System

Abstract

A system is provided.SOLUTION: A system for supporting music training, comprising: means for a user to select a music training menu; means for an endpoint to capture and transmit audio to a server in real-time; means for the server to analyze the audio and generate pitch and rhythm feedback based on the analysis; and means for the endpoint to display the feedback to the user in real-time; and means for the server to accumulate training and use the generated AI model to optimize upcoming training.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Professional training is required to accurately match pitch when singing and performing music, but receiving direct instruction is costly and time-consuming. Furthermore, beginners and self-taught people often find it difficult to access professional training methods or receive appropriate feedback tailored to their own progress. Therefore, it is necessary to solve these problems by providing an environment where music lovers can easily receive effective musical training. [Means for solving the problem]

[0005] The present invention provides a system for supporting musical training, and specifically solves the problems by the following means.

[0006] 1. Provide a means for users to select a music training menu, allowing them to select effective training content based on their preferences.

[0007] 2. By providing a means for the device to capture audio and transmit it to the server in real time, the user's performance and vocalizations can be analyzed instantly.

[0008] 3. The server analyzes the audio data and provides a means to generate feedback on pitch and rhythm based on the analysis results, allowing the user to immediately understand areas for improvement.

[0009] 4. The device provides a means to display feedback to the user in real time, allowing for immediate corrections during training.

[0010] 5. The server accumulates the training data and provides a means to use the generated AI model to optimize the next training session, continuously suggesting the best training method for each individual user.

[0011] By combining the above means, a system is realized that allows users to easily receive high-quality musical training and effectively improve their ability to accurately match pitch and rhythm.

[0012] "User" refers to a person who uses the system to receive musical training.

[0013] "Device" refers to a smartphone or tablet device used by a user to operate the training application installed by the user.

[0014] "Server" refers to a central processing unit that analyzes the voice data sent by the user and provides feedback and suggests training menus.

[0015] A "music training menu" refers to vocal training, instrument playing, or practice content for a specific piece of music selected by the user.

[0016] "Capturing audio" refers to capturing the user's voice or the sound of an instrument being played as input data using the microphone of the terminal.

[0017] "Transmitting in real time" means that the voice data is immediately transferred to the server the moment the user speaks.

[0018] "Analyzing voice data" refers to the process in which the server uses artificial intelligence (AI) technology to evaluate the pitch and rhythm of the user's voice and generate appropriate feedback.

[0019] "Generating feedback" means that the server generates information for the user based on the speech analysis about what needs to be corrected or improved.

[0020] "Displaying feedback" refers to displaying the feedback information received by the terminal from the server on the screen in a format that is easy for the user to see.

[0021] "Storing training data" means that the server stores the user's training history and audio data and uses that data to optimize future training. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

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

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] This invention is a system for supporting musical training, providing effective training using smartphones and tablet devices. The entire system is mainly composed of three elements: the user, the device, and the server.

[0044] User operations

[0045] Users install a dedicated app on their smartphone or tablet. When they launch the app, they are first shown an initial setup screen where they can adjust the microphone sensitivity and sound reverberation settings, allowing the device to accurately capture voices.

[0046] Selecting a training menu

[0047] Once the user has completed the initial setup, they can choose from a music training menu provided within the app, which includes basic training, specific vocal exercises, and practice of specific songs. Once the user selects the desired training content, the information is sent to the server.

[0048] Audio capture and real-time transmission

[0049] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0050] Server analysis and feedback generation

[0051] The server analyzes the audio data sent from the device. The analysis uses an AI algorithm to meticulously evaluate pitch and rhythm discrepancies. Based on the analysis results, the server generates real-time feedback, including specific advice such as "your high notes are unstable" or "your rhythm is too fast."

[0052] View Feedback

[0053] The device immediately displays the feedback information sent from the server to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch is out of sync.

[0054] Accumulation and optimization of training data

[0055] The server stores the user's training data. Based on the stored data, a generative AI model is used to optimize the next training session. This model is designed to suggest optimal training menus and songs based on the user's past data and training progress.

[0056] Example 1: Basic Training Session

[0057] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings the basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0058] Example 2: Practice session for assigned piece

[0059] The user selects the song "Let It Go" and begins training. The device then suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0060] The present invention enables effective musical training, and allows users to improve their ability to accurately match pitch and rhythm without receiving specialized instruction.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user installs a dedicated app on their smartphone or tablet.

[0064] Step 2:

[0065] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0066] Step 3:

[0067] The device saves the user's settings and sends them to the server.

[0068] Step 4:

[0069] The user selects a basic training or challenge song from the music training menu within the app.

[0070] Step 5:

[0071] The terminal displays the selected training menu and transmits the selection information to the server.

[0072] Step 6:

[0073] To start training, the user speaks or plays an instrument into the device's microphone.

[0074] Step 7:

[0075] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0076] Step 8:

[0077] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0078] Step 9:

[0079] The server generates feedback based on the analysis results, providing specific advice such as "the pitch is too high" or "the rhythm is too fast."

[0080] Step 10:

[0081] The device displays the feedback sent from the server to the user in real time.

[0082] Step 11:

[0083] The user can adjust their training based on the feedback and then sing or play again.

[0084] Step 12:

[0085] The device displays a button that the user presses to end the training session.

[0086] Step 13:

[0087] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[0088] Step 14:

[0089] Users can selectively share their training results on social media.

[0090] Step 15:

[0091] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0092] Step 16:

[0093] The terminal notifies the user of the optimized next training menu proposal from the server.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional music training systems have limitations in helping users effectively master pitch and rhythm. Specifically, they lack real-time feedback and a means for users to self-evaluate, limiting the effectiveness of training. Furthermore, the lack of individualized training content means that appropriate instruction cannot be provided based on the user's progress.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server

[0099] a means for a user to select a musical training menu;

[0100] a means for the terminal to capture and transmit audio to a server in real time;

[0101] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[0102] means for the terminal to display feedback to the user in real time;

[0103] The server stores the training data and uses the generated AI model to optimize the next training.

[0104] A means for the user to set up the device and adjust microphone sensitivity and sound reverberation;

[0105] A means to analyze the user's past training data and suggest the optimal training menu;

[0106] This allows users to train while receiving real-time feedback, and by being offered individually optimized training menus, it is possible to effectively improve musical skills.

[0107] "User" refers to a person who uses the musical training system.

[0108] "Terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0109] "Server" refers to a remote computer system that analyzes speech data, generates feedback, and stores and optimizes training data.

[0110] "Music training menu" refers to a list of training contents that the user can select from.

[0111] "Voice data" refers to sound information uttered by a user through a microphone on a terminal.

[0112] "Feedback" refers to advice and evaluation regarding pitch and rhythm generated based on audio data analyzed by the server.

[0113] "Real-time" refers to near-instant processing with minimal delay.

[0114] An "AI model" is an algorithm that uses artificial intelligence to analyze the user's voice data and optimize the next training menu.

[0115] "Microphone sensitivity" refers to the ability of a device's microphone to pick up sound.

[0116] "Sound reverberation" refers to the phenomenon of sound being reflected back and its effects.

[0117] "Training data" refers to the voice data and analysis results generated during training conducted by the user.

[0118] This invention is a system for supporting musical training, providing effective training using devices such as smartphones and tablets. The entire system is mainly composed of three elements: the user, the device, and the server.

[0119] First, users install a dedicated music training app on their device. When they launch the app, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These initial settings allow the device to accurately capture audio. For example, users can adjust the microphone sensitivity slider to adjust how much sound is picked up.

[0120] After the initial setup is complete, the user selects the desired training menu from the music training menu provided within the app. The information about the selected training menu is sent to the server by the device. For example, if the user selects "Basic Training," the information is sent to the server.

[0121] When a user starts training, the device's microphone captures the user's voice in real time. The captured voice data is compressed and sent to a server over the Internet. For example, when a user sings the first line of "Let It Go," the voice is immediately sent to the server.

[0122] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. If the server determines that the user's high notes are unstable, it generates feedback stating, "Your high notes are unstable." This feedback is displayed in the form of a text message or a graph.

[0123] The device receives the feedback information sent from the server and immediately displays it to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch discrepancy, allowing the user to make corrections in real time.

[0124] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. For example, the server may analyze the user's past pitch data and propose a new optimal training menu.

[0125] For example, when a user opens the app and selects the basic training menu, the device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings a basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0126] When a user selects the song "Let It Go" and begins training, the device suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0127] An example of a prompt sentence is, "Please suggest the best training content for the next training menu. The user's past data is as follows: 'Basic scale practice: pitch is not stable', 'Rhythm practice: unable to maintain a consistent tempo'."

[0128] In this way, the present invention allows users to effectively train in music without receiving specialized instruction, and improve their ability to accurately match pitch and rhythm.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1: Initial Setup

[0131] The user installs the dedicated app on their smartphone or tablet and launches it. The app displays an initial setup screen, providing the user with settings to adjust microphone sensitivity and sound reverberation. Specifically, the user can adjust the microphone sensitivity by moving a slider and check the sound reverberation using a test sound. The input is the user's operation (adjusting microphone sensitivity and checking sound reverberation), and the output is the adapted microphone settings.

[0132] Step 2: Select a training menu

[0133] After completing the initial setup, the user selects the desired menu from the music training menu provided within the app. The device sends information about the selected training menu to the server. The input is the training menu selected by the user, and the output is the menu information sent to the server. Specifically, the user makes a selection by tapping "Basic Training" or "Set Song Practice."

[0134] Step 3: Audio capture and real-time transmission

[0135] When a user starts training, the device's microphone captures the user's voice in real time. This voice data is compressed and sent to a server over the Internet. The input is the user's voice, and the output is the compressed voice data sent to the server. Specifically, when the user sings the first phrase of "Let It Go," the voice is immediately sent to the server.

[0136] Step 4: Server analysis and feedback generation

[0137] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. The input is the audio data sent to the server, and the output is feedback generated based on the analysis results. Specifically, the server determines that "the user's pitch in the high notes is unstable" and generates feedback stating, "The high notes are unstable."

[0138] Step 5: View your feedback

[0139] The terminal receives the feedback information sent from the server and immediately displays it to the user. The input is the feedback information sent from the server, and the output is the feedback message or visual display displayed to the user. Specifically, a text message such as "Please lower the pitch a little" or a bar indicating the pitch discrepancy is displayed on the screen.

[0140] Step 6: Accumulating and optimizing training data

[0141] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. The input is the user's past training data, and the output is a new training menu optimized by the generative AI model. Specifically, the server performs operations such as "analyzing the user's past pitch data and proposing the next training menu."

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] While conventional music training systems can evaluate pitch and rhythm, they are not suited to diverse applications such as improving the accuracy of factory work or providing real-time feedback. In particular, it has been difficult to analyze vibrations and operational sounds, which are necessary in the work environment, and provide feedback based on that analysis. This has made it difficult to support the improvement of the movement accuracy of workers and robots.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes a means for the terminal to capture voice and vibration and transmit them to the server in real time, a means for the server to analyze the voice and vibration data and generate feedback on pitch, rhythm, and task accuracy based on the analysis results, and a means for the server to accumulate training and task data and use the generated AI model to optimize the next training or task, thereby enabling the provision of real-time feedback aimed at improving the motion accuracy of workers and robots.

[0147] A "user" is a user who operates the system and performs musical training or training to improve work accuracy.

[0148] A "music training menu" is a list of practice items and assignments that a user can select to improve their musical skills through the system.

[0149] A "terminal" is a device that captures sound and vibrations and transmits them to a server, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[0150] The "server" is a computer system that receives the voice and vibration data sent from the terminal, analyzes it, and generates feedback.

[0151] "Feedback" refers to advice and instructions generated by the server based on the analysis results, including specific areas for improvement regarding pitch, rhythm, and work accuracy.

[0152] "Training data" refers to recorded information such as audio and vibration data generated by the user during training, analysis results, and feedback.

[0153] A "generated AI model" is an artificial intelligence algorithm and its program used to optimize the next training or task based on the user's training data or task data.

[0154] "Vibration" is a signal or data that captures physical movements and fluctuations that occur during factory operations.

[0155] "Work accuracy" is an indicator of how accurately a worker or robot performs work according to specified procedures and standards.

[0156] This invention is a system in which a user selects a music training menu, and the terminal captures and transmits the audio and vibration data to a server in real time. The server then analyzes the audio and vibration data, generates feedback based on the analysis results, and provides it to the user. The server also accumulates training and work data and uses the generated AI model to optimize the next training or work.

[0157] Details of the hardware and software used

[0158] Hardware:

[0159] Device: A smartphone, tablet, smart glasses, or head-mounted display for capturing sound and vibration.

[0160] Microphone and sensors: The device's built-in microphone and vibration sensors are used to capture the user's voice and working vibrations.

[0161] software:

[0162] Python: Used in programs that perform data analysis on the server side.

[0163] Flask: A web application framework for transmitting audio data.

[0164] SpeechRecognition libraries: Used to analyze speech data (e.g., Google's Web Speech API).

[0165] AI Algorithms: Generative AI models used for analysis and feedback generation, which generate appropriate feedback based on the analysis of audio and vibration data.

[0166] Program processing explanation

[0167] Audio and Vibration Capture

[0168] The device's microphone and vibration sensor capture the user's voice and vibrations in real time, and the captured data is sent from the device to a server.

[0169] Data analysis

[0170] The server analyzes the received audio and vibration data, processing it using AI algorithms to evaluate pitch, rhythm, and task accuracy.

[0171] Feedback Generation

[0172] Based on the analysis results, the server generates specific feedback, such as "Please correct the angle of the drill" or "The conveyor belt speed is too fast," to improve work accuracy. This feedback is sent to the device in real time.

[0173] Feedback Display

[0174] The device receives feedback from the server and displays it to the user in real time, visually indicating pitch and rhythm discrepancies, areas for improvement in the accuracy of the work, and so on.

[0175] Data accumulation and optimization

[0176] The server accumulates data from training and work sessions and uses a generative AI model to optimize future training and work. The model suggests optimal training menus and work procedures based on past data and progress.

[0177] Specific examples

[0178] Example 1: Basic Training Session

[0179] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and vibration sensitivity, and then prompts the user for vocal and vibration tests. When the user sings a basic scale, the audio and vibration data are sent to the server in real time. The server analyzes the audio and generates immediate feedback, such as "Please raise the pitch a little more," which is then displayed on the device.

[0180] Example 2: Work Accuracy Improvement Session

[0181] A factory worker puts on smart glasses and begins drilling. The glasses capture the sounds and vibrations of the work and send the data in real time to a server. The server analyzes the data and generates feedback, such as "The drill angle is not correct," which is displayed on the worker's glasses.

[0182] Example prompt sentence:

[0183] Analyze your voice data and generate specific feedback for work improvement.

[0184] For example: the drill is not at the right angle, the conveyor belt is moving too fast.

[0185] In this way, the system operates in cooperation with the server, terminal, and user, realizing real-time training and improving work accuracy.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The user selects the music training menu or the work accuracy improvement menu.

[0189] Input: User selection information

[0190] Operation: The device displays a menu screen, and the user selects the desired menu. The device then sends the selected menu information to the server.

[0191] Output: Menu information sent to the server

[0192] Step 2:

[0193] The device captures sound and vibrations in real time.

[0194] Input: User's voice, vibrations associated with work

[0195] How it works: The device's built-in microphone and vibration sensor capture sound and vibration. The captured data is temporarily stored on the device and then sent to a server in real time.

[0196] Output: Captured audio and vibration data

[0197] Step 3:

[0198] The server analyzes the received voice and vibration data.

[0199] Input: Audio and vibration data sent from the device

[0200] How it works: The server uses AI algorithms to analyze audio and vibration data, extracting data on pitch, rhythm, and work accuracy, and providing a detailed evaluation.

[0201] Output: Analysis results (data on pitch, rhythm, and work accuracy)

[0202] Step 4:

[0203] The server generates feedback based on the analysis results.

[0204] Input: Analysis results

[0205] How it works: Based on the analysis results, the server uses a generative AI model to generate specific feedback, including advice such as "lower the pitch," "match the rhythm," or "correct the angle of the drill."

[0206] Output: Feedback content

[0207] Step 5:

[0208] The device displays the feedback received from the server in real time.

[0209] Input: Feedback sent from the server

[0210] How it works: The device displays feedback to the user visually or audibly, for example, a visual alert on smart glasses or a text message on a smartphone.

[0211] Output: Feedback information displayed to the user

[0212] Step 6:

[0213] The server accumulates the user's training and work data and optimizes the next training or work.

[0214] Input: User training and work data, analysis results, feedback

[0215] How it works: The server stores training and work data in a database. It uses a generative AI model to analyze past data and prepares to suggest the next optimal training menu or work procedure for the user.

[0216] Output: Optimized training menu and work procedure suggestions

[0217] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0218] This invention is a system for supporting musical training that recognizes the user's emotional state by combining an emotion engine and provides optimal training content and feedback. The system is composed of three elements: the user, the terminal, and the server, and realizes personalized training that takes into account the user's emotional state in particular.

[0219] User operations

[0220] Users install the dedicated app on their smartphone or tablet. When they launch the app, an initial setup screen appears, allowing them to adjust the microphone sensitivity and sound reverberation settings, enabling the device to accurately capture voices.

[0221] Selecting a training menu

[0222] Once the user has completed the initial setup, they can select basic training, specific vocal exercises, and specific song practice from the music training menu provided within the app. Once the user selects the desired training content, the information is sent to the server.

[0223] Audio capture and real-time transmission

[0224] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0225] Server analysis and feedback generation

[0226] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to carefully evaluate pitch and rhythm deviations. Based on the analysis results, the server generates real-time feedback, which the device displays to the user.

[0227] Emotion engine integration

[0228] The server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is feeling impatient or irritated, that information is sent to the server.

[0229] Emotion-based feedback regulation

[0230] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback to reassure them and display it on the device.

[0231] View Feedback

[0232] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message such as "The rhythm is fast, but it feels good. Take it easy and try again slowly" is displayed on the screen.

[0233] Accumulation and optimization of training data

[0234] The server stores the user's training data, which includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model is designed to suggest optimal training menus and songs based on the user's past data and emotional state.

[0235] Example 1: Basic Training Session

[0236] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[0237] Example 2: Practice session for assigned piece

[0238] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as "You're doing very well. Keep going."

[0239] The present invention allows users to receive personalized training according to their emotional state without receiving professional instruction, effectively improving their ability to accurately match pitch and rhythm.

[0240] The processing flow will be explained below.

[0241] Step 1:

[0242] The user installs a dedicated app on their smartphone or tablet.

[0243] Step 2:

[0244] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0245] Step 3:

[0246] The device saves the user's settings and sends them to the server.

[0247] Step 4:

[0248] The user selects a basic training or challenge song from the music training menu within the app.

[0249] Step 5:

[0250] The terminal displays the selected training menu and transmits the selection information to the server.

[0251] Step 6:

[0252] To start training, the user speaks or plays an instrument into the device's microphone.

[0253] Step 7:

[0254] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0255] Step 8:

[0256] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0257] Step 9:

[0258] The device captures the user's video data and sends it to the emotion engine.

[0259] Step 10:

[0260] The server uses an emotion engine to analyze the user's emotional state and recognize specific emotions such as impatience or irritation.

[0261] Step 11:

[0262] The server generates feedback based on the results of voice analysis and emotion analysis. For example, in addition to basic feedback such as "The pitch is too high," it also generates emotion-based feedback such as "Relax and try again later."

[0263] Step 12:

[0264] The device displays real-time feedback sent from the server to the user, including technical feedback on pitch and rhythm, as well as positive feedback based on emotion.

[0265] Step 13:

[0266] The user can adjust their training based on the feedback and then sing or play again.

[0267] Step 14:

[0268] The device displays a button that the user presses to end the training session.

[0269] Step 15:

[0270] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[0271] Step 16:

[0272] Users can selectively share their training results on social media.

[0273] Step 17:

[0274] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0275] Step 18:

[0276] The terminal notifies the user of the optimized next training menu proposal from the server.

[0277] In this way, users can receive personalized training that takes into account their emotional state, effectively improving pitch and rhythm accuracy.

[0278] Example 2

[0279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0280] Conventional music training systems provide feedback without considering the user's emotional state, making it difficult to adequately relieve stress and anxiety felt by users during training. Furthermore, it is difficult to provide personalized training content suited to individual users, resulting in inefficient improvement of user proficiency.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0282] In this invention, the server includes a means for recognizing the user's emotional state, a means for adjusting the feedback content, and a means for accumulating training data and using the generated AI model to optimize the next training session, thereby providing feedback based on the user's emotional state and realizing efficient personalized training while reducing the user's stress and anxiety.

[0283] "User" refers to an individual who uses the system to provide musical training.

[0284] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[0285] "Server" refers to the central computing device that analyzes audio data, generates feedback, and stores training data.

[0286] A "musical training menu" refers to a number of musical training programs that a user can choose from.

[0287] "Voice data" refers to digital data of the voice uttered by the user during training.

[0288] "AI model" refers to the artificial intelligence algorithm used by the server to provide optimal training menus and feedback based on training data.

[0289] "Emotional state" refers to the psychological state that the user feels during training, specifically emotions such as impatience, anxiety, and irritation.

[0290] "Feedback" refers to training guidance comments provided by the server based on the analysis results and emotional state.

[0291] This invention is a system for supporting musical training that takes into account the user's emotional state and provides optimal training content and feedback. The system is composed of three elements: the user, the device, and the server. The user installs a dedicated app on a smartphone or tablet device and performs training.

[0292] User operations

[0293] First, users install a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These settings allow the device to capture voices accurately. For example, increasing microphone sensitivity allows the device to pick up even quieter voices clearly.

[0294] Selecting a training menu

[0295] Once the user has completed the initial setup, the app displays a menu of various music training options. The user can choose basic training, specific vocal exercises, or specific song practice. Once the user selects the desired training option, the information is sent from the device to the server.

[0296] Audio capture and real-time transmission

[0297] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the voice is immediately transmitted to the server. The device uses its dedicated noise canceling function to maintain the quality of the voice.

[0298] Server analysis and feedback generation

[0299] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to evaluate pitch and rhythm. Based on the analysis results, the server generates real-time feedback, which the device displays to the user. For example, specific feedback such as "The pitch of this part is too low" is generated.

[0300] Emotion engine integration

[0301] Furthermore, the server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user feels impatient or anxious during training, this information is recognized by the emotion engine.

[0302] Emotion-based feedback regulation

[0303] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback such as "Don't worry, keep going" and display it on the device.

[0304] View Feedback

[0305] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message might appear on the screen saying, "The rhythm is fast, but it feels good. Take your time and try again."

[0306] Accumulation and optimization of training data

[0307] The server stores the user's training data. This data includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model then suggests optimal training menus and songs based on the user's past data and emotional state. In this way, users can receive personalized training tailored to their emotional state.

[0308] Specific examples

[0309] Below is an example of a specific training session.

[0310] Example 1: Basic Training Session

[0311] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[0312] Example 2: Practice session for assigned piece

[0313] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as, "You're doing very well. Keep going."

[0314] Prompt Sentence Examples

[0315] Sample Prompt 1: "How do I set up my Basic Training to begin?"

[0316] Sample prompt 2: "What feedback message would you give if you felt impatient during the vocal test?"

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] Installing the dedicated app and initial settings

[0320] The user installs a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen is displayed. As input, the user adjusts the microphone sensitivity and sound reverberation. The device then stores the set parameters internally so that it can output a state that allows it to accurately capture sound. Specifically, the user operates the microphone sensitivity slider and is presented with a screen for testing sound reverberation.

[0321] Step 2:

[0322] Selecting a training menu

[0323] The user selects basic training, specific vocal training, or practice of a specific target song from the music training menu provided within the app. The user provides the selected menu information as input. The device sends the selected menu information to the server. The output is the training menu information sent to the server. Specifically, various training menus are displayed as a list on the app screen, and selections are made by tapping.

[0324] Step 3:

[0325] Real-time audio capture

[0326] When a user starts training, the device's microphone captures the user's voice in real time. The input is the user's singing or vocalization. The device encodes the captured audio data for transmission to the server. The output is the encoded audio data. Specifically, the microphone detects surrounding sounds and converts them into audio data in real time.

[0327] Step 4:

[0328] Sending audio data

[0329] The terminal transmits the encoded voice data to the server in real time. The encoded voice data exists on the terminal as input. The voice data is transmitted to the server as output. Specifically, data packets are sent via the Internet and received by the server.

[0330] Step 5:

[0331] Analysis of audio data

[0332] The server analyzes the audio data sent from the device. Audio data arrives at the server as input. Analysis results data on pitch and rhythm are generated as output. The server uses an AI algorithm to achieve this. Specifically, the received data is input into an analysis engine, and the AI ​​calculates deviations in pitch and rhythm.

[0333] Step 6:

[0334] Generate feedback

[0335] The server generates feedback based on the analysis results. The input is the audio analysis result data. The output is specific training feedback comments. The generated feedback is sent to the device. Specifically, it generates feedback data in text format, such as "The pitch of this part is a little low."

[0336] Step 7:

[0337] Emotional state analysis

[0338] The server uses the user's voice and video data to activate the emotion engine and recognize the user's emotional state. The voice and video data are provided to the server as input. The user's emotional state data is obtained as output. Specifically, the facial expression analysis algorithm analyzes the user's facial movements, and the voice tone analysis evaluates the emotion.

[0339] Step 8:

[0340] Emotion-based feedback regulation

[0341] The server adjusts the feedback content based on the recognized emotional state. The inputs are the emotional state data and the initial feedback data. The output is an adjusted feedback comment. Specifically, if anxiety is detected, a message such as "Don't worry, keep going" is added.

[0342] Step 9:

[0343] View Feedback

[0344] The device displays the feedback sent from the server to the user in real time. As input, the device receives the adjusted feedback data. As output, there is a feedback message displayed to the user. Specific behaviors include displaying the feedback as a text message or graph on the app screen.

[0345] Step 10:

[0346] Accumulation and optimization of training data

[0347] The server accumulates the user's training data and uses the generated AI model to optimize the next training content. As input, all data from the training session is stored on the server. As output, the next training menu and feedback are optimized. Specifically, the accumulated data is input into a learning algorithm, which generates a personalized menu for each user.

[0348] (Application example 2)

[0349] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0350] Conventional music training systems only provide feedback on pitch and rhythm, and lack personalized feedback that takes into account the user's emotional state. This makes it difficult to reduce the stress and anxiety users feel during training, making it difficult to achieve effective training. Furthermore, because the system does not propose optimal training menus based on the user's emotional state, it is also difficult to provide appropriate instruction tailored to each individual user's progress and emotional state.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing audio data and generating feedback regarding pitch and rhythm based on the analysis results, means for activating an emotion engine using the audio data and the user's video data to recognize the user's emotional state, and means for adjusting the feedback content and training menu based on the recognized emotional state. This makes it possible to provide personalized feedback according to the user's emotional state, enabling effective training while reducing stress and anxiety. Furthermore, by providing an optimal training menu based on the user's individual emotional state and progress, more effective instruction is possible.

[0352] "Voice data" refers to data in which voice information uttered by a user is recorded in digital format.

[0353] An "emotion engine" is an artificial intelligence algorithm that analyzes a user's emotional state from audio and video data.

[0354] "Feedback" refers to training advice and instructions that are generated based on the analysis of the voice data and the user's emotional state.

[0355] "Means for transmitting in real time" refers to a device or software that has the function of instantly transmitting audio to a server when a user is performing musical training.

[0356] "Training data" refers to records of audio data, emotional state information, feedback content, and the like related to the musical training the user has performed.

[0357] A "generated AI model" is an artificial intelligence model designed to generate optimal training content based on a user's training data.

[0358] A "musical training menu" refers to musical training items and programs that can be selected by the user.

[0359] The "means for generating feedback regarding pitch and rhythm" refers to an algorithm or program that allows the server to analyze the user's voice data, evaluate the pitch and rhythm, and generate advice based on that evaluation.

[0360] The "means for adjusting the feedback content and training menu" refers to an algorithm or system that appropriately reviews the feedback content provided and the next training menu based on the results of the user's emotion engine.

[0361] "Means for displaying in real time" refers to a device or application for instantly displaying feedback sent from the server to the user.

[0362] The "initial setting means" is a function for adjusting microphone sensitivity and sound reverberation to create an optimal environment for musical training.

[0363] This music training system is designed to make user training more effective and personalized. The system is broadly composed of the user's device, a server, an emotion engine, and a generative AI model.

[0364] First, the user installs the dedicated application on their device, which can be a smartphone or tablet. After launching the application, the user can adjust the microphone sensitivity and sound reverberation on the initial setup screen, allowing the device to accurately capture the voice.

[0365] Next, the user selects the desired training content from the music training menu within the application. The selection is sent to the server. When the user starts training, the device's microphone captures the audio in real time and sends the audio data to the server. The audio data may also include the user's video data.

[0366] The server runs an AI algorithm that analyzes the audio data. The analysis evaluates pitch and rhythm deviations and generates feedback. This feedback includes technical advice on pitch and rhythm. Additionally, an emotion engine is activated, analyzing the transmitted audio and video data to recognize the user's emotional state. Based on the recognized emotional state, the content of the feedback and the next training menu are adjusted. For example, if the user is feeling impatient or anxious, the server generates positive feedback to provide reassurance.

[0367] The generated feedback is displayed on the user's device in real time, allowing the user to receive immediate advice during training. The server also accumulates the user's training data and uses a generative AI model to optimize the next training session. This generative AI model is designed to suggest the next training menu and assigned songs based on the user's past data and emotional state.

[0368] As a concrete example, consider a user practicing "Let It Go." As the user begins to sing, the device sends audio data to the server in real time. The server analyzes the pitch and rhythm and generates technical feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it also adds positive feedback such as, "You're doing very well. Keep going."

[0369] An example of a prompt is as follows:

[0370] "Generate optimal music training feedback based on the user's voice data and emotional state. The voice data includes analysis of pitch and rhythm, and the emotional state includes impatience, anxiety, joy, etc."

[0371] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0372] Step 1:

[0373] The user installs the application on the device and performs initial settings.

[0374] Specifically, the user downloads and installs a dedicated application. On the initial setup screen, they can adjust microphone sensitivity and sound reverberation, allowing the device to accurately capture audio. The input is the user's interaction, and the output is optimized microphone settings.

[0375] Step 2:

[0376] The user selects the music training menu.

[0377] The user selects the desired training content from a menu within the application. The selection is sent to the server. The input is the user's menu selection operation, and the output is the training menu information sent to the server.

[0378] Step 3:

[0379] The device captures the audio and transmits it to the server in real time.

[0380] The user starts training, and the device's microphone captures the user's voice in real time. The captured voice data is sent to the server. The input is the user's singing voice, and the output is the voice data sent to the server.

[0381] Step 4:

[0382] The server analyzes the audio data and generates feedback.

[0383] The server analyzes the received audio data using an AI algorithm to evaluate discrepancies in pitch and rhythm. Feedback is generated based on the analysis results. The input is audio data, and the output is the analysis results and feedback. Specific operations include evaluating the accuracy of pitch and rhythm and identifying problems.

[0384] Step 5:

[0385] The server runs an emotion engine to recognize the emotional state.

[0386] The server uses the voice data and the user's video data to activate the emotion engine. The emotion engine analyzes the user's facial expressions and voice tone to recognize their current emotional state. The input is the voice and video data, and the output is the recognized emotional state. In concrete terms, an emotion analysis algorithm is executed to evaluate the emotional state.

[0387] Step 6:

[0388] Adjust feedback and training menus based on emotional state.

[0389] The server adjusts the feedback content and the next training menu based on the recognized emotional state. The input is the recognized emotional state, and the output is customized feedback based on the emotion. Specifically, it generates positive feedback for users who feel anxious.

[0390] Step 7:

[0391] The device displays feedback in real time.

[0392] The device receives feedback sent from the server and displays it to the user in real time. The input is feedback data from the server, and the output is a feedback message displayed on the device screen. Specific operations include displaying feedback on the screen as text or animation.

[0393] Step 8:

[0394] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0395] The server stores the user's voice data, feedback content, emotional state, etc. in a database. For the next training session, the generative AI model uses this data to propose the optimal training menu. The input is the accumulated training data, and the output is the next optimized training menu. Specifically, the AI ​​analyzes the accumulated data and designs the training content that is most suitable for the user.

[0396] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0397] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0402] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0403] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0404] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0406] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0407] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0408] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0409] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0410] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0411] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0412] This invention is a system for supporting musical training, providing effective training using smartphones and tablet devices. The entire system is mainly composed of three elements: the user, the device, and the server.

[0413] User operations

[0414] Users install a dedicated app on their smartphone or tablet. When they launch the app, they are first shown an initial setup screen where they can adjust the microphone sensitivity and sound reverberation settings, allowing the device to accurately capture voices.

[0415] Selecting a training menu

[0416] Once the user has completed the initial setup, they can choose from a music training menu provided within the app, which includes basic training, specific vocal exercises, and practice of specific songs. Once the user selects the desired training content, the information is sent to the server.

[0417] Audio capture and real-time transmission

[0418] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0419] Server analysis and feedback generation

[0420] The server analyzes the audio data sent from the device. The analysis uses an AI algorithm to meticulously evaluate pitch and rhythm discrepancies. Based on the analysis results, the server generates real-time feedback, including specific advice such as "your high notes are unstable" or "your rhythm is too fast."

[0421] View Feedback

[0422] The device immediately displays the feedback information sent from the server to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch is out of sync.

[0423] Accumulation and optimization of training data

[0424] The server stores the user's training data. Based on the stored data, a generative AI model is used to optimize the next training session. This model is designed to suggest optimal training menus and songs based on the user's past data and training progress.

[0425] Example 1: Basic Training Session

[0426] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings the basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0427] Example 2: Practice session for assigned piece

[0428] The user selects the song "Let It Go" and begins training. The device then suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0429] The present invention enables effective musical training, and allows users to improve their ability to accurately match pitch and rhythm without receiving specialized instruction.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] The user installs a dedicated app on their smartphone or tablet.

[0433] Step 2:

[0434] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0435] Step 3:

[0436] The device saves the user's settings and sends them to the server.

[0437] Step 4:

[0438] The user selects a basic training or challenge song from the music training menu within the app.

[0439] Step 5:

[0440] The terminal displays the selected training menu and transmits the selection information to the server.

[0441] Step 6:

[0442] To start training, the user speaks or plays an instrument into the device's microphone.

[0443] Step 7:

[0444] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0445] Step 8:

[0446] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0447] Step 9:

[0448] The server generates feedback based on the analysis results, providing specific advice such as "the pitch is too high" or "the rhythm is too fast."

[0449] Step 10:

[0450] The device displays the feedback sent from the server to the user in real time.

[0451] Step 11:

[0452] The user can adjust their training based on the feedback and then sing or play again.

[0453] Step 12:

[0454] The device displays a button that the user presses to end the training session.

[0455] Step 13:

[0456] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[0457] Step 14:

[0458] Users can selectively share their training results on social media.

[0459] Step 15:

[0460] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0461] Step 16:

[0462] The terminal notifies the user of the optimized next training menu proposal from the server.

[0463] Example 1

[0464] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0465] Conventional music training systems have limitations in helping users effectively master pitch and rhythm. Specifically, they lack real-time feedback and a means for users to self-evaluate, limiting the effectiveness of training. Furthermore, the lack of individualized training content means that appropriate instruction cannot be provided based on the user's progress.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0467] In this invention, the server

[0468] a means for a user to select a musical training menu;

[0469] a means for the terminal to capture and transmit audio to a server in real time;

[0470] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[0471] means for the terminal to display feedback to the user in real time;

[0472] The server stores the training data and uses the generated AI model to optimize the next training.

[0473] A means for the user to set up the device and adjust microphone sensitivity and sound reverberation;

[0474] A means to analyze the user's past training data and suggest the optimal training menu;

[0475] This allows users to train while receiving real-time feedback, and by being offered individually optimized training menus, it is possible to effectively improve musical skills.

[0476] "User" refers to a person who uses the musical training system.

[0477] "Terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0478] "Server" refers to a remote computer system that analyzes speech data, generates feedback, and stores and optimizes training data.

[0479] "Music training menu" refers to a list of training contents that the user can select from.

[0480] "Voice data" refers to sound information uttered by a user through a microphone on a terminal.

[0481] "Feedback" refers to advice and evaluation regarding pitch and rhythm generated based on audio data analyzed by the server.

[0482] "Real-time" refers to near-instant processing with minimal delay.

[0483] An "AI model" is an algorithm that uses artificial intelligence to analyze the user's voice data and optimize the next training menu.

[0484] "Microphone sensitivity" refers to the ability of a device's microphone to pick up sound.

[0485] "Sound reverberation" refers to the phenomenon of sound being reflected back and its effects.

[0486] "Training data" refers to the voice data and analysis results generated during training conducted by the user.

[0487] This invention is a system for supporting musical training, providing effective training using devices such as smartphones and tablets. The entire system is mainly composed of three elements: the user, the device, and the server.

[0488] First, users install a dedicated music training app on their device. When they launch the app, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These initial settings allow the device to accurately capture audio. For example, users can adjust the microphone sensitivity slider to adjust how much sound is picked up.

[0489] After the initial setup is complete, the user selects the desired training menu from the music training menu provided within the app. The information about the selected training menu is sent to the server by the device. For example, if the user selects "Basic Training," the information is sent to the server.

[0490] When a user starts training, the device's microphone captures the user's voice in real time. The captured voice data is compressed and sent to a server over the Internet. For example, when a user sings the first line of "Let It Go," the voice is immediately sent to the server.

[0491] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. If the server determines that the user's high notes are unstable, it generates feedback stating, "Your high notes are unstable." This feedback is displayed in the form of a text message or a graph.

[0492] The device receives the feedback information sent from the server and immediately displays it to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch discrepancy, allowing the user to make corrections in real time.

[0493] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. For example, the server may analyze the user's past pitch data and propose a new optimal training menu.

[0494] For example, when a user opens the app and selects the basic training menu, the device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings a basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0495] When a user selects the song "Let It Go" and begins training, the device suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0496] An example of a prompt sentence is, "Please suggest the best training content for the next training menu. The user's past data is as follows: 'Basic scale practice: pitch is not stable', 'Rhythm practice: unable to maintain a consistent tempo'."

[0497] In this way, the present invention allows users to effectively train in music without receiving specialized instruction, and improve their ability to accurately match pitch and rhythm.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Step 1: Initial Setup

[0500] The user installs the dedicated app on their smartphone or tablet and launches it. The app displays an initial setup screen, providing the user with settings to adjust microphone sensitivity and sound reverberation. Specifically, the user can adjust the microphone sensitivity by moving a slider and check the sound reverberation using a test sound. The input is the user's operation (adjusting microphone sensitivity and checking sound reverberation), and the output is the adapted microphone settings.

[0501] Step 2: Select a training menu

[0502] After completing the initial setup, the user selects the desired menu from the music training menu provided within the app. The device sends information about the selected training menu to the server. The input is the training menu selected by the user, and the output is the menu information sent to the server. Specifically, the user makes a selection by tapping "Basic Training" or "Set Song Practice."

[0503] Step 3: Audio capture and real-time transmission

[0504] When a user starts training, the device's microphone captures the user's voice in real time. This voice data is compressed and sent to a server over the Internet. The input is the user's voice, and the output is the compressed voice data sent to the server. Specifically, when the user sings the first phrase of "Let It Go," the voice is immediately sent to the server.

[0505] Step 4: Server analysis and feedback generation

[0506] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. The input is the audio data sent to the server, and the output is feedback generated based on the analysis results. Specifically, the server determines that "the user's pitch in the high notes is unstable" and generates feedback stating, "The high notes are unstable."

[0507] Step 5: View your feedback

[0508] The terminal receives the feedback information sent from the server and immediately displays it to the user. The input is the feedback information sent from the server, and the output is the feedback message or visual display displayed to the user. Specifically, a text message such as "Please lower the pitch a little" or a bar indicating the pitch discrepancy is displayed on the screen.

[0509] Step 6: Accumulating and optimizing training data

[0510] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. The input is the user's past training data, and the output is a new training menu optimized by the generative AI model. Specifically, the server performs operations such as "analyzing the user's past pitch data and proposing the next training menu."

[0511] (Application example 1)

[0512] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0513] While conventional music training systems can evaluate pitch and rhythm, they are not suited to diverse applications such as improving the accuracy of factory work or providing real-time feedback. In particular, it has been difficult to analyze vibrations and operational sounds, which are necessary in the work environment, and provide feedback based on that analysis. This has made it difficult to support the improvement of the movement accuracy of workers and robots.

[0514] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0515] In this invention, the server includes a means for the terminal to capture voice and vibration and transmit them to the server in real time, a means for the server to analyze the voice and vibration data and generate feedback on pitch, rhythm, and task accuracy based on the analysis results, and a means for the server to accumulate training and task data and use the generated AI model to optimize the next training or task, thereby enabling the provision of real-time feedback aimed at improving the motion accuracy of workers and robots.

[0516] A "user" is a user who operates the system and performs musical training or training to improve work accuracy.

[0517] A "music training menu" is a list of practice items and assignments that a user can select to improve their musical skills through the system.

[0518] A "terminal" is a device that captures sound and vibrations and transmits them to a server, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[0519] The "server" is a computer system that receives the voice and vibration data sent from the terminal, analyzes it, and generates feedback.

[0520] "Feedback" refers to advice and instructions generated by the server based on the analysis results, including specific areas for improvement regarding pitch, rhythm, and work accuracy.

[0521] "Training data" refers to recorded information such as audio and vibration data generated by the user during training, analysis results, and feedback.

[0522] A "generated AI model" is an artificial intelligence algorithm and its program used to optimize the next training or task based on the user's training data or task data.

[0523] "Vibration" is a signal or data that captures physical movements and fluctuations that occur during factory operations.

[0524] "Work accuracy" is an indicator of how accurately a worker or robot performs work according to specified procedures and standards.

[0525] This invention is a system in which a user selects a music training menu, and the terminal captures and transmits the audio and vibration data to a server in real time. The server then analyzes the audio and vibration data, generates feedback based on the analysis results, and provides it to the user. The server also accumulates training and work data and uses the generated AI model to optimize the next training or work.

[0526] Details of the hardware and software used

[0527] Hardware:

[0528] Device: A smartphone, tablet, smart glasses, or head-mounted display for capturing sound and vibration.

[0529] Microphone and sensors: The device's built-in microphone and vibration sensors are used to capture the user's voice and working vibrations.

[0530] software:

[0531] Python: Used in programs that perform data analysis on the server side.

[0532] Flask: A web application framework for transmitting audio data.

[0533] SpeechRecognition libraries: Used to analyze speech data (e.g., Google's Web Speech API).

[0534] AI Algorithms: Generative AI models used for analysis and feedback generation, which generate appropriate feedback based on the analysis of audio and vibration data.

[0535] Program processing explanation

[0536] Audio and Vibration Capture

[0537] The device's microphone and vibration sensor capture the user's voice and vibrations in real time, and the captured data is sent from the device to a server.

[0538] Data analysis

[0539] The server analyzes the received audio and vibration data, processing it using AI algorithms to evaluate pitch, rhythm, and task accuracy.

[0540] Feedback Generation

[0541] Based on the analysis results, the server generates specific feedback, such as "Please correct the angle of the drill" or "The conveyor belt speed is too fast," to improve work accuracy. This feedback is sent to the device in real time.

[0542] Feedback Display

[0543] The device receives feedback from the server and displays it to the user in real time, visually indicating pitch and rhythm discrepancies, areas for improvement in the accuracy of the work, and so on.

[0544] Data accumulation and optimization

[0545] The server accumulates data from training and work sessions and uses a generative AI model to optimize future training and work. The model suggests optimal training menus and work procedures based on past data and progress.

[0546] Specific examples

[0547] Example 1: Basic Training Session

[0548] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and vibration sensitivity, and then prompts the user for vocal and vibration tests. When the user sings a basic scale, the audio and vibration data are sent to the server in real time. The server analyzes the audio and generates immediate feedback, such as "Please raise the pitch a little more," which is then displayed on the device.

[0549] Example 2: Work Accuracy Improvement Session

[0550] A factory worker puts on smart glasses and begins drilling. The glasses capture the sounds and vibrations of the work and send the data in real time to a server. The server analyzes the data and generates feedback, such as "The drill angle is not correct," which is displayed on the worker's glasses.

[0551] Example prompt sentence:

[0552] Analyze your voice data and generate specific feedback for work improvement.

[0553] For example: the drill is not at the right angle, the conveyor belt is moving too fast.

[0554] In this way, the system operates in cooperation with the server, terminal, and user, realizing real-time training and improving work accuracy.

[0555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0556] Step 1:

[0557] The user selects the music training menu or the work accuracy improvement menu.

[0558] Input: User selection information

[0559] Operation: The device displays a menu screen, and the user selects the desired menu. The device then sends the selected menu information to the server.

[0560] Output: Menu information sent to the server

[0561] Step 2:

[0562] The device captures sound and vibrations in real time.

[0563] Input: User's voice, vibrations associated with work

[0564] How it works: The device's built-in microphone and vibration sensor capture sound and vibration. The captured data is temporarily stored on the device and then sent to a server in real time.

[0565] Output: Captured audio and vibration data

[0566] Step 3:

[0567] The server analyzes the received voice and vibration data.

[0568] Input: Audio and vibration data sent from the device

[0569] How it works: The server uses AI algorithms to analyze audio and vibration data, extracting data on pitch, rhythm, and work accuracy, and providing a detailed evaluation.

[0570] Output: Analysis results (data on pitch, rhythm, and work accuracy)

[0571] Step 4:

[0572] The server generates feedback based on the analysis results.

[0573] Input: Analysis results

[0574] How it works: Based on the analysis results, the server uses a generative AI model to generate specific feedback, including advice such as "lower the pitch," "match the rhythm," or "correct the angle of the drill."

[0575] Output: Feedback content

[0576] Step 5:

[0577] The device displays the feedback received from the server in real time.

[0578] Input: Feedback sent from the server

[0579] How it works: The device displays feedback to the user visually or audibly, for example, a visual alert on smart glasses or a text message on a smartphone.

[0580] Output: Feedback information displayed to the user

[0581] Step 6:

[0582] The server accumulates the user's training and work data and optimizes the next training or work.

[0583] Input: User training and work data, analysis results, feedback

[0584] How it works: The server stores training and work data in a database. It uses a generative AI model to analyze past data and prepares to suggest the next optimal training menu or work procedure for the user.

[0585] Output: Optimized training menu and work procedure suggestions

[0586] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0587] This invention is a system for supporting musical training that recognizes the user's emotional state by combining an emotion engine and provides optimal training content and feedback. The system is composed of three elements: the user, the terminal, and the server, and realizes personalized training that takes into account the user's emotional state in particular.

[0588] User operations

[0589] Users install the dedicated app on their smartphone or tablet. When they launch the app, an initial setup screen appears, allowing them to adjust the microphone sensitivity and sound reverberation settings, enabling the device to accurately capture voices.

[0590] Selecting a training menu

[0591] Once the user has completed the initial setup, they can select basic training, specific vocal exercises, and specific song practice from the music training menu provided within the app. Once the user selects the desired training content, the information is sent to the server.

[0592] Audio capture and real-time transmission

[0593] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0594] Server analysis and feedback generation

[0595] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to carefully evaluate pitch and rhythm deviations. Based on the analysis results, the server generates real-time feedback, which the device displays to the user.

[0596] Emotion engine integration

[0597] The server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is feeling impatient or irritated, that information is sent to the server.

[0598] Emotion-based feedback regulation

[0599] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback to reassure them and display it on the device.

[0600] View Feedback

[0601] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message such as "The rhythm is fast, but it feels good. Take it easy and try again slowly" is displayed on the screen.

[0602] Accumulation and optimization of training data

[0603] The server stores the user's training data, which includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model is designed to suggest optimal training menus and songs based on the user's past data and emotional state.

[0604] Example 1: Basic Training Session

[0605] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[0606] Example 2: Practice session for assigned piece

[0607] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as "You're doing very well. Keep going."

[0608] The present invention allows users to receive personalized training according to their emotional state without receiving professional instruction, effectively improving their ability to accurately match pitch and rhythm.

[0609] The processing flow will be explained below.

[0610] Step 1:

[0611] The user installs a dedicated app on their smartphone or tablet.

[0612] Step 2:

[0613] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0614] Step 3:

[0615] The device saves the user's settings and sends them to the server.

[0616] Step 4:

[0617] The user selects a basic training or challenge song from the music training menu within the app.

[0618] Step 5:

[0619] The terminal displays the selected training menu and transmits the selection information to the server.

[0620] Step 6:

[0621] To start training, the user speaks or plays an instrument into the device's microphone.

[0622] Step 7:

[0623] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0624] Step 8:

[0625] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0626] Step 9:

[0627] The device captures the user's video data and sends it to the emotion engine.

[0628] Step 10:

[0629] The server uses an emotion engine to analyze the user's emotional state and recognize specific emotions such as impatience or irritation.

[0630] Step 11:

[0631] The server generates feedback based on the results of voice analysis and emotion analysis. For example, in addition to basic feedback such as "The pitch is too high," it also generates emotion-based feedback such as "Relax and try again later."

[0632] Step 12:

[0633] The device displays real-time feedback sent from the server to the user, including technical feedback on pitch and rhythm, as well as positive feedback based on emotion.

[0634] Step 13:

[0635] The user can adjust their training based on the feedback and then sing or play again.

[0636] Step 14:

[0637] The device displays a button that the user presses to end the training session.

[0638] Step 15:

[0639] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[0640] Step 16:

[0641] Users can selectively share their training results on social media.

[0642] Step 17:

[0643] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0644] Step 18:

[0645] The terminal notifies the user of the optimized next training menu proposal from the server.

[0646] In this way, users can receive personalized training that takes into account their emotional state, effectively improving pitch and rhythm accuracy.

[0647] Example 2

[0648] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0649] Conventional music training systems provide feedback without considering the user's emotional state, making it difficult to adequately relieve stress and anxiety felt by users during training. Furthermore, it is difficult to provide personalized training content suited to individual users, resulting in inefficient improvement of user proficiency.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0651] In this invention, the server includes a means for recognizing the user's emotional state, a means for adjusting the feedback content, and a means for accumulating training data and using the generated AI model to optimize the next training session, thereby providing feedback based on the user's emotional state and realizing efficient personalized training while reducing the user's stress and anxiety.

[0652] "User" refers to an individual who uses the system to provide musical training.

[0653] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[0654] "Server" refers to the central computing device that analyzes audio data, generates feedback, and stores training data.

[0655] A "musical training menu" refers to a number of musical training programs that a user can choose from.

[0656] "Voice data" refers to digital data of the voice uttered by the user during training.

[0657] "AI model" refers to the artificial intelligence algorithm used by the server to provide optimal training menus and feedback based on training data.

[0658] "Emotional state" refers to the psychological state that the user feels during training, specifically emotions such as impatience, anxiety, and irritation.

[0659] "Feedback" refers to training guidance comments provided by the server based on the analysis results and emotional state.

[0660] This invention is a system for supporting musical training that takes into account the user's emotional state and provides optimal training content and feedback. The system is composed of three elements: the user, the device, and the server. The user installs a dedicated app on a smartphone or tablet device and performs training.

[0661] User operations

[0662] First, users install a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These settings allow the device to capture voices accurately. For example, increasing microphone sensitivity allows the device to pick up even quieter voices clearly.

[0663] Selecting a training menu

[0664] Once the user has completed the initial setup, the app displays a menu of various music training options. The user can choose basic training, specific vocal exercises, or specific song practice. Once the user selects the desired training option, the information is sent from the device to the server.

[0665] Audio capture and real-time transmission

[0666] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the voice is immediately transmitted to the server. The device uses its dedicated noise canceling function to maintain the quality of the voice.

[0667] Server analysis and feedback generation

[0668] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to evaluate pitch and rhythm. Based on the analysis results, the server generates real-time feedback, which the device displays to the user. For example, specific feedback such as "The pitch of this part is too low" is generated.

[0669] Emotion engine integration

[0670] Furthermore, the server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user feels impatient or anxious during training, this information is recognized by the emotion engine.

[0671] Emotion-based feedback regulation

[0672] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback such as "Don't worry, keep going" and display it on the device.

[0673] View Feedback

[0674] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message might appear on the screen saying, "The rhythm is fast, but it feels good. Take your time and try again."

[0675] Accumulation and optimization of training data

[0676] The server stores the user's training data. This data includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model then suggests optimal training menus and songs based on the user's past data and emotional state. In this way, users can receive personalized training tailored to their emotional state.

[0677] Specific examples

[0678] Below is an example of a specific training session.

[0679] Example 1: Basic Training Session

[0680] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[0681] Example 2: Practice session for assigned piece

[0682] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as, "You're doing very well. Keep going."

[0683] Prompt Sentence Examples

[0684] Sample Prompt 1: "How do I set up my Basic Training to begin?"

[0685] Sample prompt 2: "What feedback message would you give if you felt impatient during the vocal test?"

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Step 1:

[0688] Installing the dedicated app and initial settings

[0689] The user installs a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen is displayed. As input, the user adjusts the microphone sensitivity and sound reverberation. The device then stores the set parameters internally so that it can output a state that allows it to accurately capture sound. Specifically, the user operates the microphone sensitivity slider and is presented with a screen for testing sound reverberation.

[0690] Step 2:

[0691] Selecting a training menu

[0692] The user selects basic training, specific vocal training, or practice of a specific target song from the music training menu provided within the app. The user provides the selected menu information as input. The device sends the selected menu information to the server. The output is the training menu information sent to the server. Specifically, various training menus are displayed as a list on the app screen, and selections are made by tapping.

[0693] Step 3:

[0694] Real-time audio capture

[0695] When a user starts training, the device's microphone captures the user's voice in real time. The input is the user's singing or vocalization. The device encodes the captured audio data for transmission to the server. The output is the encoded audio data. Specifically, the microphone detects surrounding sounds and converts them into audio data in real time.

[0696] Step 4:

[0697] Sending audio data

[0698] The terminal transmits the encoded voice data to the server in real time. The encoded voice data exists on the terminal as input. The voice data is transmitted to the server as output. Specifically, data packets are sent via the Internet and received by the server.

[0699] Step 5:

[0700] Analysis of audio data

[0701] The server analyzes the audio data sent from the device. Audio data arrives at the server as input. Analysis results data on pitch and rhythm are generated as output. The server uses an AI algorithm to achieve this. Specifically, the received data is input into an analysis engine, and the AI ​​calculates deviations in pitch and rhythm.

[0702] Step 6:

[0703] Generate feedback

[0704] The server generates feedback based on the analysis results. The input is the audio analysis result data. The output is specific training feedback comments. The generated feedback is sent to the device. Specifically, it generates feedback data in text format, such as "The pitch of this part is a little low."

[0705] Step 7:

[0706] Emotional state analysis

[0707] The server uses the user's voice and video data to activate the emotion engine and recognize the user's emotional state. The voice and video data are provided to the server as input. The user's emotional state data is obtained as output. Specifically, the facial expression analysis algorithm analyzes the user's facial movements, and the voice tone analysis evaluates the emotion.

[0708] Step 8:

[0709] Emotion-based feedback regulation

[0710] The server adjusts the feedback content based on the recognized emotional state. The inputs are the emotional state data and the initial feedback data. The output is an adjusted feedback comment. Specifically, if anxiety is detected, a message such as "Don't worry, keep going" is added.

[0711] Step 9:

[0712] View Feedback

[0713] The device displays the feedback sent from the server to the user in real time. As input, the device receives the adjusted feedback data. As output, there is a feedback message displayed to the user. Specific behaviors include displaying the feedback as a text message or graph on the app screen.

[0714] Step 10:

[0715] Accumulation and optimization of training data

[0716] The server accumulates the user's training data and uses the generated AI model to optimize the next training content. As input, all data from the training session is stored on the server. As output, the next training menu and feedback are optimized. Specifically, the accumulated data is input into a learning algorithm, which generates a personalized menu for each user.

[0717] (Application example 2)

[0718] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0719] Conventional music training systems only provide feedback on pitch and rhythm, and lack personalized feedback that takes into account the user's emotional state. This makes it difficult to reduce the stress and anxiety users feel during training, making it difficult to achieve effective training. Furthermore, because the system does not propose optimal training menus based on the user's emotional state, it is also difficult to provide appropriate instruction tailored to each individual user's progress and emotional state.

[0720] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing audio data and generating feedback regarding pitch and rhythm based on the analysis results, means for activating an emotion engine using the audio data and the user's video data to recognize the user's emotional state, and means for adjusting the feedback content and training menu based on the recognized emotional state. This makes it possible to provide personalized feedback according to the user's emotional state, enabling effective training while reducing stress and anxiety. Furthermore, by providing an optimal training menu based on the user's individual emotional state and progress, more effective instruction is possible.

[0721] "Voice data" refers to data in which voice information uttered by a user is recorded in digital format.

[0722] An "emotion engine" is an artificial intelligence algorithm that analyzes a user's emotional state from audio and video data.

[0723] "Feedback" refers to training advice and instructions that are generated based on the analysis of the voice data and the user's emotional state.

[0724] "Means for transmitting in real time" refers to a device or software that has the function of instantly transmitting audio to a server when a user is performing musical training.

[0725] "Training data" refers to records of audio data, emotional state information, feedback content, and the like related to the musical training the user has performed.

[0726] A "generated AI model" is an artificial intelligence model designed to generate optimal training content based on a user's training data.

[0727] A "musical training menu" refers to musical training items and programs that can be selected by the user.

[0728] The "means for generating feedback regarding pitch and rhythm" refers to an algorithm or program that allows the server to analyze the user's voice data, evaluate the pitch and rhythm, and generate advice based on that evaluation.

[0729] The "means for adjusting the feedback content and training menu" refers to an algorithm or system that appropriately reviews the feedback content provided and the next training menu based on the results of the user's emotion engine.

[0730] "Means for displaying in real time" refers to a device or application for instantly displaying feedback sent from the server to the user.

[0731] The "initial setting means" is a function for adjusting microphone sensitivity and sound reverberation to create an optimal environment for musical training.

[0732] This music training system is designed to make user training more effective and personalized. The system is broadly composed of the user's device, a server, an emotion engine, and a generative AI model.

[0733] First, the user installs the dedicated application on their device, which can be a smartphone or tablet. After launching the application, the user can adjust the microphone sensitivity and sound reverberation on the initial setup screen, allowing the device to accurately capture the voice.

[0734] Next, the user selects the desired training content from the music training menu within the application. The selection is sent to the server. When the user starts training, the device's microphone captures the audio in real time and sends the audio data to the server. The audio data may also include the user's video data.

[0735] The server runs an AI algorithm that analyzes the audio data. The analysis evaluates pitch and rhythm deviations and generates feedback. This feedback includes technical advice on pitch and rhythm. Additionally, an emotion engine is activated, analyzing the transmitted audio and video data to recognize the user's emotional state. Based on the recognized emotional state, the content of the feedback and the next training menu are adjusted. For example, if the user is feeling impatient or anxious, the server generates positive feedback to provide reassurance.

[0736] The generated feedback is displayed on the user's device in real time, allowing the user to receive immediate advice during training. The server also accumulates the user's training data and uses a generative AI model to optimize the next training session. This generative AI model is designed to suggest the next training menu and assigned songs based on the user's past data and emotional state.

[0737] As a concrete example, consider a user practicing "Let It Go." As the user begins to sing, the device sends audio data to the server in real time. The server analyzes the pitch and rhythm and generates technical feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it also adds positive feedback such as, "You're doing very well. Keep going."

[0738] An example of a prompt is as follows:

[0739] "Generate optimal music training feedback based on the user's voice data and emotional state. The voice data includes analysis of pitch and rhythm, and the emotional state includes impatience, anxiety, joy, etc."

[0740] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0741] Step 1:

[0742] The user installs the application on the device and performs initial settings.

[0743] Specifically, the user downloads and installs a dedicated application. On the initial setup screen, they can adjust microphone sensitivity and sound reverberation, allowing the device to accurately capture audio. The input is the user's interaction, and the output is optimized microphone settings.

[0744] Step 2:

[0745] The user selects the music training menu.

[0746] The user selects the desired training content from a menu within the application. The selection is sent to the server. The input is the user's menu selection operation, and the output is the training menu information sent to the server.

[0747] Step 3:

[0748] The device captures the audio and transmits it to the server in real time.

[0749] The user starts training, and the device's microphone captures the user's voice in real time. The captured voice data is sent to the server. The input is the user's singing voice, and the output is the voice data sent to the server.

[0750] Step 4:

[0751] The server analyzes the audio data and generates feedback.

[0752] The server analyzes the received audio data using an AI algorithm to evaluate discrepancies in pitch and rhythm. Feedback is generated based on the analysis results. The input is audio data, and the output is the analysis results and feedback. Specific operations include evaluating the accuracy of pitch and rhythm and identifying problems.

[0753] Step 5:

[0754] The server runs an emotion engine to recognize the emotional state.

[0755] The server uses the voice data and the user's video data to activate the emotion engine. The emotion engine analyzes the user's facial expressions and voice tone to recognize their current emotional state. The input is the voice and video data, and the output is the recognized emotional state. In concrete terms, an emotion analysis algorithm is executed to evaluate the emotional state.

[0756] Step 6:

[0757] Adjust feedback and training menus based on emotional state.

[0758] The server adjusts the feedback content and the next training menu based on the recognized emotional state. The input is the recognized emotional state, and the output is customized feedback based on the emotion. Specifically, it generates positive feedback for users who feel anxious.

[0759] Step 7:

[0760] The device displays feedback in real time.

[0761] The device receives feedback sent from the server and displays it to the user in real time. The input is feedback data from the server, and the output is a feedback message displayed on the device screen. Specific operations include displaying feedback on the screen as text or animation.

[0762] Step 8:

[0763] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0764] The server stores the user's voice data, feedback content, emotional state, etc. in a database. For the next training session, the generative AI model uses this data to propose the optimal training menu. The input is the accumulated training data, and the output is the next optimized training menu. Specifically, the AI ​​analyzes the accumulated data and designs the training content that is most suitable for the user.

[0765] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0766] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0767] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0768] [Third embodiment]

[0769] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0770] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0771] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0772] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0773] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0774] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0775] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0776] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0777] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0778] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0779] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0780] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0781] This invention is a system for supporting musical training, providing effective training using smartphones and tablet devices. The entire system is mainly composed of three elements: the user, the device, and the server.

[0782] User operations

[0783] Users install a dedicated app on their smartphone or tablet. When they launch the app, they are first shown an initial setup screen where they can adjust the microphone sensitivity and sound reverberation settings, allowing the device to accurately capture voices.

[0784] Selecting a training menu

[0785] Once the user has completed the initial setup, they can choose from a music training menu provided within the app, which includes basic training, specific vocal exercises, and practice of specific songs. Once the user selects the desired training content, the information is sent to the server.

[0786] Audio capture and real-time transmission

[0787] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0788] Server analysis and feedback generation

[0789] The server analyzes the audio data sent from the device. The analysis uses an AI algorithm to meticulously evaluate pitch and rhythm discrepancies. Based on the analysis results, the server generates real-time feedback, including specific advice such as "your high notes are unstable" or "your rhythm is too fast."

[0790] View Feedback

[0791] The device immediately displays the feedback information sent from the server to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch is out of sync.

[0792] Accumulation and optimization of training data

[0793] The server stores the user's training data. Based on the stored data, a generative AI model is used to optimize the next training session. This model is designed to suggest optimal training menus and songs based on the user's past data and training progress.

[0794] Example 1: Basic Training Session

[0795] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings the basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0796] Example 2: Practice session for assigned piece

[0797] The user selects the song "Let It Go" and begins training. The device then suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0798] The present invention enables effective musical training, and allows users to improve their ability to accurately match pitch and rhythm without receiving specialized instruction.

[0799] The processing flow will be explained below.

[0800] Step 1:

[0801] The user installs a dedicated app on their smartphone or tablet.

[0802] Step 2:

[0803] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0804] Step 3:

[0805] The device saves the user's settings and sends them to the server.

[0806] Step 4:

[0807] The user selects a basic training or challenge song from the music training menu within the app.

[0808] Step 5:

[0809] The terminal displays the selected training menu and transmits the selection information to the server.

[0810] Step 6:

[0811] To start training, the user speaks or plays an instrument into the device's microphone.

[0812] Step 7:

[0813] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0814] Step 8:

[0815] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0816] Step 9:

[0817] The server generates feedback based on the analysis results, providing specific advice such as "the pitch is too high" or "the rhythm is too fast."

[0818] Step 10:

[0819] The device displays the feedback sent from the server to the user in real time.

[0820] Step 11:

[0821] The user can adjust their training based on the feedback and then sing or play again.

[0822] Step 12:

[0823] The device displays a button that the user presses to end the training session.

[0824] Step 13:

[0825] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[0826] Step 14:

[0827] Users can selectively share their training results on social media.

[0828] Step 15:

[0829] The server accumulates the training data and uses the generative AI model to optimize the next training.

[0830] Step 16:

[0831] The terminal notifies the user of the optimized next training menu proposal from the server.

[0832] Example 1

[0833] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0834] Conventional music training systems have limitations in helping users effectively master pitch and rhythm. Specifically, they lack real-time feedback and a means for users to self-evaluate, limiting the effectiveness of training. Furthermore, the lack of individualized training content means that appropriate instruction cannot be provided based on the user's progress.

[0835] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0836] In this invention, the server

[0837] a means for a user to select a musical training menu;

[0838] a means for the terminal to capture and transmit audio to a server in real time;

[0839] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[0840] means for the terminal to display feedback to the user in real time;

[0841] The server stores the training data and uses the generated AI model to optimize the next training.

[0842] A means for the user to set up the device and adjust microphone sensitivity and sound reverberation;

[0843] A means to analyze the user's past training data and suggest the optimal training menu;

[0844] This allows users to train while receiving real-time feedback, and by being offered individually optimized training menus, it is possible to effectively improve musical skills.

[0845] "User" refers to a person who uses the musical training system.

[0846] "Terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[0847] "Server" refers to a remote computer system that analyzes speech data, generates feedback, and stores and optimizes training data.

[0848] "Music training menu" refers to a list of training contents that the user can select from.

[0849] "Voice data" refers to sound information uttered by a user through a microphone on a terminal.

[0850] "Feedback" refers to advice and evaluation regarding pitch and rhythm generated based on audio data analyzed by the server.

[0851] "Real-time" refers to near-instant processing with minimal delay.

[0852] An "AI model" is an algorithm that uses artificial intelligence to analyze the user's voice data and optimize the next training menu.

[0853] "Microphone sensitivity" refers to the ability of a device's microphone to pick up sound.

[0854] "Sound reverberation" refers to the phenomenon of sound being reflected back and its effects.

[0855] "Training data" refers to the voice data and analysis results generated during training conducted by the user.

[0856] This invention is a system for supporting musical training, providing effective training using devices such as smartphones and tablets. The entire system is mainly composed of three elements: the user, the device, and the server.

[0857] First, users install a dedicated music training app on their device. When they launch the app, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These initial settings allow the device to accurately capture audio. For example, users can adjust the microphone sensitivity slider to adjust how much sound is picked up.

[0858] After the initial setup is complete, the user selects the desired training menu from the music training menu provided within the app. The information about the selected training menu is sent to the server by the device. For example, if the user selects "Basic Training," the information is sent to the server.

[0859] When a user starts training, the device's microphone captures the user's voice in real time. The captured voice data is compressed and sent to a server over the Internet. For example, when a user sings the first line of "Let It Go," the voice is immediately sent to the server.

[0860] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. If the server determines that the user's high notes are unstable, it generates feedback stating, "Your high notes are unstable." This feedback is displayed in the form of a text message or a graph.

[0861] The device receives the feedback information sent from the server and immediately displays it to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch discrepancy, allowing the user to make corrections in real time.

[0862] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. For example, the server may analyze the user's past pitch data and propose a new optimal training menu.

[0863] For example, when a user opens the app and selects the basic training menu, the device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings a basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[0864] When a user selects the song "Let It Go" and begins training, the device suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[0865] An example of a prompt sentence is, "Please suggest the best training content for the next training menu. The user's past data is as follows: 'Basic scale practice: pitch is not stable', 'Rhythm practice: unable to maintain a consistent tempo'."

[0866] In this way, the present invention allows users to effectively train in music without receiving specialized instruction, and improve their ability to accurately match pitch and rhythm.

[0867] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0868] Step 1: Initial Setup

[0869] The user installs the dedicated app on their smartphone or tablet and launches it. The app displays an initial setup screen, providing the user with settings to adjust microphone sensitivity and sound reverberation. Specifically, the user can adjust the microphone sensitivity by moving a slider and check the sound reverberation using a test sound. The input is the user's operation (adjusting microphone sensitivity and checking sound reverberation), and the output is the adapted microphone settings.

[0870] Step 2: Select a training menu

[0871] After completing the initial setup, the user selects the desired menu from the music training menu provided within the app. The device sends information about the selected training menu to the server. The input is the training menu selected by the user, and the output is the menu information sent to the server. Specifically, the user makes a selection by tapping "Basic Training" or "Set Song Practice."

[0872] Step 3: Audio capture and real-time transmission

[0873] When a user starts training, the device's microphone captures the user's voice in real time. This voice data is compressed and sent to a server over the Internet. The input is the user's voice, and the output is the compressed voice data sent to the server. Specifically, when the user sings the first phrase of "Let It Go," the voice is immediately sent to the server.

[0874] Step 4: Server analysis and feedback generation

[0875] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. The input is the audio data sent to the server, and the output is feedback generated based on the analysis results. Specifically, the server determines that "the user's pitch in the high notes is unstable" and generates feedback stating, "The high notes are unstable."

[0876] Step 5: View your feedback

[0877] The terminal receives the feedback information sent from the server and immediately displays it to the user. The input is the feedback information sent from the server, and the output is the feedback message or visual display displayed to the user. Specifically, a text message such as "Please lower the pitch a little" or a bar indicating the pitch discrepancy is displayed on the screen.

[0878] Step 6: Accumulating and optimizing training data

[0879] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. The input is the user's past training data, and the output is a new training menu optimized by the generative AI model. Specifically, the server performs operations such as "analyzing the user's past pitch data and proposing the next training menu."

[0880] (Application example 1)

[0881] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0882] While conventional music training systems can evaluate pitch and rhythm, they are not suited to diverse applications such as improving the accuracy of factory work or providing real-time feedback. In particular, it has been difficult to analyze vibrations and operational sounds, which are necessary in the work environment, and provide feedback based on that analysis. This has made it difficult to support the improvement of the movement accuracy of workers and robots.

[0883] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0884] In this invention, the server includes a means for the terminal to capture voice and vibration and transmit them to the server in real time, a means for the server to analyze the voice and vibration data and generate feedback on pitch, rhythm, and task accuracy based on the analysis results, and a means for the server to accumulate training and task data and use the generated AI model to optimize the next training or task, thereby enabling the provision of real-time feedback aimed at improving the motion accuracy of workers and robots.

[0885] A "user" is a user who operates the system and performs musical training or training to improve work accuracy.

[0886] A "music training menu" is a list of practice items and assignments that a user can select to improve their musical skills through the system.

[0887] A "terminal" is a device that captures sound and vibrations and transmits them to a server, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[0888] The "server" is a computer system that receives the voice and vibration data sent from the terminal, analyzes it, and generates feedback.

[0889] "Feedback" refers to advice and instructions generated by the server based on the analysis results, including specific areas for improvement regarding pitch, rhythm, and work accuracy.

[0890] "Training data" refers to recorded information such as audio and vibration data generated by the user during training, analysis results, and feedback.

[0891] A "generated AI model" is an artificial intelligence algorithm and its program used to optimize the next training or task based on the user's training data or task data.

[0892] "Vibration" is a signal or data that captures physical movements and fluctuations that occur during factory operations.

[0893] "Work accuracy" is an indicator of how accurately a worker or robot performs work according to specified procedures and standards.

[0894] This invention is a system in which a user selects a music training menu, and the terminal captures and transmits the audio and vibration data to a server in real time. The server then analyzes the audio and vibration data, generates feedback based on the analysis results, and provides it to the user. The server also accumulates training and work data and uses the generated AI model to optimize the next training or work.

[0895] Details of the hardware and software used

[0896] Hardware:

[0897] Device: A smartphone, tablet, smart glasses, or head-mounted display for capturing sound and vibration.

[0898] Microphone and sensors: The device's built-in microphone and vibration sensors are used to capture the user's voice and working vibrations.

[0899] software:

[0900] Python: Used in programs that perform data analysis on the server side.

[0901] Flask: A web application framework for transmitting audio data.

[0902] SpeechRecognition libraries: Used to analyze speech data (e.g., Google's Web Speech API).

[0903] AI Algorithms: Generative AI models used for analysis and feedback generation, which generate appropriate feedback based on the analysis of audio and vibration data.

[0904] Program processing explanation

[0905] Audio and Vibration Capture

[0906] The device's microphone and vibration sensor capture the user's voice and vibrations in real time, and the captured data is sent from the device to a server.

[0907] Data analysis

[0908] The server analyzes the received audio and vibration data, processing it using AI algorithms to evaluate pitch, rhythm, and task accuracy.

[0909] Feedback Generation

[0910] Based on the analysis results, the server generates specific feedback, such as "Please correct the angle of the drill" or "The conveyor belt speed is too fast," to improve work accuracy. This feedback is sent to the device in real time.

[0911] Feedback Display

[0912] The device receives feedback from the server and displays it to the user in real time, visually indicating pitch and rhythm discrepancies, areas for improvement in the accuracy of the work, and so on.

[0913] Data accumulation and optimization

[0914] The server accumulates data from training and work sessions and uses a generative AI model to optimize future training and work. The model suggests optimal training menus and work procedures based on past data and progress.

[0915] Specific examples

[0916] Example 1: Basic Training Session

[0917] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and vibration sensitivity, and then prompts the user for vocal and vibration tests. When the user sings a basic scale, the audio and vibration data are sent to the server in real time. The server analyzes the audio and generates immediate feedback, such as "Please raise the pitch a little more," which is then displayed on the device.

[0918] Example 2: Work Accuracy Improvement Session

[0919] A factory worker puts on smart glasses and begins drilling. The glasses capture the sounds and vibrations of the work and send the data in real time to a server. The server analyzes the data and generates feedback, such as "The drill angle is not correct," which is displayed on the worker's glasses.

[0920] Example prompt sentence:

[0921] Analyze your voice data and generate specific feedback for work improvement.

[0922] For example: the drill is not at the right angle, the conveyor belt is moving too fast.

[0923] In this way, the system operates in cooperation with the server, terminal, and user, realizing real-time training and improving work accuracy.

[0924] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0925] Step 1:

[0926] The user selects the music training menu or the work accuracy improvement menu.

[0927] Input: User selection information

[0928] Operation: The device displays a menu screen, and the user selects the desired menu. The device then sends the selected menu information to the server.

[0929] Output: Menu information sent to the server

[0930] Step 2:

[0931] The device captures sound and vibrations in real time.

[0932] Input: User's voice, vibrations associated with work

[0933] How it works: The device's built-in microphone and vibration sensor capture sound and vibration. The captured data is temporarily stored on the device and then sent to a server in real time.

[0934] Output: Captured audio and vibration data

[0935] Step 3:

[0936] The server analyzes the received voice and vibration data.

[0937] Input: Audio and vibration data sent from the device

[0938] How it works: The server uses AI algorithms to analyze audio and vibration data, extracting data on pitch, rhythm, and work accuracy, and providing a detailed evaluation.

[0939] Output: Analysis results (data on pitch, rhythm, and work accuracy)

[0940] Step 4:

[0941] The server generates feedback based on the analysis results.

[0942] Input: Analysis results

[0943] How it works: Based on the analysis results, the server uses a generative AI model to generate specific feedback, including advice such as "lower the pitch," "match the rhythm," or "correct the angle of the drill."

[0944] Output: Feedback content

[0945] Step 5:

[0946] The device displays the feedback received from the server in real time.

[0947] Input: Feedback sent from the server

[0948] How it works: The device displays feedback to the user visually or audibly, for example, a visual alert on smart glasses or a text message on a smartphone.

[0949] Output: Feedback information displayed to the user

[0950] Step 6:

[0951] The server accumulates the user's training and work data and optimizes the next training or work.

[0952] Input: User training and work data, analysis results, feedback

[0953] How it works: The server stores training and work data in a database. It uses a generative AI model to analyze past data and prepares to suggest the next optimal training menu or work procedure for the user.

[0954] Output: Optimized training menu and work procedure suggestions

[0955] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0956] This invention is a system for supporting musical training that recognizes the user's emotional state by combining an emotion engine and provides optimal training content and feedback. The system is composed of three elements: the user, the terminal, and the server, and realizes personalized training that takes into account the user's emotional state in particular.

[0957] User operations

[0958] Users install the dedicated app on their smartphone or tablet. When they launch the app, an initial setup screen appears, allowing them to adjust the microphone sensitivity and sound reverberation settings, enabling the device to accurately capture voices.

[0959] Selecting a training menu

[0960] Once the user has completed the initial setup, they can select basic training, specific vocal exercises, and specific song practice from the music training menu provided within the app. Once the user selects the desired training content, the information is sent to the server.

[0961] Audio capture and real-time transmission

[0962] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[0963] Server analysis and feedback generation

[0964] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to carefully evaluate pitch and rhythm deviations. Based on the analysis results, the server generates real-time feedback, which the device displays to the user.

[0965] Emotion engine integration

[0966] The server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is feeling impatient or irritated, that information is sent to the server.

[0967] Emotion-based feedback regulation

[0968] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback to reassure them and display it on the device.

[0969] View Feedback

[0970] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message such as "The rhythm is fast, but it feels good. Take it easy and try again slowly" is displayed on the screen.

[0971] Accumulation and optimization of training data

[0972] The server stores the user's training data, which includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model is designed to suggest optimal training menus and songs based on the user's past data and emotional state.

[0973] Example 1: Basic Training Session

[0974] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[0975] Example 2: Practice session for assigned piece

[0976] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as "You're doing very well. Keep going."

[0977] The present invention allows users to receive personalized training according to their emotional state without receiving professional instruction, effectively improving their ability to accurately match pitch and rhythm.

[0978] The processing flow will be explained below.

[0979] Step 1:

[0980] The user installs a dedicated app on their smartphone or tablet.

[0981] Step 2:

[0982] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[0983] Step 3:

[0984] The device saves the user's settings and sends them to the server.

[0985] Step 4:

[0986] The user selects a basic training or challenge song from the music training menu within the app.

[0987] Step 5:

[0988] The terminal displays the selected training menu and transmits the selection information to the server.

[0989] Step 6:

[0990] To start training, the user speaks or plays an instrument into the device's microphone.

[0991] Step 7:

[0992] The terminal captures the user's voice in real time and transmits the voice data to the server.

[0993] Step 8:

[0994] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[0995] Step 9:

[0996] The device captures the user's video data and sends it to the emotion engine.

[0997] Step 10:

[0998] The server uses an emotion engine to analyze the user's emotional state and recognize specific emotions such as impatience or irritation.

[0999] Step 11:

[1000] The server generates feedback based on the results of voice analysis and emotion analysis. For example, in addition to basic feedback such as "The pitch is too high," it also generates emotion-based feedback such as "Relax and try again later."

[1001] Step 12:

[1002] The device displays real-time feedback sent from the server to the user, including technical feedback on pitch and rhythm, as well as positive feedback based on emotion.

[1003] Step 13:

[1004] The user can adjust their training based on the feedback and then sing or play again.

[1005] Step 14:

[1006] The device displays a button that the user presses to end the training session.

[1007] Step 15:

[1008] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[1009] Step 16:

[1010] Users can selectively share their training results on social media.

[1011] Step 17:

[1012] The server accumulates the training data and uses the generative AI model to optimize the next training.

[1013] Step 18:

[1014] The terminal notifies the user of the optimized next training menu proposal from the server.

[1015] In this way, users can receive personalized training that takes into account their emotional state, effectively improving pitch and rhythm accuracy.

[1016] Example 2

[1017] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1018] Conventional music training systems provide feedback without considering the user's emotional state, making it difficult to adequately relieve stress and anxiety felt by users during training. Furthermore, it is difficult to provide personalized training content suited to individual users, resulting in inefficient improvement of user proficiency.

[1019] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1020] In this invention, the server includes a means for recognizing the user's emotional state, a means for adjusting the feedback content, and a means for accumulating training data and using the generated AI model to optimize the next training session, thereby providing feedback based on the user's emotional state and realizing efficient personalized training while reducing the user's stress and anxiety.

[1021] "User" refers to an individual who uses the system to provide musical training.

[1022] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[1023] "Server" refers to the central computing device that analyzes audio data, generates feedback, and stores training data.

[1024] A "musical training menu" refers to a number of musical training programs that a user can choose from.

[1025] "Voice data" refers to digital data of the voice uttered by the user during training.

[1026] "AI model" refers to the artificial intelligence algorithm used by the server to provide optimal training menus and feedback based on training data.

[1027] "Emotional state" refers to the psychological state that the user feels during training, specifically emotions such as impatience, anxiety, and irritation.

[1028] "Feedback" refers to training guidance comments provided by the server based on the analysis results and emotional state.

[1029] This invention is a system for supporting musical training that takes into account the user's emotional state and provides optimal training content and feedback. The system is composed of three elements: the user, the device, and the server. The user installs a dedicated app on a smartphone or tablet device and performs training.

[1030] User operations

[1031] First, users install a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These settings allow the device to capture voices accurately. For example, increasing microphone sensitivity allows the device to pick up even quieter voices clearly.

[1032] Selecting a training menu

[1033] Once the user has completed the initial setup, the app displays a menu of various music training options. The user can choose basic training, specific vocal exercises, or specific song practice. Once the user selects the desired training option, the information is sent from the device to the server.

[1034] Audio capture and real-time transmission

[1035] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the voice is immediately transmitted to the server. The device uses its dedicated noise canceling function to maintain the quality of the voice.

[1036] Server analysis and feedback generation

[1037] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to evaluate pitch and rhythm. Based on the analysis results, the server generates real-time feedback, which the device displays to the user. For example, specific feedback such as "The pitch of this part is too low" is generated.

[1038] Emotion engine integration

[1039] Furthermore, the server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user feels impatient or anxious during training, this information is recognized by the emotion engine.

[1040] Emotion-based feedback regulation

[1041] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback such as "Don't worry, keep going" and display it on the device.

[1042] View Feedback

[1043] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message might appear on the screen saying, "The rhythm is fast, but it feels good. Take your time and try again."

[1044] Accumulation and optimization of training data

[1045] The server stores the user's training data. This data includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model then suggests optimal training menus and songs based on the user's past data and emotional state. In this way, users can receive personalized training tailored to their emotional state.

[1046] Specific examples

[1047] Below is an example of a specific training session.

[1048] Example 1: Basic Training Session

[1049] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[1050] Example 2: Practice session for assigned piece

[1051] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as, "You're doing very well. Keep going."

[1052] Prompt Sentence Examples

[1053] Sample Prompt 1: "How do I set up my Basic Training to begin?"

[1054] Sample prompt 2: "What feedback message would you give if you felt impatient during the vocal test?"

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] Installing the dedicated app and initial settings

[1058] The user installs a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen is displayed. As input, the user adjusts the microphone sensitivity and sound reverberation. The device then stores the set parameters internally so that it can output a state that allows it to accurately capture sound. Specifically, the user operates the microphone sensitivity slider and is presented with a screen for testing sound reverberation.

[1059] Step 2:

[1060] Selecting a training menu

[1061] The user selects basic training, specific vocal training, or practice of a specific target song from the music training menu provided within the app. The user provides the selected menu information as input. The device sends the selected menu information to the server. The output is the training menu information sent to the server. Specifically, various training menus are displayed as a list on the app screen, and selections are made by tapping.

[1062] Step 3:

[1063] Real-time audio capture

[1064] When a user starts training, the device's microphone captures the user's voice in real time. The input is the user's singing or vocalization. The device encodes the captured audio data for transmission to the server. The output is the encoded audio data. Specifically, the microphone detects surrounding sounds and converts them into audio data in real time.

[1065] Step 4:

[1066] Sending audio data

[1067] The terminal transmits the encoded voice data to the server in real time. The encoded voice data exists on the terminal as input. The voice data is transmitted to the server as output. Specifically, data packets are sent via the Internet and received by the server.

[1068] Step 5:

[1069] Analysis of audio data

[1070] The server analyzes the audio data sent from the device. Audio data arrives at the server as input. Analysis results data on pitch and rhythm are generated as output. The server uses an AI algorithm to achieve this. Specifically, the received data is input into an analysis engine, and the AI ​​calculates deviations in pitch and rhythm.

[1071] Step 6:

[1072] Generate feedback

[1073] The server generates feedback based on the analysis results. The input is the audio analysis result data. The output is specific training feedback comments. The generated feedback is sent to the device. Specifically, it generates feedback data in text format, such as "The pitch of this part is a little low."

[1074] Step 7:

[1075] Emotional state analysis

[1076] The server uses the user's voice and video data to activate the emotion engine and recognize the user's emotional state. The voice and video data are provided to the server as input. The user's emotional state data is obtained as output. Specifically, the facial expression analysis algorithm analyzes the user's facial movements, and the voice tone analysis evaluates the emotion.

[1077] Step 8:

[1078] Emotion-based feedback regulation

[1079] The server adjusts the feedback content based on the recognized emotional state. The inputs are the emotional state data and the initial feedback data. The output is an adjusted feedback comment. Specifically, if anxiety is detected, a message such as "Don't worry, keep going" is added.

[1080] Step 9:

[1081] View Feedback

[1082] The device displays the feedback sent from the server to the user in real time. As input, the device receives the adjusted feedback data. As output, there is a feedback message displayed to the user. Specific behaviors include displaying the feedback as a text message or graph on the app screen.

[1083] Step 10:

[1084] Accumulation and optimization of training data

[1085] The server accumulates the user's training data and uses the generated AI model to optimize the next training content. As input, all data from the training session is stored on the server. As output, the next training menu and feedback are optimized. Specifically, the accumulated data is input into a learning algorithm, which generates a personalized menu for each user.

[1086] (Application example 2)

[1087] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1088] Conventional music training systems only provide feedback on pitch and rhythm, and lack personalized feedback that takes into account the user's emotional state. This makes it difficult to reduce the stress and anxiety users feel during training, making it difficult to achieve effective training. Furthermore, because the system does not propose optimal training menus based on the user's emotional state, it is also difficult to provide appropriate instruction tailored to each individual user's progress and emotional state.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing audio data and generating feedback regarding pitch and rhythm based on the analysis results, means for activating an emotion engine using the audio data and the user's video data to recognize the user's emotional state, and means for adjusting the feedback content and training menu based on the recognized emotional state. This makes it possible to provide personalized feedback according to the user's emotional state, enabling effective training while reducing stress and anxiety. Furthermore, by providing an optimal training menu based on the user's individual emotional state and progress, more effective instruction is possible.

[1090] "Voice data" refers to data in which voice information uttered by a user is recorded in digital format.

[1091] An "emotion engine" is an artificial intelligence algorithm that analyzes a user's emotional state from audio and video data.

[1092] "Feedback" refers to training advice and instructions that are generated based on the analysis of the voice data and the user's emotional state.

[1093] "Means for transmitting in real time" refers to a device or software that has the function of instantly transmitting audio to a server when a user is performing musical training.

[1094] "Training data" refers to records of audio data, emotional state information, feedback content, and the like related to the musical training the user has performed.

[1095] A "generated AI model" is an artificial intelligence model designed to generate optimal training content based on a user's training data.

[1096] A "musical training menu" refers to musical training items and programs that can be selected by the user.

[1097] The "means for generating feedback regarding pitch and rhythm" refers to an algorithm or program that allows the server to analyze the user's voice data, evaluate the pitch and rhythm, and generate advice based on that evaluation.

[1098] The "means for adjusting the feedback content and training menu" refers to an algorithm or system that appropriately reviews the feedback content provided and the next training menu based on the results of the user's emotion engine.

[1099] "Means for displaying in real time" refers to a device or application for instantly displaying feedback sent from the server to the user.

[1100] The "initial setting means" is a function for adjusting microphone sensitivity and sound reverberation to create an optimal environment for musical training.

[1101] This music training system is designed to make user training more effective and personalized. The system is broadly composed of the user's device, a server, an emotion engine, and a generative AI model.

[1102] First, the user installs the dedicated application on their device, which can be a smartphone or tablet. After launching the application, the user can adjust the microphone sensitivity and sound reverberation on the initial setup screen, allowing the device to accurately capture the voice.

[1103] Next, the user selects the desired training content from the music training menu within the application. The selection is sent to the server. When the user starts training, the device's microphone captures the audio in real time and sends the audio data to the server. The audio data may also include the user's video data.

[1104] The server runs an AI algorithm that analyzes the audio data. The analysis evaluates pitch and rhythm deviations and generates feedback. This feedback includes technical advice on pitch and rhythm. Additionally, an emotion engine is activated, analyzing the transmitted audio and video data to recognize the user's emotional state. Based on the recognized emotional state, the content of the feedback and the next training menu are adjusted. For example, if the user is feeling impatient or anxious, the server generates positive feedback to provide reassurance.

[1105] The generated feedback is displayed on the user's device in real time, allowing the user to receive immediate advice during training. The server also accumulates the user's training data and uses a generative AI model to optimize the next training session. This generative AI model is designed to suggest the next training menu and assigned songs based on the user's past data and emotional state.

[1106] As a concrete example, consider a user practicing "Let It Go." As the user begins to sing, the device sends audio data to the server in real time. The server analyzes the pitch and rhythm and generates technical feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it also adds positive feedback such as, "You're doing very well. Keep going."

[1107] An example of a prompt is as follows:

[1108] "Generate optimal music training feedback based on the user's voice data and emotional state. The voice data includes analysis of pitch and rhythm, and the emotional state includes impatience, anxiety, joy, etc."

[1109] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1110] Step 1:

[1111] The user installs the application on the device and performs initial settings.

[1112] Specifically, the user downloads and installs a dedicated application. On the initial setup screen, they can adjust microphone sensitivity and sound reverberation, allowing the device to accurately capture audio. The input is the user's interaction, and the output is optimized microphone settings.

[1113] Step 2:

[1114] The user selects the music training menu.

[1115] The user selects the desired training content from a menu within the application. The selection is sent to the server. The input is the user's menu selection operation, and the output is the training menu information sent to the server.

[1116] Step 3:

[1117] The device captures the audio and transmits it to the server in real time.

[1118] The user starts training, and the device's microphone captures the user's voice in real time. The captured voice data is sent to the server. The input is the user's singing voice, and the output is the voice data sent to the server.

[1119] Step 4:

[1120] The server analyzes the audio data and generates feedback.

[1121] The server analyzes the received audio data using an AI algorithm to evaluate discrepancies in pitch and rhythm. Feedback is generated based on the analysis results. The input is audio data, and the output is the analysis results and feedback. Specific operations include evaluating the accuracy of pitch and rhythm and identifying problems.

[1122] Step 5:

[1123] The server runs an emotion engine to recognize the emotional state.

[1124] The server uses the voice data and the user's video data to activate the emotion engine. The emotion engine analyzes the user's facial expressions and voice tone to recognize their current emotional state. The input is the voice and video data, and the output is the recognized emotional state. In concrete terms, an emotion analysis algorithm is executed to evaluate the emotional state.

[1125] Step 6:

[1126] Adjust feedback and training menus based on emotional state.

[1127] The server adjusts the feedback content and the next training menu based on the recognized emotional state. The input is the recognized emotional state, and the output is customized feedback based on the emotion. Specifically, it generates positive feedback for users who feel anxious.

[1128] Step 7:

[1129] The device displays feedback in real time.

[1130] The device receives feedback sent from the server and displays it to the user in real time. The input is feedback data from the server, and the output is a feedback message displayed on the device screen. Specific operations include displaying feedback on the screen as text or animation.

[1131] Step 8:

[1132] The server accumulates the training data and uses the generative AI model to optimize the next training.

[1133] The server stores the user's voice data, feedback content, emotional state, etc. in a database. For the next training session, the generative AI model uses this data to propose the optimal training menu. The input is the accumulated training data, and the output is the next optimized training menu. Specifically, the AI ​​analyzes the accumulated data and designs the training content that is most suitable for the user.

[1134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1136] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1137] [Fourth embodiment]

[1138] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1139] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1142] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1145] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1147] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1149] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1150] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1151] This invention is a system for supporting musical training, providing effective training using smartphones and tablet devices. The entire system is mainly composed of three elements: the user, the device, and the server.

[1152] User operations

[1153] Users install a dedicated app on their smartphone or tablet. When they launch the app, they are first shown an initial setup screen where they can adjust the microphone sensitivity and sound reverberation settings, allowing the device to accurately capture voices.

[1154] Selecting a training menu

[1155] Once the user has completed the initial setup, they can choose from a music training menu provided within the app, which includes basic training, specific vocal exercises, and practice of specific songs. Once the user selects the desired training content, the information is sent to the server.

[1156] Audio capture and real-time transmission

[1157] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[1158] Server analysis and feedback generation

[1159] The server analyzes the audio data sent from the device. The analysis uses an AI algorithm to meticulously evaluate pitch and rhythm discrepancies. Based on the analysis results, the server generates real-time feedback, including specific advice such as "your high notes are unstable" or "your rhythm is too fast."

[1160] View Feedback

[1161] The device immediately displays the feedback information sent from the server to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch is out of sync.

[1162] Accumulation and optimization of training data

[1163] The server stores the user's training data. Based on the stored data, a generative AI model is used to optimize the next training session. This model is designed to suggest optimal training menus and songs based on the user's past data and training progress.

[1164] Example 1: Basic Training Session

[1165] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings the basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[1166] Example 2: Practice session for assigned piece

[1167] The user selects the song "Let It Go" and begins training. The device then suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[1168] The present invention enables effective musical training, and allows users to improve their ability to accurately match pitch and rhythm without receiving specialized instruction.

[1169] The processing flow will be explained below.

[1170] Step 1:

[1171] The user installs a dedicated app on their smartphone or tablet.

[1172] Step 2:

[1173] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[1174] Step 3:

[1175] The device saves the user's settings and sends them to the server.

[1176] Step 4:

[1177] The user selects a basic training or challenge song from the music training menu within the app.

[1178] Step 5:

[1179] The terminal displays the selected training menu and transmits the selection information to the server.

[1180] Step 6:

[1181] To start training, the user speaks or plays an instrument into the device's microphone.

[1182] Step 7:

[1183] The terminal captures the user's voice in real time and transmits the voice data to the server.

[1184] Step 8:

[1185] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[1186] Step 9:

[1187] The server generates feedback based on the analysis results, providing specific advice such as "the pitch is too high" or "the rhythm is too fast."

[1188] Step 10:

[1189] The device displays the feedback sent from the server to the user in real time.

[1190] Step 11:

[1191] The user can adjust their training based on the feedback and then sing or play again.

[1192] Step 12:

[1193] The device displays a button that the user presses to end the training session.

[1194] Step 13:

[1195] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[1196] Step 14:

[1197] Users can selectively share their training results on social media.

[1198] Step 15:

[1199] The server accumulates the training data and uses the generative AI model to optimize the next training.

[1200] Step 16:

[1201] The terminal notifies the user of the optimized next training menu proposal from the server.

[1202] Example 1

[1203] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1204] Conventional music training systems have limitations in helping users effectively master pitch and rhythm. Specifically, they lack real-time feedback and a means for users to self-evaluate, limiting the effectiveness of training. Furthermore, the lack of individualized training content means that appropriate instruction cannot be provided based on the user's progress.

[1205] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1206] In this invention, the server

[1207] a means for a user to select a musical training menu;

[1208] a means for the terminal to capture and transmit audio to a server in real time;

[1209] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[1210] means for the terminal to display feedback to the user in real time;

[1211] The server stores the training data and uses the generated AI model to optimize the next training.

[1212] A means for the user to set up the device and adjust microphone sensitivity and sound reverberation;

[1213] A means to analyze the user's past training data and suggest the optimal training menu;

[1214] This allows users to train while receiving real-time feedback, and by being offered individually optimized training menus, it is possible to effectively improve musical skills.

[1215] "User" refers to a person who uses the musical training system.

[1216] "Terminal" refers to an electronic device used by a user, such as a smartphone or tablet.

[1217] "Server" refers to a remote computer system that analyzes speech data, generates feedback, and stores and optimizes training data.

[1218] "Music training menu" refers to a list of training contents that the user can select from.

[1219] "Voice data" refers to sound information uttered by a user through a microphone on a terminal.

[1220] "Feedback" refers to advice and evaluation regarding pitch and rhythm generated based on audio data analyzed by the server.

[1221] "Real-time" refers to near-instant processing with minimal delay.

[1222] An "AI model" is an algorithm that uses artificial intelligence to analyze the user's voice data and optimize the next training menu.

[1223] "Microphone sensitivity" refers to the ability of a device's microphone to pick up sound.

[1224] "Sound reverberation" refers to the phenomenon of sound being reflected back and its effects.

[1225] "Training data" refers to the voice data and analysis results generated during training conducted by the user.

[1226] This invention is a system for supporting musical training, providing effective training using devices such as smartphones and tablets. The entire system is mainly composed of three elements: the user, the device, and the server.

[1227] First, users install a dedicated music training app on their device. When they launch the app, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These initial settings allow the device to accurately capture audio. For example, users can adjust the microphone sensitivity slider to adjust how much sound is picked up.

[1228] After the initial setup is complete, the user selects the desired training menu from the music training menu provided within the app. The information about the selected training menu is sent to the server by the device. For example, if the user selects "Basic Training," the information is sent to the server.

[1229] When a user starts training, the device's microphone captures the user's voice in real time. The captured voice data is compressed and sent to a server over the Internet. For example, when a user sings the first line of "Let It Go," the voice is immediately sent to the server.

[1230] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. If the server determines that the user's high notes are unstable, it generates feedback stating, "Your high notes are unstable." This feedback is displayed in the form of a text message or a graph.

[1231] The device receives the feedback information sent from the server and immediately displays it to the user, such as a text message on the screen saying "Please lower the pitch a little" or a visual bar indicating the pitch discrepancy, allowing the user to make corrections in real time.

[1232] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. For example, the server may analyze the user's past pitch data and propose a new optimal training menu.

[1233] For example, when a user opens the app and selects the basic training menu, the device checks the microphone sensitivity and prompts the user for a vocal test. When the user sings a basic scale, the audio is sent to the server in real time. The server analyzes the audio and immediately generates feedback such as "Please raise the pitch a little more," which is then displayed on the device.

[1234] When a user selects the song "Let It Go" and begins training, the device suggests specific phrases and pitch exercises for the user to practice. When the user sings the first phrase of the song, the device captures the audio and sends it to the server. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast," which is then displayed on the device.

[1235] An example of a prompt sentence is, "Please suggest the best training content for the next training menu. The user's past data is as follows: 'Basic scale practice: pitch is not stable', 'Rhythm practice: unable to maintain a consistent tempo'."

[1236] In this way, the present invention allows users to effectively train in music without receiving specialized instruction, and improve their ability to accurately match pitch and rhythm.

[1237] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1238] Step 1: Initial Setup

[1239] The user installs the dedicated app on their smartphone or tablet and launches it. The app displays an initial setup screen, providing the user with settings to adjust microphone sensitivity and sound reverberation. Specifically, the user can adjust the microphone sensitivity by moving a slider and check the sound reverberation using a test sound. The input is the user's operation (adjusting microphone sensitivity and checking sound reverberation), and the output is the adapted microphone settings.

[1240] Step 2: Select a training menu

[1241] After completing the initial setup, the user selects the desired menu from the music training menu provided within the app. The device sends information about the selected training menu to the server. The input is the training menu selected by the user, and the output is the menu information sent to the server. Specifically, the user makes a selection by tapping "Basic Training" or "Set Song Practice."

[1242] Step 3: Audio capture and real-time transmission

[1243] When a user starts training, the device's microphone captures the user's voice in real time. This voice data is compressed and sent to a server over the Internet. The input is the user's voice, and the output is the compressed voice data sent to the server. Specifically, when the user sings the first phrase of "Let It Go," the voice is immediately sent to the server.

[1244] Step 4: Server analysis and feedback generation

[1245] The server analyzes the received audio data. This analysis uses an AI algorithm to detect deviations in pitch and rhythm. The input is the audio data sent to the server, and the output is feedback generated based on the analysis results. Specifically, the server determines that "the user's pitch in the high notes is unstable" and generates feedback stating, "The high notes are unstable."

[1246] Step 5: View your feedback

[1247] The terminal receives the feedback information sent from the server and immediately displays it to the user. The input is the feedback information sent from the server, and the output is the feedback message or visual display displayed to the user. Specifically, a text message such as "Please lower the pitch a little" or a bar indicating the pitch discrepancy is displayed on the screen.

[1248] Step 6: Accumulating and optimizing training data

[1249] The server accumulates the data obtained as a result of the training. Based on the accumulated data, it uses a generative AI model to optimize the next training menu. The input is the user's past training data, and the output is a new training menu optimized by the generative AI model. Specifically, the server performs operations such as "analyzing the user's past pitch data and proposing the next training menu."

[1250] (Application example 1)

[1251] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1252] While conventional music training systems can evaluate pitch and rhythm, they are not suited to diverse applications such as improving the accuracy of factory work or providing real-time feedback. In particular, it has been difficult to analyze vibrations and operational sounds, which are necessary in the work environment, and provide feedback based on that analysis. This has made it difficult to support the improvement of the movement accuracy of workers and robots.

[1253] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1254] In this invention, the server includes a means for the terminal to capture voice and vibration and transmit them to the server in real time, a means for the server to analyze the voice and vibration data and generate feedback on pitch, rhythm, and task accuracy based on the analysis results, and a means for the server to accumulate training and task data and use the generated AI model to optimize the next training or task, thereby enabling the provision of real-time feedback aimed at improving the motion accuracy of workers and robots.

[1255] A "user" is a user who operates the system and performs musical training or training to improve work accuracy.

[1256] A "music training menu" is a list of practice items and assignments that a user can select to improve their musical skills through the system.

[1257] A "terminal" is a device that captures sound and vibrations and transmits them to a server, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[1258] The "server" is a computer system that receives the voice and vibration data sent from the terminal, analyzes it, and generates feedback.

[1259] "Feedback" refers to advice and instructions generated by the server based on the analysis results, including specific areas for improvement regarding pitch, rhythm, and work accuracy.

[1260] "Training data" refers to recorded information such as audio and vibration data generated by the user during training, analysis results, and feedback.

[1261] A "generated AI model" is an artificial intelligence algorithm and its program used to optimize the next training or task based on the user's training data or task data.

[1262] "Vibration" is a signal or data that captures physical movements and fluctuations that occur during factory operations.

[1263] "Work accuracy" is an indicator of how accurately a worker or robot performs work according to specified procedures and standards.

[1264] This invention is a system in which a user selects a music training menu, and the terminal captures and transmits the audio and vibration data to a server in real time. The server then analyzes the audio and vibration data, generates feedback based on the analysis results, and provides it to the user. The server also accumulates training and work data and uses the generated AI model to optimize the next training or work.

[1265] Details of the hardware and software used

[1266] Hardware:

[1267] Device: A smartphone, tablet, smart glasses, or head-mounted display for capturing sound and vibration.

[1268] Microphone and sensors: The device's built-in microphone and vibration sensors are used to capture the user's voice and working vibrations.

[1269] software:

[1270] Python: Used in programs that perform data analysis on the server side.

[1271] Flask: A web application framework for transmitting audio data.

[1272] SpeechRecognition libraries: Used to analyze speech data (e.g., Google's Web Speech API).

[1273] AI Algorithms: Generative AI models used for analysis and feedback generation, which generate appropriate feedback based on the analysis of audio and vibration data.

[1274] Program processing explanation

[1275] Audio and Vibration Capture

[1276] The device's microphone and vibration sensor capture the user's voice and vibrations in real time, and the captured data is sent from the device to a server.

[1277] Data analysis

[1278] The server analyzes the received audio and vibration data, processing it using AI algorithms to evaluate pitch, rhythm, and task accuracy.

[1279] Feedback Generation

[1280] Based on the analysis results, the server generates specific feedback, such as "Please correct the angle of the drill" or "The conveyor belt speed is too fast," to improve work accuracy. This feedback is sent to the device in real time.

[1281] Feedback Display

[1282] The device receives feedback from the server and displays it to the user in real time, visually indicating pitch and rhythm discrepancies, areas for improvement in the accuracy of the work, and so on.

[1283] Data accumulation and optimization

[1284] The server accumulates data from training and work sessions and uses a generative AI model to optimize future training and work. The model suggests optimal training menus and work procedures based on past data and progress.

[1285] Specific examples

[1286] Example 1: Basic Training Session

[1287] The user opens the app and selects the basic training menu. The device checks the microphone sensitivity and vibration sensitivity, and then prompts the user for vocal and vibration tests. When the user sings a basic scale, the audio and vibration data are sent to the server in real time. The server analyzes the audio and generates immediate feedback, such as "Please raise the pitch a little more," which is then displayed on the device.

[1288] Example 2: Work Accuracy Improvement Session

[1289] A factory worker puts on smart glasses and begins drilling. The glasses capture the sounds and vibrations of the work and send the data in real time to a server. The server analyzes the data and generates feedback, such as "The drill angle is not correct," which is displayed on the worker's glasses.

[1290] Example prompt sentence:

[1291] Analyze your voice data and generate specific feedback for work improvement.

[1292] For example: the drill is not at the right angle, the conveyor belt is moving too fast.

[1293] In this way, the system operates in cooperation with the server, terminal, and user, realizing real-time training and improving work accuracy.

[1294] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1295] Step 1:

[1296] The user selects the music training menu or the work accuracy improvement menu.

[1297] Input: User selection information

[1298] Operation: The device displays a menu screen, and the user selects the desired menu. The device then sends the selected menu information to the server.

[1299] Output: Menu information sent to the server

[1300] Step 2:

[1301] The device captures sound and vibrations in real time.

[1302] Input: User's voice, vibrations associated with work

[1303] How it works: The device's built-in microphone and vibration sensor capture sound and vibration. The captured data is temporarily stored on the device and then sent to a server in real time.

[1304] Output: Captured audio and vibration data

[1305] Step 3:

[1306] The server analyzes the received voice and vibration data.

[1307] Input: Audio and vibration data sent from the device

[1308] How it works: The server uses AI algorithms to analyze audio and vibration data, extracting data on pitch, rhythm, and work accuracy, and providing a detailed evaluation.

[1309] Output: Analysis results (data on pitch, rhythm, and work accuracy)

[1310] Step 4:

[1311] The server generates feedback based on the analysis results.

[1312] Input: Analysis results

[1313] How it works: Based on the analysis results, the server uses a generative AI model to generate specific feedback, including advice such as "lower the pitch," "match the rhythm," or "correct the angle of the drill."

[1314] Output: Feedback content

[1315] Step 5:

[1316] The device displays the feedback received from the server in real time.

[1317] Input: Feedback sent from the server

[1318] How it works: The device displays feedback to the user visually or audibly, for example, a visual alert on smart glasses or a text message on a smartphone.

[1319] Output: Feedback information displayed to the user

[1320] Step 6:

[1321] The server accumulates the user's training and work data and optimizes the next training or work.

[1322] Input: User training and work data, analysis results, feedback

[1323] How it works: The server stores training and work data in a database. It uses a generative AI model to analyze past data and prepares to suggest the next optimal training menu or work procedure for the user.

[1324] Output: Optimized training menu and work procedure suggestions

[1325] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1326] This invention is a system for supporting musical training that recognizes the user's emotional state by combining an emotion engine and provides optimal training content and feedback. The system is composed of three elements: the user, the terminal, and the server, and realizes personalized training that takes into account the user's emotional state in particular.

[1327] User operations

[1328] Users install the dedicated app on their smartphone or tablet. When they launch the app, an initial setup screen appears, allowing them to adjust the microphone sensitivity and sound reverberation settings, enabling the device to accurately capture voices.

[1329] Selecting a training menu

[1330] Once the user has completed the initial setup, they can select basic training, specific vocal exercises, and specific song practice from the music training menu provided within the app. Once the user selects the desired training content, the information is sent to the server.

[1331] Audio capture and real-time transmission

[1332] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the device will immediately transmit the singing voice to the server.

[1333] Server analysis and feedback generation

[1334] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to carefully evaluate pitch and rhythm deviations. Based on the analysis results, the server generates real-time feedback, which the device displays to the user.

[1335] Emotion engine integration

[1336] The server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is feeling impatient or irritated, that information is sent to the server.

[1337] Emotion-based feedback regulation

[1338] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback to reassure them and display it on the device.

[1339] View Feedback

[1340] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message such as "The rhythm is fast, but it feels good. Take it easy and try again slowly" is displayed on the screen.

[1341] Accumulation and optimization of training data

[1342] The server stores the user's training data, which includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model is designed to suggest optimal training menus and songs based on the user's past data and emotional state.

[1343] Example 1: Basic Training Session

[1344] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[1345] Example 2: Practice session for assigned piece

[1346] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as "You're doing very well. Keep going."

[1347] The present invention allows users to receive personalized training according to their emotional state without receiving professional instruction, effectively improving their ability to accurately match pitch and rhythm.

[1348] The processing flow will be explained below.

[1349] Step 1:

[1350] The user installs a dedicated app on their smartphone or tablet.

[1351] Step 2:

[1352] The user launches the app and configures settings such as microphone sensitivity and sound reverberation from the initial setup screen.

[1353] Step 3:

[1354] The device saves the user's settings and sends them to the server.

[1355] Step 4:

[1356] The user selects a basic training or challenge song from the music training menu within the app.

[1357] Step 5:

[1358] The terminal displays the selected training menu and transmits the selection information to the server.

[1359] Step 6:

[1360] To start training, the user speaks or plays an instrument into the device's microphone.

[1361] Step 7:

[1362] The terminal captures the user's voice in real time and transmits the voice data to the server.

[1363] Step 8:

[1364] The server analyzes the audio data it receives using an AI algorithm to detect discrepancies in pitch and rhythm.

[1365] Step 9:

[1366] The device captures the user's video data and sends it to the emotion engine.

[1367] Step 10:

[1368] The server uses an emotion engine to analyze the user's emotional state and recognize specific emotions such as impatience or irritation.

[1369] Step 11:

[1370] The server generates feedback based on the results of voice analysis and emotion analysis. For example, in addition to basic feedback such as "The pitch is too high," it also generates emotion-based feedback such as "Relax and try again later."

[1371] Step 12:

[1372] The device displays real-time feedback sent from the server to the user, including technical feedback on pitch and rhythm, as well as positive feedback based on emotion.

[1373] Step 13:

[1374] The user can adjust their training based on the feedback and then sing or play again.

[1375] Step 14:

[1376] The device displays a button that the user presses to end the training session.

[1377] Step 15:

[1378] The device saves the training results and displays detailed analysis results in the form of graphs and comments.

[1379] Step 16:

[1380] Users can selectively share their training results on social media.

[1381] Step 17:

[1382] The server accumulates the training data and uses the generative AI model to optimize the next training.

[1383] Step 18:

[1384] The terminal notifies the user of the optimized next training menu proposal from the server.

[1385] In this way, users can receive personalized training that takes into account their emotional state, effectively improving pitch and rhythm accuracy.

[1386] Example 2

[1387] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1388] Conventional music training systems provide feedback without considering the user's emotional state, making it difficult to adequately relieve stress and anxiety felt by users during training. Furthermore, it is difficult to provide personalized training content suited to individual users, resulting in inefficient improvement of user proficiency.

[1389] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1390] In this invention, the server includes a means for recognizing the user's emotional state, a means for adjusting the feedback content, and a means for accumulating training data and using the generated AI model to optimize the next training session, thereby providing feedback based on the user's emotional state and realizing efficient personalized training while reducing the user's stress and anxiety.

[1391] "User" refers to an individual who uses the system to provide musical training.

[1392] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[1393] "Server" refers to the central computing device that analyzes audio data, generates feedback, and stores training data.

[1394] A "musical training menu" refers to a number of musical training programs that a user can choose from.

[1395] "Voice data" refers to digital data of the voice uttered by the user during training.

[1396] "AI model" refers to the artificial intelligence algorithm used by the server to provide optimal training menus and feedback based on training data.

[1397] "Emotional state" refers to the psychological state that the user feels during training, specifically emotions such as impatience, anxiety, and irritation.

[1398] "Feedback" refers to training guidance comments provided by the server based on the analysis results and emotional state.

[1399] This invention is a system for supporting musical training that takes into account the user's emotional state and provides optimal training content and feedback. The system is composed of three elements: the user, the device, and the server. The user installs a dedicated app on a smartphone or tablet device and performs training.

[1400] User operations

[1401] First, users install a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen appears, allowing users to adjust microphone sensitivity and sound reverberation. These settings allow the device to capture voices accurately. For example, increasing microphone sensitivity allows the device to pick up even quieter voices clearly.

[1402] Selecting a training menu

[1403] Once the user has completed the initial setup, the app displays a menu of various music training options. The user can choose basic training, specific vocal exercises, or specific song practice. Once the user selects the desired training option, the information is sent from the device to the server.

[1404] Audio capture and real-time transmission

[1405] When a user starts training, the device's microphone captures the user's voice in real time and transmits it to the server. For example, if the user sings "Let It Go," the voice is immediately transmitted to the server. The device uses its dedicated noise canceling function to maintain the quality of the voice.

[1406] Server analysis and feedback generation

[1407] The server analyzes the audio data sent from the device. This analysis uses AI algorithms to evaluate pitch and rhythm. Based on the analysis results, the server generates real-time feedback, which the device displays to the user. For example, specific feedback such as "The pitch of this part is too low" is generated.

[1408] Emotion engine integration

[1409] Furthermore, the server uses the voice data and the user's video data to activate an emotion engine. This emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user feels impatient or anxious during training, this information is recognized by the emotion engine.

[1410] Emotion-based feedback regulation

[1411] Based on the user's emotional state, the server can adjust the feedback and training menu. For example, if the user is feeling anxious, the server can generate positive feedback such as "Don't worry, keep going" and display it on the device.

[1412] View Feedback

[1413] The device displays real-time feedback on pitch and rhythm sent from the server, as well as emotion-based adjustment feedback, to the user. For example, a message might appear on the screen saying, "The rhythm is fast, but it feels good. Take your time and try again."

[1414] Accumulation and optimization of training data

[1415] The server stores the user's training data. This data includes audio data, feedback, and emotional state information, and is used to optimize the next training session. The generative AI model then suggests optimal training menus and songs based on the user's past data and emotional state. In this way, users can receive personalized training tailored to their emotional state.

[1416] Specific examples

[1417] Below is an example of a specific training session.

[1418] Example 1: Basic Training Session

[1419] The user opens the app, selects the basic training menu, and performs a vocal test. The device sends the audio in real time to the server, which analyzes the pitch and generates feedback such as "Please raise the pitch a little more." If the emotion engine detects the user becoming impatient, it also provides additional positive feedback such as "Try to relax a little."

[1420] Example 2: Practice session for assigned piece

[1421] The user selects "Let It Go" to begin training. The device suggests specific phrases or pitch exercises, which the user then performs. The server analyzes the audio and generates feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it adds positive feedback such as, "You're doing very well. Keep going."

[1422] Prompt Sentence Examples

[1423] Sample Prompt 1: "How do I set up my Basic Training to begin?"

[1424] Sample prompt 2: "What feedback message would you give if you felt impatient during the vocal test?"

[1425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] Installing the dedicated app and initial settings

[1428] The user installs a dedicated app on their smartphone or tablet. When the app is launched, an initial setup screen is displayed. As input, the user adjusts the microphone sensitivity and sound reverberation. The device then stores the set parameters internally so that it can output a state that allows it to accurately capture sound. Specifically, the user operates the microphone sensitivity slider and is presented with a screen for testing sound reverberation.

[1429] Step 2:

[1430] Selecting a training menu

[1431] The user selects basic training, specific vocal training, or practice of a specific target song from the music training menu provided within the app. The user provides the selected menu information as input. The device sends the selected menu information to the server. The output is the training menu information sent to the server. Specifically, various training menus are displayed as a list on the app screen, and selections are made by tapping.

[1432] Step 3:

[1433] Real-time audio capture

[1434] When a user starts training, the device's microphone captures the user's voice in real time. The input is the user's singing or vocalization. The device encodes the captured audio data for transmission to the server. The output is the encoded audio data. Specifically, the microphone detects surrounding sounds and converts them into audio data in real time.

[1435] Step 4:

[1436] Sending audio data

[1437] The terminal transmits the encoded voice data to the server in real time. The encoded voice data exists on the terminal as input. The voice data is transmitted to the server as output. Specifically, data packets are sent via the Internet and received by the server.

[1438] Step 5:

[1439] Analysis of audio data

[1440] The server analyzes the audio data sent from the device. Audio data arrives at the server as input. Analysis results data on pitch and rhythm are generated as output. The server uses an AI algorithm to achieve this. Specifically, the received data is input into an analysis engine, and the AI ​​calculates deviations in pitch and rhythm.

[1441] Step 6:

[1442] Generate feedback

[1443] The server generates feedback based on the analysis results. The input is the audio analysis result data. The output is specific training feedback comments. The generated feedback is sent to the device. Specifically, it generates feedback data in text format, such as "The pitch of this part is a little low."

[1444] Step 7:

[1445] Emotional state analysis

[1446] The server uses the user's voice and video data to activate the emotion engine and recognize the user's emotional state. The voice and video data are provided to the server as input. The user's emotional state data is obtained as output. Specifically, the facial expression analysis algorithm analyzes the user's facial movements, and the voice tone analysis evaluates the emotion.

[1447] Step 8:

[1448] Emotion-based feedback regulation

[1449] The server adjusts the feedback content based on the recognized emotional state. The inputs are the emotional state data and the initial feedback data. The output is an adjusted feedback comment. Specifically, if anxiety is detected, a message such as "Don't worry, keep going" is added.

[1450] Step 9:

[1451] View Feedback

[1452] The device displays the feedback sent from the server to the user in real time. As input, the device receives the adjusted feedback data. As output, there is a feedback message displayed to the user. Specific behaviors include displaying the feedback as a text message or graph on the app screen.

[1453] Step 10:

[1454] Accumulation and optimization of training data

[1455] The server accumulates the user's training data and uses the generated AI model to optimize the next training content. As input, all data from the training session is stored on the server. As output, the next training menu and feedback are optimized. Specifically, the accumulated data is input into a learning algorithm, which generates a personalized menu for each user.

[1456] (Application example 2)

[1457] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1458] Conventional music training systems only provide feedback on pitch and rhythm, and lack personalized feedback that takes into account the user's emotional state. This makes it difficult to reduce the stress and anxiety users feel during training, making it difficult to achieve effective training. Furthermore, because the system does not propose optimal training menus based on the user's emotional state, it is also difficult to provide appropriate instruction tailored to each individual user's progress and emotional state.

[1459] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing audio data and generating feedback regarding pitch and rhythm based on the analysis results, means for activating an emotion engine using the audio data and the user's video data to recognize the user's emotional state, and means for adjusting the feedback content and training menu based on the recognized emotional state. This makes it possible to provide personalized feedback according to the user's emotional state, enabling effective training while reducing stress and anxiety. Furthermore, by providing an optimal training menu based on the user's individual emotional state and progress, more effective instruction is possible.

[1460] "Voice data" refers to data in which voice information uttered by a user is recorded in digital format.

[1461] An "emotion engine" is an artificial intelligence algorithm that analyzes a user's emotional state from audio and video data.

[1462] "Feedback" refers to training advice and instructions that are generated based on the analysis of the voice data and the user's emotional state.

[1463] "Means for transmitting in real time" refers to a device or software that has the function of instantly transmitting audio to a server when a user is performing musical training.

[1464] "Training data" refers to records of audio data, emotional state information, feedback content, and the like related to the musical training the user has performed.

[1465] A "generated AI model" is an artificial intelligence model designed to generate optimal training content based on a user's training data.

[1466] A "musical training menu" refers to musical training items and programs that can be selected by the user.

[1467] The "means for generating feedback regarding pitch and rhythm" refers to an algorithm or program that allows the server to analyze the user's voice data, evaluate the pitch and rhythm, and generate advice based on that evaluation.

[1468] The "means for adjusting the feedback content and training menu" refers to an algorithm or system that appropriately reviews the feedback content provided and the next training menu based on the results of the user's emotion engine.

[1469] "Means for displaying in real time" refers to a device or application for instantly displaying feedback sent from the server to the user.

[1470] The "initial setting means" is a function for adjusting microphone sensitivity and sound reverberation to create an optimal environment for musical training.

[1471] This music training system is designed to make user training more effective and personalized. The system is broadly composed of the user's device, a server, an emotion engine, and a generative AI model.

[1472] First, the user installs the dedicated application on their device, which can be a smartphone or tablet. After launching the application, the user can adjust the microphone sensitivity and sound reverberation on the initial setup screen, allowing the device to accurately capture the voice.

[1473] Next, the user selects the desired training content from the music training menu within the application. The selection is sent to the server. When the user starts training, the device's microphone captures the audio in real time and sends the audio data to the server. The audio data may also include the user's video data.

[1474] The server runs an AI algorithm that analyzes the audio data. The analysis evaluates pitch and rhythm deviations and generates feedback. This feedback includes technical advice on pitch and rhythm. Additionally, an emotion engine is activated, analyzing the transmitted audio and video data to recognize the user's emotional state. Based on the recognized emotional state, the content of the feedback and the next training menu are adjusted. For example, if the user is feeling impatient or anxious, the server generates positive feedback to provide reassurance.

[1475] The generated feedback is displayed on the user's device in real time, allowing the user to receive immediate advice during training. The server also accumulates the user's training data and uses a generative AI model to optimize the next training session. This generative AI model is designed to suggest the next training menu and assigned songs based on the user's past data and emotional state.

[1476] As a concrete example, consider a user practicing "Let It Go." As the user begins to sing, the device sends audio data to the server in real time. The server analyzes the pitch and rhythm and generates technical feedback such as, "The rhythm in this part is too fast." If the emotion engine detects the user's anxiety, it also adds positive feedback such as, "You're doing very well. Keep going."

[1477] An example of a prompt is as follows:

[1478] "Generate optimal music training feedback based on the user's voice data and emotional state. The voice data includes analysis of pitch and rhythm, and the emotional state includes impatience, anxiety, joy, etc."

[1479] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1480] Step 1:

[1481] The user installs the application on the device and performs initial settings.

[1482] Specifically, the user downloads and installs a dedicated application. On the initial setup screen, they can adjust microphone sensitivity and sound reverberation, allowing the device to accurately capture audio. The input is the user's interaction, and the output is optimized microphone settings.

[1483] Step 2:

[1484] The user selects the music training menu.

[1485] The user selects the desired training content from a menu within the application. The selection is sent to the server. The input is the user's menu selection operation, and the output is the training menu information sent to the server.

[1486] Step 3:

[1487] The device captures the audio and transmits it to the server in real time.

[1488] The user starts training, and the device's microphone captures the user's voice in real time. The captured voice data is sent to the server. The input is the user's singing voice, and the output is the voice data sent to the server.

[1489] Step 4:

[1490] The server analyzes the audio data and generates feedback.

[1491] The server analyzes the received audio data using an AI algorithm to evaluate discrepancies in pitch and rhythm. Feedback is generated based on the analysis results. The input is audio data, and the output is the analysis results and feedback. Specific operations include evaluating the accuracy of pitch and rhythm and identifying problems.

[1492] Step 5:

[1493] The server runs an emotion engine to recognize the emotional state.

[1494] The server uses the voice data and the user's video data to activate the emotion engine. The emotion engine analyzes the user's facial expressions and voice tone to recognize their current emotional state. The input is the voice and video data, and the output is the recognized emotional state. In concrete terms, an emotion analysis algorithm is executed to evaluate the emotional state.

[1495] Step 6:

[1496] Adjust feedback and training menus based on emotional state.

[1497] The server adjusts the feedback content and the next training menu based on the recognized emotional state. The input is the recognized emotional state, and the output is customized feedback based on the emotion. Specifically, it generates positive feedback for users who feel anxious.

[1498] Step 7:

[1499] The device displays feedback in real time.

[1500] The device receives feedback sent from the server and displays it to the user in real time. The input is feedback data from the server, and the output is a feedback message displayed on the device screen. Specific operations include displaying feedback on the screen as text or animation.

[1501] Step 8:

[1502] The server accumulates the training data and uses the generative AI model to optimize the next training.

[1503] The server stores the user's voice data, feedback content, emotional state, etc. in a database. For the next training session, the generative AI model uses this data to propose the optimal training menu. The input is the accumulated training data, and the output is the next optimized training menu. Specifically, the AI ​​analyzes the accumulated data and designs the training content that is most suitable for the user.

[1504] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1505] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1506] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1507] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1508] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1509] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1510] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1511] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1512] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1513] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1514] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1515] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1516] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1517] 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.

[1518] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1519] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1520] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1521] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1522] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1523] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1524] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1525] The following is further disclosed regarding the above embodiment.

[1526] Below is a proposed draft of the claims for a patent application.

[1527] (Claim 1)

[1528] A system for assisting musical training, comprising:

[1529] a means for a user to select a musical training menu;

[1530] a means for the terminal to capture and transmit the audio to a server in real time;

[1531] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[1532] means for the terminal to display feedback to the user in real time;

[1533] The server stores the training data and uses the generated AI model to optimize the next training.

[1534] A system including:

[1535] (Claim 2)

[1536] 10. The system of claim 1, further comprising means for recording a user's training session for subsequent self-analysis and sharing.

[1537] (Claim 3)

[1538] 2. The system of claim 1, further comprising an initial setting means for adjusting microphone sensitivity and sound reverberation.

[1539] "Example 1"

[1540] (Claim 1)

[1541] a means for a user to select a musical training menu;

[1542] a means for the terminal to capture and transmit audio to a server in real time;

[1543] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[1544] means for the terminal to display feedback to the user in real time;

[1545] The server stores the training data and uses the generated AI model to optimize the next training.

[1546] A means for the user to set up the device and adjust microphone sensitivity and sound reverberation;

[1547] A means to analyze the user's past training data and suggest the optimal training menu;

[1548] A system including:

[1549] (Claim 2)

[1550] 10. The system of claim 1, further comprising means for recording a user's training session for subsequent self-analysis and sharing.

[1551] (Claim 3)

[1552] 10. The system of claim 1, further comprising means for a user to perform a speech test and for the terminal to transmit the speech to a server and display feedback.

[1553] "Application Example 1"

[1554] (Claim 1)

[1555] a means for a user to select a musical training menu;

[1556] A means for the device to capture voice and vibration and transmit them to a server in real time;

[1557] a means for the server to analyze the audio and vibration data and generate feedback regarding pitch, rhythm, and work accuracy based on the analysis results;

[1558] means for the terminal to display feedback to the user in real time;

[1559] The server stores the training and operation data and uses the generated AI model to optimize the next training or operation.

[1560] A system including:

[1561] (Claim 2)

[1562] 10. The system of claim 1, further comprising means for recording a user's training and work sessions for subsequent self-analysis and sharing.

[1563] (Claim 3)

[1564] 2. The system according to claim 1, further comprising an initial setting means for adjusting microphone sensitivity, vibration sensitivity and sound reverberation.

[1565] "Example 2: Combining Emotion Engines"

[1566] (Claim 1)

[1567] a means for a user to select a musical training menu;

[1568] a means for the terminal to capture and transmit the audio to a server in real time;

[1569] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[1570] means for the terminal to display feedback to the user in real time;

[1571] The server stores the training data and uses the generated AI model to optimize the next training.

[1572] a means for the server to recognize the emotional state of the user using the audio data and video data;

[1573] a means for adjusting the feedback content based on the perceived emotional state;

[1574] A system including:

[1575] (Claim 2)

[1576] 10. The system of claim 1, further comprising means for recording a user's training session for subsequent self-analysis and sharing.

[1577] (Claim 3)

[1578] 2. The system of claim 1, further comprising an initial setting means for adjusting microphone sensitivity and sound reverberation.

[1579] "Application example 2 when combining emotion engines"

[1580] Follow the steps to output

[1581] 2. Extract the novel aspects of the technology from the application examples

[1582] In this application example, a distinctive feature of this novel technology is that it performs emotion analysis, personalizes feedback based on that analysis, and provides optimal training content according to the user's emotional state.

[1583] 5. Convert proper nouns, proper names, people's names, and company names into generic names, and convert nouns into superordinate expressions and output them.

[1584] (Claim 1)

[1585] A system for assisting musical training, comprising:

[1586] a means for a user to select a musical training menu;

[1587] a means for the terminal to capture and transmit the audio to a server in real time;

[1588] A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results;

[1589] a means for the server to use the voice data and the user's video data to activate an emotion engine and recognize the user's emotional state;

[1590] a means for adjusting feedback and training programs based on the perceived emotional state;

[1591] means for the terminal to display feedback to the user in real time;

[1592] The server stores the training data and uses the generated AI model to optimize the next training.

[1593] A system including:

[1594] (Claim 2)

[1595] 10. The system of claim 1, further comprising means for recording a user's training session for subsequent self-analysis and sharing.

[1596] (Claim 3)

[1597] 2. The system of claim 1, further comprising an initial setting means for adjusting microphone sensitivity and sound reverberation. [Explanation of symbols]

[1598] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for assisting musical training, comprising: a means for a user to select a musical training menu; a means for the terminal to capture and transmit the audio to a server in real time; A means for the server to analyze the audio data and generate feedback regarding pitch and rhythm based on the analysis results; means for the terminal to display feedback to the user in real time; The server stores the training data and uses the generated AI model to optimize the next training. A system including:

2. 10. The system of claim 1, further comprising means for recording a user's training session for subsequent self-analysis and sharing.

3. 2. The system of claim 1, further comprising an initial setting means for adjusting microphone sensitivity and sound reverberation.

Images