system

Abstract

We provide the system. [Solution] A means of inputting voice, A speech recognition means that converts the input audio into text data, A natural language processing means that analyzes the converted text data and generates a response text, A speech synthesis means that converts the generated response text into speech data, A system including means for outputting the audio data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 as a 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] Conventional language learning has problems such as reservations and time constraints, and a shortage of instructors who can handle multiple languages. In particular, for users who want to freely learn multiple languages, these constraints are factors that reduce learning efficiency. Also, the cost is high, and there is a lack of an environment that can be easily used. It is necessary to solve these problems so that users can perform language learning efficiently and economically.

Means for Solving the Problems

[0005] This invention provides a system that accurately recognizes user speech by inputting voice and converting that voice into text data using speech recognition technology. Furthermore, it analyzes the text data obtained through natural language processing to generate appropriate response text. This response text is then converted into voice data using speech synthesis technology and output. This makes it possible to realize a system that allows users to practice multilingual conversation anytime without reservations and to provide an environment that can be used without incurring high costs.

[0006] "Voice input means" refers to devices or software that receive user speech as digital voice data.

[0007] "Speech recognition means" refers to a technology or device that converts speech acquired by a speech input means into text data.

[0008] "Natural language processing means" refers to an algorithm or system that analyzes text data and generates an appropriate response based on the user's intent.

[0009] "Speech synthesis means" refers to a technology or device that converts generated text data into speech data.

[0010] "Output means" refers to a device or function that physically plays back audio data generated by speech synthesis means and allows the user to listen to it. [Brief explanation of the drawing]

[0011] [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, when an emotion engine is combined. [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]

[0012] 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.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a multilingual conversation practice system that converts speech to text in real time, generates appropriate responses based on the content, and outputs them back as speech. An embodiment of this system is described below.

[0033] The user uses a terminal equipped with a microphone to input voice into the system. When the user speaks, the terminal captures this voice as a digital signal. This digital voice signal is converted into text data by a speech recognition device within the terminal. This text data is transmitted to a server over the network.

[0034] The server uses natural language processing to analyze the received text data. During this analysis, the server understands the user's intent and the content of their question, and generates an appropriate response. This response is written in text format, and then converted into audio data using speech synthesis. This audio data is sent from the server to the terminal and played back by the terminal's output device so that the user can hear it.

[0035] As a concrete example, consider a user learning Japanese who asks, "What's the weather like today?" This utterance is recorded by the device, converted to text, and sent to the server. The server analyzes the intent of the question from the received text and generates a response text, for example, "The weather in Tokyo today is sunny." This response is then converted back into speech by a speech synthesis system and played back on the user's device. This allows the user to hear the answer to their question in their own language, enabling them to practice conversation efficiently.

[0036] This system allows users to freely choose their desired language and use it repeatedly, enabling effective language learning. Furthermore, it supports multiple languages ​​in addition to Japanese, making it flexible enough to accommodate any language learner. This allows for an economical learning environment that can be accessed regardless of location or time.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user uses a microphone to ask questions or speak to the system verbally. The user's speech is captured as a digital audio signal by the voice input device provided on the terminal.

[0040] Step 2:

[0041] The terminal uses speech recognition to convert the acquired digital speech signal into text data. This conversion process allows the spoken content to be stored on the terminal in text format.

[0042] Step 3:

[0043] The terminal sends the converted text data to the server. This transmission is performed via secure network communication, ensuring the safety of the data.

[0044] Step 4:

[0045] The server analyzes the received text data using natural language processing. Through this analysis, the server understands the user's intent and the content of the question, and generates an appropriate response text.

[0046] Step 5:

[0047] The server sends the generated response text to a speech synthesis system, which converts it into speech data. A high-quality synthesis process is applied to the speech synthesis system to produce natural-sounding speech.

[0048] Step 6:

[0049] The server sends the converted audio data to the user's device. This audio data is transmitted via streaming and delivered without delay.

[0050] Step 7:

[0051] The terminal plays back the received audio data using its output device. This playback allows the user to hear the system's response.

[0052] (Example 1)

[0053] 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."

[0054] Current multilingual conversation practice systems often struggle to efficiently and in real time convert speech to text and generate appropriate responses. Furthermore, there is a need to provide a flexible environment that allows users to freely choose their learning time and practice in various languages.

[0055] 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.

[0056] In this invention, the server includes means for acquiring speech, means for converting the acquired speech into encoded information, means for natural language processing that analyzes the converted encoded information to generate response information, means for speech synthesis that converts the generated response information into encoded information, and means for outputting the encoded information. This makes it possible for the user to efficiently practice multilingual conversation at a desired timing.

[0057] "Means for acquiring sound" refers to devices or systems that collect voice signals emitted by users and process those signals as digital data.

[0058] "Speech recognition means" refers to technologies and algorithms for analyzing acquired speech signals and converting them into corresponding text data.

[0059] "Encoded information" refers to a representation format used for communication and recording, which converts audio and text data into a digital format.

[0060] "Natural language processing methods" refer to technologies and algorithms for processing the language that humans use on a daily basis and analyzing its meaning and intent.

[0061] "Response information" refers to appropriate responses and information for the user, generated based on the results of analysis using natural language processing tools.

[0062] "Speech synthesis means" refers to technologies and algorithms for analyzing generated text data and converting it into corresponding speech signals.

[0063] "Means for outputting encoded information" refers to devices or mechanisms for reproducing the generated audio signal, thereby transmitting information to the user as audio.

[0064] The embodiments for carrying out the invention are described below.

[0065] The present invention is a multilingual conversation practice system that converts speech into text in real time, generates appropriate responses, and outputs those responses as speech. Users can input speech using a terminal equipped with a microphone. The terminal uses an input device (e.g., a microphone) to convert the user's speech into a digital signal. The speech signal is converted into encoded information using speech recognition means (e.g., a common cloud-based speech recognition service). This encoded information is transmitted to a server via a network.

[0066] The server analyzes the encoded information and generates an appropriate response to the user's question or intent. This analysis uses a generative AI model (e.g., a natural language processing tool). The generated response is represented as encoded information and converted back into a speech signal using speech synthesis. This speech signal is returned from the server to the terminal and presented to the user through the terminal's output device.

[0067] As a concrete example, consider a user learning Japanese who asks their device, "What's the weather like today?" The device records this voice, converts it into encoded information, and sends it to the server. The server uses a generative AI model to analyze this information and generates a response such as, "The weather in Tokyo today is sunny." This response is then synthesized into speech and played back on the user's device. This allows the user to practice language efficiently through a natural conversational experience.

[0068] As an example of a prompt, the system can be instructed to "Use the generative AI model to provide an appropriate response when the user inputs 'What's the weather like in Tokyo?' in Japanese." In this way, flexible conversation practice in diverse language environments becomes possible.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The user speaks into the device using the microphone. Specifically, the device receives the voice input from the user via the microphone and acquires this voice as an analog signal. At this point, the input is an analog audio signal, and the device, upon receiving this signal, uses its internal digital conversion process to convert it into a digital audio signal. The output at this point is a digital audio signal.

[0072] Step 2:

[0073] The terminal inputs a digital audio signal into a speech recognition system and converts it into encoded information, i.e., text data. Specifically, it uses a speech recognition engine to analyze each element of the audio and expresses its content as text information. At this time, text data is output based on the digital audio signal.

[0074] Step 3:

[0075] The terminal sends the obtained text data to the server over the network. Here, the data is appropriately encoded using the necessary protocols for transmission, making it receivable on the server side. The input is text data, and the output is a data packet destined for the server.

[0076] Step 4:

[0077] The server analyzes the received text data using natural language processing techniques. It uses a generative AI model to understand the user's intent and questions, and generates corresponding response information. Specifically, it analyzes text data, and the generative AI model dynamically generates response text. In this process, the input is text data, and the output is text data as response information.

[0078] Step 5:

[0079] The server inputs the generated response information into a speech synthesis system and converts it into speech data as encoded information. The speech synthesis engine converts the text information into speech, generating an easily understandable audio signal. The input is text data as response information, and the output is playable audio data.

[0080] Step 6:

[0081] The server transmits audio data to the terminal, which then plays the audio data through an audio playback device. The user can complete the conversation with the system by listening to this outputted audio. The input is audio data, and the output is audio that the user can hear.

[0082] (Application Example 1)

[0083] 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."

[0084] In today's busy lifestyle, individuals often have limited time and space to effectively acquire a language. Furthermore, there is a need for an environment that allows for efficient and repeated learning at home without the need for language classes or textbooks. Additionally, there is a lack of flexible learning methods that support multiple languages ​​and do not require reservations or prior preparation.

[0085] 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.

[0086] In this invention, the server includes a device for receiving speech, a speech recognition device for converting the received speech into text data, and a natural language processing device for analyzing the converted text data and generating response characters. This allows users to learn languages ​​in a mobile environment within their home in conjunction with home automation equipment. Furthermore, by providing dialogue practice that supports multiple languages ​​and offering a learning experience that can be used anytime, the barriers to language acquisition can be reduced.

[0087] A "sound receiving device" is a device that has the function of receiving voice input from a user as an electrical signal and converting it into digital data.

[0088] A "speech recognition device" is a device that analyzes received speech data and converts it into corresponding text data.

[0089] A "natural language processing device" is a device that analyzes converted character data, understands the intent of the input information, and generates appropriate response characters.

[0090] A "speech synthesis device" is a device that converts generated response characters into speech data and makes them playable as human speech.

[0091] "Home automation devices" are devices installed in the home and designed to automate various tasks, including conversational support for language learning.

[0092] "Multilingual support" refers to the ability of a system to process speech input and output in multiple languages ​​and generate appropriate responses.

[0093] A "mobile environment" refers to a configuration that provides the flexibility for learners to use the system even outside of their designated location.

[0094] "Learning at home" refers to a situation where users can acquire a language at their own residence, regardless of time or location.

[0095] The system implementing this invention is a device for users to effectively learn a language at home. Specifically, it operates in conjunction with home automation equipment.

[0096] The server primarily uses a speech recognition device and a natural language processing device. The speech recognition device receives speech from the user and converts it into text data. The "speech_recognition" library is a possible software to use. The text data is analyzed by the natural language processing device on the server to understand the user's intent and generate an appropriate response. The "OpenAI® API" is used to generate the response string.

[0097] The generated response string is converted into speech by a speech synthesizer. Using the "gTTS" library, the response can be converted into speech in real time. The converted speech data is output from the terminal device, and the user can listen to it.

[0098] As a concrete example, consider a scenario where a user asks "What's the weather like today?" while at home. This statement is collected via a microphone and converted into text by a speech recognition device. The converted text data is analyzed on a server, and the "OpenAI API" generates an appropriate response, such as "The weather today is sunny." This is then converted into audio data and output from the terminal.

[0099] Examples of prompt messages include the following:

[0100] Generate appropriate responses to users: What's the weather like today?

[0101] This system provides users with a flexible environment to learn a variety of languages ​​according to their individual needs.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user inputs voice through a microphone. The terminal captures the user's voice as a digital audio signal. This input audio data is sent to a speech recognition device.

[0105] Step 2:

[0106] The speech recognition device converts the input digital speech signal into text data. Specifically, it uses the "speech_recognition" library to convert speech to text. This text data is then sent to the server.

[0107] Step 3:

[0108] The server receives text data and performs natural language processing. Here, it uses the "OpenAI API" to analyze the text data and understand the user's intent. This process generates an appropriate response text.

[0109] Step 4:

[0110] The generated response text is converted into speech data by a speech synthesizer. The server uses the "gTTS" library to convert the text into speech and generate the speech data.

[0111] Step 5:

[0112] The generated audio data is sent to the terminal and output to the user as audio. The user can hear this audio response.

[0113] 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.

[0114] This invention adds an emotion recognition function to a multilingual conversation practice system that uses user voice input. This system allows users to learn languages ​​at their own pace and further provides a more personalized learning experience by recognizing the user's emotional state and adjusting its responses accordingly.

[0115] In one embodiment of the system, the user first speaks through the device's microphone. This voice input is converted into digital voice data within the device. Next, the voice is converted into text data by the device's voice recognition function. This text data is then sent to a server for further analysis.

[0116] The server not only analyzes the content of received text data using natural language processing, but also evaluates the emotions contained in the voice and text data using an emotion engine. This emotion analysis identifies the user's current emotional state. Based on this information, the server generates a response appropriate to the user's emotions. For example, if the user shows interest, it provides more detailed information; conversely, if the user expresses dissatisfaction, it attempts to explain from a different angle, dynamically adjusting the response.

[0117] Furthermore, the data analyzed by the emotion engine is saved as the user's learning history, and this data is reflected in subsequent learning sessions. This allows the server to continuously provide learning content optimized for each individual user.

[0118] As a concrete example, suppose an English-speaking user learning Japanese asks, "I want to know how conversations start," and the emotion engine recognizes the user's interest. The server considers the user's emotions and responds, "Generally, it's good to start with 'Konnichiwa' (hello), but other expressions are used depending on the place," and further deepens the learning by adding more detailed cultural background information.

[0119] Thus, the present invention enables flexible responses that take user emotions into consideration, thereby enhancing the effectiveness of language learning. Even when users experience emotions such as curiosity, interest, or frustration, the system responds appropriately by modeling these emotions. This allows learners to have a more interactive experience.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The user uses a microphone to input questions or what they want to say by voice. The user's speech is captured as digital audio data by the device.

[0123] Step 2:

[0124] The device uses speech recognition to convert the acquired digital speech data into text data. This conversion process allows the user's speech to be treated as text information.

[0125] Step 3:

[0126] The device sends the converted text data to the emotion engine, which identifies the user's emotions. The emotion engine evaluates the user's emotional state through voice intonation and text content analysis.

[0127] Step 4:

[0128] The device sends text data containing emotional data to the server. The server sends the received data to a natural language processing system and generates a response text based on the content of the text and the user's emotions.

[0129] Step 5:

[0130] The server converts the generated response text into speech data using a speech synthesis system. This conversion transforms the text information back into speech information, which can then be provided to the user.

[0131] Step 6:

[0132] The server transmits audio data to the user's device. The transmitted audio data is delivered to the user without delay via streaming.

[0133] Step 7:

[0134] The device plays the received audio data. The device's speaker is used to allow the user to hear the response aloud.

[0135] Step 8:

[0136] If a user continues learning, they will be provided with feedback about the emotions they experienced and how those emotions affected them. This feedback will be saved to help adjust future learning content.

[0137] (Example 2)

[0138] 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 will be referred to as the "terminal."

[0139] Conventional conversation practice systems have been unable to generate responses that take into account the user's emotional state, making it difficult to provide a personalized learning experience. Furthermore, while supporting diverse languages, they lacked the ability to flexibly adjust responses through real-time sentiment analysis. Additionally, it was difficult to provide a continuously optimized learning environment by utilizing the user's learning history.

[0140] 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.

[0141] In this invention, the server includes means for inputting speech, means for converting it into digital data, means for speech recognition, means for natural language processing, means for evaluating emotions, means for generating responses, and means for recording responses and analysis results. This makes it possible to dynamically generate responses according to the user's emotional state and provide a personalized language learning experience.

[0142] "Means of voice input" refers to devices or functions for receiving voice information from users.

[0143] "Means of converting to digital data" refers to the function of encoding analog audio into a digital format.

[0144] "Speech recognition means" refers to technology that analyzes digital speech data and converts it into text format.

[0145] "Natural language processing" refers to technologies that analyze text data, understand its meaning, and generate corresponding information.

[0146] "Means of evaluating emotions" refers to technologies that identify and evaluate a user's emotional state from text or audio.

[0147] "Means for generating responses" refers to technologies that construct appropriate responses based on user input and emotional state.

[0148] "Means for recording responses and analysis results" refers to a function that stores generated information and analysis results in a database or similar system for later use.

[0149] This invention is a conversation practice system that generates responses in real time, taking into account the user's emotional state, when the user engages in interactive language learning through voice input. This system supports more effective language acquisition by providing a personalized learning experience that responds to the user's emotions.

[0150] The system's implementation begins with the use of a terminal. The terminal receives audio input from the user via a microphone and converts that audio into digital data. Specifically, it uses the terminal's recording function or the standard functions of its operating system to encode the audio into a digital format.

[0151] Next, the speech recognition software on the device (e.g., a speech recognition API) converts the digital speech data into text data. In this step, the speech waveform is analyzed and transcribed based on standard phonemes.

[0152] The converted text data is sent to the server. The server uses natural language processing techniques (e.g., natural language processing libraries) to analyze the text. This analysis helps the server understand the meaning of the input text and generate information.

[0153] The server then uses sentiment analysis software (e.g., sentiment analysis engine) to evaluate the user's emotions. In this process, it calculates an emotion score from keywords and phrases in the text to specifically identify the user's current emotional state.

[0154] After the emotion is evaluated, the server uses a generative AI model (e.g., a natural language generation model) to generate a response appropriate to the user's emotion. For example, if the prompt is "Provide a detailed explanation to the user who has shown interest," a response appropriate to the context will be generated.

[0155] Finally, the generated response is returned to the terminal and provided to the user. This response process is dynamic and continuously optimized, taking into account the user's learning history and emotional state. Thus, from voice input via the terminal to analysis on the server, emotion evaluation, and response generation, the user can enjoy a sophisticated, emotion-based language learning experience.

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The user inputs audio through the device's microphone. Since the input audio is an analog signal, it is converted to a digital format using the device's recording function. This digital audio data is then saved as an audio waveform.

[0159] Step 2:

[0160] The terminal sends the stored digital audio data to speech recognition software. The speech recognition software analyzes this digital data and identifies phonemes. As a result of the analysis, the audio waveform is converted into text data. Here, the input is digital audio data, and the output is the converted text data.

[0161] Step 3:

[0162] The terminal sends the converted text data to the server. In this process, metadata such as user ID and session information is also sent along with the text data. The HTTPS protocol is used to ensure secure data communication during this process.

[0163] Step 4:

[0164] The server uses a natural language processing engine based on the received text data. The server analyzes the text content to identify the intent of the question and the information being sought. The input for this analysis is text data, and the output is information about the meaning of the text.

[0165] Step 5:

[0166] The server uses an emotion analysis engine to evaluate the user's emotions from the analyzed text. It calculates an emotion score based on the tone and keywords of the input text, identifying the user's emotional state. The output of this process is the emotion evaluation result.

[0167] Step 6:

[0168] The server uses a generative AI model to generate an appropriate response based on the evaluated sentiment. The generative AI model is input with a prompt and outputs a text response corresponding to the user's sentiment state. For example, the prompt might be, "This user is interested; please explain further."

[0169] Step 7:

[0170] The server sends the generated response text back to the terminal. The terminal presents the received response to the user. In this step, the input is the response text from the server, and the output is a display or audio for the user.

[0171] Step 8:

[0172] The server stores the results of analysis and sentiment evaluation, as well as the generated responses, in a database as the user's learning history. This stored data is used in future learning sessions, continuously optimizing the user experience. The output is learning history data intended for use in subsequent learning sessions.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0175] Modern self-study systems fail to generate responses that take into account the user's emotional state, thus not providing a personalized learning experience. This makes it easy for users to lose interest in learning, hindering effective language acquisition. Furthermore, multilingual systems often lack sufficient dynamic conversational adjustments based on emotional states, making it difficult to provide support tailored to the user's learning needs.

[0176] 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.

[0177] In this invention, the server includes a device for inputting speech, an emotion recognition means for evaluating the emotional state from the text and speech data, and a response adjustment means for dynamically adjusting the response text according to the emotional state. This makes it possible to adjust the response based on the user's emotional state and provide a personalized language learning experience. As a result, the user is more likely to maintain interest and can achieve more effective learning.

[0178] "A device or means for inputting voice" refers to a device or equipment that receives voice data from a user and inputs it into a system.

[0179] "Speech recognition means" refers to technology that analyzes input speech data and converts it into text format.

[0180] "Natural language processing means" refers to technologies for understanding converted text data and generating appropriate response text.

[0181] "Speech synthesis means" refers to a technology that converts the generated response text back into speech data and outputs it as speech.

[0182] "Emotion recognition means" refers to technologies for evaluating and understanding a user's emotional state from voice and text data.

[0183] "Response adjustment means" refers to technology that dynamically adjusts the system's response based on the recognized emotional state and provides it to the user.

[0184] This system is designed for users to practice multilingual conversation through consumer robots. Specifically, it uses the following hardware and software:

[0185] The device is equipped with a microphone for voice input and a speaker for voice output. Users speak into the device to input voice. The Google® Speech-to-Text API is used for speech recognition, and the input voice data is converted into text format. This allows the content of the voice to be transmitted to the server as text data.

[0186] The server uses OpenAI's generative AI model to analyze the received text data, performing natural language processing to generate appropriate responses. Simultaneously, it uses IBM Watson® Tone Analyzer to evaluate the user's emotional state from both speech and text. This emotion recognition helps determine whether the user is interested or tired, for example.

[0187] The generated response text is synthesized into speech by the server and output to the user as audio via the terminal. During this process, the response is dynamically adjusted to suit the user's emotional state. For example, if the user is tired, simpler topics and shorter responses are provided; if they are interested, the response is adjusted to support more detailed information and additional topics.

[0188] For example, if a user says, "Today I want to learn some simple Japanese expressions," the system analyzes the statement and uses sentiment recognition to determine that the user is seeking a simple conversation. The server then generates a friendly response such as, "Hello, how can I help you today?" and provides a detailed, beginner-friendly explanation.

[0189] As an example of a prompt, a user might say to the AI ​​generator, "I want to practice short conversations in Japanese. After the user asks 'What's the weather like today?', prepare several responses to pique their interest." Based on this prompt, the system can dynamically adjust its response to provide the optimal learning environment for the user.

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] The device receives voice input from the user via the microphone. This voice data is then passed to the system as input data.

[0193] Step 2:

[0194] The device uses the Google Speech-to-Text API to convert the input speech data into text format. This converted text data is then output for the next processing step.

[0195] Step 3:

[0196] Text data is sent from the terminal to the server. The server uses this text as input and performs natural language processing using OpenAI's generative AI model to generate response text. This response text is then provided for the next processing step.

[0197] Step 4:

[0198] The server uses IBM Watson Tone Analyzer to evaluate the user's emotional state from the input voice and text data. This evaluation result, along with the generated response, becomes the input data for the next processing step.

[0199] Step 5:

[0200] The server dynamically adjusts the response text generated based on the evaluated emotional state. For example, if the user shows interest, the response text is modified to add more detailed explanations.

[0201] Step 6:

[0202] The server converts the adjusted response text into speech data using speech synthesis technology. This speech data is then sent back to the terminal as the final output.

[0203] Step 7:

[0204] The device provides the outputted audio data to the user through its speaker. This allows the user to receive a response as audio.

[0205] Through the above processes, the system can provide users with a personalized language learning experience.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention is a multilingual conversation practice system that converts speech to text in real time, generates appropriate responses based on the content, and outputs them back as speech. An embodiment of this system is described below.

[0223] The user uses a terminal equipped with a microphone to input voice into the system. When the user speaks, the terminal captures this voice as a digital signal. This digital voice signal is converted into text data by a speech recognition device within the terminal. This text data is transmitted to a server over the network.

[0224] The server uses natural language processing to analyze the received text data. During this analysis, the server understands the user's intent and the content of their question, and generates an appropriate response. This response is written in text format, and then converted into audio data using speech synthesis. This audio data is sent from the server to the terminal and played back by the terminal's output device so that the user can hear it.

[0225] As a concrete example, consider a user learning Japanese who asks, "What's the weather like today?" This utterance is recorded by the device, converted to text, and sent to the server. The server analyzes the intent of the question from the received text and generates a response text, for example, "The weather in Tokyo today is sunny." This response is then converted back into speech by a speech synthesis system and played back on the user's device. This allows the user to hear the answer to their question in their own language, enabling them to practice conversation efficiently.

[0226] This system allows users to freely choose their desired language and use it repeatedly, enabling effective language learning. Furthermore, it supports multiple languages ​​in addition to Japanese, making it flexible enough to accommodate any language learner. This allows for an economical learning environment that can be accessed regardless of location or time.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The user uses a microphone to ask questions or speak to the system verbally. The user's speech is captured as a digital audio signal by the voice input device provided on the terminal.

[0230] Step 2:

[0231] The terminal uses speech recognition to convert the acquired digital speech signal into text data. This conversion process allows the spoken content to be stored on the terminal in text format.

[0232] Step 3:

[0233] The terminal sends the converted text data to the server. This transmission is performed via secure network communication, ensuring the safety of the data.

[0234] Step 4:

[0235] The server analyzes the received text data using natural language processing. Through this analysis, the server understands the user's intent and the content of the question, and generates an appropriate response text.

[0236] Step 5:

[0237] The server sends the generated response text to a speech synthesis system, which converts it into speech data. A high-quality synthesis process is applied to the speech synthesis system to produce natural-sounding speech.

[0238] Step 6:

[0239] The server sends the converted audio data to the user's device. This audio data is transmitted via streaming and delivered without delay.

[0240] Step 7:

[0241] The terminal plays back the received audio data using its output device. This playback allows the user to hear the system's response.

[0242] (Example 1)

[0243] 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."

[0244] Current multilingual conversation practice systems often struggle to efficiently and in real time convert speech to text and generate appropriate responses. Furthermore, there is a need to provide a flexible environment that allows users to freely choose their learning time and practice in various languages.

[0245] 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.

[0246] In this invention, the server includes means for acquiring speech, means for converting the acquired speech into encoded information, means for natural language processing that analyzes the converted encoded information to generate response information, means for speech synthesis that converts the generated response information into encoded information, and means for outputting the encoded information. This makes it possible for the user to efficiently practice multilingual conversation at a desired timing.

[0247] "Means for acquiring sound" refers to devices or systems that collect voice signals emitted by users and process those signals as digital data.

[0248] "Speech recognition means" refers to technologies and algorithms for analyzing acquired speech signals and converting them into corresponding text data.

[0249] "Encoded information" refers to a representation format used for communication and recording, which converts audio and text data into a digital format.

[0250] "Natural language processing methods" refer to technologies and algorithms for processing the language that humans use on a daily basis and analyzing its meaning and intent.

[0251] "Response information" refers to appropriate responses and information for the user, generated based on the results of analysis using natural language processing tools.

[0252] "Speech synthesis means" refers to technologies and algorithms for analyzing generated text data and converting it into corresponding speech signals.

[0253] "Means for outputting encoded information" refers to devices or mechanisms for reproducing the generated audio signal, thereby transmitting information to the user as audio.

[0254] The embodiments for carrying out the invention are described below.

[0255] The present invention is a multilingual conversation practice system that converts speech into text in real time, generates appropriate responses, and outputs those responses as speech. Users can input speech using a terminal equipped with a microphone. The terminal uses an input device (e.g., a microphone) to convert the user's speech into a digital signal. The speech signal is converted into encoded information using speech recognition means (e.g., a common cloud-based speech recognition service). This encoded information is transmitted to a server via a network.

[0256] The server analyzes the encoded information and generates an appropriate response to the user's question or intent. This analysis uses a generative AI model (e.g., a natural language processing tool). The generated response is represented as encoded information and converted back into a speech signal using speech synthesis. This speech signal is returned from the server to the terminal and presented to the user through the terminal's output device.

[0257] As a concrete example, consider a user learning Japanese who asks their device, "What's the weather like today?" The device records this voice, converts it into encoded information, and sends it to the server. The server uses a generative AI model to analyze this information and generates a response such as, "The weather in Tokyo today is sunny." This response is then synthesized into speech and played back on the user's device. This allows the user to practice language efficiently through a natural conversational experience.

[0258] As an example of a prompt, the system can be instructed to "Use the generative AI model to provide an appropriate response when the user inputs 'What's the weather like in Tokyo?' in Japanese." In this way, flexible conversation practice in diverse language environments becomes possible.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The user speaks into the device using the microphone. Specifically, the device receives the voice input from the user via the microphone and acquires this voice as an analog signal. At this point, the input is an analog audio signal, and the device, upon receiving this signal, uses its internal digital conversion process to convert it into a digital audio signal. The output at this point is a digital audio signal.

[0262] Step 2:

[0263] The terminal inputs a digital audio signal into a speech recognition system and converts it into encoded information, i.e., text data. Specifically, it uses a speech recognition engine to analyze each element of the audio and expresses its content as text information. At this time, text data is output based on the digital audio signal.

[0264] Step 3:

[0265] The terminal sends the obtained text data to the server over the network. Here, the data is appropriately encoded using the necessary protocols for transmission, making it receivable on the server side. The input is text data, and the output is a data packet destined for the server.

[0266] Step 4:

[0267] The server analyzes the received text data using natural language processing techniques. It uses a generative AI model to understand the user's intent and questions, and generates corresponding response information. Specifically, it analyzes text data, and the generative AI model dynamically generates response text. In this process, the input is text data, and the output is text data as response information.

[0268] Step 5:

[0269] The server inputs the generated response information into a speech synthesis system and converts it into speech data as encoded information. The speech synthesis engine converts the text information into speech, generating an easily understandable audio signal. The input is text data as response information, and the output is playable audio data.

[0270] Step 6:

[0271] The server transmits audio data to the terminal, which then plays the audio data through an audio playback device. The user can complete the conversation with the system by listening to this outputted audio. The input is audio data, and the output is audio that the user can hear.

[0272] (Application Example 1)

[0273] 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."

[0274] In today's busy lifestyle, individuals often have limited time and space to effectively acquire a language. Furthermore, there is a need for an environment that allows for efficient and repeated learning at home without the need for language classes or textbooks. Additionally, there is a lack of flexible learning methods that support multiple languages ​​and do not require reservations or prior preparation.

[0275] 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.

[0276] In this invention, the server includes a device for receiving speech, a speech recognition device for converting the received speech into text data, and a natural language processing device for analyzing the converted text data and generating response characters. This allows users to learn languages ​​in a mobile environment within their home in conjunction with home automation equipment. Furthermore, by providing dialogue practice that supports multiple languages ​​and offering a learning experience that can be used anytime, the barriers to language acquisition can be reduced.

[0277] A "sound receiving device" is a device that has the function of receiving voice input from a user as an electrical signal and converting it into digital data.

[0278] A "speech recognition device" is a device that analyzes received speech data and converts it into corresponding text data.

[0279] A "natural language processing device" is a device that analyzes converted character data, understands the intent of the input information, and generates appropriate response characters.

[0280] A "speech synthesis device" is a device that converts generated response characters into speech data and makes them playable as human speech.

[0281] "Home automation devices" are devices installed in the home and designed to automate various tasks, including conversational support for language learning.

[0282] "Multilingual support" refers to the ability of a system to process speech input and output in multiple languages ​​and generate appropriate responses.

[0283] A "mobile environment" refers to a configuration that provides the flexibility for learners to use the system even outside of their designated location.

[0284] "Learning at home" refers to a situation where users can advance language acquisition regardless of time and place in their own residences.

[0285] The system for implementing this invention is a device for users to effectively conduct language learning at home. Here, specifically, it operates in cooperation with household automation equipment.

[0286] The server mainly uses a speech recognition device and a natural language processing device. The speech recognition device receives the user's voice and converts it into character data. As the software to be used, the "speech_recognition" library can be considered. The character data is analyzed by the natural language processing device on the server to understand the user's speech intention and generate an appropriate response. The "OpenAI API" is used for response generation to generate a response string.

[0287] The generated response string is converted into voice by a speech synthesis device. By using the "gTTS" library for this, the response can be vocalized in real time. The converted voice data is output from the terminal device, and the user can listen to it.

[0288] As a specific example, consider the case where a user asks "What's the weather today?" within the home. This utterance is collected through the microphone and converted into text by the speech recognition device. The converted character data is analyzed on the server, and appropriate information such as "The weather today is sunny" is generated by the "OpenAI API". This is converted into voice data and output from the terminal.

[0289] Examples of prompt sentences can be texts like the following.

[0290] Generate an appropriate response to the user: What's the weather today?

[0291] This system can provide an environment where users can flexibly conduct diverse language learning according to their respective needs.

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The user inputs voice through a microphone. The terminal captures the user's voice as a digital audio signal. This input audio data is sent to a speech recognition device.

[0295] Step 2:

[0296] The speech recognition device converts the input digital speech signal into text data. Specifically, it uses the "speech_recognition" library to convert speech to text. This text data is then sent to the server.

[0297] Step 3:

[0298] The server receives text data and performs natural language processing. Here, it uses the "OpenAI API" to analyze the text data and understand the user's intent. This process generates an appropriate response text.

[0299] Step 4:

[0300] The generated response text is converted into speech data by a speech synthesizer. The server uses the "gTTS" library to convert the text into speech and generate the speech data.

[0301] Step 5:

[0302] The generated audio data is sent to the terminal and output to the user as audio. The user can hear this audio response.

[0303] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0304] The present invention adds an emotion recognition function to a multilingual conversation practice system using voice input by a user. This system enables the user to perform language learning in their free time, and further provides a more personalized learning experience by recognizing the user's emotional state and adjusting the response.

[0305] In an embodiment of the system, first, the user makes a speech through the microphone of the terminal. This voice input is converted into digital voice data in the terminal. Next, the voice is converted into text data by the voice recognition function in the terminal. This text data is transmitted to the server for further analysis.

[0306] The server not only analyzes the content of the received text data by natural language processing, but also evaluates the emotion contained in the voice and text data using an emotion engine. By this emotion analysis, the user's current emotional state is identified. Based on this information, the server generates a response suitable for the user's emotion. For example, when the user shows interest, more detailed information is provided, and conversely, when dissatisfaction is shown, an explanation from another angle is attempted, and the response is dynamically adjusted.

[0307] Furthermore, the data analyzed by the emotion engine is stored as the user's learning history, and the data is reflected in subsequent learning sessions. Thereby, the server can continue to provide learning content optimized for each user.

[0308] As a concrete example, suppose an English-speaking user learning Japanese asks, "I want to know how conversations start," and the emotion engine recognizes the user's interest. The server considers the user's emotions and responds, "Generally, it's good to start with 'Konnichiwa' (hello), but other expressions are used depending on the place," and further deepens the learning by adding more detailed cultural background information.

[0309] Thus, the present invention enables flexible responses that take user emotions into consideration, thereby enhancing the effectiveness of language learning. Even when users experience emotions such as curiosity, interest, or frustration, the system responds appropriately by modeling these emotions. This allows learners to have a more interactive experience.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The user uses a microphone to input questions or what they want to say by voice. The user's speech is captured as digital audio data by the device.

[0313] Step 2:

[0314] The device uses speech recognition to convert the acquired digital speech data into text data. This conversion process allows the user's speech to be treated as text information.

[0315] Step 3:

[0316] The device sends the converted text data to the emotion engine, which identifies the user's emotions. The emotion engine evaluates the user's emotional state through voice intonation and text content analysis.

[0317] Step 4:

[0318] The device sends text data containing emotional data to the server. The server sends the received data to a natural language processing system and generates a response text based on the content of the text and the user's emotions.

[0319] Step 5:

[0320] The server converts the generated response text into speech data using a speech synthesis system. This conversion transforms the text information back into speech information, which can then be provided to the user.

[0321] Step 6:

[0322] The server transmits audio data to the user's device. The transmitted audio data is delivered to the user without delay via streaming.

[0323] Step 7:

[0324] The device plays the received audio data. The device's speaker is used to allow the user to hear the response aloud.

[0325] Step 8:

[0326] If a user continues learning, they will be provided with feedback about the emotions they experienced and how those emotions affected them. This feedback will be saved to help adjust future learning content.

[0327] (Example 2)

[0328] 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".

[0329] Conventional conversation practice systems have been unable to generate responses that take into account the user's emotional state, making it difficult to provide a personalized learning experience. Furthermore, while supporting diverse languages, they lacked the ability to flexibly adjust responses through real-time sentiment analysis. Additionally, it was difficult to provide a continuously optimized learning environment by utilizing the user's learning history.

[0330] 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.

[0331] In this invention, the server includes means for inputting speech, means for converting it into digital data, means for speech recognition, means for natural language processing, means for evaluating emotions, means for generating responses, and means for recording responses and analysis results. This makes it possible to dynamically generate responses according to the user's emotional state and provide a personalized language learning experience.

[0332] "Means of voice input" refers to devices or functions for receiving voice information from users.

[0333] "Means of converting to digital data" refers to the function of encoding analog audio into a digital format.

[0334] "Speech recognition means" refers to technology that analyzes digital speech data and converts it into text format.

[0335] "Natural language processing" refers to technologies that analyze text data, understand its meaning, and generate corresponding information.

[0336] "Means of evaluating emotions" refers to technologies that identify and evaluate a user's emotional state from text or audio.

[0337] "Means for generating responses" refers to technologies that construct appropriate responses based on user input and emotional state.

[0338] "Means for recording responses and analysis results" refers to a function that stores generated information and analysis results in a database or similar system for later use.

[0339] This invention is a conversation practice system that generates responses in real time, taking into account the user's emotional state, when the user engages in interactive language learning through voice input. This system supports more effective language acquisition by providing a personalized learning experience that responds to the user's emotions.

[0340] The system's implementation begins with the use of a terminal. The terminal receives audio input from the user via a microphone and converts that audio into digital data. Specifically, it uses the terminal's recording function or the standard functions of its operating system to encode the audio into a digital format.

[0341] Next, the speech recognition software on the device (e.g., a speech recognition API) converts the digital speech data into text data. In this step, the speech waveform is analyzed and transcribed based on standard phonemes.

[0342] The converted text data is sent to the server. The server uses natural language processing techniques (e.g., natural language processing libraries) to analyze the text. This analysis helps the server understand the meaning of the input text and generate information.

[0343] The server then uses sentiment analysis software (e.g., sentiment analysis engine) to evaluate the user's emotions. In this process, it calculates an emotion score from keywords and phrases in the text to specifically identify the user's current emotional state.

[0344] After the emotion is evaluated, the server uses a generative AI model (e.g., a natural language generation model) to generate a response appropriate to the user's emotion. For example, if the prompt is "Provide a detailed explanation to the user who has shown interest," a response appropriate to the context will be generated.

[0345] Finally, the generated response is returned to the terminal and provided to the user. This response process is dynamic and continuously optimized, taking into account the user's learning history and emotional state. Thus, from voice input via the terminal to analysis on the server, emotion evaluation, and response generation, the user can enjoy a sophisticated, emotion-based language learning experience.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The user inputs audio through the device's microphone. Since the input audio is an analog signal, it is converted to a digital format using the device's recording function. This digital audio data is then saved as an audio waveform.

[0349] Step 2:

[0350] The terminal sends the stored digital audio data to speech recognition software. The speech recognition software analyzes this digital data and identifies phonemes. As a result of the analysis, the audio waveform is converted into text data. Here, the input is digital audio data, and the output is the converted text data.

[0351] Step 3:

[0352] The terminal sends the converted text data to the server. In this process, metadata such as user ID and session information is also sent along with the text data. The HTTPS protocol is used to ensure secure data communication during this process.

[0353] Step 4:

[0354] The server uses a natural language processing engine based on the received text data. The server analyzes the text content to identify the intent of the question and the information being sought. The input for this analysis is text data, and the output is information about the meaning of the text.

[0355] Step 5:

[0356] The server uses an emotion analysis engine to evaluate the user's emotions from the analyzed text. It calculates an emotion score based on the tone and keywords of the input text, identifying the user's emotional state. The output of this process is the emotion evaluation result.

[0357] Step 6:

[0358] The server uses a generative AI model to generate an appropriate response based on the evaluated sentiment. The generative AI model is input with a prompt and outputs a text response corresponding to the user's sentiment state. For example, the prompt might be, "This user is interested; please explain further."

[0359] Step 7:

[0360] The server sends the generated response text back to the terminal. The terminal presents the received response to the user. In this step, the input is the response text from the server, and the output is a display or audio for the user.

[0361] Step 8:

[0362] The server stores the results of analysis and sentiment evaluation, as well as the generated responses, in a database as the user's learning history. This stored data is used in future learning sessions, continuously optimizing the user experience. The output is learning history data intended for use in subsequent learning sessions.

[0363] (Application Example 2)

[0364] 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."

[0365] Modern self-study systems fail to generate responses that take into account the user's emotional state, thus not providing a personalized learning experience. This makes it easy for users to lose interest in learning, hindering effective language acquisition. Furthermore, multilingual systems often lack sufficient dynamic conversational adjustments based on emotional states, making it difficult to provide support tailored to the user's learning needs.

[0366] 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.

[0367] In this invention, the server includes a device for inputting speech, an emotion recognition means for evaluating the emotional state from the text and speech data, and a response adjustment means for dynamically adjusting the response text according to the emotional state. This makes it possible to adjust the response based on the user's emotional state and provide a personalized language learning experience. As a result, the user is more likely to maintain interest and can achieve more effective learning.

[0368] "A device or means for inputting voice" refers to a device or equipment that receives voice data from a user and inputs it into a system.

[0369] "Speech recognition means" refers to technology that analyzes input speech data and converts it into text format.

[0370] "Natural language processing means" refers to technologies for understanding converted text data and generating appropriate response text.

[0371] "Speech synthesis means" refers to a technology that converts the generated response text back into speech data and outputs it as speech.

[0372] "Emotion recognition means" refers to technologies for evaluating and understanding a user's emotional state from voice and text data.

[0373] "Response adjustment means" refers to technology that dynamically adjusts the system's response based on the recognized emotional state and provides it to the user.

[0374] This system is designed for users to practice multilingual conversation through consumer robots. Specifically, it uses the following hardware and software:

[0375] The device is equipped with a microphone for voice input and a speaker for voice output. Users speak into the device to input voice. The Google Speech-to-Text API is used for speech recognition, and the input voice data is converted into text format. This allows the content of the voice to be transmitted to the server as text data.

[0376] The server uses OpenAI's generative AI model to analyze the received text data, performing natural language processing to generate appropriate responses. Simultaneously, it uses IBM Watson Tone Analyzer to evaluate the user's emotional state from both speech and text. This emotion recognition helps determine whether the user is interested or tired, for example.

[0377] The generated response text is synthesized into speech by the server and output to the user as audio via the terminal. During this process, the response is dynamically adjusted to suit the user's emotional state. For example, if the user is tired, simpler topics and shorter responses are provided; if they are interested, the response is adjusted to support more detailed information and additional topics.

[0378] For example, if a user says, "Today I want to learn some simple Japanese expressions," the system analyzes the statement and uses sentiment recognition to determine that the user is seeking a simple conversation. The server then generates a friendly response such as, "Hello, how can I help you today?" and provides a detailed, beginner-friendly explanation.

[0379] As an example of a prompt, a user might say to the AI ​​generator, "I want to practice short conversations in Japanese. After the user asks 'What's the weather like today?', prepare several responses to pique their interest." Based on this prompt, the system can dynamically adjust its response to provide the optimal learning environment for the user.

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The device receives voice input from the user via the microphone. This voice data is then passed to the system as input data.

[0383] Step 2:

[0384] The device uses the Google Speech-to-Text API to convert the input speech data into text format. This converted text data is then output for the next processing step.

[0385] Step 3:

[0386] Text data is sent from the terminal to the server. The server uses this text as input and performs natural language processing using OpenAI's generative AI model to generate response text. This response text is then provided for the next processing step.

[0387] Step 4:

[0388] The server uses IBM Watson Tone Analyzer to evaluate the user's emotional state from the input voice and text data. This evaluation result, along with the generated response, becomes the input data for the next processing step.

[0389] Step 5:

[0390] The server dynamically adjusts the response text generated based on the evaluated emotional state. For example, if the user shows interest, the response text is modified to add more detailed explanations.

[0391] Step 6:

[0392] The server converts the adjusted response text into speech data using speech synthesis technology. This speech data is then sent back to the terminal as the final output.

[0393] Step 7:

[0394] The device provides the outputted audio data to the user through its speaker. This allows the user to receive a response as audio.

[0395] Through the above processes, the system can provide users with a personalized language learning experience.

[0396] 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.

[0397] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0398] 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.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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".

[0412] This invention is a multilingual conversation practice system that converts speech to text in real time, generates appropriate responses based on the content, and outputs them back as speech. An embodiment of this system is described below.

[0413] The user uses a terminal equipped with a microphone to input voice into the system. When the user speaks, the terminal captures this voice as a digital signal. This digital voice signal is converted into text data by a speech recognition device within the terminal. This text data is transmitted to a server over the network.

[0414] The server uses natural language processing to analyze the received text data. During this analysis, the server understands the user's intent and the content of their question, and generates an appropriate response. This response is written in text format, and then converted into audio data using speech synthesis. This audio data is sent from the server to the terminal and played back by the terminal's output device so that the user can hear it.

[0415] As a concrete example, consider a user learning Japanese who asks, "What's the weather like today?" This utterance is recorded by the device, converted to text, and sent to the server. The server analyzes the intent of the question from the received text and generates a response text, for example, "The weather in Tokyo today is sunny." This response is then converted back into speech by a speech synthesis system and played back on the user's device. This allows the user to hear the answer to their question in their own language, enabling them to practice conversation efficiently.

[0416] This system allows users to freely choose their desired language and use it repeatedly, enabling effective language learning. Furthermore, it supports multiple languages ​​in addition to Japanese, making it flexible enough to accommodate any language learner. This allows for an economical learning environment that can be accessed regardless of location or time.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The user uses a microphone to ask questions or speak to the system verbally. The user's speech is captured as a digital audio signal by the voice input device provided on the terminal.

[0420] Step 2:

[0421] The terminal uses speech recognition to convert the acquired digital speech signal into text data. This conversion process allows the spoken content to be stored on the terminal in text format.

[0422] Step 3:

[0423] The terminal sends the converted text data to the server. This transmission is performed via secure network communication, ensuring the safety of the data.

[0424] Step 4:

[0425] The server analyzes the received text data using natural language processing. Through this analysis, the server understands the user's intent and the content of the question, and generates an appropriate response text.

[0426] Step 5:

[0427] The server sends the generated response text to a speech synthesis system, which converts it into speech data. A high-quality synthesis process is applied to the speech synthesis system to produce natural-sounding speech.

[0428] Step 6:

[0429] The server sends the converted audio data to the user's device. This audio data is transmitted via streaming and delivered without delay.

[0430] Step 7:

[0431] The terminal plays back the received audio data using its output device. This playback allows the user to hear the system's response.

[0432] (Example 1)

[0433] 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."

[0434] Current multilingual conversation practice systems often struggle to efficiently and in real time convert speech to text and generate appropriate responses. Furthermore, there is a need to provide a flexible environment that allows users to freely choose their learning time and practice in various languages.

[0435] 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.

[0436] In this invention, the server includes means for acquiring speech, means for converting the acquired speech into encoded information, means for natural language processing that analyzes the converted encoded information to generate response information, means for speech synthesis that converts the generated response information into encoded information, and means for outputting the encoded information. This makes it possible for the user to efficiently practice multilingual conversation at a desired timing.

[0437] "Means for acquiring sound" refers to devices or systems that collect voice signals emitted by users and process those signals as digital data.

[0438] "Speech recognition means" refers to technologies and algorithms for analyzing acquired speech signals and converting them into corresponding text data.

[0439] "Encoded information" refers to a representation format used for communication and recording, which converts audio and text data into a digital format.

[0440] "Natural language processing methods" refer to technologies and algorithms for processing the language that humans use on a daily basis and analyzing its meaning and intent.

[0441] "Response information" refers to appropriate responses and information for the user, generated based on the results of analysis using natural language processing tools.

[0442] "Speech synthesis means" refers to technologies and algorithms for analyzing generated text data and converting it into corresponding speech signals.

[0443] "Means for outputting encoded information" refers to devices or mechanisms for reproducing the generated audio signal, thereby transmitting information to the user as audio.

[0444] The embodiments for carrying out the invention are described below.

[0445] The present invention is a multilingual conversation practice system that converts speech into text in real time, generates appropriate responses, and outputs those responses as speech. Users can input speech using a terminal equipped with a microphone. The terminal uses an input device (e.g., a microphone) to convert the user's speech into a digital signal. The speech signal is converted into encoded information using speech recognition means (e.g., a common cloud-based speech recognition service). This encoded information is transmitted to a server via a network.

[0446] The server analyzes the encoded information and generates an appropriate response to the user's question or intent. This analysis uses a generative AI model (e.g., a natural language processing tool). The generated response is represented as encoded information and converted back into a speech signal using speech synthesis. This speech signal is returned from the server to the terminal and presented to the user through the terminal's output device.

[0447] As a concrete example, consider a user learning Japanese who asks their device, "What's the weather like today?" The device records this voice, converts it into encoded information, and sends it to the server. The server uses a generative AI model to analyze this information and generates a response such as, "The weather in Tokyo today is sunny." This response is then synthesized into speech and played back on the user's device. This allows the user to practice language efficiently through a natural conversational experience.

[0448] As an example of a prompt, the system can be instructed to "Use the generative AI model to provide an appropriate response when the user inputs 'What's the weather like in Tokyo?' in Japanese." In this way, flexible conversation practice in diverse language environments becomes possible.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The user speaks into the device using the microphone. Specifically, the device receives the voice input from the user via the microphone and acquires this voice as an analog signal. At this point, the input is an analog audio signal, and the device, upon receiving this signal, uses its internal digital conversion process to convert it into a digital audio signal. The output at this point is a digital audio signal.

[0452] Step 2:

[0453] The terminal inputs a digital audio signal into a speech recognition system and converts it into encoded information, i.e., text data. Specifically, it uses a speech recognition engine to analyze each element of the audio and expresses its content as text information. At this time, text data is output based on the digital audio signal.

[0454] Step 3:

[0455] The terminal sends the obtained text data to the server over the network. Here, the data is appropriately encoded using the necessary protocols for transmission, making it receivable on the server side. The input is text data, and the output is a data packet destined for the server.

[0456] Step 4:

[0457] The server analyzes the received text data using natural language processing techniques. It uses a generative AI model to understand the user's intent and questions, and generates corresponding response information. Specifically, it analyzes text data, and the generative AI model dynamically generates response text. In this process, the input is text data, and the output is text data as response information.

[0458] Step 5:

[0459] The server inputs the generated response information into a speech synthesis system and converts it into speech data as encoded information. The speech synthesis engine converts the text information into speech, generating an easily understandable audio signal. The input is text data as response information, and the output is playable audio data.

[0460] Step 6:

[0461] The server transmits audio data to the terminal, which then plays the audio data through an audio playback device. The user can complete the conversation with the system by listening to this outputted audio. The input is audio data, and the output is audio that the user can hear.

[0462] (Application Example 1)

[0463] 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."

[0464] In today's busy lifestyle, individuals often have limited time and space to effectively acquire a language. Furthermore, there is a need for an environment that allows for efficient and repeated learning at home without the need for language classes or textbooks. Additionally, there is a lack of flexible learning methods that support multiple languages ​​and do not require reservations or prior preparation.

[0465] 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.

[0466] In this invention, the server includes a device for receiving speech, a speech recognition device for converting the received speech into text data, and a natural language processing device for analyzing the converted text data and generating response characters. This allows users to learn languages ​​in a mobile environment within their home in conjunction with home automation equipment. Furthermore, by providing dialogue practice that supports multiple languages ​​and offering a learning experience that can be used anytime, the barriers to language acquisition can be reduced.

[0467] A "sound receiving device" is a device that has the function of receiving voice input from a user as an electrical signal and converting it into digital data.

[0468] A "speech recognition device" is a device that analyzes received speech data and converts it into corresponding text data.

[0469] A "natural language processing device" is a device that analyzes converted character data, understands the intent of the input information, and generates appropriate response characters.

[0470] A "speech synthesis device" is a device that converts generated response characters into speech data and makes them playable as human speech.

[0471] "Home automation devices" are devices installed in the home and designed to automate various tasks, including conversational support for language learning.

[0472] "Multilingual support" refers to the ability of a system to process speech input and output in multiple languages ​​and generate appropriate responses.

[0473] A "mobile environment" refers to a configuration that provides the flexibility for learners to use the system even outside of their designated location.

[0474] "Learning at home" refers to a situation where users can acquire a language at their own residence, regardless of time or location.

[0475] The system implementing this invention is a device for users to effectively learn a language at home. Specifically, it operates in conjunction with home automation equipment.

[0476] The server primarily uses a speech recognition device and a natural language processing device. The speech recognition device receives speech from the user and converts it into text data. The "speech_recognition" library is a possible software to use. The text data is analyzed by the natural language processing device on the server to understand the user's intent and generate an appropriate response. The "OpenAI API" is used to generate the response string.

[0477] The generated response string is converted into speech by a speech synthesizer. Using the "gTTS" library, the response can be converted into speech in real time. The converted speech data is output from the terminal device, and the user can listen to it.

[0478] As a concrete example, consider a scenario where a user asks "What's the weather like today?" while at home. This statement is collected via a microphone and converted into text by a speech recognition device. The converted text data is analyzed on a server, and the "OpenAI API" generates an appropriate response, such as "The weather today is sunny." This is then converted into audio data and output from the terminal.

[0479] Examples of prompt messages include the following:

[0480] Generate appropriate responses to users: What's the weather like today?

[0481] This system provides users with a flexible environment to learn a variety of languages ​​according to their individual needs.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The user inputs voice through a microphone. The terminal captures the user's voice as a digital audio signal. This input audio data is sent to a speech recognition device.

[0485] Step 2:

[0486] The speech recognition device converts the input digital speech signal into text data. Specifically, it uses the "speech_recognition" library to convert speech to text. This text data is then sent to the server.

[0487] Step 3:

[0488] The server receives text data and performs natural language processing. Here, it uses the "OpenAI API" to analyze the text data and understand the user's intent. This process generates an appropriate response text.

[0489] Step 4:

[0490] The generated response text is converted into speech data by a speech synthesizer. The server uses the "gTTS" library to convert the text into speech and generate the speech data.

[0491] Step 5:

[0492] The generated audio data is sent to the terminal and output to the user as audio. The user can hear this audio response.

[0493] 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.

[0494] This invention adds an emotion recognition function to a multilingual conversation practice system that uses user voice input. This system allows users to learn languages ​​at their own pace and further provides a more personalized learning experience by recognizing the user's emotional state and adjusting its responses accordingly.

[0495] In one embodiment of the system, the user first speaks through the device's microphone. This voice input is converted into digital voice data within the device. Next, the voice is converted into text data by the device's voice recognition function. This text data is then sent to a server for further analysis.

[0496] The server not only analyzes the content of received text data using natural language processing, but also evaluates the emotions contained in the voice and text data using an emotion engine. This emotion analysis identifies the user's current emotional state. Based on this information, the server generates a response appropriate to the user's emotions. For example, if the user shows interest, it provides more detailed information; conversely, if the user expresses dissatisfaction, it attempts to explain from a different angle, dynamically adjusting the response.

[0497] Furthermore, the data analyzed by the emotion engine is saved as the user's learning history, and this data is reflected in subsequent learning sessions. This allows the server to continuously provide learning content optimized for each individual user.

[0498] As a concrete example, suppose an English-speaking user learning Japanese asks, "I want to know how conversations start," and the emotion engine recognizes the user's interest. The server considers the user's emotions and responds, "Generally, it's good to start with 'Konnichiwa' (hello), but other expressions are used depending on the place," and further deepens the learning by adding more detailed cultural background information.

[0499] Thus, the present invention enables flexible responses that take user emotions into consideration, thereby enhancing the effectiveness of language learning. Even when users experience emotions such as curiosity, interest, or frustration, the system responds appropriately by modeling these emotions. This allows learners to have a more interactive experience.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The user uses a microphone to input questions or what they want to say by voice. The user's speech is captured as digital audio data by the device.

[0503] Step 2:

[0504] The device uses speech recognition to convert the acquired digital speech data into text data. This conversion process allows the user's speech to be treated as text information.

[0505] Step 3:

[0506] The device sends the converted text data to the emotion engine, which identifies the user's emotions. The emotion engine evaluates the user's emotional state through voice intonation and text content analysis.

[0507] Step 4:

[0508] The device sends text data containing emotional data to the server. The server sends the received data to a natural language processing system and generates a response text based on the content of the text and the user's emotions.

[0509] Step 5:

[0510] The server converts the generated response text into speech data using a speech synthesis system. This conversion transforms the text information back into speech information, which can then be provided to the user.

[0511] Step 6:

[0512] The server transmits audio data to the user's device. The transmitted audio data is delivered to the user without delay via streaming.

[0513] Step 7:

[0514] The device plays the received audio data. The device's speaker is used to allow the user to hear the response aloud.

[0515] Step 8:

[0516] If a user continues learning, they will be provided with feedback about the emotions they experienced and how those emotions affected them. This feedback will be saved to help adjust future learning content.

[0517] (Example 2)

[0518] 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."

[0519] Conventional conversation practice systems have been unable to generate responses that take into account the user's emotional state, making it difficult to provide a personalized learning experience. Furthermore, while supporting diverse languages, they lacked the ability to flexibly adjust responses through real-time sentiment analysis. Additionally, it was difficult to provide a continuously optimized learning environment by utilizing the user's learning history.

[0520] 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.

[0521] In this invention, the server includes means for inputting speech, means for converting it into digital data, means for speech recognition, means for natural language processing, means for evaluating emotions, means for generating responses, and means for recording responses and analysis results. This makes it possible to dynamically generate responses according to the user's emotional state and provide a personalized language learning experience.

[0522] "Means of voice input" refers to devices or functions for receiving voice information from users.

[0523] "Means of converting to digital data" refers to the function of encoding analog audio into a digital format.

[0524] "Speech recognition means" refers to technology that analyzes digital speech data and converts it into text format.

[0525] "Natural language processing" refers to technologies that analyze text data, understand its meaning, and generate corresponding information.

[0526] "Means of evaluating emotions" refers to technologies that identify and evaluate a user's emotional state from text or audio.

[0527] "Means for generating responses" refers to technologies that construct appropriate responses based on user input and emotional state.

[0528] "Means for recording responses and analysis results" refers to a function that stores generated information and analysis results in a database or similar system for later use.

[0529] This invention is a conversation practice system that generates responses in real time, taking into account the user's emotional state, when the user engages in interactive language learning through voice input. This system supports more effective language acquisition by providing a personalized learning experience that responds to the user's emotions.

[0530] The system's implementation begins with the use of a terminal. The terminal receives audio input from the user via a microphone and converts that audio into digital data. Specifically, it uses the terminal's recording function or the standard functions of its operating system to encode the audio into a digital format.

[0531] Next, the speech recognition software on the device (e.g., a speech recognition API) converts the digital speech data into text data. In this step, the speech waveform is analyzed and transcribed based on standard phonemes.

[0532] The converted text data is sent to the server. The server uses natural language processing techniques (e.g., natural language processing libraries) to analyze the text. This analysis helps the server understand the meaning of the input text and generate information.

[0533] The server then uses sentiment analysis software (e.g., sentiment analysis engine) to evaluate the user's emotions. In this process, it calculates an emotion score from keywords and phrases in the text to specifically identify the user's current emotional state.

[0534] After the emotion is evaluated, the server uses a generative AI model (e.g., a natural language generation model) to generate a response appropriate to the user's emotion. For example, if the prompt is "Provide a detailed explanation to the user who has shown interest," a response appropriate to the context will be generated.

[0535] Finally, the generated response is returned to the terminal and provided to the user. This response process is dynamic and continuously optimized, taking into account the user's learning history and emotional state. Thus, from voice input via the terminal to analysis on the server, emotion evaluation, and response generation, the user can enjoy a sophisticated, emotion-based language learning experience.

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] The user inputs audio through the device's microphone. Since the input audio is an analog signal, it is converted to a digital format using the device's recording function. This digital audio data is then saved as an audio waveform.

[0539] Step 2:

[0540] The terminal sends the stored digital audio data to speech recognition software. The speech recognition software analyzes this digital data and identifies phonemes. As a result of the analysis, the audio waveform is converted into text data. Here, the input is digital audio data, and the output is the converted text data.

[0541] Step 3:

[0542] The terminal sends the converted text data to the server. In this process, metadata such as user ID and session information is also sent along with the text data. The HTTPS protocol is used to ensure secure data communication during this process.

[0543] Step 4:

[0544] The server uses a natural language processing engine based on the received text data. The server analyzes the text content to identify the intent of the question and the information being sought. The input for this analysis is text data, and the output is information about the meaning of the text.

[0545] Step 5:

[0546] The server uses an emotion analysis engine to evaluate the user's emotions from the analyzed text. It calculates an emotion score based on the tone and keywords of the input text, identifying the user's emotional state. The output of this process is the emotion evaluation result.

[0547] Step 6:

[0548] The server uses a generative AI model to generate an appropriate response based on the evaluated sentiment. The generative AI model is input with a prompt and outputs a text response corresponding to the user's sentiment state. For example, the prompt might be, "This user is interested; please explain further."

[0549] Step 7:

[0550] The server sends the generated response text back to the terminal. The terminal presents the received response to the user. In this step, the input is the response text from the server, and the output is a display or audio for the user.

[0551] Step 8:

[0552] The server stores the results of analysis and sentiment evaluation, as well as the generated responses, in a database as the user's learning history. This stored data is used in future learning sessions, continuously optimizing the user experience. The output is learning history data intended for use in subsequent learning sessions.

[0553] (Application Example 2)

[0554] 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."

[0555] Modern self-study systems fail to generate responses that take into account the user's emotional state, thus not providing a personalized learning experience. This makes it easy for users to lose interest in learning, hindering effective language acquisition. Furthermore, multilingual systems often lack sufficient dynamic conversational adjustments based on emotional states, making it difficult to provide support tailored to the user's learning needs.

[0556] 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.

[0557] In this invention, the server includes a device for inputting speech, an emotion recognition means for evaluating the emotional state from the text and speech data, and a response adjustment means for dynamically adjusting the response text according to the emotional state. This makes it possible to adjust the response based on the user's emotional state and provide a personalized language learning experience. As a result, the user is more likely to maintain interest and can achieve more effective learning.

[0558] "A device or means for inputting voice" refers to a device or equipment that receives voice data from a user and inputs it into a system.

[0559] "Speech recognition means" refers to technology that analyzes input speech data and converts it into text format.

[0560] "Natural language processing means" refers to technologies for understanding converted text data and generating appropriate response text.

[0561] "Speech synthesis means" refers to a technology that converts the generated response text back into speech data and outputs it as speech.

[0562] "Emotion recognition means" refers to technologies for evaluating and understanding a user's emotional state from voice and text data.

[0563] "Response adjustment means" refers to technology that dynamically adjusts the system's response based on the recognized emotional state and provides it to the user.

[0564] This system is designed for users to practice multilingual conversation through consumer robots. Specifically, it uses the following hardware and software:

[0565] The device is equipped with a microphone for voice input and a speaker for voice output. Users speak into the device to input voice. The Google Speech-to-Text API is used for speech recognition, and the input voice data is converted into text format. This allows the content of the voice to be transmitted to the server as text data.

[0566] The server uses OpenAI's generative AI model to analyze the received text data, performing natural language processing to generate appropriate responses. Simultaneously, it uses IBM Watson Tone Analyzer to evaluate the user's emotional state from both speech and text. This emotion recognition helps determine whether the user is interested or tired, for example.

[0567] The generated response text is synthesized into speech by the server and output to the user as audio via the terminal. During this process, the response is dynamically adjusted to suit the user's emotional state. For example, if the user is tired, simpler topics and shorter responses are provided; if they are interested, the response is adjusted to support more detailed information and additional topics.

[0568] For example, if a user says, "Today I want to learn some simple Japanese expressions," the system analyzes the statement and uses sentiment recognition to determine that the user is seeking a simple conversation. The server then generates a friendly response such as, "Hello, how can I help you today?" and provides a detailed, beginner-friendly explanation.

[0569] As an example of a prompt, a user might say to the AI ​​generator, "I want to practice short conversations in Japanese. After the user asks 'What's the weather like today?', prepare several responses to pique their interest." Based on this prompt, the system can dynamically adjust its response to provide the optimal learning environment for the user.

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] The device receives voice input from the user via the microphone. This voice data is then passed to the system as input data.

[0573] Step 2:

[0574] The device uses the Google Speech-to-Text API to convert the input speech data into text format. This converted text data is then output for the next processing step.

[0575] Step 3:

[0576] Text data is sent from the terminal to the server. The server uses this text as input and performs natural language processing using OpenAI's generative AI model to generate response text. This response text is then provided for the next processing step.

[0577] Step 4:

[0578] The server uses IBM Watson Tone Analyzer to evaluate the user's emotional state from the input voice and text data. This evaluation result, along with the generated response, becomes the input data for the next processing step.

[0579] Step 5:

[0580] The server dynamically adjusts the response text generated based on the evaluated emotional state. For example, if the user shows interest, the response text is modified to add more detailed explanations.

[0581] Step 6:

[0582] The server converts the adjusted response text into speech data using speech synthesis technology. This speech data is then sent back to the terminal as the final output.

[0583] Step 7:

[0584] The device provides the outputted audio data to the user through its speaker. This allows the user to receive a response as audio.

[0585] Through the above processes, the system can provide users with a personalized language learning experience.

[0586] 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.

[0587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention is a multilingual conversation practice system that converts speech to text in real time, generates appropriate responses based on the content, and outputs them back as speech. An embodiment of this system is described below.

[0604] The user uses a terminal equipped with a microphone to input voice into the system. When the user speaks, the terminal captures this voice as a digital signal. This digital voice signal is converted into text data by a speech recognition device within the terminal. This text data is transmitted to a server over the network.

[0605] The server uses natural language processing to analyze the received text data. During this analysis, the server understands the user's intent and the content of their question, and generates an appropriate response. This response is written in text format, and then converted into audio data using speech synthesis. This audio data is sent from the server to the terminal and played back by the terminal's output device so that the user can hear it.

[0606] As a concrete example, consider a user learning Japanese who asks, "What's the weather like today?" This utterance is recorded by the device, converted to text, and sent to the server. The server analyzes the intent of the question from the received text and generates a response text, for example, "The weather in Tokyo today is sunny." This response is then converted back into speech by a speech synthesis system and played back on the user's device. This allows the user to hear the answer to their question in their own language, enabling them to practice conversation efficiently.

[0607] This system allows users to freely choose their desired language and use it repeatedly, enabling effective language learning. Furthermore, it supports multiple languages ​​in addition to Japanese, making it flexible enough to accommodate any language learner. This allows for an economical learning environment that can be accessed regardless of location or time.

[0608] The following describes the processing flow.

[0609] Step 1:

[0610] The user uses a microphone to ask questions or speak to the system verbally. The user's speech is captured as a digital audio signal by the voice input device provided on the terminal.

[0611] Step 2:

[0612] The terminal uses speech recognition to convert the acquired digital speech signal into text data. This conversion process allows the spoken content to be stored on the terminal in text format.

[0613] Step 3:

[0614] The terminal sends the converted text data to the server. This transmission is performed via secure network communication, ensuring the safety of the data.

[0615] Step 4:

[0616] The server analyzes the received text data using natural language processing. Through this analysis, the server understands the user's intent and the content of the question, and generates an appropriate response text.

[0617] Step 5:

[0618] The server sends the generated response text to a speech synthesis system, which converts it into speech data. A high-quality synthesis process is applied to the speech synthesis system to produce natural-sounding speech.

[0619] Step 6:

[0620] The server sends the converted audio data to the user's device. This audio data is transmitted via streaming and delivered without delay.

[0621] Step 7:

[0622] The terminal plays back the received audio data using its output device. This playback allows the user to hear the system's response.

[0623] (Example 1)

[0624] 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".

[0625] Current multilingual conversation practice systems often struggle to efficiently and in real time convert speech to text and generate appropriate responses. Furthermore, there is a need to provide a flexible environment that allows users to freely choose their learning time and practice in various languages.

[0626] 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.

[0627] In this invention, the server includes means for acquiring speech, means for converting the acquired speech into encoded information, means for natural language processing that analyzes the converted encoded information to generate response information, means for speech synthesis that converts the generated response information into encoded information, and means for outputting the encoded information. This makes it possible for the user to efficiently practice multilingual conversation at a desired timing.

[0628] "Means for acquiring sound" refers to devices or systems that collect voice signals emitted by users and process those signals as digital data.

[0629] "Speech recognition means" refers to technologies and algorithms for analyzing acquired speech signals and converting them into corresponding text data.

[0630] "Encoded information" refers to a representation format used for communication and recording, which converts audio and text data into a digital format.

[0631] "Natural language processing methods" refer to technologies and algorithms for processing the language that humans use on a daily basis and analyzing its meaning and intent.

[0632] "Response information" refers to appropriate responses and information for the user, generated based on the results of analysis using natural language processing tools.

[0633] "Speech synthesis means" refers to technologies and algorithms for analyzing generated text data and converting it into corresponding speech signals.

[0634] "Means for outputting encoded information" refers to devices or mechanisms for reproducing the generated audio signal, thereby transmitting information to the user as audio.

[0635] The embodiments for carrying out the invention are described below.

[0636] The present invention is a multilingual conversation practice system that converts speech into text in real time, generates appropriate responses, and outputs those responses as speech. Users can input speech using a terminal equipped with a microphone. The terminal uses an input device (e.g., a microphone) to convert the user's speech into a digital signal. The speech signal is converted into encoded information using speech recognition means (e.g., a common cloud-based speech recognition service). This encoded information is transmitted to a server via a network.

[0637] The server analyzes the encoded information and generates an appropriate response to the user's question or intent. This analysis uses a generative AI model (e.g., a natural language processing tool). The generated response is represented as encoded information and converted back into a speech signal using speech synthesis. This speech signal is returned from the server to the terminal and presented to the user through the terminal's output device.

[0638] As a concrete example, consider a user learning Japanese who asks their device, "What's the weather like today?" The device records this voice, converts it into encoded information, and sends it to the server. The server uses a generative AI model to analyze this information and generates a response such as, "The weather in Tokyo today is sunny." This response is then synthesized into speech and played back on the user's device. This allows the user to practice language efficiently through a natural conversational experience.

[0639] As an example of a prompt, the system can be instructed to "Use the generative AI model to provide an appropriate response when the user inputs 'What's the weather like in Tokyo?' in Japanese." In this way, flexible conversation practice in diverse language environments becomes possible.

[0640] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0641] Step 1:

[0642] The user speaks into the device using the microphone. Specifically, the device receives the voice input from the user via the microphone and acquires this voice as an analog signal. At this point, the input is an analog audio signal, and the device, upon receiving this signal, uses its internal digital conversion process to convert it into a digital audio signal. The output at this point is a digital audio signal.

[0643] Step 2:

[0644] The terminal inputs a digital audio signal into a speech recognition system and converts it into encoded information, i.e., text data. Specifically, it uses a speech recognition engine to analyze each element of the audio and expresses its content as text information. At this time, text data is output based on the digital audio signal.

[0645] Step 3:

[0646] The terminal sends the obtained text data to the server over the network. Here, the data is appropriately encoded using the necessary protocols for transmission, making it receivable on the server side. The input is text data, and the output is a data packet destined for the server.

[0647] Step 4:

[0648] The server analyzes the received text data using natural language processing techniques. It uses a generative AI model to understand the user's intent and questions, and generates corresponding response information. Specifically, it analyzes text data, and the generative AI model dynamically generates response text. In this process, the input is text data, and the output is text data as response information.

[0649] Step 5:

[0650] The server inputs the generated response information into a speech synthesis system and converts it into speech data as encoded information. The speech synthesis engine converts the text information into speech, generating an easily understandable audio signal. The input is text data as response information, and the output is playable audio data.

[0651] Step 6:

[0652] The server transmits audio data to the terminal, which then plays the audio data through an audio playback device. The user can complete the conversation with the system by listening to this outputted audio. The input is audio data, and the output is audio that the user can hear.

[0653] (Application Example 1)

[0654] 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".

[0655] In today's busy lifestyle, individuals often have limited time and space to effectively acquire a language. Furthermore, there is a need for an environment that allows for efficient and repeated learning at home without the need for language classes or textbooks. Additionally, there is a lack of flexible learning methods that support multiple languages ​​and do not require reservations or prior preparation.

[0656] 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.

[0657] In this invention, the server includes a device for receiving speech, a speech recognition device for converting the received speech into text data, and a natural language processing device for analyzing the converted text data and generating response characters. This allows users to learn languages ​​in a mobile environment within their home in conjunction with home automation equipment. Furthermore, by providing dialogue practice that supports multiple languages ​​and offering a learning experience that can be used anytime, the barriers to language acquisition can be reduced.

[0658] A "sound receiving device" is a device that has the function of receiving voice input from a user as an electrical signal and converting it into digital data.

[0659] A "speech recognition device" is a device that analyzes received speech data and converts it into corresponding text data.

[0660] A "natural language processing device" is a device that analyzes converted character data, understands the intent of the input information, and generates appropriate response characters.

[0661] A "speech synthesis device" is a device that converts generated response characters into speech data and makes them playable as human speech.

[0662] "Home automation devices" are devices installed in the home and designed to automate various tasks, including conversational support for language learning.

[0663] "Multilingual support" refers to the ability of a system to process speech input and output in multiple languages ​​and generate appropriate responses.

[0664] A "mobile environment" refers to a configuration that provides the flexibility for learners to use the system even outside of their designated location.

[0665] "Learning at home" refers to a situation where users can acquire a language at their own residence, regardless of time or location.

[0666] The system implementing this invention is a device for users to effectively learn a language at home. Specifically, it operates in conjunction with home automation equipment.

[0667] The server primarily uses a speech recognition device and a natural language processing device. The speech recognition device receives speech from the user and converts it into text data. The "speech_recognition" library is a possible software to use. The text data is analyzed by the natural language processing device on the server to understand the user's intent and generate an appropriate response. The "OpenAI API" is used to generate the response string.

[0668] The generated response string is converted into speech by a speech synthesizer. Using the "gTTS" library, the response can be converted into speech in real time. The converted speech data is output from the terminal device, and the user can listen to it.

[0669] As a concrete example, consider a scenario where a user asks "What's the weather like today?" while at home. This statement is collected via a microphone and converted into text by a speech recognition device. The converted text data is analyzed on a server, and the "OpenAI API" generates an appropriate response, such as "The weather today is sunny." This is then converted into audio data and output from the terminal.

[0670] Examples of prompt messages include the following:

[0671] Generate appropriate responses to users: What's the weather like today?

[0672] This system provides users with a flexible environment to learn a variety of languages ​​according to their individual needs.

[0673] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0674] Step 1:

[0675] The user inputs voice through a microphone. The terminal captures the user's voice as a digital audio signal. This input audio data is sent to a speech recognition device.

[0676] Step 2:

[0677] The speech recognition device converts the input digital speech signal into text data. Specifically, it uses the "speech_recognition" library to convert speech to text. This text data is then sent to the server.

[0678] Step 3:

[0679] The server receives text data and performs natural language processing. Here, it uses the "OpenAI API" to analyze the text data and understand the user's intent. This process generates an appropriate response text.

[0680] Step 4:

[0681] The generated response text is converted into speech data by a speech synthesizer. The server uses the "gTTS" library to convert the text into speech and generate the speech data.

[0682] Step 5:

[0683] The generated audio data is sent to the terminal and output to the user as audio. The user can hear this audio response.

[0684] 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.

[0685] This invention adds an emotion recognition function to a multilingual conversation practice system that uses user voice input. This system allows users to learn languages ​​at their own pace and further provides a more personalized learning experience by recognizing the user's emotional state and adjusting its responses accordingly.

[0686] In one embodiment of the system, the user first speaks through the device's microphone. This voice input is converted into digital voice data within the device. Next, the voice is converted into text data by the device's voice recognition function. This text data is then sent to a server for further analysis.

[0687] The server not only analyzes the content of received text data using natural language processing, but also evaluates the emotions contained in the voice and text data using an emotion engine. This emotion analysis identifies the user's current emotional state. Based on this information, the server generates a response appropriate to the user's emotions. For example, if the user shows interest, it provides more detailed information; conversely, if the user expresses dissatisfaction, it attempts to explain from a different angle, dynamically adjusting the response.

[0688] Furthermore, the data analyzed by the emotion engine is saved as the user's learning history, and this data is reflected in subsequent learning sessions. This allows the server to continuously provide learning content optimized for each individual user.

[0689] As a concrete example, suppose an English-speaking user learning Japanese asks, "I want to know how conversations start," and the emotion engine recognizes the user's interest. The server considers the user's emotions and responds, "Generally, it's good to start with 'Konnichiwa' (hello), but other expressions are used depending on the place," and further deepens the learning by adding more detailed cultural background information.

[0690] Thus, the present invention enables flexible responses that take user emotions into consideration, thereby enhancing the effectiveness of language learning. Even when users experience emotions such as curiosity, interest, or frustration, the system responds appropriately by modeling these emotions. This allows learners to have a more interactive experience.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] The user uses a microphone to input questions or what they want to say by voice. The user's speech is captured as digital audio data by the device.

[0694] Step 2:

[0695] The device uses speech recognition to convert the acquired digital speech data into text data. This conversion process allows the user's speech to be treated as text information.

[0696] Step 3:

[0697] The device sends the converted text data to the emotion engine, which identifies the user's emotions. The emotion engine evaluates the user's emotional state through voice intonation and text content analysis.

[0698] Step 4:

[0699] The device sends text data containing emotional data to the server. The server sends the received data to a natural language processing system and generates a response text based on the content of the text and the user's emotions.

[0700] Step 5:

[0701] The server converts the generated response text into speech data using a speech synthesis system. This conversion transforms the text information back into speech information, which can then be provided to the user.

[0702] Step 6:

[0703] The server transmits audio data to the user's device. The transmitted audio data is delivered to the user without delay via streaming.

[0704] Step 7:

[0705] The device plays the received audio data. The device's speaker is used to allow the user to hear the response aloud.

[0706] Step 8:

[0707] If a user continues learning, they will be provided with feedback about the emotions they experienced and how those emotions affected them. This feedback will be saved to help adjust future learning content.

[0708] (Example 2)

[0709] 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".

[0710] Conventional conversation practice systems have been unable to generate responses that take into account the user's emotional state, making it difficult to provide a personalized learning experience. Furthermore, while supporting diverse languages, they lacked the ability to flexibly adjust responses through real-time sentiment analysis. Additionally, it was difficult to provide a continuously optimized learning environment by utilizing the user's learning history.

[0711] 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.

[0712] In this invention, the server includes means for inputting speech, means for converting it into digital data, means for speech recognition, means for natural language processing, means for evaluating emotions, means for generating responses, and means for recording responses and analysis results. This makes it possible to dynamically generate responses according to the user's emotional state and provide a personalized language learning experience.

[0713] "Means of voice input" refers to devices or functions for receiving voice information from users.

[0714] "Means of converting to digital data" refers to the function of encoding analog audio into a digital format.

[0715] "Speech recognition means" refers to technology that analyzes digital speech data and converts it into text format.

[0716] "Natural language processing" refers to technologies that analyze text data, understand its meaning, and generate corresponding information.

[0717] "Means of evaluating emotions" refers to technologies that identify and evaluate a user's emotional state from text or audio.

[0718] "Means for generating responses" refers to technologies that construct appropriate responses based on user input and emotional state.

[0719] "Means for recording responses and analysis results" refers to a function that stores generated information and analysis results in a database or similar system for later use.

[0720] This invention is a conversation practice system that generates responses in real time, taking into account the user's emotional state, when the user engages in interactive language learning through voice input. This system supports more effective language acquisition by providing a personalized learning experience that responds to the user's emotions.

[0721] The system's implementation begins with the use of a terminal. The terminal receives audio input from the user via a microphone and converts that audio into digital data. Specifically, it uses the terminal's recording function or the standard functions of its operating system to encode the audio into a digital format.

[0722] Next, the speech recognition software on the device (e.g., a speech recognition API) converts the digital speech data into text data. In this step, the speech waveform is analyzed and transcribed based on standard phonemes.

[0723] The converted text data is sent to the server. The server uses natural language processing techniques (e.g., natural language processing libraries) to analyze the text. This analysis helps the server understand the meaning of the input text and generate information.

[0724] The server then uses sentiment analysis software (e.g., sentiment analysis engine) to evaluate the user's emotions. In this process, it calculates an emotion score from keywords and phrases in the text to specifically identify the user's current emotional state.

[0725] After the emotion is evaluated, the server uses a generative AI model (e.g., a natural language generation model) to generate a response appropriate to the user's emotion. For example, if the prompt is "Provide a detailed explanation to the user who has shown interest," a response appropriate to the context will be generated.

[0726] Finally, the generated response is returned to the terminal and provided to the user. This response process is dynamic and continuously optimized, taking into account the user's learning history and emotional state. Thus, from voice input via the terminal to analysis on the server, emotion evaluation, and response generation, the user can enjoy a sophisticated, emotion-based language learning experience.

[0727] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0728] Step 1:

[0729] The user inputs audio through the device's microphone. Since the input audio is an analog signal, it is converted to a digital format using the device's recording function. This digital audio data is then saved as an audio waveform.

[0730] Step 2:

[0731] The terminal sends the stored digital audio data to speech recognition software. The speech recognition software analyzes this digital data and identifies phonemes. As a result of the analysis, the audio waveform is converted into text data. Here, the input is digital audio data, and the output is the converted text data.

[0732] Step 3:

[0733] The terminal sends the converted text data to the server. In this process, metadata such as user ID and session information is also sent along with the text data. The HTTPS protocol is used to ensure secure data communication during this process.

[0734] Step 4:

[0735] The server uses a natural language processing engine based on the received text data. The server analyzes the text content to identify the intent of the question and the information being sought. The input for this analysis is text data, and the output is information about the meaning of the text.

[0736] Step 5:

[0737] The server uses an emotion analysis engine to evaluate the user's emotions from the analyzed text. It calculates an emotion score based on the tone and keywords of the input text, identifying the user's emotional state. The output of this process is the emotion evaluation result.

[0738] Step 6:

[0739] The server uses a generative AI model to generate an appropriate response based on the evaluated sentiment. The generative AI model is input with a prompt and outputs a text response corresponding to the user's sentiment state. For example, the prompt might be, "This user is interested; please explain further."

[0740] Step 7:

[0741] The server sends the generated response text back to the terminal. The terminal presents the received response to the user. In this step, the input is the response text from the server, and the output is a display or audio for the user.

[0742] Step 8:

[0743] The server stores the results of analysis and sentiment evaluation, as well as the generated responses, in a database as the user's learning history. This stored data is used in future learning sessions, continuously optimizing the user experience. The output is learning history data intended for use in subsequent learning sessions.

[0744] (Application Example 2)

[0745] 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".

[0746] Modern self-study systems fail to generate responses that take into account the user's emotional state, thus not providing a personalized learning experience. This makes it easy for users to lose interest in learning, hindering effective language acquisition. Furthermore, multilingual systems often lack sufficient dynamic conversational adjustments based on emotional states, making it difficult to provide support tailored to the user's learning needs.

[0747] 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.

[0748] In this invention, the server includes a device for inputting speech, an emotion recognition means for evaluating the emotional state from the text and speech data, and a response adjustment means for dynamically adjusting the response text according to the emotional state. This makes it possible to adjust the response based on the user's emotional state and provide a personalized language learning experience. As a result, the user is more likely to maintain interest and can achieve more effective learning.

[0749] "A device or means for inputting voice" refers to a device or equipment that receives voice data from a user and inputs it into a system.

[0750] "Speech recognition means" refers to technology that analyzes input speech data and converts it into text format.

[0751] "Natural language processing means" refers to technologies for understanding converted text data and generating appropriate response text.

[0752] "Speech synthesis means" refers to a technology that converts the generated response text back into speech data and outputs it as speech.

[0753] "Emotion recognition means" refers to technologies for evaluating and understanding a user's emotional state from voice and text data.

[0754] "Response adjustment means" refers to technology that dynamically adjusts the system's response based on the recognized emotional state and provides it to the user.

[0755] This system is designed for users to practice multilingual conversation through consumer robots. Specifically, it uses the following hardware and software:

[0756] The device is equipped with a microphone for voice input and a speaker for voice output. Users speak into the device to input voice. The Google Speech-to-Text API is used for speech recognition, and the input voice data is converted into text format. This allows the content of the voice to be transmitted to the server as text data.

[0757] The server uses OpenAI's generative AI model to analyze the received text data, performing natural language processing to generate appropriate responses. Simultaneously, it uses IBM Watson Tone Analyzer to evaluate the user's emotional state from both speech and text. This emotion recognition helps determine whether the user is interested or tired, for example.

[0758] The generated response text is synthesized into speech by the server and output to the user as audio via the terminal. During this process, the response is dynamically adjusted to suit the user's emotional state. For example, if the user is tired, simpler topics and shorter responses are provided; if they are interested, the response is adjusted to support more detailed information and additional topics.

[0759] For example, if a user says, "Today I want to learn some simple Japanese expressions," the system analyzes the statement and uses sentiment recognition to determine that the user is seeking a simple conversation. The server then generates a friendly response such as, "Hello, how can I help you today?" and provides a detailed, beginner-friendly explanation.

[0760] As an example of a prompt, a user might say to the AI ​​generator, "I want to practice short conversations in Japanese. After the user asks 'What's the weather like today?', prepare several responses to pique their interest." Based on this prompt, the system can dynamically adjust its response to provide the optimal learning environment for the user.

[0761] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0762] Step 1:

[0763] The device receives voice input from the user via the microphone. This voice data is then passed to the system as input data.

[0764] Step 2:

[0765] The device uses the Google Speech-to-Text API to convert the input speech data into text format. This converted text data is then output for the next processing step.

[0766] Step 3:

[0767] Text data is sent from the terminal to the server. The server uses this text as input and performs natural language processing using OpenAI's generative AI model to generate response text. This response text is then provided for the next processing step.

[0768] Step 4:

[0769] The server uses IBM Watson Tone Analyzer to evaluate the user's emotional state from the input voice and text data. This evaluation result, along with the generated response, becomes the input data for the next processing step.

[0770] Step 5:

[0771] The server dynamically adjusts the response text generated based on the evaluated emotional state. For example, if the user shows interest, the response text is modified to add more detailed explanations.

[0772] Step 6:

[0773] The server converts the adjusted response text into speech data using speech synthesis technology. This speech data is then sent back to the terminal as the final output.

[0774] Step 7:

[0775] The device provides the outputted audio data to the user through its speaker. This allows the user to receive a response as audio.

[0776] Through the above processes, the system can provide users with a personalized language learning experience.

[0777] 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.

[0778] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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."

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] The following is further disclosed regarding the embodiments described above.

[0799] (Claim 1)

[0800] A means of inputting voice,

[0801] A speech recognition means that converts the input audio into text data,

[0802] A natural language processing means that analyzes the converted text data and generates a response text,

[0803] A speech synthesis means that converts the generated response text into speech data,

[0804] A system including means for outputting the audio data.

[0805] (Claim 2)

[0806] The system according to claim 1, which provides an environment for a user to learn a language at a desired time.

[0807] (Claim 3)

[0808] The system described in claim 1, which supports conversation practice in multiple languages ​​and is available without reservation.

[0809] "Example 1"

[0810] (Claim 1)

[0811] Means of acquiring sound,

[0812] A speech recognition means that converts the acquired audio into encoded information,

[0813] A natural language processing means that analyzes the converted encoded information and generates response information,

[0814] A speech synthesis means that converts the generated response information into encoded information,

[0815] A system including means for outputting the encoded information.

[0816] (Claim 2)

[0817] The system according to claim 1, which provides an environment for users to acquire knowledge at a desired time.

[0818] (Claim 3)

[0819] The system described in claim 1, which supports conversation practice in multiple languages ​​and is available without prior reservation.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] A device that receives sound,

[0823] A speech recognition device that converts the received audio into text data,

[0824] A natural language processing device that analyzes the converted character data and generates response characters,

[0825] A speech synthesis device that converts the generated response characters into speech data,

[0826] A system including a device that outputs the audio data,

[0827] A device that connects with home automation equipment, supporting language learners through voice interaction and allowing them to hear responses generated by a voice output function,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which provides an environment for the user to acquire a language at a time of their choosing, and is integrated into an automated device that is portable within the home.

[0831] (Claim 3)

[0832] The system according to claim 1, which supports dialogue practice in multiple languages ​​and can be used without prior preparation.

[0833] "Example 2 of combining an emotion engine"

[0834] (Claim 1)

[0835] A means of inputting voice,

[0836] A means for converting the input audio into digital data,

[0837] A speech recognition means for converting the digital data into text,

[0838] A natural language processing means for analyzing the text and generating information,

[0839] A means for evaluating emotions based on the said information,

[0840] A means of generating responses in response to emotions,

[0841] A means of returning the generated response to the user,

[0842] A system including means for recording the response and analysis results.

[0843] (Claim 2)

[0844] The system according to claim 1, which provides a learning experience that corresponds to the user's emotional state.

[0845] (Claim 3)

[0846] The system according to claim 1, which supports multiple functions and allows for dynamic response adjustment.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] A device means for inputting sound,

[0850] A speech recognition means that converts the input audio into text data,

[0851] A natural language processing means that analyzes the converted text data and generates a response text,

[0852] A speech synthesis means that converts the generated response text into speech data,

[0853] A device means for outputting the audio data,

[0854] An emotion recognition means for evaluating emotional states from the text and audio data,

[0855] A system including a response adjustment means for dynamically adjusting response text according to the emotional state.

[0856] (Claim 2)

[0857] The system according to claim 1, which provides an environment for a user to learn a language at a desired time and personalizes the learning content based on the user's emotional state.

[0858] (Claim 3)

[0859] The system according to claim 1, which supports multilingual conversation practice, has a function to adjust responses based on emotional state, and is available without reservation. [Explanation of Symbols]

[0860] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of inputting voice, A speech recognition means that converts the input audio into text data, A natural language processing means that analyzes the converted text data and generates a response text, A speech synthesis means that converts the generated response text into speech data, A system including means for outputting the audio data.

2. The system according to claim 1, which provides an environment for a user to learn a language at a time of their choosing.

3. The system described in claim 1, which supports conversation practice in multiple languages ​​and is available without reservation.

Images