilizing an emotion engine in addition to a combination of smart glasses, speech recognition technology, and generative artificial intelligence, the system can customize responses to the user's emotions.

[0132] Personalized emotion recognition and response

[0133] The device acquires the user's voice input and converts that voice data into text data. Furthermore, it utilizes an emotion engine to analyze the user's emotional state from the voice data. This emotion analysis is based on factors such as voice tone, speaking speed, and word choice.

[0134] The server receives emotional information transmitted along with the text data and generates English content according to that emotional state. For example, if the user is relaxed, it will select content that creates a relaxed atmosphere.

[0135] Content presentation and feedback

[0136] The device presents the generated English content to the user in audio or visual format. By making adjustments that respond to the user's emotions, the user can learn in a more receptive way. For example, encouraging language is used for a user who is feeling down.

[0137] The server periodically monitors the user's learning progress and generates progress-based feedback based on sentiment data. This feedback provides specific advice on how the user can improve. For example, it can offer sentiment-based praise such as, "Your speech today was delivered with confidence."

[0138] Strengthening user engagement

[0139] This system allows users to learn English in a learning environment that constantly recognizes their own emotional state. As a result, a more effective and satisfying learning experience is provided. Furthermore, emotional information is accumulated in a database as long-term learning history and used to improve future learning content. This leads to greater individualization for each user and is expected to improve learning efficiency.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The user wears smart glasses and gives voice commands to request information specified in English. For example, they might say, "Tell me about today's interesting articles."

[0143] Step 2:

[0144] The device captures the user's voice through its built-in microphone and converts it into text data using speech recognition technology. Simultaneously, the voice data is input into an emotion engine to analyze the user's emotional state.

[0145] Step 3:

[0146] The device sends the converted text data and sentiment analysis results to the server. The sentiment analysis results include, for example, whether the user is excited or relaxed.

[0147] Step 4:

[0148] The server uses generative artificial intelligence to generate optimal English content based on the received text data and sentiment information. It adjusts the tone and content of the article according to the user's emotional state.

[0149] Step 5:

[0150] The server formats the generated English content and sends it to the terminal, including audio and text data. Adjustments are made based on the user's emotions.

[0151] Step 6:

[0152] The device presents the generated English content to the user in both audio and text formats. This allows the user to receive information in a way that is appropriate to their emotions.

[0153] Step 7:

[0154] The device monitors further user interactions and sends that data to the server. This includes user reactions and changes in emotion.

[0155] Step 8:

[0156] The server analyzes interaction history and sentiment data to generate feedback based on the user's learning progress. This feedback takes emotional aspects into account, providing the user with specific advice and praise.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] The problem that this invention aims to solve is the failure to provide personalized and effective learning experiences when uniform learning content is provided without considering the learner's emotional state. Conventional systems have difficulty providing individualized support based on the learner's emotions and learning progress, which has sometimes led to decreased learning efficiency.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes a speech conversion means, an emotion analysis means, and a creative means. This makes it possible to provide language learning content that is individually adapted to the user's emotional state in real time.

[0162] "Speech conversion means" refers to a technology or device for converting speech information into text information.

[0163] "Emotional analysis means" refers to a technology or device that analyzes a user's emotional state from voice or text information and generates emotional information.

[0164] "Creative means" refers to a technology or device that uses generative artificial intelligence to create language learning content based on generated emotional and textual information.

[0165] "Presentation means" refers to a technology or device that provides personalized language learning content to the user visually or aurally.

[0166] "Progress evaluation means" refers to a technology or device that monitors the user's learning progress and performs analysis while taking their emotional state into consideration.

[0167] "Response generation means" refers to a technology or device that generates and provides feedback based on learning status and emotional information.

[0168] "Information storage means" refers to a technology or device that records the user's interaction history and builds a long-term learning information database.

[0169] The present invention is a system that personalizes the learning experience based on the user's emotional state. This system comprises a voice conversion means, an emotion analysis means, a creation means, a presentation means, a progress evaluation means, and a response generation means.

[0170] First, the device uses a microphone or the voice input function of a smart device to acquire the user's voice input. Specific hardware examples include smart glasses and Bluetooth earphones. The voice input is converted into text data using speech recognition software. A specific example of this software is a speech recognition engine.

[0171] Next, the device uses this converted text information to analyze the user's emotional state using sentiment analysis software. Sentiment analysis takes into account voice tone, speaking speed, and word choice. Specifically, the sentiment analysis engine processes the data.

[0172] The server then receives the generated emotional and textual information and uses a generative AI model to create language learning content. This creative process utilizes a content generation engine. An example of a prompt is, "Generate relaxing English learning content for the user."

[0173] Next, the device presents the generated learning content to the user. The presentation method is either visual or audible. Specifically, it may be displayed visually on the smart glasses' display or played as audio through a Bluetooth speaker.

[0174] The server continuously monitors the user's learning progress, evaluates and analyzes it based on sentiment information, and provides a detailed understanding of how the user is progressing.

[0175] Finally, the system generates feedback based on learning progress and emotional information. This feedback is provided to the user and includes advice to further improve the learning experience. For example, it might say, "You made very good progress today."

[0176] This system is expected to improve learning efficiency by providing users with personalized learning experiences tailored to their emotional state.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The device acquires voice input from the user. Voice input is acquired through the microphone of smart glasses or earphones. The acquired voice data is converted into text data using a speech recognition engine. In this process, the input is an audio signal, and the output is the corresponding text data. The speech recognition engine analyzes the audio signal and outputs it as text.

[0180] Step 2:

[0181] The terminal performs sentiment analysis using the converted text data. The sentiment analysis engine analyzes the characteristics of the text and audio data, such as tone and speed, to determine the user's emotional state. In this step, text data and audio characteristic data are taken as input, and sentiment information is generated as output. The sentiment analysis engine evaluates the input data and assigns sentiment labels.

[0182] Step 3:

[0183] The server receives text data and sentiment information sent from the terminal. Based on this data, a generative AI model is used to generate appropriate language learning content. The input for this step is sentiment information and text data, and the output is customized learning content. The generative AI model takes a prompt sentence, for example, "Generate relaxing English learning content for the user," as input and performs the operation to create content.

[0184] Step 4:

[0185] The device presents the generated learning content to the user. This presentation is done via voice reading or display. The input is the generated learning content, and the output is the format presented to the user. In practice, visual content is displayed on the smart glasses' screen, and audio content is played through a Bluetooth speaker.

[0186] Step 5:

[0187] The server monitors the user's learning progress and analyzes data, including sentiment information. Based on the analysis results, it evaluates the effectiveness of the learning content and the user's emotional state. The inputs are progress data and sentiment information, and the outputs are evaluation and analysis results. The progress monitoring engine continuously analyzes the data and works to understand the learning trends.

[0188] Step 6:

[0189] The server generates feedback based on analysis results and sentiment information. This generated feedback is provided to the user and includes messages that suggest areas for improvement in learning and motivate them. The input is analysis results and sentiment information, and the output is the feedback message. The feedback generation engine uses evaluation information to create feedback and communicates it to the user.

[0190] (Application Example 2)

[0191] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0192] Currently, information systems in smart cities lack sufficient content customization that takes into account users' emotional states, limiting the potential for improving the user experience. Furthermore, the lack of flexible information delivery that responds to temporary emotional fluctuations prevents users from maximizing their convenience. In addition, there is a need to provide a more personalized experience by utilizing users' long-term history.

[0193] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0194] In this invention, the server includes a voice recognition means, an emotion recognition means, a generation means, and a means for generating information about public facilities and providing guide information optimized based on the user's emotions. This enables the provision of dynamic and personalized information that reflects the user's emotional state.

[0195] 1. "Speech recognition means" refers to a device that has the function of acquiring speech data and converting it into text data.

[0196] 2. "Generation means" refers to a device that uses generative artificial intelligence to generate content based on acquired text data.

[0197] 3. "Emotion recognition means" refers to a device that analyzes the user's voice data and performs processing to determine their emotional state.

[0198] 4. "Means of customization" refers to a device for generating optimal content tailored to the user's state based on analysis results.

[0199] 5. “Presentation means” refers to a device for providing the generated content to the user in audio or visual form.

[0200] 6. A "progress management device" is a device for monitoring the user's progress and collecting and analyzing that data.

[0201] 7. A "feedback generation means" is a device for generating and providing information and advice based on the user's progress.

[0202] 8. "Means for generating and providing information" refers to a device for generating and providing optimized guide information about public facilities based on the user's emotions.

[0203] This invention is a system for providing users with emotionally appropriate information within a smart city. The system mainly consists of terminals and servers. A detailed embodiment of this system is described here.

[0204] The terminal is a device equipped with speech recognition capabilities (e.g., smart glasses) that receives voice input from the user. Specifically, the terminal uses speech recognition to convert the voice data into text data in real time. This utilizes speech recognition APIs such as Google Cloud Speech-to-Text.

[0205] Next, the server uses emotion recognition tools to analyze the text and audio data transmitted from the terminal and determine the user's emotional state. This process utilizes emotion analysis tools such as IBM Watson® Tone Analyzer. Based on the analysis, the server generates appropriate content using a generative AI model (e.g., OpenAI GPT-4®).

[0206] This generation method accesses a broad database containing information on public facilities and combines information best suited to the user's emotions to create guide information. The generated content can be customized to reflect the user's individual needs and interests.

[0207] Finally, using a presentation method, the device presents the generated customized information to the user either audibly or visually. This allows the user to receive information optimized for their emotional state. For example, if the user is relaxed, a prompt such as "Please recommend a park where I can feel tranquility and beauty" will be met with recommendations for appropriate facilities.

[0208] The operation of this system will improve the user experience within smart cities and enable more comfortable and effective information delivery.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The device acquires the user's voice input. This input can be in various forms, such as phone calls or instructions. Speech recognition is used to convert this voice data into text data. The Google Cloud Speech-to-Text API is used for this purpose, and the text input is sent to the server.

[0212] Step 2:

[0213] The server analyzes the user's emotional state using emotion recognition based on text data received from the terminal. Emotional data is generated using an emotion analysis engine (e.g., IBM Watson Tone Analyzer) based on factors such as voice tone and word selection. This output represents the user's emotional state.

[0214] Step 3:

[0215] The server utilizes a generative AI model based on emotional data to generate information best suited to the user's emotions. The generation process prepares content in response to prompts. For example, if the user is in a relaxed emotional state, a prompt such as "Please recommend a park where I can feel tranquility and beauty" might be used, and facility information would be created based on this prompt.

[0216] Step 4:

[0217] The server customizes the generated information to create optimal guide information tailored to the user. This process takes into account the user's past interaction data and current situation, adjusting the information provided to make it more engaging and relevant.

[0218] Step 5:

[0219] The device presents the user with customized guide information received from the server. This information can be presented visually on the smart glasses' display or verbally using a speech synthesis API (e.g., Amazon Polly). This ensures that the information is presented in a way that is easily accepted and understandable to the user.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention implements a system that effectively supports users' English language learning in their daily lives by combining smart glasses and artificial intelligence. This system has functions for speech recognition, presentation of generated English content, monitoring of learning progress, and provision of feedback.

[0237] Speech recognition and English content generation

[0238] The device accepts voice commands from the user. For example, suppose the user says, "Tell me today's news," using voice input. The device then converts this command into text data using voice recognition.

[0239] The converted text is sent to a server, where a generating artificial intelligence generates appropriate English news based on this text information. The generated content is selected through access to the latest news database.

[0240] English content presentation

[0241] The device plays the generated English news content to the user as audio or displays it as text on the smart glasses' display. For example, "Today's main news is about developments in the foreign exchange market." This allows the user to be exposed to English both visually and aurally.

[0242] Learning progress management and feedback

[0243] The device temporarily stores a history of the user's conversations and the content they listen to, and periodically sends it to the server.

[0244] The server analyzes this data to track the user's improvement in English skills. For example, it focuses on aspects such as pronunciation, grammar, and vocabulary frequency.

[0245] Based on the analysis results, the server provides feedback to the user. For example, it might say, "Your pronunciation has improved since yesterday; keep up the good work!"

[0246] This format allows users to learn English interactively anytime, anywhere, and to efficiently progress while monitoring their own progress. This system reduces the burden of learning while realizing practical and sustainable English education.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The user wears smart glasses and gives voice commands in English to request information. For example, they might say, "Tell me today's news."

[0250] Step 2:

[0251] The device captures the user's voice through its built-in microphone. Using speech recognition technology, the voice is converted into text data. This converted text accurately represents the instructions.

[0252] Step 3:

[0253] The device sends text data to the server along with contextual information such as the user's location and time. This enables more personalized responses.

[0254] Step 4:

[0255] The server analyzes the received text data and uses generative artificial intelligence to generate appropriate English content. For example, it accesses a database of the latest news, selects relevant news articles, and generates text in natural language format.

[0256] Step 5:

[0257] The server formats the generated English content in a way that is easy for the user to understand and sends it to the terminal. This content includes both audio and text data.

[0258] Step 6:

[0259] The device presents the generated content to the user. By using the voice output function to convey the news content to the user and simultaneously displaying it as text on the smart glasses' display, it promotes learning through both visual and auditory means.

[0260] Step 7:

[0261] The device monitors user responses and further interactions, and may send this information to the server as feedback. This data is used for progress management.

[0262] Step 8:

[0263] The server analyzes the learning data and generates feedback based on the user's progress. This feedback is sent periodically to the device, providing the user with encouragement such as "persistence pays off" and suggestions for improvement.

[0264] (Example 1)

[0265] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0266] Existing English learning systems lack sufficient personalized learning support based on users' progress and learning history. Furthermore, their limited ability to efficiently analyze voice-input information and generate and present relevant content makes it difficult to maximize learning effectiveness. Additionally, the inability to utilize learning history long-term makes it challenging to provide continuous learning support to users.

[0267] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0268] In this invention, the server includes a voice input conversion means, a generation means, and a presentation means. This makes it possible to efficiently convert the user's voice input into text information and generate and present personalized content based on that information. Furthermore, by managing learning progress and providing feedback, it is possible to realize continuous and effective learning support and improve the efficiency of the user's English learning.

[0269] "Voice input conversion means" refers to a technology that analyzes voice information and converts it into text information, and involves obtaining the user's utterance as a string of characters through speech recognition.

[0270] "Generation method" refers to a technology that creates new information content using generative artificial intelligence based on acquired textual information.

[0271] "Presentation means" refers to technologies for conveying generated information content to users visually or aurally, and is a means of dynamically displaying or playing information audibly.

[0272] "Learning progress management methods" refer to technologies that quantitatively grasp the progress of skill improvement by temporarily saving and analyzing a user's learning history.

[0273] A "feedback generation method" is a technology that creates information to communicate areas for improvement and changes to users based on analysis results, with the aim of providing individualized learning support.

[0274] "Data storage methods" refer to technologies that build databases to store learning history over the long term and use it for future learning.

[0275] "Personalization" refers to providing a more effective learning experience by adjusting learning content and feedback according to the user's characteristics and history.

[0276] This invention is a system that combines speech input conversion technology and generation technology to facilitate language acquisition in the user's daily life. The system aims to analyze the user's speech input, generate English content using a generation AI model, manage learning progress, and provide feedback.

[0277] The terminal has the ability to receive voice commands from the user and uses existing voice recognition software (e.g., a voice recognition API) to perform voice recognition. After converting the voice input into text information, it uses an internet connection and API communication technology to send the text information to the server.

[0278] The server utilizes generative AI models (e.g., natural language processing models) to generate appropriate English content based on the received text information. Specifically, it can access external information sources (e.g., news APIs) to provide the latest news and educational content. This generated content is tailored to the user's interests and incorporates features to keep them engaged in learning.

[0279] The device presents the generated English content to the user either as audio or text. Audio output uses text-to-speech technology (e.g., a text-to-speech API). Visual presentation is achieved by displaying text on smart glasses or a mobile device screen. This allows the user to engage with English through both auditory and visual means.

[0280] This system temporarily stores the user's activity history and conversation content to monitor their learning progress and analyze their progress. This data, periodically sent to the server, is used to analyze the user's learning performance. Based on this analysis, the user receives feedback such as, "Your pronunciation has improved since yesterday. Keep up the good work!" This allows users to continue learning while keeping track of their own progress.

[0281] For example, if a user gives a voice command such as "Tell me yesterday's sports news in English," the content is converted into text, a generative AI model on the server generates relevant English news, and it is presented to the user via the device. This prompt format allows users to use topics they are interested in on a daily basis, making language learning enjoyable.

[0282] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0283] Step 1:

[0284] The terminal receives voice input from the user. When the user says "Tell me yesterday's sports news in English", this voice becomes the input. The terminal uses voice recognition software to convert the voice data into character data. As a result, character data in text format is output.

[0285] Step 2:

[0286] The terminal sends the converted character data to the server. At this time, secure communication is performed using HTTPS, and the character data is provided to the server as input. The server receives this data and can perform the following processing.

[0287] Step 3:

[0288] The server activates the generation AI model and analyzes the received character data. Through this analysis, it is determined what kind of content is required. Based on this character data, the server obtains relevant information from the latest news API and generates relevant English news content. The generated English content is output.

[0289] Step 4:

[0290] The terminal receives the generated English content sent from the server. Based on this, it performs an operation to present it to the user through vision or hearing. Specifically, it displays text on the display of smart glasses or presents it to the user as voice using synthetic voice technology. As a result, the user can access English news content.

[0291] Step 5:

[0292] The device records user activity and temporarily stores learning progress. Data on which content the user watched or listened to and for how long is used as input, and this data is recorded to understand learning trends. This data is later sent to the server.

[0293] Step 6:

[0294] The server analyzes the learning data received from the device. Detailed data, including learning history and pronunciation evaluations, is used as input to check the user's skill improvement. Based on this analysis, the server generates feedback and outputs a feedback message to the user. This message, such as "Your pronunciation has improved since yesterday," is conveyed to the user via the device.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] This invention aims to provide efficient learning support in users' daily lives, and in particular, to provide continuous and effective support for English language learning. Many learning support tools currently on the market struggle to adequately meet the individual needs of users and offer limited interactive learning experiences. To address these challenges, this invention aims to provide a learning system that seamlessly integrates into the user's daily life.

[0298] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0299] In this invention, the server includes data conversion means for acquiring voice input and converting the voice data into text data, generation means for generating information content based on the acquired text data using generative artificial intelligence, and output means for presenting the generated information content to the user audibly or visually. This allows users to naturally acquire learning opportunities in their daily lives. Furthermore, the efficient learning experience is enhanced by the provision of appropriate information presentation and feedback.

[0300] A "data conversion means that acquires voice input and converts voice data into text data" is a function that receives voice information and converts it into corresponding character information using a language model.

[0301] "Generative means for generating information content based on text data acquired using generative artificial intelligence" refers to a function that uses knowledge databases and learning models to create appropriate information based on given text information.

[0302] "Output means for presenting generated information content to the user in audio or visual form" refers to a function for providing the generated information to the user using display on a screen or speech synthesis functionality.

[0303] "An evaluation management system that monitors and analyzes users' learning progress" refers to a function that records users' learning activities, analyzes the data, and evaluates their learning progress.

[0304] A "feedback generation method that provides feedback based on learning progress" is a function that presents advice and areas for improvement according to the user's progress during the learning process.

[0305] "An information storage method that records user behavior history and builds a long-term learning database" refers to a function that collects user activity data and builds learning history and trends over time.

[0306] "Communication means for acquiring information from external resources via an Internet connection" refers to a function for accessing data and services existing externally through a network and acquiring necessary information.

[0307] "Activity cooperation means for providing information in a timely manner based on the user's life activities" refers to a function for making adjustments to provide information at an optimal timing according to the user's daily actions.

[0308] The system for implementing this invention is constructed using a smart device (mainly smart glasses) and a network connection. Hereinafter, the components and operations of the system will be described.

[0309] First, the user gives an instruction using the voice input function of the smart device. This voice data is converted into text data by applying voice recognition technology. For voice recognition, a highly accurate language model is used, and for example, Google Cloud Speech-to-Text API may be used.

[0310] After that, the server acquires the converted text data and generates appropriate information content using a generative artificial intelligence (generative AI model). For this generative AI model, for example, by using OpenAI's GPT model, news and learning content corresponding to the user's request are generated. In the generation process, necessary data is acquired from the latest external information sources via the Internet, and the content is created based on that data.

[0311] The generated information content is transmitted from the server to the smart device and output visually or audibly to the user. Visually, text is displayed on the display of the smart glasses, and audibly, information is provided in a form audible to the user using a text-to-speech system (such as Amazon Polly).

[0312] Simultaneously, the device monitors the user's learning progress, and the server collects and analyzes the progress data. Learning history and behavioral data are stored in a long-term learning database, and the server generates feedback based on this data and sends it to the smart device. This feedback helps to improve the quality of the user's learning.

[0313] For example, if a user says, "Tell me the main news stories this morning," speech recognition converts this instruction into text, and the server uses a generative AI model to generate the latest news. The generated news is displayed visually on the smart glasses and played aloud. Feedback is provided, such as, "You have learned more vocabulary related to the news than yesterday."

[0314] Example of a prompt:

[0315] User request: "What are the main news stories this morning?"

[0316] Prompt to the generative AI model: "Search for the latest news and provide concise English news articles on key topics."

[0317] This configuration allows users to continue learning efficiently and naturally at various moments in their daily lives.

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The user provides voice input through a smart device. The input voice data is captured through the device's microphone. In this process, the user's voice commands are reproduced and recorded as digital voice data.

[0321] Step 2:

[0322] The device sends the captured audio data to a speech recognition engine, which converts it into text data. The input is audio data, and the output is the corresponding text data. The speech recognition engine uses an advanced language model (e.g., Google Cloud Speech-to-Text) to analyze the audio data and accurately convert it into text.

[0323] Step 3:

[0324] The server receives text data sent from the terminal and generates informational content using a generative AI model. The input is text data, and the output is the generated informational content. Specifically, the server sends prompts to the OpenAI GPT model to retrieve and generate the latest news information, etc.

[0325] Step 4:

[0326] The server transmits the generated information content to the terminal, which then presents it to the user via a smart device. The input is the generated information content, and the output is the visual or audio information presented to the user. The terminal displays text on its screen and also uses a speech synthesis engine to play the information aloud.

[0327] Step 5:

[0328] The device collects user learning progress data and reports it periodically to the server. Input is user usage data (e.g., viewing time, interaction content), and output is a log sent to the server as progress data. This data is important for recording learning outcomes and habits.

[0329] Step 6:

[0330] The server analyzes accumulated user progress data and generates feedback. The input is the accumulated data, and the output is a feedback message for the user. The server queries the database and generates advice based on the user's learning patterns and progress.

[0331] Step 7:

[0332] Feedback is sent to the user via the device. The input is feedback from the server, and the output is feedback information presented to the user. The device enhances the user's motivation to learn by clearly presenting the feedback content through displays and audio.

[0333] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0334] This invention is a system that realizes a more personalized English learning experience by incorporating an emotion engine to recognize the user's emotional state and provide English content that is appropriate to that state. By utilizing an emotion engine in addition to a combination of smart glasses, speech recognition technology, and generative artificial intelligence, the system can customize responses to the user's emotions.

[0335] Personalized emotion recognition and response

[0336] The device acquires the user's voice input and converts that voice data into text data. Furthermore, it utilizes an emotion engine to analyze the user's emotional state from the voice data. This emotion analysis is based on factors such as voice tone, speaking speed, and word choice.

[0337] The server receives emotional information transmitted along with the text data and generates English content according to that emotional state. For example, if the user is relaxed, it will select content that creates a relaxed atmosphere.

[0338] Content presentation and feedback

[0339] The device presents the generated English content to the user in audio or visual format. By making adjustments that respond to the user's emotions, the user can learn in a more receptive way. For example, encouraging language is used for a user who is feeling down.

[0340] The server periodically monitors the user's learning progress and generates progress-based feedback based on sentiment data. This feedback provides specific advice on how the user can improve. For example, it can offer sentiment-based praise such as, "Your speech today was delivered with confidence."

[0341] Strengthening user engagement

[0342] This system allows users to learn English in a learning environment that constantly recognizes their own emotional state. As a result, a more effective and satisfying learning experience is provided. Furthermore, emotional information is accumulated in a database as long-term learning history and used to improve future learning content. This leads to greater individualization for each user and is expected to improve learning efficiency.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] The user wears smart glasses and gives voice commands to request information specified in English. For example, they might say, "Tell me about today's interesting articles."

[0346] Step 2:

[0347] The device captures the user's voice through its built-in microphone and converts it into text data using speech recognition technology. Simultaneously, the voice data is input into an emotion engine to analyze the user's emotional state.

[0348] Step 3:

[0349] The device sends the converted text data and sentiment analysis results to the server. The sentiment analysis results include, for example, whether the user is excited or relaxed.

[0350] Step 4:

[0351] The server uses generative artificial intelligence to generate optimal English content based on the received text data and sentiment information. It adjusts the tone and content of the article according to the user's emotional state.

[0352] Step 5:

[0353] The server formats the generated English content and sends it to the terminal, including audio and text data. Adjustments are made based on the user's emotions.

[0354] Step 6:

[0355] The device presents the generated English content to the user in both audio and text formats. This allows the user to receive information in a way that is appropriate to their emotions.

[0356] Step 7:

[0357] The device monitors further user interactions and sends that data to the server. This includes user reactions and changes in emotion.

[0358] Step 8:

[0359] The server analyzes interaction history and sentiment data to generate feedback based on the user's learning progress. This feedback takes emotional aspects into account, providing the user with specific advice and praise.

[0360] (Example 2)

[0361] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0362] The problem that this invention aims to solve is the failure to provide personalized and effective learning experiences when uniform learning content is provided without considering the learner's emotional state. Conventional systems have difficulty providing individualized support based on the learner's emotions and learning progress, which has sometimes led to decreased learning efficiency.

[0363] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0364] In this invention, the server includes a speech conversion means, an emotion analysis means, and a creative means. This makes it possible to provide language learning content that is individually adapted to the user's emotional state in real time.

[0365] "Speech conversion means" refers to a technology or device for converting speech information into text information.

[0366] "Emotional analysis means" refers to a technology or device that analyzes a user's emotional state from voice or text information and generates emotional information.

[0367] "Creative means" refers to a technology or device that uses generative artificial intelligence to create language learning content based on generated emotional and textual information.

[0368] "Presentation means" refers to a technology or device that provides personalized language learning content to the user visually or aurally.

[0369] "Progress evaluation means" refers to a technology or device that monitors the user's learning progress and performs analysis while taking their emotional state into consideration.

[0370] "Response generation means" refers to a technology or device that generates and provides feedback based on learning status and emotional information.

[0371] "Information storage means" refers to a technology or device that records the user's interaction history and builds a long-term learning information database.

[0372] The present invention is a system that personalizes the learning experience based on the user's emotional state. This system comprises a voice conversion means, an emotion analysis means, a creation means, a presentation means, a progress evaluation means, and a response generation means.

[0373] First, the device uses a microphone or the voice input function of a smart device to acquire the user's voice input. Specific hardware examples include smart glasses and Bluetooth earphones. The voice input is converted into text data using speech recognition software. A specific example of this software is a speech recognition engine.

[0374] Next, the device uses this converted text information to analyze the user's emotional state using sentiment analysis software. Sentiment analysis takes into account voice tone, speaking speed, and word choice. Specifically, the sentiment analysis engine processes the data.

[0375] The server then receives the generated emotional and textual information and uses a generative AI model to create language learning content. This creative process utilizes a content generation engine. An example of a prompt is, "Generate relaxing English learning content for the user."

[0376] Next, the device presents the generated learning content to the user. The presentation method is either visual or audible. Specifically, it may be displayed visually on the smart glasses' display or played as audio through a Bluetooth speaker.

[0377] The server continuously monitors the user's learning progress, evaluates and analyzes it based on sentiment information, and provides a detailed understanding of how the user is progressing.

[0378] Finally, the system generates feedback based on learning progress and emotional information. This feedback is provided to the user and includes advice to further improve the learning experience. For example, it might say, "You made very good progress today."

[0379] This system is expected to improve learning efficiency by providing users with personalized learning experiences tailored to their emotional state.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] The device acquires voice input from the user. Voice input is acquired through the microphone of smart glasses or earphones. The acquired voice data is converted into text data using a speech recognition engine. In this process, the input is an audio signal, and the output is the corresponding text data. The speech recognition engine analyzes the audio signal and outputs it as text.

[0383] Step 2:

[0384] The terminal performs sentiment analysis using the converted text data. The sentiment analysis engine analyzes the characteristics of the text and audio data, such as tone and speed, to determine the user's emotional state. In this step, text data and audio characteristic data are taken as input, and sentiment information is generated as output. The sentiment analysis engine evaluates the input data and assigns sentiment labels.

[0385] Step 3:

[0386] The server receives text data and sentiment information sent from the terminal. Based on this data, a generative AI model is used to generate appropriate language learning content. The input for this step is sentiment information and text data, and the output is customized learning content. The generative AI model takes a prompt sentence, for example, "Generate relaxing English learning content for the user," as input and performs the operation to create content.

[0387] Step 4:

[0388] The device presents the generated learning content to the user. This presentation is done via voice reading or display. The input is the generated learning content, and the output is the format presented to the user. In practice, visual content is displayed on the smart glasses' screen, and audio content is played through a Bluetooth speaker.

[0389] Step 5:

[0390] The server monitors the user's learning progress and analyzes data, including sentiment information. Based on the analysis results, it evaluates the effectiveness of the learning content and the user's emotional state. The inputs are progress data and sentiment information, and the outputs are evaluation and analysis results. The progress monitoring engine continuously analyzes the data and works to understand the learning trends.

[0391] Step 6:

[0392] The server generates feedback based on analysis results and sentiment information. This generated feedback is provided to the user and includes messages that suggest areas for improvement in learning and motivate them. The input is analysis results and sentiment information, and the output is the feedback message. The feedback generation engine uses evaluation information to create feedback and communicates it to the user.

[0393] (Application Example 2)

[0394] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0395] Currently, information systems in smart cities lack sufficient content customization that takes into account users' emotional states, limiting the potential for improving the user experience. Furthermore, the lack of flexible information delivery that responds to temporary emotional fluctuations prevents users from maximizing their convenience. In addition, there is a need to provide a more personalized experience by utilizing users' long-term history.

[0396] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0397] In this invention, the server includes a voice recognition means, an emotion recognition means, a generation means, and a means for generating information about public facilities and providing guide information optimized based on the user's emotions. This enables the provision of dynamic and personalized information that reflects the user's emotional state.

[0398] 1. "Speech recognition means" refers to a device that has the function of acquiring speech data and converting it into text data.

[0399] 2. "Generation means" refers to a device that uses generative artificial intelligence to generate content based on acquired text data.

[0400] 3. "Emotion recognition means" refers to a device that analyzes the user's voice data and performs processing to determine their emotional state.

[0401] 4. "Means of customization" refers to a device for generating optimal content tailored to the user's state based on analysis results.

[0402] 5. “Presentation means” refers to a device for providing the generated content to the user in audio or visual form.

[0403] 6. A "progress management device" is a device for monitoring the user's progress and collecting and analyzing that data.

[0404] 7. A "feedback generation means" is a device for generating and providing information and advice based on the user's progress.

[0405] 8. "Means for generating and providing information" refers to a device for generating and providing optimized guide information about public facilities based on the user's emotions.

[0406] This invention is a system for providing users with emotionally appropriate information within a smart city. The system mainly consists of terminals and servers. A detailed embodiment of this system is described here.

[0407] The terminal is a device equipped with speech recognition capabilities (e.g., smart glasses) that receives voice input from the user. Specifically, the terminal uses speech recognition to convert the voice data into text data in real time. This utilizes speech recognition APIs such as Google Cloud Speech-to-Text.

[0408] Next, the server uses emotion recognition tools to analyze the text and audio data sent from the terminal and determine the user's emotional state. This process utilizes emotion analysis tools such as IBM Watson Tone Analyzer. Based on the analysis, the server uses a generative AI model (e.g., OpenAI GPT-4) to generate appropriate content.

[0409] This generation method accesses a broad database containing information on public facilities and combines information best suited to the user's emotions to create guide information. The generated content can be customized to reflect the user's individual needs and interests.

[0410] Finally, using a presentation method, the device presents the generated customized information to the user either audibly or visually. This allows the user to receive information optimized for their emotional state. For example, if the user is relaxed, a prompt such as "Please recommend a park where I can feel tranquility and beauty" will be met with recommendations for appropriate facilities.

[0411] The operation of this system will improve the user experience within smart cities and enable more comfortable and effective information delivery.

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The device acquires the user's voice input. This input can be in various forms, such as phone calls or instructions. Speech recognition is used to convert this voice data into text data. The Google Cloud Speech-to-Text API is used for this purpose, and the text input is sent to the server.

[0415] Step 2:

[0416] The server analyzes the user's emotional state using emotion recognition based on text data received from the terminal. Emotional data is generated using an emotion analysis engine (e.g., IBM Watson Tone Analyzer) based on factors such as voice tone and word selection. This output represents the user's emotional state.

[0417] Step 3:

[0418] The server utilizes a generative AI model based on emotional data to generate information best suited to the user's emotions. The generation process prepares content in response to prompts. For example, if the user is in a relaxed emotional state, a prompt such as "Please recommend a park where I can feel tranquility and beauty" might be used, and facility information would be created based on this prompt.

[0419] Step 4:

[0420] The server customizes the generated information to create optimal guide information tailored to the user. This process takes into account the user's past interaction data and current situation, adjusting the information provided to make it more engaging and relevant.

[0421] Step 5:

[0422] The device presents the user with customized guide information received from the server. This information can be presented visually on the smart glasses' display or verbally using a speech synthesis API (e.g., Amazon Polly). This ensures that the information is presented in a way that is easily accepted and understandable to the user.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0439] This invention implements a system that effectively supports users' English language learning in their daily lives by combining smart glasses and artificial intelligence. This system has functions for speech recognition, presentation of generated English content, monitoring of learning progress, and provision of feedback.

[0440] Speech recognition and English content generation

[0441] The device accepts voice commands from the user. For example, suppose the user says, "Tell me today's news," using voice input. The device then converts this command into text data using voice recognition.

[0442] The converted text is sent to a server, where a generating artificial intelligence generates appropriate English news based on this text information. The generated content is selected through access to the latest news database.

[0443] English content presentation

[0444] The device plays the generated English news content to the user as audio or displays it as text on the smart glasses' display. For example, "Today's main news is about developments in the foreign exchange market." This allows the user to be exposed to English both visually and aurally.

[0445] Learning progress management and feedback

[0446] The device temporarily stores a history of the user's conversations and the content they listen to, and periodically sends it to the server.

[0447] The server analyzes this data to track the user's improvement in English skills. For example, it focuses on aspects such as pronunciation, grammar, and vocabulary frequency.

[0448] Based on the analysis results, the server provides feedback to the user. For example, it might say, "Your pronunciation has improved since yesterday; keep up the good work!"

[0449] This format allows users to learn English interactively anytime, anywhere, and to efficiently progress while monitoring their own progress. This system reduces the burden of learning while realizing practical and sustainable English education.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The user wears smart glasses and gives voice commands in English to request information. For example, they might say, "Tell me today's news."

[0453] Step 2:

[0454] The device captures the user's voice through its built-in microphone. Using speech recognition technology, the voice is converted into text data. This converted text accurately represents the instructions.

[0455] Step 3:

[0456] The device sends text data to the server along with contextual information such as the user's location and time. This enables more personalized responses.

[0457] Step 4:

[0458] The server analyzes the received text data and uses generative artificial intelligence to generate appropriate English content. For example, it accesses a database of the latest news, selects relevant news articles, and generates text in natural language format.

[0459] Step 5:

[0460] The server formats the generated English content in a way that is easy for the user to understand and sends it to the terminal. This content includes both audio and text data.

[0461] Step 6:

[0462] The device presents the generated content to the user. By using the voice output function to convey the news content to the user and simultaneously displaying it as text on the smart glasses' display, it promotes learning through both visual and auditory means.

[0463] Step 7:

[0464] The device monitors user responses and further interactions, and may send this information to the server as feedback. This data is used for progress management.

[0465] Step 8:

[0466] The server analyzes the learning data and generates feedback based on the user's progress. This feedback is sent periodically to the device, providing the user with encouragement such as "persistence pays off" and suggestions for improvement.

[0467] (Example 1)

[0468] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0469] Existing English learning systems lack sufficient personalized learning support based on users' progress and learning history. Furthermore, their limited ability to efficiently analyze voice-input information and generate and present relevant content makes it difficult to maximize learning effectiveness. Additionally, the inability to utilize learning history long-term makes it challenging to provide continuous learning support to users.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes a voice input conversion means, a generation means, and a presentation means. This makes it possible to efficiently convert the user's voice input into text information and generate and present personalized content based on that information. Furthermore, by managing learning progress and providing feedback, it is possible to realize continuous and effective learning support and improve the efficiency of the user's English learning.

[0472] "Voice input conversion means" refers to a technology that analyzes voice information and converts it into text information, and involves obtaining the user's utterance as a string of characters through speech recognition.

[0473] "Generation method" refers to a technology that creates new information content using generative artificial intelligence based on acquired textual information.

[0474] "Presentation means" refers to technologies for conveying generated information content to users visually or aurally, and is a means of dynamically displaying or playing information audibly.

[0475] "Learning progress management methods" refer to technologies that quantitatively grasp the progress of skill improvement by temporarily saving and analyzing a user's learning history.

[0476] A "feedback generation method" is a technology that creates information to communicate areas for improvement and changes to users based on analysis results, with the aim of providing individualized learning support.

[0477] "Data storage methods" refer to technologies that build databases to store learning history over the long term and use it for future learning.

[0478] "Personalization" refers to providing a more effective learning experience by adjusting learning content and feedback according to the user's characteristics and history.

[0479] This invention is a system that combines speech input conversion technology and generation technology to facilitate language acquisition in the user's daily life. The system aims to analyze the user's speech input, generate English content using a generation AI model, manage learning progress, and provide feedback.

[0480] The terminal has the ability to receive voice commands from the user and uses existing voice recognition software (e.g., a voice recognition API) to perform voice recognition. After converting the voice input into text information, it uses an internet connection and API communication technology to send the text information to the server.

[0481] The server utilizes generative AI models (e.g., natural language processing models) to generate appropriate English content based on the received text information. Specifically, it can access external information sources (e.g., news APIs) to provide the latest news and educational content. This generated content is tailored to the user's interests and incorporates features to keep them engaged in learning.

[0482] The device presents the generated English content to the user either as audio or text. Audio output uses text-to-speech technology (e.g., a text-to-speech API). Visual presentation is achieved by displaying text on smart glasses or a mobile device screen. This allows the user to engage with English through both auditory and visual means.

[0483] This system temporarily stores the user's activity history and conversation content to monitor their learning progress and analyze their progress. This data, periodically sent to the server, is used to analyze the user's learning performance. Based on this analysis, the user receives feedback such as, "Your pronunciation has improved since yesterday. Keep up the good work!" This allows users to continue learning while keeping track of their own progress.

[0484] For example, if a user gives a voice command such as "Tell me yesterday's sports news in English," the content is converted into text, a generative AI model on the server generates relevant English news, and it is presented to the user via the device. This prompt format allows users to use topics they are interested in on a daily basis, making language learning enjoyable.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The device accepts voice input from the user. When the user says, "Tell me yesterday's sports news in English," this voice becomes the input. The device uses voice recognition software to convert the voice data into text data. As a result, the text data is output.

[0488] Step 2:

[0489] The terminal sends the converted character data to the server. Secure communication is performed using HTTPS, and the character data is provided to the server as input. The server receives this data and can then perform the following processing.

[0490] Step 3:

[0491] The server activates a generative AI model and analyzes the received text data. This analysis determines what kind of content is required. Based on this text data, the server retrieves relevant information from the latest news API and generates relevant English news content. The generated English content becomes the output.

[0492] Step 4:

[0493] The device receives pre-generated English content sent from the server. Based on this, it performs actions to present the content to the user visually or aurally. Specifically, it displays text on the smart glasses' display or presents it to the user as audio using synthesized speech technology. As a result, the user can access English news content.

[0494] Step 5:

[0495] The device records user activity and temporarily stores learning progress. Data on which content the user watched or listened to and for how long is used as input, and this data is recorded to understand learning trends. This data is later sent to the server.

[0496] Step 6:

[0497] The server analyzes the learning data received from the device. Detailed data, including learning history and pronunciation evaluations, is used as input to check the user's skill improvement. Based on this analysis, the server generates feedback and outputs a feedback message to the user. This message, such as "Your pronunciation has improved since yesterday," is conveyed to the user via the device.

[0498] (Application Example 1)

[0499] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] This invention aims to provide efficient learning support in users' daily lives, and in particular, to provide continuous and effective support for English language learning. Many learning support tools currently on the market struggle to adequately meet the individual needs of users and offer limited interactive learning experiences. To address these challenges, this invention aims to provide a learning system that seamlessly integrates into the user's daily life.

[0501] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0502] In this invention, the server includes data conversion means for acquiring voice input and converting the voice data into text data, generation means for generating information content based on the acquired text data using generative artificial intelligence, and output means for presenting the generated information content to the user audibly or visually. This allows users to naturally acquire learning opportunities in their daily lives. Furthermore, the efficient learning experience is enhanced by the provision of appropriate information presentation and feedback.

[0503] A "data conversion means that acquires voice input and converts voice data into text data" is a function that receives voice information and converts it into corresponding character information using a language model.

[0504] "Generative means for generating information content based on text data acquired using generative artificial intelligence" refers to a function that uses knowledge databases and learning models to create appropriate information based on given text information.

[0505] "Output means for presenting generated information content to the user in audio or visual form" refers to a function for providing the generated information to the user using display on a screen or speech synthesis functionality.

[0506] "An evaluation management system that monitors and analyzes users' learning progress" refers to a function that records users' learning activities, analyzes the data, and evaluates their learning progress.

[0507] A "feedback generation method that provides feedback based on learning progress" is a function that presents advice and areas for improvement according to the user's progress during the learning process.

[0508] "An information storage method that records user behavior history and builds a long-term learning database" refers to a function that collects user activity data and builds learning history and trends over time.

[0509] "A means of communication that obtains information from external resources via an internet connection" refers to a function that accesses data and services existing externally through a network and obtains the necessary information.

[0510] "Activity coordination means that provide information in a timely manner based on the user's daily activities" refers to a function that adjusts to provide information at the optimal timing in accordance with the user's daily actions.

[0511] The system for implementing this invention is constructed using smart devices (primarily smart glasses) and network connectivity. The system's components and operation are described below.

[0512] First, the user gives instructions using the voice input function of their smart device. This voice data is converted into text data using speech recognition technology. High-precision language models are used for speech recognition, such as the Google Cloud Speech-to-Text API.

[0513] Subsequently, the server retrieves the converted text data and uses generative artificial intelligence (generative AI model) to generate appropriate information content. This generative AI model, for example, using OpenAI's GPT model, generates news and learning content tailored to the user's requests. During the generation process, necessary data is obtained from the latest external information sources via the internet, and content is created based on that data.

[0514] The generated information content is sent from the server to a smart device and output to the user either visually or audibly. Visually, text is displayed on the smart glasses' screen, and audibly, information is provided to the user in an audible form using a speech synthesis system (such as Amazon Polly).

[0515] Simultaneously, the device monitors the user's learning progress, and the server collects and analyzes the progress data. Learning history and behavioral data are stored in a long-term learning database, and the server generates feedback based on this data and sends it to the smart device. This feedback helps to improve the quality of the user's learning.

[0516] For example, if a user says, "Tell me the main news stories this morning," speech recognition converts this instruction into text, and the server uses a generative AI model to generate the latest news. The generated news is displayed visually on the smart glasses and played aloud. Feedback is provided, such as, "You have learned more vocabulary related to the news than yesterday."

[0517] Example of a prompt:

[0518] User request: "What are the main news stories this morning?"

[0519] Prompt to the generative AI model: "Search for the latest news and provide concise English news articles on key topics."

[0520] This configuration allows users to continue learning efficiently and naturally at various moments in their daily lives.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The user provides voice input through a smart device. The input voice data is captured through the device's microphone. In this process, the user's voice commands are reproduced and recorded as digital voice data.

[0524] Step 2:

[0525] The device sends the captured audio data to a speech recognition engine, which converts it into text data. The input is audio data, and the output is the corresponding text data. The speech recognition engine uses an advanced language model (e.g., Google Cloud Speech-to-Text) to analyze the audio data and accurately convert it into text.

[0526] Step 3:

[0527] The server receives text data sent from the terminal and generates informational content using a generative AI model. The input is text data, and the output is the generated informational content. Specifically, the server sends prompts to the OpenAI GPT model to retrieve and generate the latest news information, etc.

[0528] Step 4:

[0529] The server transmits the generated information content to the terminal, which then presents it to the user via a smart device. The input is the generated information content, and the output is the visual or audio information presented to the user. The terminal displays text on its screen and also uses a speech synthesis engine to play the information aloud.

[0530] Step 5:

[0531] The device collects user learning progress data and reports it periodically to the server. Input is user usage data (e.g., viewing time, interaction content), and output is a log sent to the server as progress data. This data is important for recording learning outcomes and habits.

[0532] Step 6:

[0533] The server analyzes accumulated user progress data and generates feedback. The input is the accumulated data, and the output is feedback messages for the user. The server queries the database and generates advice based on the user's learning patterns and progress.

[0534] Step 7:

[0535] Feedback is sent to the user via the device. The input is feedback from the server, and the output is feedback information presented to the user. The device enhances the user's motivation to learn by clearly presenting the feedback content through displays and audio.

[0536] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0537] This invention is a system that realizes a more personalized English learning experience by incorporating an emotion engine to recognize the user's emotional state and provide English content that is appropriate to that state. By utilizing an emotion engine in addition to a combination of smart glasses, speech recognition technology, and generative artificial intelligence, the system can customize responses to the user's emotions.

[0538] Personalized emotion recognition and response

[0539] The device acquires the user's voice input and converts that voice data into text data. Furthermore, it utilizes an emotion engine to analyze the user's emotional state from the voice data. This emotion analysis is based on factors such as voice tone, speaking speed, and word choice.

[0540] The server receives emotional information transmitted along with the text data and generates English content according to that emotional state. For example, if the user is relaxed, it will select content that creates a relaxed atmosphere.

[0541] Content presentation and feedback

[0542] The device presents the generated English content to the user in audio or visual format. By making adjustments that respond to the user's emotions, the user can learn in a more receptive way. For example, encouraging language is used for a user who is feeling down.

[0543] The server periodically monitors the user's learning progress and generates progress-based feedback based on sentiment data. This feedback provides specific advice on how the user can improve. For example, it can offer sentiment-based praise such as, "Your speech today was delivered with confidence."

[0544] Strengthening user engagement

[0545] This system allows users to learn English in a learning environment that constantly recognizes their own emotional state. As a result, a more effective and satisfying learning experience is provided. Furthermore, emotional information is accumulated in a database as long-term learning history and used to improve future learning content. This leads to greater individualization for each user and is expected to improve learning efficiency.

[0546] The following describes the processing flow.

[0547] Step 1:

[0548] The user wears smart glasses and gives voice commands to request information specified in English. For example, they might say, "Tell me about today's interesting articles."

[0549] Step 2:

[0550] The device captures the user's voice through its built-in microphone and converts it into text data using speech recognition technology. Simultaneously, the voice data is input into an emotion engine to analyze the user's emotional state.

[0551] Step 3:

[0552] The device sends the converted text data and sentiment analysis results to the server. The sentiment analysis results include, for example, whether the user is excited or relaxed.

[0553] Step 4:

[0554] The server uses generative artificial intelligence to generate optimal English content based on the received text data and sentiment information. It adjusts the tone and content of the article according to the user's emotional state.

[0555] Step 5:

[0556] The server formats the generated English content and sends it to the terminal, including both audio and text data. Adjustments are made based on the user's emotions.

[0557] Step 6:

[0558] The device presents the generated English content to the user in both audio and text formats. This allows the user to receive information in a way that is appropriate to their emotions.

[0559] Step 7:

[0560] The device monitors further user interactions and sends that data to the server. This includes user reactions and changes in emotion.

[0561] Step 8:

[0562] The server analyzes interaction history and sentiment data to generate feedback based on the user's learning progress. This feedback takes emotional aspects into account, providing the user with specific advice and praise.

[0563] (Example 2)

[0564] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] The problem that this invention aims to solve is the failure to provide personalized and effective learning experiences when uniform learning content is provided without considering the learner's emotional state. Conventional systems have difficulty providing individualized support based on the learner's emotions and learning progress, which has sometimes led to decreased learning efficiency.

[0566] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0567] In this invention, the server includes a speech conversion means, an emotion analysis means, and a creative means. This makes it possible to provide language learning content that is individually adapted to the user's emotional state in real time.

[0568] "Speech conversion means" refers to a technology or device for converting speech information into text information.

[0569] "Emotional analysis means" refers to a technology or device that analyzes a user's emotional state from voice or text information and generates emotional information.

[0570] "Creative means" refers to a technology or device that uses generative artificial intelligence to create language learning content based on generated emotional and textual information.

[0571] "Presentation means" refers to a technology or device that provides personalized language learning content to the user visually or aurally.

[0572] "Progress evaluation means" refers to a technology or device that monitors the user's learning progress and performs analysis while taking their emotional state into consideration.

[0573] "Response generation means" refers to a technology or device that generates and provides feedback based on learning status and emotional information.

[0574] "Information storage means" refers to a technology or device that records the user's interaction history and builds a long-term learning information database.

[0575] The present invention is a system that personalizes the learning experience based on the user's emotional state. This system comprises a voice conversion means, an emotion analysis means, a creation means, a presentation means, a progress evaluation means, and a response generation means.

[0576] First, the device uses a microphone or the voice input function of a smart device to acquire the user's voice input. Specific hardware examples include smart glasses and Bluetooth earphones. The voice input is converted into text data using speech recognition software. A specific example of this software is a speech recognition engine.

[0577] Next, the device uses this converted text information to analyze the user's emotional state using sentiment analysis software. Sentiment analysis takes into account voice tone, speaking speed, and word choice. Specifically, the sentiment analysis engine processes the data.

[0578] The server then receives the generated sentiment and text information and uses a generative AI model to create language learning content. This creative process utilizes a content generation engine. An example of a prompt is, "Generate relaxing English learning content for the user."

[0579] Next, the device presents the generated learning content to the user. The presentation method is either visual or audible. Specifically, it may be displayed visually on the smart glasses' display or played as audio through a Bluetooth speaker.

[0580] The server continuously monitors the user's learning progress, evaluates and analyzes it based on sentiment information, and provides a detailed understanding of how the user is progressing.

[0581] Finally, the system generates feedback based on learning progress and emotional information. This feedback is provided to the user and includes advice to further improve the learning experience. For example, it might say, "You made very good progress today."

[0582] This system is expected to improve learning efficiency by providing users with personalized learning experiences tailored to their emotional state.

[0583] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0584] Step 1:

[0585] The device acquires voice input from the user. Voice input is acquired through the microphone of smart glasses or earphones. The acquired voice data is converted into text data using a speech recognition engine. In this process, the input is an audio signal, and the output is the corresponding text data. The speech recognition engine analyzes the audio signal and outputs it as text.

[0586] Step 2:

[0587] The terminal performs sentiment analysis using the converted text data. The sentiment analysis engine analyzes the characteristics of the text and audio data, such as tone and speed, to determine the user's emotional state. In this step, text data and audio characteristic data are taken as input, and sentiment information is generated as output. The sentiment analysis engine evaluates the input data and assigns sentiment labels.

[0588] Step 3:

[0589] The server receives text data and sentiment information sent from the terminal. Based on this data, a generative AI model is used to generate appropriate language learning content. The input for this step is sentiment information and text data, and the output is customized learning content. The generative AI model takes a prompt sentence, for example, "Generate relaxing English learning content for the user," as input and performs the operation to create content.

[0590] Step 4:

[0591] The device presents the generated learning content to the user. This presentation is done via voice reading or display. The input is the generated learning content, and the output is the format presented to the user. In practice, visual content is displayed on the smart glasses' screen, and audio content is played through a Bluetooth speaker.

[0592] Step 5:

[0593] The server monitors the user's learning progress and analyzes data, including sentiment information. Based on the analysis results, it evaluates the effectiveness of the learning content and the user's emotional state. The inputs are progress data and sentiment information, and the outputs are evaluation and analysis results. The progress monitoring engine continuously analyzes the data and works to understand the learning trends.

[0594] Step 6:

[0595] The server generates feedback based on analysis results and sentiment information. This generated feedback is provided to the user and includes messages that suggest areas for improvement in learning and motivate them. The input is analysis results and sentiment information, and the output is the feedback message. The feedback generation engine uses evaluation information to create feedback and communicates it to the user.

[0596] (Application Example 2)

[0597] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0598] Currently, information systems in smart cities lack sufficient content customization that takes into account users' emotional states, limiting the potential for improving the user experience. Furthermore, the lack of flexible information delivery that responds to temporary emotional fluctuations prevents users from maximizing their convenience. In addition, there is a need to provide a more personalized experience by utilizing users' long-term history.

[0599] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0600] In this invention, the server includes a voice recognition means, an emotion recognition means, a generation means, and a means for generating information about public facilities and providing guide information optimized based on the user's emotions. This enables the provision of dynamic and personalized information that reflects the user's emotional state.

[0601] 1. "Speech recognition means" refers to a device that has the function of acquiring speech data and converting it into text data.

[0602] 2. "Generation means" refers to a device that uses generative artificial intelligence to generate content based on acquired text data.

[0603] 3. "Emotion recognition means" refers to a device that analyzes the user's voice data and performs processing to determine their emotional state.

[0604] 4. "Means of customization" refers to a device for generating optimal content tailored to the user's state based on analysis results.

[0605] 5. “Presentation means” refers to a device for providing the generated content to the user in audio or visual form.

[0606] 6. A "progress management device" is a device for monitoring the user's progress and collecting and analyzing that data.

[0607] 7. A "feedback generation means" is a device for generating and providing information and advice based on the user's progress.

[0608] 8. "Means for generating and providing information" refers to a device for generating and providing optimized guide information about public facilities based on the user's emotions.

[0609] This invention is a system for providing users with emotionally appropriate information within a smart city. The system mainly consists of terminals and servers. A detailed embodiment of this system is described here.

[0610] The terminal is a device equipped with speech recognition capabilities (e.g., smart glasses) that receives voice input from the user. Specifically, the terminal uses speech recognition to convert the voice data into text data in real time. This utilizes speech recognition APIs such as Google Cloud Speech-to-Text.

[0611] Next, the server uses emotion recognition tools to analyze the text and audio data sent from the terminal and determine the user's emotional state. This process utilizes emotion analysis tools such as IBM Watson Tone Analyzer. Based on the analysis, the server uses a generative AI model (e.g., OpenAI GPT-4) to generate appropriate content.

[0612] This generation method accesses a broad database containing information on public facilities and combines information best suited to the user's emotions to create guide information. The generated content can be customized to reflect the user's individual needs and interests.

[0613] Finally, using a presentation method, the device presents the generated customized information to the user either audibly or visually. This allows the user to receive information optimized for their emotional state. For example, if the user is relaxed, a prompt such as "Please recommend a park where I can feel tranquility and beauty" will be met with recommendations for appropriate facilities.

[0614] The operation of this system will improve the user experience within smart cities and enable more comfortable and effective information delivery.

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The device acquires the user's voice input. This input can be in various forms, such as phone calls or instructions. Speech recognition is used to convert this voice data into text data. The Google Cloud Speech-to-Text API is used for this purpose, and the text input is sent to the server.

[0618] Step 2:

[0619] The server analyzes the user's emotional state using emotion recognition based on text data received from the terminal. Emotional data is generated using an emotion analysis engine (e.g., IBM Watson Tone Analyzer) based on factors such as voice tone and word selection. This output represents the user's emotional state.

[0620] Step 3:

[0621] The server utilizes a generative AI model based on emotional data to generate information best suited to the user's emotions. The generation process prepares content in response to prompts. For example, if the user is in a relaxed emotional state, a prompt such as "Please recommend a park where I can feel tranquility and beauty" might be used, and facility information would be created based on this prompt.

[0622] Step 4:

[0623] The server customizes the generated information to create optimal guide information tailored to the user. This process takes into account the user's past interaction data and current situation, adjusting the information provided to make it more engaging and relevant.

[0624] Step 5:

[0625] The device presents the user with customized guide information received from the server. This information can be presented visually on the smart glasses' display or verbally using a speech synthesis API (e.g., Amazon Polly). This ensures that the information is presented in a way that is easily accepted and understandable to the user.

[0626] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] This invention implements a system that effectively supports users' English language learning in their daily lives by combining smart glasses and artificial intelligence. This system has functions for speech recognition, presentation of generated English content, monitoring of learning progress, and provision of feedback.

[0644] Speech recognition and English content generation

[0645] The device accepts voice commands from the user. For example, suppose the user says, "Tell me today's news," using voice input. The device then converts this command into text data using voice recognition.

[0646] The converted text is sent to a server, where a generating artificial intelligence generates appropriate English news based on this text information. The generated content is selected through access to the latest news database.

[0647] English content presentation

[0648] The device plays the generated English news content to the user as audio or displays it as text on the smart glasses' display. For example, "Today's main news is about developments in the foreign exchange market." This allows the user to be exposed to English both visually and aurally.

[0649] Learning progress management and feedback

[0650] The device temporarily stores a history of the user's conversations and the content they listen to, and periodically sends it to the server.

[0651] The server analyzes this data to track the user's improvement in English skills. For example, it focuses on aspects such as pronunciation, grammar, and vocabulary frequency.

[0652] Based on the analysis results, the server provides feedback to the user. For example, it might say, "Your pronunciation has improved since yesterday; keep up the good work!"

[0653] This format allows users to learn English interactively anytime, anywhere, and to efficiently progress while monitoring their own progress. This system reduces the burden of learning while realizing practical and sustainable English education.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The user wears smart glasses and gives voice commands in English to request information. For example, they might say, "Tell me today's news."

[0657] Step 2:

[0658] The device captures the user's voice through its built-in microphone. Using speech recognition technology, the voice is converted into text data. This converted text accurately represents the instructions.

[0659] Step 3:

[0660] The device sends text data to the server along with contextual information such as the user's location and time. This enables more personalized responses.

[0661] Step 4:

[0662] The server analyzes the received text data and uses generative artificial intelligence to generate appropriate English content. For example, it accesses a database of the latest news, selects relevant news articles, and generates text in natural language format.

[0663] Step 5:

[0664] The server formats the generated English content in a way that is easy for the user to understand and sends it to the terminal. This content includes both audio and text data.

[0665] Step 6:

[0666] The device presents the generated content to the user. By using the voice output function to convey the news content to the user and simultaneously displaying it as text on the smart glasses' display, it promotes learning through both visual and auditory means.

[0667] Step 7:

[0668] The device monitors user responses and further interactions, and may send this information to the server as feedback. This data is used for progress management.

[0669] Step 8:

[0670] The server analyzes the learning data and generates feedback based on the user's progress. This feedback is sent periodically to the device, providing the user with encouragement such as "persistence pays off" and suggestions for improvement.

[0671] (Example 1)

[0672] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] Existing English learning systems lack sufficient personalized learning support based on users' progress and learning history. Furthermore, their limited ability to efficiently analyze voice-input information and generate and present relevant content makes it difficult to maximize learning effectiveness. Additionally, the inability to utilize learning history long-term makes it challenging to provide continuous learning support to users.

[0674] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0675] In this invention, the server includes a voice input conversion means, a generation means, and a presentation means. This makes it possible to efficiently convert the user's voice input into text information and generate and present personalized content based on that information. Furthermore, by managing learning progress and providing feedback, it is possible to realize continuous and effective learning support and improve the efficiency of the user's English learning.

[0676] "Voice input conversion means" refers to a technology that analyzes voice information and converts it into text information, and involves obtaining the user's utterance as a string of characters through speech recognition.

[0677] "Generation method" refers to a technology that creates new information content using generative artificial intelligence based on acquired textual information.

[0678] "Presentation means" refers to technologies for conveying generated information content to users visually or aurally, and is a means of dynamically displaying or playing information audibly.

[0679] "Learning progress management methods" refer to technologies that quantitatively grasp the progress of skill improvement by temporarily saving and analyzing a user's learning history.

[0680] A "feedback generation method" is a technology that creates information to communicate areas for improvement and changes to users based on analysis results, with the aim of providing individualized learning support.

[0681] "Data storage methods" refer to technologies that build databases to store learning history over the long term and use it for future learning.

[0682] "Personalization" refers to providing a more effective learning experience by adjusting learning content and feedback according to the user's characteristics and history.

[0683] This invention is a system that combines speech input conversion technology and generation technology to facilitate language acquisition in the user's daily life. The system aims to analyze the user's speech input, generate English content using a generation AI model, manage learning progress, and provide feedback.

[0684] The terminal has the ability to receive voice commands from the user and uses existing voice recognition software (e.g., a voice recognition API) to perform voice recognition. After converting the voice input into text information, it uses an internet connection and API communication technology to send the text information to the server.

[0685] The server utilizes generative AI models (e.g., natural language processing models) to generate appropriate English content based on the received text information. Specifically, it can access external information sources (e.g., news APIs) to provide the latest news and educational content. This generated content is tailored to the user's interests and incorporates features to keep them engaged in learning.

[0686] The device presents the generated English content to the user either as audio or text. Audio output uses text-to-speech technology (e.g., a text-to-speech API). Visual presentation is achieved by displaying text on smart glasses or a mobile device screen. This allows the user to engage with English through both auditory and visual means.

[0687] This system temporarily stores the user's activity history and conversation content to monitor their learning progress and analyze their progress. This data, periodically sent to the server, is used to analyze the user's learning performance. Based on this analysis, the user receives feedback such as, "Your pronunciation has improved since yesterday. Keep up the good work!" This allows users to continue learning while keeping track of their own progress.

[0688] For example, if a user gives a voice command such as "Tell me yesterday's sports news in English," the content is converted into text, a generative AI model on the server generates relevant English news, and it is presented to the user via the device. This prompt format allows users to use topics they are interested in on a daily basis, making language learning enjoyable.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The device accepts voice input from the user. When the user says, "Tell me yesterday's sports news in English," this voice becomes the input. The device uses voice recognition software to convert the voice data into text data. As a result, the text data is output.

[0692] Step 2:

[0693] The terminal sends the converted character data to the server. Secure communication is performed using HTTPS, and the character data is provided to the server as input. The server receives this data and can then perform the following processing.

[0694] Step 3:

[0695] The server activates a generative AI model and analyzes the received text data. This analysis determines what kind of content is required. Based on this text data, the server retrieves relevant information from the latest news API and generates relevant English news content. The generated English content becomes the output.

[0696] Step 4:

[0697] The device receives pre-generated English content sent from the server. Based on this, it performs actions to present the content to the user visually or aurally. Specifically, it displays text on the smart glasses' display or presents it to the user as audio using synthesized speech technology. As a result, the user can access English news content.

[0698] Step 5:

[0699] The device records user activity and temporarily stores learning progress. Data on which content the user watched or listened to and for how long is used as input, and this data is recorded to understand learning trends. This data is later sent to the server.

[0700] Step 6:

[0701] The server analyzes the learning data received from the device. Detailed data, including learning history and pronunciation evaluations, is used as input to check the user's skill improvement. Based on this analysis, the server generates feedback and outputs a feedback message to the user. This message, such as "Your pronunciation has improved since yesterday," is conveyed to the user via the device.

[0702] (Application Example 1)

[0703] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] This invention aims to provide efficient learning support in users' daily lives, and in particular, to provide continuous and effective support for English language learning. Many learning support tools currently on the market struggle to adequately meet the individual needs of users and offer limited interactive learning experiences. To address these challenges, this invention aims to provide a learning system that seamlessly integrates into the user's daily life.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0706] In this invention, the server includes data conversion means for acquiring voice input and converting the voice data into text data, generation means for generating information content based on the acquired text data using generative artificial intelligence, and output means for presenting the generated information content to the user audibly or visually. This allows users to naturally acquire learning opportunities in their daily lives. Furthermore, the efficient learning experience is enhanced by the provision of appropriate information presentation and feedback.

[0707] A "data conversion means that acquires voice input and converts voice data into text data" is a function that receives voice information and converts it into corresponding character information using a language model.

[0708] "Generative means for generating information content based on text data acquired using generative artificial intelligence" refers to a function that uses knowledge databases and learning models to create appropriate information based on given text information.

[0709] "Output means for presenting generated information content to the user in audio or visual form" refers to a function for providing the generated information to the user using display on a screen or speech synthesis functionality.

[0710] "An evaluation management system that monitors and analyzes users' learning progress" refers to a function that records users' learning activities, analyzes the data, and evaluates their learning progress.

[0711] A "feedback generation method that provides feedback based on learning progress" is a function that presents advice and areas for improvement according to the user's progress during the learning process.

[0712] "An information storage method that records user behavior history and builds a long-term learning database" refers to a function that collects user activity data and builds learning history and trends over time.

[0713] "A means of communication that obtains information from external resources via an internet connection" refers to a function that accesses data and services existing externally through a network and obtains the necessary information.

[0714] "Activity coordination means that provide information in a timely manner based on the user's daily activities" refers to a function that adjusts to provide information at the optimal timing in accordance with the user's daily actions.

[0715] The system for implementing this invention is constructed using smart devices (primarily smart glasses) and network connectivity. The system's components and operation are described below.

[0716] First, the user gives instructions using the voice input function of their smart device. This voice data is converted into text data using speech recognition technology. High-precision language models are used for speech recognition, such as the Google Cloud Speech-to-Text API.

[0717] Subsequently, the server retrieves the converted text data and uses generative artificial intelligence (generative AI model) to generate appropriate information content. This generative AI model, for example, using OpenAI's GPT model, generates news and learning content tailored to the user's requests. During the generation process, necessary data is obtained from the latest external information sources via the internet, and content is created based on that data.

[0718] The generated information content is sent from the server to a smart device and output to the user either visually or audibly. Visually, text is displayed on the smart glasses' screen, and audibly, information is provided to the user in an audible form using a speech synthesis system (such as Amazon Polly).

[0719] Simultaneously, the device monitors the user's learning progress, and the server collects and analyzes the progress data. Learning history and behavioral data are stored in a long-term learning database, and the server generates feedback based on this data and sends it to the smart device. This feedback helps to improve the quality of the user's learning.

[0720] For example, if a user says, "Tell me the main news stories this morning," speech recognition converts this instruction into text, and the server uses a generative AI model to generate the latest news. The generated news is displayed visually on the smart glasses and played aloud. Feedback is provided, such as, "You have learned more vocabulary related to the news than yesterday."

[0721] Example of a prompt:

[0722] User request: "What are the main news stories this morning?"

[0723] Prompt to the generative AI model: "Search for the latest news and provide concise English news articles on key topics."

[0724] This configuration allows users to continue learning efficiently and naturally at various moments in their daily lives.

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The user provides voice input through a smart device. The input voice data is captured through the device's microphone. In this process, the user's voice commands are reproduced and recorded as digital voice data.

[0728] Step 2:

[0729] The device sends the captured audio data to a speech recognition engine, which converts it into text data. The input is audio data, and the output is the corresponding text data. The speech recognition engine uses an advanced language model (e.g., Google Cloud Speech-to-Text) to analyze the audio data and accurately convert it into text.

[0730] Step 3:

[0731] The server receives text data sent from the terminal and generates informational content using a generative AI model. The input is text data, and the output is the generated informational content. Specifically, the server sends prompts to the OpenAI GPT model to retrieve and generate the latest news information, etc.

[0732] Step 4:

[0733] The server transmits the generated information content to the terminal, which then presents it to the user via a smart device. The input is the generated information content, and the output is the visual or audio information presented to the user. The terminal displays text on its screen and also uses a speech synthesis engine to play the information aloud.

[0734] Step 5:

[0735] The device collects user learning progress data and reports it periodically to the server. Input is user usage data (e.g., viewing time, interaction content), and output is a log sent to the server as progress data. This data is important for recording learning outcomes and habits.

[0736] Step 6:

[0737] The server analyzes accumulated user progress data and generates feedback. The input is the accumulated data, and the output is feedback messages for the user. The server queries the database and generates advice based on the user's learning patterns and progress.

[0738] Step 7:

[0739] Feedback is sent to the user via the device. The input is feedback from the server, and the output is feedback information presented to the user. The device enhances the user's motivation to learn by clearly presenting the feedback content through displays and audio.

[0740] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0741] This invention is a system that realizes a more personalized English learning experience by incorporating an emotion engine to recognize the user's emotional state and provide English content that is appropriate to that state. By utilizing an emotion engine in addition to a combination of smart glasses, speech recognition technology, and generative artificial intelligence, the system can customize responses to the user's emotions.

[0742] Personalized emotion recognition and response

[0743] The device acquires the user's voice input and converts that voice data into text data. Furthermore, it utilizes an emotion engine to analyze the user's emotional state from the voice data. This emotion analysis is based on factors such as voice tone, speaking speed, and word choice.

[0744] The server receives emotional information transmitted along with the text data and generates English content according to that emotional state. For example, if the user is relaxed, it will select content that creates a relaxed atmosphere.

[0745] Content presentation and feedback

[0746] The device presents the generated English content to the user in audio or visual format. By making adjustments that respond to the user's emotions, the user can learn in a more receptive way. For example, encouraging language is used for a user who is feeling down.

[0747] The server periodically monitors the user's learning progress and generates progress-based feedback based on sentiment data. This feedback provides specific advice on how the user can improve. For example, it can offer sentiment-based praise such as, "Your speech today was delivered with confidence."

[0748] Strengthening user engagement

[0749] This system allows users to learn English in a learning environment that constantly recognizes their own emotional state. As a result, a more effective and satisfying learning experience is provided. Furthermore, emotional information is accumulated in a database as long-term learning history and used to improve future learning content. This leads to greater individualization for each user and is expected to improve learning efficiency.

[0750] The following describes the processing flow.

[0751] Step 1:

[0752] The user wears smart glasses and gives voice commands to request information specified in English. For example, they might say, "Tell me about today's interesting articles."

[0753] Step 2:

[0754] The device captures the user's voice through its built-in microphone and converts it into text data using speech recognition technology. Simultaneously, the voice data is input into an emotion engine to analyze the user's emotional state.

[0755] Step 3:

[0756] The device sends the converted text data and sentiment analysis results to the server. The sentiment analysis results include, for example, whether the user is excited or relaxed.

[0757] Step 4:

[0758] The server uses generative artificial intelligence to generate optimal English content based on the received text data and sentiment information. It adjusts the tone and content of the article according to the user's emotional state.

[0759] Step 5:

[0760] The server formats the generated English content and sends it to the terminal, including both audio and text data. Adjustments are made based on the user's emotions.

[0761] Step 6:

[0762] The device presents the generated English content to the user in both audio and text formats. This allows the user to receive information in a way that is appropriate to their emotions.

[0763] Step 7:

[0764] The device monitors further user interactions and sends that data to the server. This includes user reactions and changes in emotion.

[0765] Step 8:

[0766] The server analyzes interaction history and sentiment data to generate feedback based on the user's learning progress. This feedback takes emotional aspects into account, providing the user with specific advice and praise.

[0767] (Example 2)

[0768] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0769] The problem that this invention aims to solve is the failure to provide personalized and effective learning experiences when uniform learning content is provided without considering the learner's emotional state. Conventional systems have difficulty providing individualized support based on the learner's emotions and learning progress, which has sometimes led to decreased learning efficiency.

[0770] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0771] In this invention, the server includes a speech conversion means, an emotion analysis means, and a creative means. This makes it possible to provide language learning content that is individually adapted to the user's emotional state in real time.

[0772] "Speech conversion means" refers to a technology or device for converting speech information into text information.

[0773] "Emotional analysis means" refers to a technology or device that analyzes a user's emotional state from voice or text information and generates emotional information.

[0774] "Creative means" refers to a technology or device that uses generative artificial intelligence to create language learning content based on generated emotional and textual information.

[0775] "Presentation means" refers to a technology or device that provides personalized language learning content to the user visually or aurally.

[0776] "Progress evaluation means" refers to a technology or device that monitors the user's learning progress and performs analysis while taking their emotional state into consideration.

[0777] "Response generation means" refers to a technology or device that generates and provides feedback based on learning status and emotional information.

[0778] "Information storage means" refers to a technology or device that records the user's interaction history and builds a long-term learning information database.

[0779] The present invention is a system that personalizes the learning experience based on the user's emotional state. This system comprises a voice conversion means, an emotion analysis means, a creation means, a presentation means, a progress evaluation means, and a response generation means.

[0780] First, the device uses a microphone or the voice input function of a smart device to acquire the user's voice input. Specific hardware examples include smart glasses and Bluetooth earphones. The voice input is converted into text data using speech recognition software. A specific example of this software is a speech recognition engine.

[0781] Next, the device uses this converted text information to analyze the user's emotional state using sentiment analysis software. Sentiment analysis takes into account voice tone, speaking speed, and word choice. Specifically, the sentiment analysis engine processes the data.

[0782] The server then receives the generated sentiment and text information and uses a generative AI model to create language learning content. This creative process utilizes a content generation engine. An example of a prompt is, "Generate relaxing English learning content for the user."

[0783] Next, the device presents the generated learning content to the user. The presentation method is either visual or audible. Specifically, it may be displayed visually on the smart glasses' display or played as audio through a Bluetooth speaker.

[0784] The server continuously monitors the user's learning progress, evaluates and analyzes it based on sentiment information, and provides a detailed understanding of how the user is progressing.

[0785] Finally, the system generates feedback based on learning progress and emotional information. This feedback is provided to the user and includes advice to further improve the learning experience. For example, it might say, "You made very good progress today."

[0786] This system is expected to improve learning efficiency by providing users with personalized learning experiences tailored to their emotional state.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The device acquires voice input from the user. Voice input is acquired through the microphone of smart glasses or earphones. The acquired voice data is converted into text data using a speech recognition engine. In this process, the input is an audio signal, and the output is the corresponding text data. The speech recognition engine analyzes the audio signal and outputs it as text.

[0790] Step 2:

[0791] The terminal performs sentiment analysis using the converted text data. The sentiment analysis engine analyzes the characteristics of the text and audio data, such as tone and speed, to determine the user's emotional state. In this step, text data and audio characteristic data are taken as input, and sentiment information is generated as output. The sentiment analysis engine evaluates the input data and assigns sentiment labels.

[0792] Step 3:

[0793] The server receives text data and sentiment information sent from the terminal. Based on this data, a generative AI model is used to generate appropriate language learning content. The input for this step is sentiment information and text data, and the output is customized learning content. The generative AI model takes a prompt sentence, for example, "Generate relaxing English learning content for the user," as input and performs the operation to create content.

[0794] Step 4:

[0795] The device presents the generated learning content to the user. This presentation is done via voice reading or display. The input is the generated learning content, and the output is the format presented to the user. In practice, visual content is displayed on the smart glasses' screen, and audio content is played through a Bluetooth speaker.

[0796] Step 5:

[0797] The server monitors the user's learning progress and analyzes data, including sentiment information. Based on the analysis results, it evaluates the effectiveness of the learning content and the user's emotional state. The inputs are progress data and sentiment information, and the outputs are evaluation and analysis results. The progress monitoring engine continuously analyzes the data and works to understand the learning trends.

[0798] Step 6:

[0799] The server generates feedback based on analysis results and sentiment information. This generated feedback is provided to the user and includes messages that suggest areas for improvement in learning and motivate them. The input is analysis results and sentiment information, and the output is the feedback message. The feedback generation engine uses evaluation information to create feedback and communicates it to the user.

[0800] (Application Example 2)

[0801] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0802] Currently, information systems in smart cities lack sufficient content customization that takes into account users' emotional states, limiting the potential for improving the user experience. Furthermore, the lack of flexible information delivery that responds to temporary emotional fluctuations prevents users from maximizing their convenience. In addition, there is a need to provide a more personalized experience by utilizing users' long-term history.

[0803] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0804] In this invention, the server includes a voice recognition means, an emotion recognition means, a generation means, and a means for generating information about public facilities and providing guide information optimized based on the user's emotions. This enables the provision of dynamic and personalized information that reflects the user's emotional state.

[0805] 1. "Speech recognition means" refers to a device that has the function of acquiring speech data and converting it into text data.

[0806] 2. "Generation means" refers to a device that uses generative artificial intelligence to generate content based on acquired text data.

[0807] 3. "Emotion recognition means" refers to a device that analyzes the user's voice data and performs processing to determine their emotional state.

[0808] 4. "Means of customization" refers to a device for generating optimal content tailored to the user's state based on analysis results.

[0809] 5. “Presentation means” refers to a device for providing the generated content to the user in audio or visual form.

[0810] 6. A "progress management device" is a device for monitoring the user's progress and collecting and analyzing that data.

[0811] 7. A "feedback generation means" is a device for generating and providing information and advice based on the user's progress.

[0812] 8. "Means for generating and providing information" refers to a device for generating and providing optimized guide information about public facilities based on the user's emotions.

[0813] This invention is a system for providing users with emotionally appropriate information within a smart city. The system mainly consists of terminals and servers. A detailed embodiment of this system is described here.

[0814] The terminal is a device equipped with speech recognition capabilities (e.g., smart glasses) that receives voice input from the user. Specifically, the terminal uses speech recognition to convert the voice data into text data in real time. This utilizes speech recognition APIs such as Google Cloud Speech-to-Text.

[0815] Next, the server uses emotion recognition tools to analyze the text and audio data sent from the terminal and determine the user's emotional state. This process utilizes emotion analysis tools such as IBM Watson Tone Analyzer. Based on the analysis, the server uses a generative AI model (e.g., OpenAI GPT-4) to generate appropriate content.

[0816] This generation method accesses a broad database containing information on public facilities and combines information best suited to the user's emotions to create guide information. The generated content can be customized to reflect the user's individual needs and interests.

[0817] Finally, using a presentation method, the device presents the generated customized information to the user either audibly or visually. This allows the user to receive information optimized for their emotional state. For example, if the user is relaxed, a prompt such as "Please recommend a park where I can feel tranquility and beauty" will be met with recommendations for appropriate facilities.

[0818] The operation of this system will improve the user experience within smart cities and enable more comfortable and effective information delivery.

[0819] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0820] Step 1:

[0821] The device acquires the user's voice input. This input can be in various forms, such as phone calls or instructions. Speech recognition is used to convert this voice data into text data. The Google Cloud Speech-to-Text API is used for this purpose, and the text input is sent to the server.

[0822] Step 2:

[0823] The server analyzes the user's emotional state using emotion recognition based on text data received from the terminal. Emotional data is generated using an emotion analysis engine (e.g., IBM Watson Tone Analyzer) based on factors such as voice tone and word selection. This output represents the user's emotional state.

[0824] Step 3:

[0825] The server utilizes a generative AI model based on emotional data to generate information best suited to the user's emotions. The generation process prepares content in response to prompts. For example, if the user is in a relaxed emotional state, a prompt such as "Please recommend a park where I can feel tranquility and beauty" might be used, and facility information would be created based on this prompt.

[0826] Step 4:

[0827] The server customizes the generated information to create optimal guide information tailored to the user. This process takes into account the user's past interaction data and current situation, adjusting the information provided to make it more engaging and relevant.

[0828] Step 5:

[0829] The device presents the user with customized guide information received from the server. This information can be presented visually on the smart glasses' display or verbally using a speech synthesis API (e.g., Amazon Polly). This ensures that the information is presented in a way that is easily accepted and understandable to the user.

[0830] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0831] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0832] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0834] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0835] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0836] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0837] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0838] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0839] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0840] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0841] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0842] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0843] 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.

[0844] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0845] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0846] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0847] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0848] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0849] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0850] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] A speech recognition means that acquires voice input and converts the voice data into text data,

[0854] A method for generating English content based on text data acquired using generative artificial intelligence,

[0855] A presentation means for presenting the generated English content to the user audibly or visually,

[0856] A progress management system that monitors and analyzes the user's learning progress,

[0857] A feedback generation means that provides feedback based on learning progress,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which personalizes responses using contextual data for voice input.

[0861] (Claim 3)

[0862] The system according to claim 1, comprising data storage means for recording user interaction history and constructing a long-term learning database.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A voice input conversion means that acquires voice input and converts the voice information into text information,

[0866] A generation means for generating information content based on text information obtained using generation technology,

[0867] A presentation means for presenting the generated information content to the user in audio or visual form,

[0868] A learning progress management system that monitors and analyzes the learning progress of users,

[0869] A feedback generation means that provides feedback based on learning progress,

[0870] A data storage method that collects learning history and stores learning data long-term,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which uses contextual data for voice input to personalize responses.

[0874] (Claim 3)

[0875] The system according to claim 1, which records the user's dialogue history and builds learning data over a long period of time.

[0876] "Application Example 1"

[0877] (Claim 1)

[0878] A data conversion means that acquires voice input and converts the voice data into text data,

[0879] A generation method for generating information content based on text data acquired using generative artificial intelligence,

[0880] An output means for presenting the generated information content to the user in audio or visual form,

[0881] An evaluation management system that monitors and analyzes the learning progress of users,

[0882] A feedback generation means that provides feedback based on learning progress,

[0883] A means of storing information that records the user's behavior history and builds a long-term learning database,

[0884] A means of communication that obtains information from external resources via an internet connection,

[0885] A means of coordinating activities that provides timely information based on the user's daily activities,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which uses contextual data for voice input to personalize responses.

[0889] (Claim 3)

[0890] The system according to claim 1, comprising information generation means for recording the user's interaction history and generating information to promote self-learning.

[0891] "Example 2 of combining an emotion engine"

[0892] (Claim 1)

[0893] A voice conversion means that recognizes voice input and converts voice information into text information,

[0894] A means of emotion analysis for performing emotion analysis and generating emotion information,

[0895] A creative means for creating language learning content using generated emotional and textual information and generative artificial intelligence,

[0896] A presentation means that presents the created language learning content in an individualized manner and provides it to the user visually or audibly,

[0897] A progress evaluation method that monitors the user's learning progress and performs analysis while considering their emotional state,

[0898] A response generation means that generates and provides feedback based on learning status and emotional information,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which utilizes emotional information and individualizes responses using contextual information for voice input.

[0902] (Claim 3)

[0903] The system according to claim 1, comprising information storage means for recording user interaction history and constructing a long-term learning information database.

[0904] "Application example 2 when combining with an emotional engine"

[0905] (Claim 1)

[0906] A speech recognition means that acquires voice input and converts the voice data into text data,

[0907] A generation method for generating content based on text data acquired using generative artificial intelligence,

[0908] An emotion recognition method for analyzing the user's emotional state,

[0909] A means of customizing content according to the user's state based on analyzed emotions,

[0910] A presentation means for presenting the generated content audibly or visually,

[0911] A progress management system that monitors and analyzes user progress,

[0912] A feedback generation means that provides feedback based on progress,

[0913] A means for generating information about public facilities and providing guide information optimized based on user sentiment,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, which uses contextual data for voice input to personalize responses and further personalizes information based on emotional state.

[0917] (Claim 3)

[0918] The system according to claim 1, comprising means for recording the user's interaction history, building a long-term database, and accumulating emotional data to be used to improve future information provision. [Explanation of symbols]

[0919] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A speech recognition means that acquires voice input and converts the voice data into text data, A method for generating English content based on text data acquired using generative artificial intelligence, A presentation means for presenting the generated English content to the user audibly or visually, A progress management system that monitors and analyzes the user's learning progress, A feedback generation means that provides feedback based on learning progress, A system that includes this.

2. The system according to claim 1, which personalizes responses using contextual data for voice input.

3. The system according to claim 1, comprising data storage means for recording user interaction history and constructing a long-term learning database.

Images