System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting voice data of a user; means for inputting the voice data to a generative artificial intelligence model and analyzing the voice data; means for evaluating a singing skill of the user based on a result of the analysis; means for extracting an optimal voice training plan from a database based on a result of the evaluation; and means for providing the voice training plan to a user terminal.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] Conventional voice training methods are expensive, and it is difficult to find the optimal training method for each individual user. It is also difficult to objectively evaluate an individual's singing ability and find specific ways to improve based on that evaluation. The present invention aims to solve these problems by providing a system that can provide users with high-quality voice training at low cost. [Means for solving the problem]

[0005] The present invention provides a system including means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, and means for providing the voice training plan to a user terminal, thereby enabling users to have their singing ability objectively evaluated and to receive an individually tailored training plan at low cost.

[0006] "Audio data" is digitized sound information recorded from the user's singing or vocalization.

[0007] A "generative artificial intelligence model" is an algorithm trained to analyze voice data using machine learning and deep learning.

[0008] "Analysis" is the process of using a generative artificial intelligence model to evaluate the characteristics of audio data and extract elements such as pitch, rhythm, pronunciation, and emotional expression.

[0009] "Evaluation" refers to the act of expressing the user's singing ability in the form of a score or comments based on the analysis results.

[0010] The "database" is a collection of information that stores past data on improving singing ability and training methods.

[0011] A "voice training plan" is a teaching plan that includes specific practice methods and areas for improvement to improve the user's singing ability.

[0012] A "user terminal" is a device, such as a smartphone or tablet, that a user uses to operate the voice training system.

[0013] "Providing" means sending the generated voice training plan to the user's device so that the user can view and practice it. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate an individual's singing ability and provide an optimal voice training plan.

[0036] Collecting user voice data

[0037] Users record their singing through a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device then stores the audio data in its local storage.

[0038] Sending and analyzing voice data

[0039] The device then sends the recorded voice data over the internet to a server. The server receives the voice data and inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0040] Singing ability evaluation

[0041] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "unstable pitch and weak sense of rhythm." The server saves the evaluation results and uses them in the next step.

[0042] Extract and generate the best voice training plan

[0043] The server references the evaluation results and extracts the optimal vocal training plan from a database of past training. The selected training plan is tailored to the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0044] Training plan distribution and implementation

[0045] The generated training plan is sent from the server to the device. The device displays the received training plan within the app so that the user can view it. The user can then begin practicing according to the training plan.

[0046] Specific examples

[0047] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data to the server, which analyzes it. The analysis results in an evaluation that "your pitch is somewhat unstable and your rhythm tends to lag." Based on this evaluation, the server generates a training plan that includes pitch practice and rhythm strengthening exercises and sends it to the device. By following this plan and starting to practice, User A can effectively improve their singing ability.

[0048] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan at low cost.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0052] Step 2:

[0053] The user presses the record button. The device activates the microphone and starts collecting audio data. The user starts singing.

[0054] Step 3:

[0055] When the user finishes singing, they press the stop button, and the device stops recording and saves the audio file to local storage.

[0056] Step 4:

[0057] The device sends the recorded voice data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data.

[0058] Step 5:

[0059] The server receives the voice data and inputs it into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0060] Step 6:

[0061] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0062] Step 7:

[0063] The server evaluates the user's singing ability based on the analysis results, and the evaluation is in the form of a score and comments, indicating specific weaknesses and strengths.

[0064] Step 8:

[0065] Based on the evaluation results, the server extracts the optimal voice training plan from the database, and selects a training plan tailored to the user's specific weaknesses.

[0066] Step 9:

[0067] The server then customizes the training plan for the user, including adding specific exercises and improvements.

[0068] Step 10:

[0069] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0070] Step 11:

[0071] Users can review the training plan and follow the instructions to begin practicing, which includes videos, audio guides, and exercises.

[0072] Step 12:

[0073] After a certain period of training, the user records again to check their progress, and the device sends the new recording to the server for re-evaluation.

[0074] By proceeding step by step in this way, the user can effectively improve their singing ability. The specific operations at each step demonstrate that the entire system functions smoothly.

[0075] Example 1

[0076] 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."

[0077] Conventional singing ability evaluation systems have had the problem of being difficult to accurately evaluate a user's singing ability and provide an individually customized vocal training plan. Furthermore, the means for efficiently providing evaluation results and training plans to users are limited, leaving users with a lack of effective ways to improve their weaknesses. This has led to the problem that it is difficult for users to effectively improve their singing ability in a short period of time.

[0078] 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.

[0079] In this invention, the server includes a means for uploading a user's voice data to the server, a means for inputting the data into a generative artificial intelligence model for analysis, a means for extracting an optimal vocal training plan from a database based on the evaluation results, and a means for customizing the training plan to suit the user's specific weaknesses. This makes it possible to accurately evaluate a user's singing ability and provide an optimal vocal training plan that addresses each weakness. Furthermore, the training plan includes specific practice methods and areas for improvement and is delivered to the user's terminal using an encrypted protocol, allowing the user to train safely and efficiently.

[0080] "User voice data" refers to recorded voice data collected by a user using a dedicated device.

[0081] A "generative artificial intelligence model" is an artificial intelligence model that learns from large amounts of data and performs appropriate processing and analysis on given input data.

[0082] A "server" is a central computer system that stores, processes, and distributes data to other devices over a network.

[0083] The "evaluation means" is a means for evaluating the user's singing ability in the form of numerical values ​​or comments based on data analyzed by the generative artificial intelligence model.

[0084] A "database" is a system configured to efficiently manage, store, and search large amounts of data.

[0085] A "voice training plan" is a plan that specifies practice methods and training steps designed to improve a user's singing ability.

[0086] The "customization means" is a means for individually adjusting the optimal training plan based on the user's evaluation results, and changing the plan to suit the user's specific weaknesses and needs.

[0087] An "encrypted protocol" is a communication method used to protect the contents of data when it is sent and received, and is a technology that prevents third parties from reading the contents.

[0088] A "user terminal" is a device that can be directly operated by a user, such as a smartphone or tablet.

[0089] The "practice method" indicates the specific practice content and procedures that the user should follow in order to improve their singing ability.

[0090] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate a user's singing ability and provide an individually customized vocal training plan. The following describes specific embodiments of the invention.

[0091] Collecting user voice data

[0092] The user launches a dedicated application on a device such as a smartphone or tablet. The application displays an interface for recording audio. The user presses the record button to start singing and the stop button to end recording. The device saves the recorded audio data in local storage. This temporarily saves the audio data.

[0093] Sending and analyzing voice data

[0094] The device uploads the saved voice data to a server via the internet. The data is securely transmitted using an encrypted protocol (e.g., HTTPS). The server receives the voice data and inputs it into a generative AI model (e.g., OpenAI's GPT-3, Google's BERT, etc.). The generative AI model analyzes the voice data and extracts features such as pitch, rhythm, pronunciation, and emotional expression. The analysis results are returned to the server.

[0095] Singing ability evaluation

[0096] The server evaluates the user's singing ability based on the data analyzed by the generative AI model. The evaluation is provided in the form of a number (e.g., 0-100 points) or a comment. For example, the evaluation result may be displayed as "unstable pitch and weak sense of rhythm." The server then stores the evaluation results in a database.

[0097] Extract and generate the best voice training plan

[0098] The server then references the evaluation results and extracts the optimal vocal training plan from its database. The training plan addresses the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes the plan and generates it in a format (e.g., PDF or video) that includes specific practice methods and areas for improvement.

[0099] Training plan distribution and implementation

[0100] The server sends the generated training plan to the device. The plan is sent using an encrypted protocol, ensuring secure data delivery. The device displays the training plan within the app so that the user can review it. The user then begins practicing according to the plan. The application displays a metronome and pitch guide, allowing the user to practice according to the appropriate guide.

[0101] Specific examples

[0102] For example, User A starts the application and records a passage from "Let It Be." The device uploads the recorded audio data to the server, which analyzes it using a generative AI model. The analysis results indicate that "the pitch is somewhat unstable and the rhythm tends to lag." Based on this evaluation, the server generates a training plan including pitch practice and rhythm strengthening exercises and sends it to the device. User A follows this plan and begins practicing using the metronome and pitch guide provided within the app.

[0103] Prompt Sentence Examples

[0104] Analyze the user's singing voice data and evaluate it based on pitch, rhythm, pronunciation, and emotional expression. Also, propose the optimal vocal training plan based on the evaluation results.

[0105] In this way, the system accurately evaluates the user's singing ability and provides an optimal, individually tailored vocal training plan, enabling the user to effectively improve their singing ability in a short period of time.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] The user launches the application and moves to the recording screen. The application displays the recording interface, and the user presses the record button to begin singing. The input is the user's singing voice, and the device records that voice and collects audio data from the time the record button is pressed to the time the stop button is pressed. The output is the recorded audio data, which is saved in the device's local storage. Specifically, the audio signal is input to the device through the microphone and saved as digital data.

[0109] Step 2:

[0110] The device uploads the recorded audio data to the server via the Internet. The input is the recorded audio data, and the output is the data sent to the server. This involves encrypting the data (e.g., using SSL / TLS) and sending it. Specifically, the device sends the audio data via the network to the server's API endpoint using the POST method.

[0111] Step 3:

[0112] The server inputs the received voice data into a generative artificial intelligence model. The input is voice data, which the AI ​​model analyzes. The output is the analysis results for pitch, rhythm, pronunciation, emotional expression, etc. The server sends prompt sentences to the model to analyze these characteristics. Specifically, the voice data is passed to the input layer of the AI ​​model, where it undergoes computational processing and characteristic data is output.

[0113] Step 4:

[0114] The server evaluates the user's singing ability based on the analysis results of the generated AI model. The evaluation includes pitch accuracy, rhythmic stability, and pronunciation clarity. The input is the analysis results, and the output is the user's singing ability evaluation score and feedback in the form of comments. Specifically, the evaluation algorithm converts the characteristic data into a numerical score and generates feedback based on that score.

[0115] Step 5:

[0116] The server references the evaluation results and extracts the optimal voice training plan from the database. The input is the user's evaluation results, and the output is the optimal training plan. The server takes into account past training data and evaluation results to select a plan tailored to specific weaknesses (e.g., improving pitch stability or rhythmic sense). Specifically, it issues a query to the database and extracts relevant training data.

[0117] Step 6:

[0118] The server further customizes the selected training plan. The input is the extracted training plan and the user's evaluation results, and the output is a customized training plan. Specifically, the training content is adjusted and modified based on the evaluation results, and a training plan tailored to the user is created.

[0119] Step 7:

[0120] The server sends a customized voice training plan to the user's device. The input is the customized training plan, and the output is the data sent to the device. The transmission uses an encrypted protocol. Specifically, the server sends data to the device using an authentication token.

[0121] Step 8:

[0122] The voice training plan received by the device is displayed within the app. The input is the training plan sent from the server, and the output is the display content that the user can visually confirm. Specifically, the application constructs an interface based on the data acquired and presents the user with appropriate practice methods.

[0123] Step 9:

[0124] The user begins practicing according to the training plan. The input is the training plan displayed in the application, and the output is the practice results and feedback. Specifically, the user uses the metronome and pitch guide within the application to perform the instructed practice. The user's practice data is used in the subsequent evaluation process.

[0125] (Application example 1)

[0126] 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."

[0127] Traditional voice training often requires individual instruction from a professional instructor, which entails high costs and time constraints. While online instruction is becoming more common, few systems exist that provide detailed evaluations tailored to individual singing abilities or generate and provide appropriate training plans. Furthermore, there is a lack of systems that automatically collect and analyze users' singing data and provide effective training plans based on the results, making it difficult for users to efficiently improve their singing abilities.

[0128] 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.

[0129] In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for transmitting the voice data to the server via the Internet, means for customizing the training plan based on the user's singing ability evaluation results, and means for displaying the generated training plan on the user terminal. This allows users to receive training plans to efficiently improve their singing ability at home or elsewhere without relying on professional instructors.

[0130] "User" refers to an individual who uses the system to provide voice data and whose singing ability is evaluated.

[0131] "Audio Data" refers to a digital audio file of a user's singing recording.

[0132] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes input data and generates the analysis results.

[0133] "Analysis results" refers to evaluation information resulting from analyzing voice data using a generative artificial intelligence model.

[0134] "Singing ability" refers to the user's singing abilities, such as pitch, rhythm, pronunciation, and emotional expression.

[0135] A "database" refers to a collection of information that stores past training data and evaluation data.

[0136] A "voice training plan" refers to a plan that includes specific practice content and improvement methods created to improve a user's singing ability.

[0137] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0138] "Server" refers to a computer system used to analyze audio data and generate training plans.

[0139] "Customization" refers to individualizing a training plan based on a user's specific needs and assessment results.

[0140] "Internet" refers to the global network used to transmit audio data to servers.

[0141] About the system program

[0142] Hardware and software used

[0143] This system is implemented using the following hardware and software.

[0144] Hardware: Smartphones, personal computers, servers

[0145] Software: Flask (web server framework), Pytorch or Tensorflow (for building and training AI models), Requests (for handling HTTP requests)

[0146] Natural language description of the process

[0147] 1. Collecting user voice data

[0148] The user records any singing using a smartphone or personal computer.

[0149] For example, 30 seconds of singing is recorded as a digital audio file and saved to local storage.

[0150] 2. Transmission of data to a server over the Internet

[0151] The device uploads the recorded audio data to a server via the Internet as an HTTP POST request.

[0152] Send data using the Requests library.

[0153] 3. Analysis of audio data

[0154] The server inputs the received voice data into a generative artificial intelligence model and analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0155] This is done by an AI model using Pytorch or Tensorflow.

[0156] 4. Singing ability evaluation

[0157] The server evaluates the user's singing ability based on the analysis results of the generative AI model. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag."

[0158] 5. Extract and generate a voice training plan

[0159] Based on the evaluation results, the server extracts and generates an optimal voice training plan from the database tailored to the user's specific weaknesses.

[0160] It references a database of past training sessions and generates a customized training plan for each user.

[0161] 6. Delivering and implementing training plans

[0162] The generated training plan is sent from the server to the user's device, which then displays the received training plan in the application, allowing the user to view and practice it.

[0163] Specific examples

[0164] For example, User A records a passage of "Let It Be" using a smartphone. User A presses the record button on the device and completes singing for 30 seconds. The device then sends the recorded audio data to the server, which analyzes it. The generative AI model analyzes pitch, rhythm, pronunciation, and emotional expression, and evaluates the result as "slightly unstable pitch and prone to delays in rhythm." Based on this evaluation, the server generates a customized training plan including pitch practice and rhythm strengthening exercises and sends it to the user's device. User A can effectively improve their singing ability by checking and practicing the training plan on their smartphone.

[0165] Prompt Sentence Examples

[0166] An example of a prompt for a generative AI model is:

[0167] "Please analyze user A's singing recording. Evaluate pitch, rhythm, pronunciation, and emotional expression, and provide a score. Generate an optimal training plan based on the evaluation results."

[0168] This makes it possible for the system to provide training plans that allow users to efficiently improve their singing ability at home, without relying on professional instructors.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] Users collect audio data using a smartphone or personal computer. Specifically, they press the record button on the application and sing a song of their choice. When recording is complete, they press the stop button and save the recorded data to local storage. The input is the user's singing voice, and the output is a digital audio file (e.g., user_recording.wav).

[0172] Step 2:

[0173] The device uploads recorded audio data to the server. The user device sends the recorded audio file to the server as an HTTP POST request. The input is a digital audio file, and the output is the audio data received by the server. The specific operation is to use the Requests library to send the data.

[0174] Step 3:

[0175] The server inputs the received audio data into a generative AI model for analysis. The input is the received audio data, and the output is the analysis results. The AI ​​model uses Pytorch or Tensorflow to analyze the audio data to analyze features such as pitch, rhythm, pronunciation, and emotional expression.

[0176] Step 4:

[0177] The server evaluates the user's singing ability based on the analysis results. The input is the analysis results obtained from the generative AI model, and the output is an evaluation score and comments on the user's singing ability. The evaluation results are expressed in concrete terms, such as "your pitch is a little unstable and your rhythm tends to lag."

[0178] Step 5:

[0179] The server extracts and generates the optimal vocal training plan from the database based on the evaluation results. The input is the singing ability evaluation score and comments, and the output is a customized vocal training plan. Specifically, it references the past training database and selects training methods that address the user's specific weaknesses.

[0180] Step 6:

[0181] The server sends the generated training plan to the user terminal. The input is the generated voice training plan, and the output is the training plan delivered to the user terminal. Specifically, the training plan is sent to the user terminal using an HTTP request.

[0182] Step 7:

[0183] The training plan received by the user's device is displayed within the application, allowing the user to view and practice. The input is the received voice training plan, and the output is the display of the training plan on the application. Specifically, the contents of the plan are displayed on the application UI, and the user begins practicing according to them.

[0184] This allows users to receive training plans to improve their singing ability efficiently at home, etc., without relying on professional instructors.

[0185] 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.

[0186] This invention relates to a system that combines voice recognition technology, a generative artificial intelligence model, and an emotion engine to evaluate the singing ability of each user and provide an optimal voice training plan.

[0187] User voice data collection and emotion recognition

[0188] Users record themselves singing using a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device saves this audio data in local storage and uses an emotion engine to analyze the user's emotions during recording.

[0189] Transmission and analysis of voice and emotion data

[0190] The device then sends the recorded voice data and the emotional data analyzed by the emotion engine to a server via the internet. The server receives the voice data and emotional data and inputs them into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0191] Singing ability evaluation

[0192] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The evaluation is then corrected based on the emotion recognition results. For example, if the user is emotionally unstable or nervous, this effect can be reflected in the singing ability evaluation, providing more accurate feedback.

[0193] Extract and generate the best voice training plan

[0194] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotion recognition results. The selected training plan addresses the user's specific weaknesses (e.g., improving pitch stability, strengthening rhythmic sense) as well as their emotional state (relaxation, improving concentration). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0195] Training plan distribution and implementation

[0196] The generated training plan is sent from the server to the device. The device displays the received training plan within the app for the user to view. The user then begins practicing according to the training plan. The plan includes video and audio guides, practice tasks, as well as advice and exercises tailored to the user's emotional state.

[0197] Specific examples

[0198] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data, along with the emotional data analyzed by the emotion engine during recording, to the server. The server analyzes the data and determines that the user's pitch is somewhat unstable and the rhythm tends to lag behind, and that the emotional analysis indicates a high level of tension. Based on these results, the server generates a training plan that includes pitch practice, rhythm strengthening exercises, and relaxation exercises, and sends it to the device. User A can start practicing according to this plan and effectively improve their singing ability by practicing the relaxation exercises suggested during practice.

[0199] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan that takes into account the user's emotional state at low cost.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0203] Step 2:

[0204] The user presses the record button. The device activates the microphone and starts collecting voice data. At the same time, the emotion engine also activates and begins analyzing the user's emotional state.

[0205] Step 3:

[0206] When the user finishes singing, they press the stop button. The device stops recording and saves the audio file in local storage. The emotion engine also finishes analyzing the data and saves the emotion data.

[0207] Step 4:

[0208] The device transmits the recorded voice data and emotion data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data and emotion data.

[0209] Step 5:

[0210] The server receives the voice data and emotion data and inputs them into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0211] Step 6:

[0212] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0213] Step 7:

[0214] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and you tend to be behind the rhythm." The evaluation is corrected based on the analysis results of the emotion engine. For example, it may include feedback such as "Your pitch became more unstable because you were nervous."

[0215] Step 8:

[0216] The server extracts the optimal voice training plan from the database based on the evaluation results and emotion recognition results. The server selects a training plan that takes into account the user's specific weaknesses as well as their emotional state.

[0217] Step 9:

[0218] The server then customizes the training plan for the user, including specific practice methods and areas for improvement, as well as exercises that address emotional states.

[0219] Step 10:

[0220] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0221] Step 11:

[0222] Users can view and follow the instructions for their training plan, which includes video and audio guides, practice exercises, and advice and exercises tailored to the user's emotional state.

[0223] Step 12:

[0224] After a certain period of training, the user records again to check their progress, and the device sends the new recording and emotional data to the server for re-evaluation.

[0225] In this way, through detailed processing steps, users can objectively evaluate their singing ability and receive a training plan that takes into account their emotional state. Through the specific operations of each step, it can be seen that the entire system functions smoothly.

[0226] Example 2

[0227] 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."

[0228] Conventional voice data analysis systems do not take into account a user's emotional state when evaluating their singing ability, resulting in poor evaluation accuracy and making it difficult to provide an individually customized training plan based on the user's specific weaknesses and emotional state.

[0229] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results and the user's emotional data, means for extracting an optimal voice training plan from a database based on the evaluation results and the emotional data, and means for providing the voice training plan to the user terminal. This enables accurate evaluation of singing ability taking into account the user's emotional state and provides an individually customized training plan.

[0230] "User's voice data" refers to data that represents voice information such as singing or conversation recorded by a user in digital format.

[0231] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that learns from large amounts of data and analyzes and predicts new data.

[0232] "Analysis" is the process of analyzing features and patterns based on input data and extracting the results.

[0233] "User emotion data" is data that analyzes the emotional state of the user while recording the voice and expresses it as numerical values ​​or categories.

[0234] "Evaluating singing ability" means evaluating elements of the user's singing, such as pitch, rhythm, pronunciation, and emotional expression, as scores or comments.

[0235] A "database" is a system for efficiently storing, managing, and searching data, or a collection of accumulated information.

[0236] A "voice training plan" is a written plan that includes practice methods, exercises, and improvements designed to improve a user's singing ability.

[0237] A "user terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0238] This invention relates to a system that combines voice recognition technology, a generative AI model, and an emotion engine to evaluate the singing ability of individual users and provide an optimal vocal training plan. This system collects the user's voice data, analyzes it using a generative AI model, and provides an evaluation and training plan based on the results.

[0239] User voice data collection and emotion recognition

[0240] The user launches the dedicated application, and the recording interface appears on the device. The user presses the record button and sings, recording the audio data. After recording is complete, the device saves the audio data in local storage. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and extract emotion data.

[0241] Transmission and analysis of voice and emotion data

[0242] The device sends the stored voice and emotion data to a server via the internet. When the server receives this data, it inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the results to the server.

[0243] Singing ability evaluation

[0244] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, and the evaluation is also corrected by taking into account the emotion recognition results. For example, if the emotional state is "nervous," this influence is reflected in the evaluation and detailed feedback is provided.

[0245] Generate and deliver optimal voice training plans

[0246] The server extracts an optimal vocal training plan from the database based on the evaluation results and emotional data. This plan addresses the user's specific weaknesses and emotional state. A customized training plan including specific practice methods, areas for improvement, and exercises is generated and sent to the device.

[0247] Implementing your training plan

[0248] The device receives a training plan, which is then displayed in the app for the user to view. The user can then begin practicing according to the plan and periodically check their progress. The plan may include video and audio guides, practice assignments, relaxation exercises, and more.

[0249] Specific examples

[0250] For example, User A launches the app and records a passage from "Let It Be." The device sends the audio data and emotional data indicating "high tension" to the server. The server then analyzes the audio data using a generative AI model and produces an evaluation result indicating "your pitch is somewhat unstable and your rhythm tends to lag." It then corrects the evaluation based on the emotional data and provides specific feedback. The server then generates a training plan that includes improving pitch stability, strengthening your sense of rhythm, and relaxation exercises, and sends it to the device. User A follows this plan and begins practicing, including the suggested relaxation exercises.

[0251] Examples of prompt statements

[0252] Below are some example prompts to input to a generative AI model:

[0253] 1. "Write a script that analyzes a user's voice data and evaluates their singing ability. Evaluation criteria should include pitch, rhythm, pronunciation, and emotional expression."

[0254] 2. "Based on the emotion recognition results, please design an algorithm to correct the singing ability evaluation and create a program that outputs the results in the form of a score and comments."

[0255] In this way, the present invention realizes a system that provides an objective evaluation of singing ability that also takes into account the user's emotional state, and an individualized training plan at low cost.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1:

[0258] The user launches the dedicated app and the recording interface appears on the device. The user taps the record button and starts singing. When the user finishes recording, the device saves the audio data to local storage. At the same time, the device uses an emotion engine to analyze the user's emotional state and extract emotion data.

[0259] Input: User's singing voice

[0260] Output: Audio data (recorded file) and emotion data (analysis results)

[0261] Step 2:

[0262] The device transmits the stored voice data and emotion data to a server via the Internet, which receives the data and stores it in a database.

[0263] Input: Voice data, emotion data

[0264] Output: Storage of voice data and emotion data on the server

[0265] Step 3:

[0266] The server inputs the audio data into a generative AI model. The AI ​​model analyzes pitch, rhythm, pronunciation, emotional expression, and other factors to extract various characteristics. For example, it evaluates the stability of pitch and the accuracy of rhythm. At the same time, emotional data is also analyzed, resulting in a comprehensive analysis result.

[0267] Input: Voice data, emotion data

[0268] Output: Analysis results (pitch, rhythm, pronunciation, emotional expression)

[0269] Step 4:

[0270] The server evaluates the user's singing ability based on the analysis results. The evaluation is displayed in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The server then corrects the emotion recognition results and generates detailed feedback.

[0271] Input: Analysis results (pitch, rhythm, pronunciation, emotional expression), emotional data

[0272] Output: Evaluation results (score, comments)

[0273] Step 5:

[0274] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotional data. This plan includes improving pitch stability, strengthening rhythmic sense, and relaxation exercises. The plan is customized for each user, and specific practice methods are provided.

[0275] Input: Evaluation results, emotion data

[0276] Output: Voice Training Plan (Customized Plan)

[0277] Step 6:

[0278] The server sends the generated voice training plan to the device. The device receives the plan and displays it within the app. The user begins practicing according to the plan, and the app records the practice progress.

[0279] Enter: Voice Training Plan

[0280] Output: Plan display and practice record to user

[0281] In this way, the user, the terminal, and the server cooperate to carry out the process at each step, thereby providing an accurate singing ability evaluation and an individualized training plan that takes into account the user's emotional state.

[0282] (Application example 2)

[0283] 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."

[0284] While conventional vocal training systems provide technical evaluations of pitch and rhythm, they struggle to provide feedback and training plans that take the user's emotional state into account. As a result, users often practice singing while experiencing emotional issues such as tension or anxiety, resulting in ineffective training. Furthermore, there has been a lack of methods for accurately evaluating a user's singing ability and providing a customized training plan tailored to their individual needs.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0286] In this invention, the server includes means for collecting a user's voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for analyzing the user's emotional state, means for reflecting the emotional state in the evaluation results, means for generating a training plan according to the user's emotional state, means for uploading the voice data and emotional state data to the server, and means for including specific practice methods and areas for improvement in the voice training plan, as well as exercises according to the user's emotional state. This enables more effective and customized voice training that takes into account not only the user's technical ability but also their emotional state.

[0287] "Audio data" is digital data that includes audio signals such as singing recorded by a user.

[0288] A "generative artificial intelligence model" is a system that includes an artificial intelligence algorithm that analyzes audio data as input and evaluates characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0289] The "evaluation results" are data including scores and comments on the user's singing ability analyzed by the generative artificial intelligence model, as well as an evaluation of the user's emotional state.

[0290] A "voice training plan" is a teaching program that includes specific practice methods, areas for improvement, and exercises to improve the user's singing ability.

[0291] "Emotional state" is data that indicates the psychological state, such as tension, anxiety, or relaxation, that the user feels while singing.

[0292] "Means for analyzing" refers to methods and apparatus that use generative artificial intelligence models to evaluate audio data and emotional states.

[0293] The "means for extracting" refers to a method and apparatus for extracting an optimal voice training plan from a database based on the user's evaluation results.

[0294] The "means for providing" refers to a method and device for displaying and distributing the extracted voice training plan on the user's terminal.

[0295] "Uploading means" refers to a method and apparatus for transmitting a user's voice data and emotional state data to a server over the Internet.

[0296] The "means for analyzing emotional state" refers to a method and device for analyzing the psychological state of a user from the user's voice data and facial expression data.

[0297] The "reflecting means" refers to a method and device for incorporating the analyzed emotional state into the evaluation of the user's singing ability.

[0298] The "means for generating" refers to a method and apparatus for creating a customized training plan for a user based on the assessment results and emotional state.

[0299] The present invention is a system for users to evaluate their singing ability and provide a personalized vocal training plan. The system collects the user's voice data and emotional state data, and generates personalized feedback and training plans based on the analysis results.

[0300] System Configuration

[0301] The system consists of the following main components:

[0302] 1. User Device

[0303] The user terminals are smartphones and head-mounted displays, which are devices that allow users to record their singing and capture their emotional state.

[0304] It provides an audio recording interface and stores the recording data in local storage.

[0305] An emotion engine is used to analyze the user's emotional state.

[0306] 2. Server

[0307] The system receives voice data and emotion data and analyzes them using a generative AI model, such as Python, pydub, EmotionEngine, and SingingEvaluation.

[0308] The system evaluates the user's singing ability and extracts and generates a voice training plan from a database based on the evaluation results.

[0309] This training plan includes specific drills, areas for improvement, and even exercises tailored to your emotional state.

[0310] 3. Network Infrastructure

[0311] It supports data communication between the user device and the server. Voice data and emotion data are uploaded to the server via an internet connection, and analysis results and training plans are sent to the user device.

[0312] Data collection and analysis

[0313] 1. Collection of audio data

[0314] The user uses the application to record themselves singing. Once the recording is complete, the audio data is saved to local storage. At that time, the emotion engine analyzes the user's emotional state, and the emotional data is also saved.

[0315] 2. Data transmission

[0316] The recorded voice data and emotion data are sent to the server via the network, where the server receives the data and begins analyzing it.

[0317] 3. Data Analysis

[0318] The server uses a generative AI model to analyze the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The results of the emotion analysis performed by the emotion engine are also taken into account in the evaluation.

[0319] Creation and delivery of training plans

[0320] Based on the analysis results, the server evaluates the user's singing ability and extracts an optimal vocal training plan from the database based on the evaluation. The training plan includes exercises that address the user's specific weaknesses (e.g., pitch, rhythm) and emotional state (relaxation, concentration).

[0321] The generated training plan is sent from the server to the user's device and displayed within the app. The user can then begin practicing according to the plan and monitor their progress within the application.

[0322] Specific examples

[0323] For example, a user launches the app and records a passage from a "famous song." The recording is made through the smartphone's microphone, while the camera in the head-mounted display captures the user's facial expressions and analyzes their emotional state. Once the recording is complete, the audio data and emotional data are sent to the server. The server analyzes this data and provides a detailed evaluation of pitch and rhythm, as well as the emotional state the user felt while singing. A training plan is automatically generated based on the results and sent to the user's device. The user can view the generated plan and begin practicing.

[0324] Example of input prompt for generative AI model

[0325] The following prompt sentences are used to provide examples of input to a generative artificial intelligence model:

[0326] "Based on the following audio data and its emotional analysis results, please evaluate the user's singing ability and generate the optimal vocal training plan.

[0327] Audio data: (attached audio file)

[0328] Emotion analysis results: "Emotion: Tension, Confidence: 0.85"

[0329] Expected output: Evaluation of pitch, rhythm, pronunciation, and emotional expression, and a training plan based on the evaluation. For example, specific practice methods to improve the causes of pitch instability and suggestions for relaxation exercises to reduce tension.

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] The user starts the application using a smartphone or a head-mounted display and records their singing.

[0333] Input: User's voice and facial expression data

[0334] Specific operation: The user presses the record button, finishes singing, and then presses the stop button. The application saves the voice data and facial expression data to local storage.

[0335] Step 2:

[0336] The device sends the recorded voice data and the emotion data analyzed by the emotion engine to the server.

[0337] Input: Voice and emotion data in local storage

[0338] Specific operation: The application uploads voice data and emotion data to a server via an internet connection.

[0339] Step 3:

[0340] The server inputs the received voice data and emotion data into a generative artificial intelligence model for analysis.

[0341] Input: Voice data and emotion data uploaded to the server

[0342] Specific operation: Run the script and input data into a generative artificial intelligence model (e.g., Python and pydub, EmotionEngine, SingingEvaluation) for analysis.

[0343] Step 4:

[0344] The server generates analysis results and evaluates the user's singing ability.

[0345] Input: Analysis results from a generative artificial intelligence model

[0346] Output: A detailed assessment of the user's pitch, rhythm, pronunciation, and emotional expression.

[0347] Specific operation: Based on the analysis results, an evaluation is generated in the form of a score and comments, and the emotional state is also reflected along with the evaluation.

[0348] Step 5:

[0349] Based on the evaluation results, the server extracts the optimal voice training plan from the database and customizes and generates it.

[0350] Input: User evaluation results and emotion data

[0351] Output: Personalized voice training plan

[0352] Specific operation: Extract appropriate practice methods and exercises from the database and generate an optimal plan based on the user's evaluation results and emotional state.

[0353] Step 6:

[0354] The server transmits the generated voice training plan to the user terminal.

[0355] Enter: a customized voice training plan.

[0356] Output: Sending the training plan to the user's device

[0357] Specific operation: The server sends the training plan to the user's device via the Internet, where it is displayed within the application.

[0358] Step 7:

[0359] The user follows the voice training plan sent to them and begins practicing.

[0360] Input: Training plan displayed on user's device

[0361] What it does: The user follows a training plan within the app, practicing with audio guidance and videos, and the app provides feedback on their progress and emotional state during practice.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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."

[0378] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate an individual's singing ability and provide an optimal voice training plan.

[0379] Collecting user voice data

[0380] Users record their singing through a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device then stores the audio data in its local storage.

[0381] Sending and analyzing voice data

[0382] The device then sends the recorded voice data over the internet to a server. The server receives the voice data and inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0383] Singing ability evaluation

[0384] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "unstable pitch and weak sense of rhythm." The server saves the evaluation results and uses them in the next step.

[0385] Extract and generate the best voice training plan

[0386] The server references the evaluation results and extracts the optimal vocal training plan from a database of past training. The selected training plan is tailored to the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0387] Training plan distribution and implementation

[0388] The generated training plan is sent from the server to the device. The device displays the received training plan within the app so that the user can view it. The user can then begin practicing according to the training plan.

[0389] Specific examples

[0390] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data to the server, which analyzes it. The analysis results in an evaluation that "your pitch is somewhat unstable and your rhythm tends to lag." Based on this evaluation, the server generates a training plan that includes pitch practice and rhythm strengthening exercises and sends it to the device. By following this plan and starting to practice, User A can effectively improve their singing ability.

[0391] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan at low cost.

[0392] The processing flow will be explained below.

[0393] Step 1:

[0394] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0395] Step 2:

[0396] The user presses the record button. The device activates the microphone and starts collecting audio data. The user starts singing.

[0397] Step 3:

[0398] When the user finishes singing, they press the stop button, and the device stops recording and saves the audio file to local storage.

[0399] Step 4:

[0400] The device sends the recorded voice data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data.

[0401] Step 5:

[0402] The server receives the voice data and inputs it into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0403] Step 6:

[0404] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0405] Step 7:

[0406] The server evaluates the user's singing ability based on the analysis results, and the evaluation is in the form of a score and comments, indicating specific weaknesses and strengths.

[0407] Step 8:

[0408] Based on the evaluation results, the server extracts the optimal voice training plan from the database, and selects a training plan tailored to the user's specific weaknesses.

[0409] Step 9:

[0410] The server then customizes the training plan for the user, including adding specific exercises and improvements.

[0411] Step 10:

[0412] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0413] Step 11:

[0414] Users can review the training plan and follow the instructions to begin practicing, which includes videos, audio guides, and exercises.

[0415] Step 12:

[0416] After a certain period of training, the user records again to check their progress, and the device sends the new recording to the server for re-evaluation.

[0417] By proceeding step by step in this way, the user can effectively improve their singing ability. The specific operations at each step demonstrate that the entire system functions smoothly.

[0418] Example 1

[0419] 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."

[0420] Conventional singing ability evaluation systems have had the problem of being difficult to accurately evaluate a user's singing ability and provide an individually customized vocal training plan. Furthermore, the means for efficiently providing evaluation results and training plans to users are limited, leaving users with a lack of effective ways to improve their weaknesses. This has led to the problem that it is difficult for users to effectively improve their singing ability in a short period of time.

[0421] 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.

[0422] In this invention, the server includes a means for uploading a user's voice data to the server, a means for inputting the data into a generative artificial intelligence model for analysis, a means for extracting an optimal vocal training plan from a database based on the evaluation results, and a means for customizing the training plan to suit the user's specific weaknesses. This makes it possible to accurately evaluate a user's singing ability and provide an optimal vocal training plan that addresses each weakness. Furthermore, the training plan includes specific practice methods and areas for improvement and is delivered to the user's terminal using an encrypted protocol, allowing the user to train safely and efficiently.

[0423] "User voice data" refers to recorded voice data collected by a user using a dedicated device.

[0424] A "generative artificial intelligence model" is an artificial intelligence model that learns from large amounts of data and performs appropriate processing and analysis on given input data.

[0425] A "server" is a central computer system that stores, processes, and distributes data to other devices over a network.

[0426] The "evaluation means" is a means for evaluating the user's singing ability in the form of numerical values ​​or comments based on data analyzed by the generative artificial intelligence model.

[0427] A "database" is a system configured to efficiently manage, store, and search large amounts of data.

[0428] A "voice training plan" is a plan that specifies practice methods and training steps designed to improve a user's singing ability.

[0429] The "customization means" is a means for individually adjusting the optimal training plan based on the user's evaluation results, and changing the plan to suit the user's specific weaknesses and needs.

[0430] An "encrypted protocol" is a communication method used to protect the contents of data when it is sent and received, and is a technology that prevents third parties from reading the contents.

[0431] A "user terminal" is a device that can be directly operated by a user, such as a smartphone or tablet.

[0432] The "practice method" indicates the specific practice content and procedures that the user should follow in order to improve their singing ability.

[0433] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate a user's singing ability and provide an individually customized vocal training plan. The following describes specific embodiments of the invention.

[0434] Collecting user voice data

[0435] The user launches a dedicated application on a device such as a smartphone or tablet. The application displays an interface for recording audio. The user presses the record button to start singing and the stop button to end recording. The device saves the recorded audio data in local storage. This temporarily saves the audio data.

[0436] Sending and analyzing voice data

[0437] The device uploads the saved voice data to a server via the internet. The data is securely transmitted using an encrypted protocol (e.g., HTTPS). The server receives the voice data and inputs it into a generative AI model (e.g., OpenAI's GPT-3, Google's BERT, etc.). The generative AI model analyzes the voice data and extracts features such as pitch, rhythm, pronunciation, and emotional expression. The analysis results are returned to the server.

[0438] Singing ability evaluation

[0439] The server evaluates the user's singing ability based on the data analyzed by the generative AI model. The evaluation is provided in the form of a number (e.g., 0-100 points) or a comment. For example, the evaluation result may be displayed as "unstable pitch and weak sense of rhythm." The server then stores the evaluation results in a database.

[0440] Extract and generate the best voice training plan

[0441] The server then references the evaluation results and extracts the optimal vocal training plan from its database. The training plan addresses the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes the plan and generates it in a format (e.g., PDF or video) that includes specific practice methods and areas for improvement.

[0442] Training plan distribution and implementation

[0443] The server sends the generated training plan to the device. The plan is sent using an encrypted protocol, ensuring secure data delivery. The device displays the training plan within the app so that the user can review it. The user then begins practicing according to the plan. The application displays a metronome and pitch guide, allowing the user to practice according to the appropriate guide.

[0444] Specific examples

[0445] For example, User A starts the application and records a passage from "Let It Be." The device uploads the recorded audio data to the server, which analyzes it using a generative AI model. The analysis results indicate that "the pitch is somewhat unstable and the rhythm tends to lag." Based on this evaluation, the server generates a training plan including pitch practice and rhythm strengthening exercises and sends it to the device. User A follows this plan and begins practicing using the metronome and pitch guide provided within the app.

[0446] Prompt Sentence Examples

[0447] Analyze the user's singing voice data and evaluate it based on pitch, rhythm, pronunciation, and emotional expression. Also, propose the optimal vocal training plan based on the evaluation results.

[0448] In this way, the system accurately evaluates the user's singing ability and provides an optimal, individually tailored vocal training plan, enabling the user to effectively improve their singing ability in a short period of time.

[0449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0450] Step 1:

[0451] The user launches the application and moves to the recording screen. The application displays the recording interface, and the user presses the record button to begin singing. The input is the user's singing voice, and the device records that voice and collects audio data from the time the record button is pressed to the time the stop button is pressed. The output is the recorded audio data, which is saved in the device's local storage. Specifically, the audio signal is input to the device through the microphone and saved as digital data.

[0452] Step 2:

[0453] The device uploads the recorded audio data to the server via the Internet. The input is the recorded audio data, and the output is the data sent to the server. This involves encrypting the data (e.g., using SSL / TLS) and sending it. Specifically, the device sends the audio data via the network to the server's API endpoint using the POST method.

[0454] Step 3:

[0455] The server inputs the received voice data into a generative artificial intelligence model. The input is voice data, which the AI ​​model analyzes. The output is the analysis results for pitch, rhythm, pronunciation, emotional expression, etc. The server sends prompt sentences to the model to analyze these characteristics. Specifically, the voice data is passed to the input layer of the AI ​​model, where it undergoes computational processing and characteristic data is output.

[0456] Step 4:

[0457] The server evaluates the user's singing ability based on the analysis results of the generated AI model. The evaluation includes pitch accuracy, rhythmic stability, and pronunciation clarity. The input is the analysis results, and the output is the user's singing ability evaluation score and feedback in the form of comments. Specifically, the evaluation algorithm converts the characteristic data into a numerical score and generates feedback based on that score.

[0458] Step 5:

[0459] The server references the evaluation results and extracts the optimal voice training plan from the database. The input is the user's evaluation results, and the output is the optimal training plan. The server takes into account past training data and evaluation results to select a plan tailored to specific weaknesses (e.g., improving pitch stability or rhythmic sense). Specifically, it issues a query to the database and extracts relevant training data.

[0460] Step 6:

[0461] The server further customizes the selected training plan. The input is the extracted training plan and the user's evaluation results, and the output is a customized training plan. Specifically, the training content is adjusted and modified based on the evaluation results, and a training plan tailored to the user is created.

[0462] Step 7:

[0463] The server sends a customized voice training plan to the user's device. The input is the customized training plan, and the output is the data sent to the device. The transmission uses an encrypted protocol. Specifically, the server sends data to the device using an authentication token.

[0464] Step 8:

[0465] The voice training plan received by the device is displayed within the app. The input is the training plan sent from the server, and the output is the display content that the user can visually confirm. Specifically, the application constructs an interface based on the data acquired and presents the user with appropriate practice methods.

[0466] Step 9:

[0467] The user begins practicing according to the training plan. The input is the training plan displayed in the application, and the output is the practice results and feedback. Specifically, the user uses the metronome and pitch guide within the application to perform the instructed practice. The user's practice data is used in the subsequent evaluation process.

[0468] (Application example 1)

[0469] 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."

[0470] Traditional voice training often requires individual instruction from a professional instructor, which entails high costs and time constraints. While online instruction is becoming more common, few systems exist that provide detailed evaluations tailored to individual singing abilities or generate and provide appropriate training plans. Furthermore, there is a lack of systems that automatically collect and analyze users' singing data and provide effective training plans based on the results, making it difficult for users to efficiently improve their singing abilities.

[0471] 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.

[0472] In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for transmitting the voice data to the server via the Internet, means for customizing the training plan based on the user's singing ability evaluation results, and means for displaying the generated training plan on the user terminal. This allows users to receive training plans to efficiently improve their singing ability at home or elsewhere without relying on professional instructors.

[0473] "User" refers to an individual who uses the system to provide voice data and whose singing ability is evaluated.

[0474] "Audio Data" refers to a digital audio file of a user's singing recording.

[0475] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes input data and generates the analysis results.

[0476] "Analysis results" refers to evaluation information resulting from analyzing voice data using a generative artificial intelligence model.

[0477] "Singing ability" refers to the user's singing abilities, such as pitch, rhythm, pronunciation, and emotional expression.

[0478] A "database" refers to a collection of information that stores past training data and evaluation data.

[0479] A "voice training plan" refers to a plan that includes specific practice content and improvement methods created to improve a user's singing ability.

[0480] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0481] "Server" refers to a computer system used to analyze audio data and generate training plans.

[0482] "Customization" refers to individualizing a training plan based on a user's specific needs and assessment results.

[0483] "Internet" refers to the global network used to transmit audio data to servers.

[0484] About the system program

[0485] Hardware and software used

[0486] This system is implemented using the following hardware and software.

[0487] Hardware: Smartphones, personal computers, servers

[0488] Software: Flask (web server framework), Pytorch or Tensorflow (for building and training AI models), Requests (for handling HTTP requests)

[0489] Natural language description of the process

[0490] 1. Collecting user voice data

[0491] The user records any singing using a smartphone or personal computer.

[0492] For example, 30 seconds of singing is recorded as a digital audio file and saved to local storage.

[0493] 2. Transmission of data to a server over the Internet

[0494] The device uploads the recorded audio data to a server via the Internet as an HTTP POST request.

[0495] Send data using the Requests library.

[0496] 3. Analysis of audio data

[0497] The server inputs the received voice data into a generative artificial intelligence model and analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0498] This is done by an AI model using Pytorch or Tensorflow.

[0499] 4. Singing ability evaluation

[0500] The server evaluates the user's singing ability based on the analysis results of the generative AI model. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag."

[0501] 5. Extract and generate a voice training plan

[0502] Based on the evaluation results, the server extracts and generates an optimal voice training plan from the database tailored to the user's specific weaknesses.

[0503] It references a database of past training sessions and generates a customized training plan for each user.

[0504] 6. Delivering and implementing training plans

[0505] The generated training plan is sent from the server to the user's device, which then displays the received training plan in the application, allowing the user to view and practice it.

[0506] Specific examples

[0507] For example, User A records a passage of "Let It Be" using a smartphone. User A presses the record button on the device and completes singing for 30 seconds. The device then sends the recorded audio data to the server, which analyzes it. The generative AI model analyzes pitch, rhythm, pronunciation, and emotional expression, and evaluates the result as "slightly unstable pitch and prone to delays in rhythm." Based on this evaluation, the server generates a customized training plan including pitch practice and rhythm strengthening exercises and sends it to the user's device. User A can effectively improve their singing ability by checking and practicing the training plan on their smartphone.

[0508] Prompt Sentence Examples

[0509] An example of a prompt for a generative AI model is:

[0510] "Please analyze user A's singing recording. Evaluate pitch, rhythm, pronunciation, and emotional expression, and provide a score. Generate an optimal training plan based on the evaluation results."

[0511] This makes it possible for the system to provide training plans that allow users to efficiently improve their singing ability at home, without relying on professional instructors.

[0512] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0513] Step 1:

[0514] Users collect audio data using a smartphone or personal computer. Specifically, they press the record button on the application and sing a song of their choice. When recording is complete, they press the stop button and save the recorded data to local storage. The input is the user's singing voice, and the output is a digital audio file (e.g., user_recording.wav).

[0515] Step 2:

[0516] The device uploads recorded audio data to the server. The user device sends the recorded audio file to the server as an HTTP POST request. The input is a digital audio file, and the output is the audio data received by the server. The specific operation is to use the Requests library to send the data.

[0517] Step 3:

[0518] The server inputs the received audio data into a generative AI model for analysis. The input is the received audio data, and the output is the analysis results. The AI ​​model uses Pytorch or Tensorflow to analyze the audio data to analyze features such as pitch, rhythm, pronunciation, and emotional expression.

[0519] Step 4:

[0520] The server evaluates the user's singing ability based on the analysis results. The input is the analysis results obtained from the generative AI model, and the output is an evaluation score and comments on the user's singing ability. The evaluation results are expressed in concrete terms, such as "your pitch is a little unstable and your rhythm tends to lag."

[0521] Step 5:

[0522] The server extracts and generates the optimal vocal training plan from the database based on the evaluation results. The input is the singing ability evaluation score and comments, and the output is a customized vocal training plan. Specifically, it references the past training database and selects training methods that address the user's specific weaknesses.

[0523] Step 6:

[0524] The server sends the generated training plan to the user terminal. The input is the generated voice training plan, and the output is the training plan delivered to the user terminal. Specifically, the training plan is sent to the user terminal using an HTTP request.

[0525] Step 7:

[0526] The training plan received by the user's device is displayed within the application, allowing the user to view and practice. The input is the received voice training plan, and the output is the display of the training plan on the application. Specifically, the contents of the plan are displayed on the application UI, and the user begins practicing according to them.

[0527] This allows users to receive training plans to improve their singing ability efficiently at home, etc., without relying on professional instructors.

[0528] 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.

[0529] This invention relates to a system that combines voice recognition technology, a generative artificial intelligence model, and an emotion engine to evaluate the singing ability of each user and provide an optimal voice training plan.

[0530] User voice data collection and emotion recognition

[0531] Users record themselves singing using a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device saves this audio data in local storage and uses an emotion engine to analyze the user's emotions during recording.

[0532] Transmission and analysis of voice and emotion data

[0533] The device then sends the recorded voice data and the emotional data analyzed by the emotion engine to a server via the internet. The server receives the voice data and emotional data and inputs them into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0534] Singing ability evaluation

[0535] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The evaluation is then corrected based on the emotion recognition results. For example, if the user is emotionally unstable or nervous, this effect can be reflected in the singing ability evaluation, providing more accurate feedback.

[0536] Extract and generate the best voice training plan

[0537] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotion recognition results. The selected training plan addresses the user's specific weaknesses (e.g., improving pitch stability, strengthening rhythmic sense) as well as their emotional state (relaxation, improving concentration). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0538] Training plan distribution and implementation

[0539] The generated training plan is sent from the server to the device. The device displays the received training plan within the app for the user to view. The user then begins practicing according to the training plan. The plan includes video and audio guides, practice tasks, as well as advice and exercises tailored to the user's emotional state.

[0540] Specific examples

[0541] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data, along with the emotional data analyzed by the emotion engine during recording, to the server. The server analyzes the data and determines that the user's pitch is somewhat unstable and the rhythm tends to lag behind, and that the emotional analysis indicates a high level of tension. Based on these results, the server generates a training plan that includes pitch practice, rhythm strengthening exercises, and relaxation exercises, and sends it to the device. User A can start practicing according to this plan and effectively improve their singing ability by practicing the relaxation exercises suggested during practice.

[0542] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan that takes into account the user's emotional state at low cost.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0546] Step 2:

[0547] The user presses the record button. The device activates the microphone and starts collecting voice data. At the same time, the emotion engine also activates and begins analyzing the user's emotional state.

[0548] Step 3:

[0549] When the user finishes singing, they press the stop button. The device stops recording and saves the audio file in local storage. The emotion engine also finishes analyzing the data and saves the emotion data.

[0550] Step 4:

[0551] The device transmits the recorded voice data and emotion data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data and emotion data.

[0552] Step 5:

[0553] The server receives the voice data and emotion data and inputs them into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0554] Step 6:

[0555] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0556] Step 7:

[0557] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and you tend to be behind the rhythm." The evaluation is corrected based on the analysis results of the emotion engine. For example, it may include feedback such as "Your pitch became more unstable because you were nervous."

[0558] Step 8:

[0559] The server extracts the optimal voice training plan from the database based on the evaluation results and emotion recognition results. The server selects a training plan that takes into account the user's specific weaknesses as well as their emotional state.

[0560] Step 9:

[0561] The server then customizes the training plan for the user, including specific practice methods and areas for improvement, as well as exercises that address emotional states.

[0562] Step 10:

[0563] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0564] Step 11:

[0565] Users can view and follow the instructions for their training plan, which includes video and audio guides, practice exercises, and advice and exercises tailored to the user's emotional state.

[0566] Step 12:

[0567] After a certain period of training, the user records again to check their progress, and the device sends the new recording and emotional data to the server for re-evaluation.

[0568] In this way, through detailed processing steps, users can objectively evaluate their singing ability and receive a training plan that takes into account their emotional state. Through the specific operations of each step, it can be seen that the entire system functions smoothly.

[0569] Example 2

[0570] 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."

[0571] Conventional voice data analysis systems do not take into account a user's emotional state when evaluating their singing ability, resulting in poor evaluation accuracy and making it difficult to provide an individually customized training plan based on the user's specific weaknesses and emotional state.

[0572] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results and the user's emotional data, means for extracting an optimal voice training plan from a database based on the evaluation results and the emotional data, and means for providing the voice training plan to the user terminal. This enables accurate evaluation of singing ability taking into account the user's emotional state and provides an individually customized training plan.

[0573] "User's voice data" refers to data that represents voice information such as singing or conversation recorded by a user in digital format.

[0574] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that learns from large amounts of data and analyzes and predicts new data.

[0575] "Analysis" is the process of analyzing features and patterns based on input data and extracting the results.

[0576] "User emotion data" is data that analyzes the emotional state of the user while recording the voice and expresses it as numerical values ​​or categories.

[0577] "Evaluating singing ability" means evaluating elements of the user's singing, such as pitch, rhythm, pronunciation, and emotional expression, as scores or comments.

[0578] A "database" is a system for efficiently storing, managing, and searching data, or a collection of accumulated information.

[0579] A "voice training plan" is a written plan that includes practice methods, exercises, and improvements designed to improve a user's singing ability.

[0580] A "user terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0581] This invention relates to a system that combines voice recognition technology, a generative AI model, and an emotion engine to evaluate the singing ability of individual users and provide an optimal vocal training plan. This system collects the user's voice data, analyzes it using a generative AI model, and provides an evaluation and training plan based on the results.

[0582] User voice data collection and emotion recognition

[0583] The user launches the dedicated application, and the recording interface appears on the device. The user presses the record button and sings, recording the audio data. After recording is complete, the device saves the audio data in local storage. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and extract emotion data.

[0584] Transmission and analysis of voice and emotion data

[0585] The device sends the stored voice and emotion data to a server via the internet. When the server receives this data, it inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the results to the server.

[0586] Singing ability evaluation

[0587] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, and the evaluation is also corrected by taking into account the emotion recognition results. For example, if the emotional state is "nervous," this influence is reflected in the evaluation and detailed feedback is provided.

[0588] Generate and deliver optimal voice training plans

[0589] The server extracts an optimal vocal training plan from the database based on the evaluation results and emotional data. This plan addresses the user's specific weaknesses and emotional state. A customized training plan including specific practice methods, areas for improvement, and exercises is generated and sent to the device.

[0590] Implementing your training plan

[0591] The device receives a training plan, which is then displayed in the app for the user to view. The user can then begin practicing according to the plan and periodically check their progress. The plan may include video and audio guides, practice assignments, relaxation exercises, and more.

[0592] Specific examples

[0593] For example, User A launches the app and records a passage from "Let It Be." The device sends the audio data and emotional data indicating "high tension" to the server. The server then analyzes the audio data using a generative AI model and produces an evaluation result indicating "your pitch is somewhat unstable and your rhythm tends to lag." It then corrects the evaluation based on the emotional data and provides specific feedback. The server then generates a training plan that includes improving pitch stability, strengthening your sense of rhythm, and relaxation exercises, and sends it to the device. User A follows this plan and begins practicing, including the suggested relaxation exercises.

[0594] Examples of prompt statements

[0595] Below are some example prompts to input to a generative AI model:

[0596] 1. "Write a script that analyzes a user's voice data and evaluates their singing ability. Evaluation criteria should include pitch, rhythm, pronunciation, and emotional expression."

[0597] 2. "Based on the emotion recognition results, please design an algorithm to correct the singing ability evaluation and create a program that outputs the results in the form of a score and comments."

[0598] In this way, the present invention realizes a system that provides an objective evaluation of singing ability that also takes into account the user's emotional state, and an individualized training plan at low cost.

[0599] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] The user launches the dedicated app and the recording interface appears on the device. The user taps the record button and starts singing. When the user finishes recording, the device saves the audio data to local storage. At the same time, the device uses an emotion engine to analyze the user's emotional state and extract emotion data.

[0602] Input: User's singing voice

[0603] Output: Audio data (recorded file) and emotion data (analysis results)

[0604] Step 2:

[0605] The device transmits the stored voice data and emotion data to a server via the Internet, which receives the data and stores it in a database.

[0606] Input: Voice data, emotion data

[0607] Output: Storage of voice data and emotion data on the server

[0608] Step 3:

[0609] The server inputs the audio data into a generative AI model. The AI ​​model analyzes pitch, rhythm, pronunciation, emotional expression, and other factors to extract various characteristics. For example, it evaluates the stability of pitch and the accuracy of rhythm. At the same time, emotional data is also analyzed, resulting in a comprehensive analysis result.

[0610] Input: Voice data, emotion data

[0611] Output: Analysis results (pitch, rhythm, pronunciation, emotional expression)

[0612] Step 4:

[0613] The server evaluates the user's singing ability based on the analysis results. The evaluation is displayed in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The server then corrects the emotion recognition results and generates detailed feedback.

[0614] Input: Analysis results (pitch, rhythm, pronunciation, emotional expression), emotional data

[0615] Output: Evaluation results (score, comments)

[0616] Step 5:

[0617] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotional data. This plan includes improving pitch stability, strengthening rhythmic sense, and relaxation exercises. The plan is customized for each user, and specific practice methods are provided.

[0618] Input: Evaluation results, emotion data

[0619] Output: Voice Training Plan (Customized Plan)

[0620] Step 6:

[0621] The server sends the generated voice training plan to the device. The device receives the plan and displays it within the app. The user begins practicing according to the plan, and the app records the practice progress.

[0622] Enter: Voice Training Plan

[0623] Output: Plan display and practice record to user

[0624] In this way, the user, the terminal, and the server cooperate to carry out the process at each step, thereby providing an accurate singing ability evaluation and an individualized training plan that takes into account the user's emotional state.

[0625] (Application example 2)

[0626] 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."

[0627] While conventional vocal training systems provide technical evaluations of pitch and rhythm, they struggle to provide feedback and training plans that take the user's emotional state into account. As a result, users often practice singing while experiencing emotional issues such as tension or anxiety, resulting in ineffective training. Furthermore, there has been a lack of methods for accurately evaluating a user's singing ability and providing a customized training plan tailored to their individual needs.

[0628] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0629] In this invention, the server includes means for collecting a user's voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for analyzing the user's emotional state, means for reflecting the emotional state in the evaluation results, means for generating a training plan according to the user's emotional state, means for uploading the voice data and emotional state data to the server, and means for including specific practice methods and areas for improvement in the voice training plan, as well as exercises according to the user's emotional state. This enables more effective and customized voice training that takes into account not only the user's technical ability but also their emotional state.

[0630] "Audio data" is digital data that includes audio signals such as singing recorded by a user.

[0631] A "generative artificial intelligence model" is a system that includes an artificial intelligence algorithm that analyzes audio data as input and evaluates characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0632] The "evaluation results" are data including scores and comments on the user's singing ability analyzed by the generative artificial intelligence model, as well as an evaluation of the user's emotional state.

[0633] A "voice training plan" is a teaching program that includes specific practice methods, areas for improvement, and exercises to improve the user's singing ability.

[0634] "Emotional state" is data that indicates the psychological state, such as tension, anxiety, or relaxation, that the user feels while singing.

[0635] "Means for analyzing" refers to methods and apparatus that use generative artificial intelligence models to evaluate audio data and emotional states.

[0636] The "means for extracting" refers to a method and apparatus for extracting an optimal voice training plan from a database based on the user's evaluation results.

[0637] The "means for providing" refers to a method and device for displaying and distributing the extracted voice training plan on the user's terminal.

[0638] "Uploading means" refers to a method and apparatus for transmitting a user's voice data and emotional state data to a server over the Internet.

[0639] The "means for analyzing emotional state" refers to a method and device for analyzing the psychological state of a user from the user's voice data and facial expression data.

[0640] The "reflecting means" refers to a method and device for incorporating the analyzed emotional state into the evaluation of the user's singing ability.

[0641] The "means for generating" refers to a method and apparatus for creating a customized training plan for a user based on the assessment results and emotional state.

[0642] The present invention is a system for users to evaluate their singing ability and provide a personalized vocal training plan. The system collects the user's voice data and emotional state data, and generates personalized feedback and training plans based on the analysis results.

[0643] System Configuration

[0644] The system consists of the following main components:

[0645] 1. User Device

[0646] The user terminals are smartphones and head-mounted displays, which are devices that allow users to record their singing and capture their emotional state.

[0647] It provides an audio recording interface and stores the recording data in local storage.

[0648] An emotion engine is used to analyze the user's emotional state.

[0649] 2. Server

[0650] The system receives voice data and emotion data and analyzes them using a generative AI model, such as Python, pydub, EmotionEngine, and SingingEvaluation.

[0651] The system evaluates the user's singing ability and extracts and generates a voice training plan from a database based on the evaluation results.

[0652] This training plan includes specific drills, areas for improvement, and even exercises tailored to your emotional state.

[0653] 3. Network Infrastructure

[0654] It supports data communication between the user device and the server. Voice data and emotion data are uploaded to the server via an internet connection, and analysis results and training plans are sent to the user device.

[0655] Data collection and analysis

[0656] 1. Collection of audio data

[0657] The user uses the application to record themselves singing. Once the recording is complete, the audio data is saved to local storage. At that time, the emotion engine analyzes the user's emotional state, and the emotional data is also saved.

[0658] 2. Data transmission

[0659] The recorded voice data and emotion data are sent to the server via the network, where the server receives the data and begins analyzing it.

[0660] 3. Data Analysis

[0661] The server uses a generative AI model to analyze the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The results of the emotion analysis performed by the emotion engine are also taken into account in the evaluation.

[0662] Creation and delivery of training plans

[0663] Based on the analysis results, the server evaluates the user's singing ability and extracts an optimal vocal training plan from the database based on the evaluation. The training plan includes exercises that address the user's specific weaknesses (e.g., pitch, rhythm) and emotional state (relaxation, concentration).

[0664] The generated training plan is sent from the server to the user's device and displayed within the app. The user can then begin practicing according to the plan and monitor their progress within the application.

[0665] Specific examples

[0666] For example, a user launches the app and records a passage from a "famous song." The recording is made through the smartphone's microphone, while the camera in the head-mounted display captures the user's facial expressions and analyzes their emotional state. Once the recording is complete, the audio data and emotional data are sent to the server. The server analyzes this data and provides a detailed evaluation of pitch and rhythm, as well as the emotional state the user felt while singing. A training plan is automatically generated based on the results and sent to the user's device. The user can view the generated plan and begin practicing.

[0667] Example of input prompt for generative AI model

[0668] The following prompt sentences are used to provide examples of input to a generative artificial intelligence model:

[0669] "Based on the following audio data and its emotional analysis results, please evaluate the user's singing ability and generate the optimal vocal training plan.

[0670] Audio data: (attached audio file)

[0671] Emotion analysis results: "Emotion: Tension, Confidence: 0.85"

[0672] Expected output: Evaluation of pitch, rhythm, pronunciation, and emotional expression, and a training plan based on the evaluation. For example, specific practice methods to improve the causes of pitch instability and suggestions for relaxation exercises to reduce tension.

[0673] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0674] Step 1:

[0675] The user starts the application using a smartphone or a head-mounted display and records their singing.

[0676] Input: User's voice and facial expression data

[0677] Specific operation: The user presses the record button, finishes singing, and then presses the stop button. The application saves the voice data and facial expression data to local storage.

[0678] Step 2:

[0679] The device sends the recorded voice data and the emotion data analyzed by the emotion engine to the server.

[0680] Input: Voice and emotion data in local storage

[0681] Specific operation: The application uploads voice data and emotion data to a server via an internet connection.

[0682] Step 3:

[0683] The server inputs the received voice data and emotion data into a generative artificial intelligence model for analysis.

[0684] Input: Voice data and emotion data uploaded to the server

[0685] Specific operation: Run the script and input data into a generative artificial intelligence model (e.g., Python and pydub, EmotionEngine, SingingEvaluation) for analysis.

[0686] Step 4:

[0687] The server generates analysis results and evaluates the user's singing ability.

[0688] Input: Analysis results from a generative artificial intelligence model

[0689] Output: A detailed assessment of the user's pitch, rhythm, pronunciation, and emotional expression.

[0690] Specific operation: Based on the analysis results, an evaluation is generated in the form of a score and comments, and the emotional state is also reflected along with the evaluation.

[0691] Step 5:

[0692] Based on the evaluation results, the server extracts the optimal voice training plan from the database and customizes and generates it.

[0693] Input: User evaluation results and emotion data

[0694] Output: Personalized voice training plan

[0695] Specific operation: Extract appropriate practice methods and exercises from the database and generate an optimal plan based on the user's evaluation results and emotional state.

[0696] Step 6:

[0697] The server transmits the generated voice training plan to the user terminal.

[0698] Enter: a customized voice training plan.

[0699] Output: Sending the training plan to the user's device

[0700] Specific operation: The server sends the training plan to the user's device via the Internet, where it is displayed within the application.

[0701] Step 7:

[0702] The user follows the voice training plan sent to them and begins practicing.

[0703] Input: Training plan displayed on user's device

[0704] What it does: The user follows a training plan within the app, practicing with audio guidance and videos, and the app provides feedback on their progress and emotional state during practice.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] [Third embodiment]

[0709] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0710] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0711] 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).

[0712] 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.

[0713] 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.

[0714] 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).

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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."

[0721] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate an individual's singing ability and provide an optimal voice training plan.

[0722] Collecting user voice data

[0723] Users record their singing through a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device then stores the audio data in its local storage.

[0724] Sending and analyzing voice data

[0725] The device then sends the recorded voice data over the internet to a server. The server receives the voice data and inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0726] Singing ability evaluation

[0727] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "unstable pitch and weak sense of rhythm." The server saves the evaluation results and uses them in the next step.

[0728] Extract and generate the best voice training plan

[0729] The server references the evaluation results and extracts the optimal vocal training plan from a database of past training. The selected training plan is tailored to the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0730] Training plan distribution and implementation

[0731] The generated training plan is sent from the server to the device. The device displays the received training plan within the app so that the user can view it. The user can then begin practicing according to the training plan.

[0732] Specific examples

[0733] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data to the server, which analyzes it. The analysis results in an evaluation that "your pitch is somewhat unstable and your rhythm tends to lag." Based on this evaluation, the server generates a training plan that includes pitch practice and rhythm strengthening exercises and sends it to the device. By following this plan and starting to practice, User A can effectively improve their singing ability.

[0734] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan at low cost.

[0735] The processing flow will be explained below.

[0736] Step 1:

[0737] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0738] Step 2:

[0739] The user presses the record button. The device activates the microphone and starts collecting audio data. The user starts singing.

[0740] Step 3:

[0741] When the user finishes singing, they press the stop button, and the device stops recording and saves the audio file to local storage.

[0742] Step 4:

[0743] The device sends the recorded voice data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data.

[0744] Step 5:

[0745] The server receives the voice data and inputs it into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0746] Step 6:

[0747] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0748] Step 7:

[0749] The server evaluates the user's singing ability based on the analysis results, and the evaluation is in the form of a score and comments, indicating specific weaknesses and strengths.

[0750] Step 8:

[0751] Based on the evaluation results, the server extracts the optimal voice training plan from the database, and selects a training plan tailored to the user's specific weaknesses.

[0752] Step 9:

[0753] The server then customizes the training plan for the user, including adding specific exercises and improvements.

[0754] Step 10:

[0755] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0756] Step 11:

[0757] Users can review the training plan and follow the instructions to begin practicing, which includes videos, audio guides, and exercises.

[0758] Step 12:

[0759] After a certain period of training, the user records again to check their progress, and the device sends the new recording to the server for re-evaluation.

[0760] By proceeding step by step in this way, the user can effectively improve their singing ability. The specific operations at each step demonstrate that the entire system functions smoothly.

[0761] Example 1

[0762] 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."

[0763] Conventional singing ability evaluation systems have had the problem of being difficult to accurately evaluate a user's singing ability and provide an individually customized vocal training plan. Furthermore, the means for efficiently providing evaluation results and training plans to users are limited, leaving users with a lack of effective ways to improve their weaknesses. This has led to the problem that it is difficult for users to effectively improve their singing ability in a short period of time.

[0764] 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.

[0765] In this invention, the server includes a means for uploading a user's voice data to the server, a means for inputting the data into a generative artificial intelligence model for analysis, a means for extracting an optimal vocal training plan from a database based on the evaluation results, and a means for customizing the training plan to suit the user's specific weaknesses. This makes it possible to accurately evaluate a user's singing ability and provide an optimal vocal training plan that addresses each weakness. Furthermore, the training plan includes specific practice methods and areas for improvement and is delivered to the user's terminal using an encrypted protocol, allowing the user to train safely and efficiently.

[0766] "User voice data" refers to recorded voice data collected by a user using a dedicated device.

[0767] A "generative artificial intelligence model" is an artificial intelligence model that learns from large amounts of data and performs appropriate processing and analysis on given input data.

[0768] A "server" is a central computer system that stores, processes, and distributes data to other devices over a network.

[0769] The "evaluation means" is a means for evaluating the user's singing ability in the form of numerical values ​​or comments based on data analyzed by the generative artificial intelligence model.

[0770] A "database" is a system configured to efficiently manage, store, and search large amounts of data.

[0771] A "voice training plan" is a plan that specifies practice methods and training steps designed to improve a user's singing ability.

[0772] The "customization means" is a means for individually adjusting the optimal training plan based on the user's evaluation results, and changing the plan to suit the user's specific weaknesses and needs.

[0773] An "encrypted protocol" is a communication method used to protect the contents of data when it is sent and received, and is a technology that prevents third parties from reading the contents.

[0774] A "user terminal" is a device that can be directly operated by a user, such as a smartphone or tablet.

[0775] The "practice method" indicates the specific practice content and procedures that the user should follow in order to improve their singing ability.

[0776] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate a user's singing ability and provide an individually customized vocal training plan. The following describes specific embodiments of the invention.

[0777] Collecting user voice data

[0778] The user launches a dedicated application on a device such as a smartphone or tablet. The application displays an interface for recording audio. The user presses the record button to start singing and the stop button to end recording. The device saves the recorded audio data in local storage. This temporarily saves the audio data.

[0779] Sending and analyzing voice data

[0780] The device uploads the saved voice data to a server via the internet. The data is securely transmitted using an encrypted protocol (e.g., HTTPS). The server receives the voice data and inputs it into a generative AI model (e.g., OpenAI's GPT-3, Google's BERT, etc.). The generative AI model analyzes the voice data and extracts features such as pitch, rhythm, pronunciation, and emotional expression. The analysis results are returned to the server.

[0781] Singing ability evaluation

[0782] The server evaluates the user's singing ability based on the data analyzed by the generative AI model. The evaluation is provided in the form of a number (e.g., 0-100 points) or a comment. For example, the evaluation result may be displayed as "unstable pitch and weak sense of rhythm." The server then stores the evaluation results in a database.

[0783] Extract and generate the best voice training plan

[0784] The server then references the evaluation results and extracts the optimal vocal training plan from its database. The training plan addresses the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes the plan and generates it in a format (e.g., PDF or video) that includes specific practice methods and areas for improvement.

[0785] Training plan distribution and implementation

[0786] The server sends the generated training plan to the device. The plan is sent using an encrypted protocol, ensuring secure data delivery. The device displays the training plan within the app so that the user can review it. The user then begins practicing according to the plan. The application displays a metronome and pitch guide, allowing the user to practice according to the appropriate guide.

[0787] Specific examples

[0788] For example, User A starts the application and records a passage from "Let It Be." The device uploads the recorded audio data to the server, which analyzes it using a generative AI model. The analysis results indicate that "the pitch is somewhat unstable and the rhythm tends to lag." Based on this evaluation, the server generates a training plan including pitch practice and rhythm strengthening exercises and sends it to the device. User A follows this plan and begins practicing using the metronome and pitch guide provided within the app.

[0789] Prompt Sentence Examples

[0790] Analyze the user's singing voice data and evaluate it based on pitch, rhythm, pronunciation, and emotional expression. Also, propose the optimal vocal training plan based on the evaluation results.

[0791] In this way, the system accurately evaluates the user's singing ability and provides an optimal, individually tailored vocal training plan, enabling the user to effectively improve their singing ability in a short period of time.

[0792] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0793] Step 1:

[0794] The user launches the application and moves to the recording screen. The application displays the recording interface, and the user presses the record button to begin singing. The input is the user's singing voice, and the device records that voice and collects audio data from the time the record button is pressed to the time the stop button is pressed. The output is the recorded audio data, which is saved in the device's local storage. Specifically, the audio signal is input to the device through the microphone and saved as digital data.

[0795] Step 2:

[0796] The device uploads the recorded audio data to the server via the Internet. The input is the recorded audio data, and the output is the data sent to the server. This involves encrypting the data (e.g., using SSL / TLS) and sending it. Specifically, the device sends the audio data via the network to the server's API endpoint using the POST method.

[0797] Step 3:

[0798] The server inputs the received voice data into a generative artificial intelligence model. The input is voice data, which the AI ​​model analyzes. The output is the analysis results for pitch, rhythm, pronunciation, emotional expression, etc. The server sends prompt sentences to the model to analyze these characteristics. Specifically, the voice data is passed to the input layer of the AI ​​model, where it undergoes computational processing and characteristic data is output.

[0799] Step 4:

[0800] The server evaluates the user's singing ability based on the analysis results of the generated AI model. The evaluation includes pitch accuracy, rhythmic stability, and pronunciation clarity. The input is the analysis results, and the output is the user's singing ability evaluation score and feedback in the form of comments. Specifically, the evaluation algorithm converts the characteristic data into a numerical score and generates feedback based on that score.

[0801] Step 5:

[0802] The server references the evaluation results and extracts the optimal voice training plan from the database. The input is the user's evaluation results, and the output is the optimal training plan. The server takes into account past training data and evaluation results to select a plan tailored to specific weaknesses (e.g., improving pitch stability or rhythmic sense). Specifically, it issues a query to the database and extracts relevant training data.

[0803] Step 6:

[0804] The server further customizes the selected training plan. The input is the extracted training plan and the user's evaluation results, and the output is a customized training plan. Specifically, the training content is adjusted and modified based on the evaluation results, and a training plan tailored to the user is created.

[0805] Step 7:

[0806] The server sends a customized voice training plan to the user's device. The input is the customized training plan, and the output is the data sent to the device. The transmission uses an encrypted protocol. Specifically, the server sends data to the device using an authentication token.

[0807] Step 8:

[0808] The voice training plan received by the device is displayed within the app. The input is the training plan sent from the server, and the output is the display content that the user can visually confirm. Specifically, the application constructs an interface based on the data acquired and presents the user with appropriate practice methods.

[0809] Step 9:

[0810] The user begins practicing according to the training plan. The input is the training plan displayed in the application, and the output is the practice results and feedback. Specifically, the user uses the metronome and pitch guide within the application to perform the instructed practice. The user's practice data is used in the subsequent evaluation process.

[0811] (Application example 1)

[0812] 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."

[0813] Traditional voice training often requires individual instruction from a professional instructor, which entails high costs and time constraints. While online instruction is becoming more common, few systems exist that provide detailed evaluations tailored to individual singing abilities or generate and provide appropriate training plans. Furthermore, there is a lack of systems that automatically collect and analyze users' singing data and provide effective training plans based on the results, making it difficult for users to efficiently improve their singing abilities.

[0814] 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.

[0815] In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for transmitting the voice data to the server via the Internet, means for customizing the training plan based on the user's singing ability evaluation results, and means for displaying the generated training plan on the user terminal. This allows users to receive training plans to efficiently improve their singing ability at home or elsewhere without relying on professional instructors.

[0816] "User" refers to an individual who uses the system to provide voice data and whose singing ability is evaluated.

[0817] "Audio Data" refers to a digital audio file of a user's singing recording.

[0818] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes input data and generates the analysis results.

[0819] "Analysis results" refers to evaluation information resulting from analyzing voice data using a generative artificial intelligence model.

[0820] "Singing ability" refers to the user's singing abilities, such as pitch, rhythm, pronunciation, and emotional expression.

[0821] A "database" refers to a collection of information that stores past training data and evaluation data.

[0822] A "voice training plan" refers to a plan that includes specific practice content and improvement methods created to improve a user's singing ability.

[0823] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0824] "Server" refers to a computer system used to analyze audio data and generate training plans.

[0825] "Customization" refers to individualizing a training plan based on a user's specific needs and assessment results.

[0826] "Internet" refers to the global network used to transmit audio data to servers.

[0827] About the system program

[0828] Hardware and software used

[0829] This system is implemented using the following hardware and software.

[0830] Hardware: Smartphones, personal computers, servers

[0831] Software: Flask (web server framework), Pytorch or Tensorflow (for building and training AI models), Requests (for handling HTTP requests)

[0832] Natural language description of the process

[0833] 1. Collecting user voice data

[0834] The user records any singing using a smartphone or personal computer.

[0835] For example, 30 seconds of singing is recorded as a digital audio file and saved to local storage.

[0836] 2. Transmission of data to a server over the Internet

[0837] The device uploads the recorded audio data to a server via the Internet as an HTTP POST request.

[0838] Send data using the Requests library.

[0839] 3. Analysis of audio data

[0840] The server inputs the received voice data into a generative artificial intelligence model and analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0841] This is done by an AI model using Pytorch or Tensorflow.

[0842] 4. Singing ability evaluation

[0843] The server evaluates the user's singing ability based on the analysis results of the generative AI model. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag."

[0844] 5. Extract and generate a voice training plan

[0845] Based on the evaluation results, the server extracts and generates an optimal voice training plan from the database tailored to the user's specific weaknesses.

[0846] It references a database of past training sessions and generates a customized training plan for each user.

[0847] 6. Delivering and implementing training plans

[0848] The generated training plan is sent from the server to the user's device, which then displays the received training plan in the application, allowing the user to view and practice it.

[0849] Specific examples

[0850] For example, User A records a passage of "Let It Be" using a smartphone. User A presses the record button on the device and completes singing for 30 seconds. The device then sends the recorded audio data to the server, which analyzes it. The generative AI model analyzes pitch, rhythm, pronunciation, and emotional expression, and evaluates the result as "slightly unstable pitch and prone to delays in rhythm." Based on this evaluation, the server generates a customized training plan including pitch practice and rhythm strengthening exercises and sends it to the user's device. User A can effectively improve their singing ability by checking and practicing the training plan on their smartphone.

[0851] Prompt Sentence Examples

[0852] An example of a prompt for a generative AI model is:

[0853] "Please analyze user A's singing recording. Evaluate pitch, rhythm, pronunciation, and emotional expression, and provide a score. Generate an optimal training plan based on the evaluation results."

[0854] This makes it possible for the system to provide training plans that allow users to efficiently improve their singing ability at home, without relying on professional instructors.

[0855] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0856] Step 1:

[0857] Users collect audio data using a smartphone or personal computer. Specifically, they press the record button on the application and sing a song of their choice. When recording is complete, they press the stop button and save the recorded data to local storage. The input is the user's singing voice, and the output is a digital audio file (e.g., user_recording.wav).

[0858] Step 2:

[0859] The device uploads recorded audio data to the server. The user device sends the recorded audio file to the server as an HTTP POST request. The input is a digital audio file, and the output is the audio data received by the server. The specific operation is to use the Requests library to send the data.

[0860] Step 3:

[0861] The server inputs the received audio data into a generative AI model for analysis. The input is the received audio data, and the output is the analysis results. The AI ​​model uses Pytorch or Tensorflow to analyze the audio data to analyze features such as pitch, rhythm, pronunciation, and emotional expression.

[0862] Step 4:

[0863] The server evaluates the user's singing ability based on the analysis results. The input is the analysis results obtained from the generative AI model, and the output is an evaluation score and comments on the user's singing ability. The evaluation results are expressed in concrete terms, such as "your pitch is a little unstable and your rhythm tends to lag."

[0864] Step 5:

[0865] The server extracts and generates the optimal vocal training plan from the database based on the evaluation results. The input is the singing ability evaluation score and comments, and the output is a customized vocal training plan. Specifically, it references the past training database and selects training methods that address the user's specific weaknesses.

[0866] Step 6:

[0867] The server sends the generated training plan to the user terminal. The input is the generated voice training plan, and the output is the training plan delivered to the user terminal. Specifically, the training plan is sent to the user terminal using an HTTP request.

[0868] Step 7:

[0869] The training plan received by the user's device is displayed within the application, allowing the user to view and practice. The input is the received voice training plan, and the output is the display of the training plan on the application. Specifically, the contents of the plan are displayed on the application UI, and the user begins practicing according to them.

[0870] This allows users to receive training plans to improve their singing ability efficiently at home, etc., without relying on professional instructors.

[0871] 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.

[0872] This invention relates to a system that combines voice recognition technology, a generative artificial intelligence model, and an emotion engine to evaluate the singing ability of each user and provide an optimal voice training plan.

[0873] User voice data collection and emotion recognition

[0874] Users record themselves singing using a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device saves this audio data in local storage and uses an emotion engine to analyze the user's emotions during recording.

[0875] Transmission and analysis of voice and emotion data

[0876] The device then sends the recorded voice data and the emotional data analyzed by the emotion engine to a server via the internet. The server receives the voice data and emotional data and inputs them into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[0877] Singing ability evaluation

[0878] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The evaluation is then corrected based on the emotion recognition results. For example, if the user is emotionally unstable or nervous, this effect can be reflected in the singing ability evaluation, providing more accurate feedback.

[0879] Extract and generate the best voice training plan

[0880] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotion recognition results. The selected training plan addresses the user's specific weaknesses (e.g., improving pitch stability, strengthening rhythmic sense) as well as their emotional state (relaxation, improving concentration). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[0881] Training plan distribution and implementation

[0882] The generated training plan is sent from the server to the device. The device displays the received training plan within the app for the user to view. The user then begins practicing according to the training plan. The plan includes video and audio guides, practice tasks, as well as advice and exercises tailored to the user's emotional state.

[0883] Specific examples

[0884] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data, along with the emotional data analyzed by the emotion engine during recording, to the server. The server analyzes the data and determines that the user's pitch is somewhat unstable and the rhythm tends to lag behind, and that the emotional analysis indicates a high level of tension. Based on these results, the server generates a training plan that includes pitch practice, rhythm strengthening exercises, and relaxation exercises, and sends it to the device. User A can start practicing according to this plan and effectively improve their singing ability by practicing the relaxation exercises suggested during practice.

[0885] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan that takes into account the user's emotional state at low cost.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The user launches the app and goes to the recording screen. The device displays the recording interface.

[0889] Step 2:

[0890] The user presses the record button. The device activates the microphone and starts collecting voice data. At the same time, the emotion engine also activates and begins analyzing the user's emotional state.

[0891] Step 3:

[0892] When the user finishes singing, they press the stop button. The device stops recording and saves the audio file in local storage. The emotion engine also finishes analyzing the data and saves the emotion data.

[0893] Step 4:

[0894] The device transmits the recorded voice data and emotion data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data and emotion data.

[0895] Step 5:

[0896] The server receives the voice data and emotion data and inputs them into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[0897] Step 6:

[0898] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[0899] Step 7:

[0900] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and you tend to be behind the rhythm." The evaluation is corrected based on the analysis results of the emotion engine. For example, it may include feedback such as "Your pitch became more unstable because you were nervous."

[0901] Step 8:

[0902] The server extracts the optimal voice training plan from the database based on the evaluation results and emotion recognition results. The server selects a training plan that takes into account the user's specific weaknesses as well as their emotional state.

[0903] Step 9:

[0904] The server then customizes the training plan for the user, including specific practice methods and areas for improvement, as well as exercises that address emotional states.

[0905] Step 10:

[0906] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[0907] Step 11:

[0908] Users can view and follow the instructions for their training plan, which includes video and audio guides, practice exercises, and advice and exercises tailored to the user's emotional state.

[0909] Step 12:

[0910] After a certain period of training, the user records again to check their progress, and the device sends the new recording and emotional data to the server for re-evaluation.

[0911] In this way, through detailed processing steps, users can objectively evaluate their singing ability and receive a training plan that takes into account their emotional state. Through the specific operations of each step, it can be seen that the entire system functions smoothly.

[0912] Example 2

[0913] 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."

[0914] Conventional voice data analysis systems do not take into account a user's emotional state when evaluating their singing ability, resulting in poor evaluation accuracy and making it difficult to provide an individually customized training plan based on the user's specific weaknesses and emotional state.

[0915] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results and the user's emotional data, means for extracting an optimal voice training plan from a database based on the evaluation results and the emotional data, and means for providing the voice training plan to the user terminal. This enables accurate evaluation of singing ability taking into account the user's emotional state and provides an individually customized training plan.

[0916] "User's voice data" refers to data that represents voice information such as singing or conversation recorded by a user in digital format.

[0917] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that learns from large amounts of data and analyzes and predicts new data.

[0918] "Analysis" is the process of analyzing features and patterns based on input data and extracting the results.

[0919] "User emotion data" is data that analyzes the emotional state of the user while recording the voice and expresses it as numerical values ​​or categories.

[0920] "Evaluating singing ability" means evaluating elements of the user's singing, such as pitch, rhythm, pronunciation, and emotional expression, as scores or comments.

[0921] A "database" is a system for efficiently storing, managing, and searching data, or a collection of accumulated information.

[0922] A "voice training plan" is a written plan that includes practice methods, exercises, and improvements designed to improve a user's singing ability.

[0923] A "user terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[0924] This invention relates to a system that combines voice recognition technology, a generative AI model, and an emotion engine to evaluate the singing ability of individual users and provide an optimal vocal training plan. This system collects the user's voice data, analyzes it using a generative AI model, and provides an evaluation and training plan based on the results.

[0925] User voice data collection and emotion recognition

[0926] The user launches the dedicated application, and the recording interface appears on the device. The user presses the record button and sings, recording the audio data. After recording is complete, the device saves the audio data in local storage. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and extract emotion data.

[0927] Transmission and analysis of voice and emotion data

[0928] The device sends the stored voice and emotion data to a server via the internet. When the server receives this data, it inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the results to the server.

[0929] Singing ability evaluation

[0930] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, and the evaluation is also corrected by taking into account the emotion recognition results. For example, if the emotional state is "nervous," this influence is reflected in the evaluation and detailed feedback is provided.

[0931] Generate and deliver optimal voice training plans

[0932] The server extracts an optimal vocal training plan from the database based on the evaluation results and emotional data. This plan addresses the user's specific weaknesses and emotional state. A customized training plan including specific practice methods, areas for improvement, and exercises is generated and sent to the device.

[0933] Implementing your training plan

[0934] The device receives a training plan, which is then displayed in the app for the user to view. The user can then begin practicing according to the plan and periodically check their progress. The plan may include video and audio guides, practice assignments, relaxation exercises, and more.

[0935] Specific examples

[0936] For example, User A launches the app and records a passage from "Let It Be." The device sends the audio data and emotional data indicating "high tension" to the server. The server then analyzes the audio data using a generative AI model and produces an evaluation result indicating "your pitch is somewhat unstable and your rhythm tends to lag." It then corrects the evaluation based on the emotional data and provides specific feedback. The server then generates a training plan that includes improving pitch stability, strengthening your sense of rhythm, and relaxation exercises, and sends it to the device. User A follows this plan and begins practicing, including the suggested relaxation exercises.

[0937] Examples of prompt statements

[0938] Below are some example prompts to input to a generative AI model:

[0939] 1. "Write a script that analyzes a user's voice data and evaluates their singing ability. Evaluation criteria should include pitch, rhythm, pronunciation, and emotional expression."

[0940] 2. "Based on the emotion recognition results, please design an algorithm to correct the singing ability evaluation and create a program that outputs the results in the form of a score and comments."

[0941] In this way, the present invention realizes a system that provides an objective evaluation of singing ability that also takes into account the user's emotional state, and an individualized training plan at low cost.

[0942] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0943] Step 1:

[0944] The user launches the dedicated app and the recording interface appears on the device. The user taps the record button and starts singing. When the user finishes recording, the device saves the audio data to local storage. At the same time, the device uses an emotion engine to analyze the user's emotional state and extract emotion data.

[0945] Input: User's singing voice

[0946] Output: Audio data (recorded file) and emotion data (analysis results)

[0947] Step 2:

[0948] The device transmits the stored voice data and emotion data to a server via the Internet, which receives the data and stores it in a database.

[0949] Input: Voice data, emotion data

[0950] Output: Storage of voice data and emotion data on the server

[0951] Step 3:

[0952] The server inputs the audio data into a generative AI model. The AI ​​model analyzes pitch, rhythm, pronunciation, emotional expression, and other factors to extract various characteristics. For example, it evaluates the stability of pitch and the accuracy of rhythm. At the same time, emotional data is also analyzed, resulting in a comprehensive analysis result.

[0953] Input: Voice data, emotion data

[0954] Output: Analysis results (pitch, rhythm, pronunciation, emotional expression)

[0955] Step 4:

[0956] The server evaluates the user's singing ability based on the analysis results. The evaluation is displayed in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The server then corrects the emotion recognition results and generates detailed feedback.

[0957] Input: Analysis results (pitch, rhythm, pronunciation, emotional expression), emotional data

[0958] Output: Evaluation results (score, comments)

[0959] Step 5:

[0960] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotional data. This plan includes improving pitch stability, strengthening rhythmic sense, and relaxation exercises. The plan is customized for each user, and specific practice methods are provided.

[0961] Input: Evaluation results, emotion data

[0962] Output: Voice Training Plan (Customized Plan)

[0963] Step 6:

[0964] The server sends the generated voice training plan to the device. The device receives the plan and displays it within the app. The user begins practicing according to the plan, and the app records the practice progress.

[0965] Enter: Voice Training Plan

[0966] Output: Plan display and practice record to user

[0967] In this way, the user, the terminal, and the server cooperate to carry out the process at each step, thereby providing an accurate singing ability evaluation and an individualized training plan that takes into account the user's emotional state.

[0968] (Application example 2)

[0969] 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."

[0970] While conventional vocal training systems provide technical evaluations of pitch and rhythm, they struggle to provide feedback and training plans that take the user's emotional state into account. As a result, users often practice singing while experiencing emotional issues such as tension or anxiety, resulting in ineffective training. Furthermore, there has been a lack of methods for accurately evaluating a user's singing ability and providing a customized training plan tailored to their individual needs.

[0971] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0972] In this invention, the server includes means for collecting a user's voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for analyzing the user's emotional state, means for reflecting the emotional state in the evaluation results, means for generating a training plan according to the user's emotional state, means for uploading the voice data and emotional state data to the server, and means for including specific practice methods and areas for improvement in the voice training plan, as well as exercises according to the user's emotional state. This enables more effective and customized voice training that takes into account not only the user's technical ability but also their emotional state.

[0973] "Audio data" is digital data that includes audio signals such as singing recorded by a user.

[0974] A "generative artificial intelligence model" is a system that includes an artificial intelligence algorithm that analyzes audio data as input and evaluates characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[0975] The "evaluation results" are data including scores and comments on the user's singing ability analyzed by the generative artificial intelligence model, as well as an evaluation of the user's emotional state.

[0976] A "voice training plan" is a teaching program that includes specific practice methods, areas for improvement, and exercises to improve the user's singing ability.

[0977] "Emotional state" is data that indicates the psychological state, such as tension, anxiety, or relaxation, that the user feels while singing.

[0978] "Means for analyzing" refers to methods and apparatus that use generative artificial intelligence models to evaluate audio data and emotional states.

[0979] The "means for extracting" refers to a method and apparatus for extracting an optimal voice training plan from a database based on the user's evaluation results.

[0980] The "means for providing" refers to a method and device for displaying and distributing the extracted voice training plan on the user's terminal.

[0981] "Uploading means" refers to a method and apparatus for transmitting a user's voice data and emotional state data to a server over the Internet.

[0982] The "means for analyzing emotional state" refers to a method and device for analyzing the psychological state of a user from the user's voice data and facial expression data.

[0983] The "reflecting means" refers to a method and device for incorporating the analyzed emotional state into the evaluation of the user's singing ability.

[0984] The "means for generating" refers to a method and apparatus for creating a customized training plan for a user based on the assessment results and emotional state.

[0985] The present invention is a system for users to evaluate their singing ability and provide a personalized vocal training plan. The system collects the user's voice data and emotional state data, and generates personalized feedback and training plans based on the analysis results.

[0986] System Configuration

[0987] The system consists of the following main components:

[0988] 1. User Device

[0989] The user terminals are smartphones and head-mounted displays, which are devices that allow users to record their singing and capture their emotional state.

[0990] It provides an audio recording interface and stores the recording data in local storage.

[0991] An emotion engine is used to analyze the user's emotional state.

[0992] 2. Server

[0993] The system receives voice data and emotion data and analyzes them using a generative AI model, such as Python, pydub, EmotionEngine, and SingingEvaluation.

[0994] The system evaluates the user's singing ability and extracts and generates a voice training plan from a database based on the evaluation results.

[0995] This training plan includes specific drills, areas for improvement, and even exercises tailored to your emotional state.

[0996] 3. Network Infrastructure

[0997] It supports data communication between the user device and the server. Voice data and emotion data are uploaded to the server via an internet connection, and analysis results and training plans are sent to the user device.

[0998] Data collection and analysis

[0999] 1. Collection of audio data

[1000] The user uses the application to record themselves singing. Once the recording is complete, the audio data is saved to local storage. At that time, the emotion engine analyzes the user's emotional state, and the emotional data is also saved.

[1001] 2. Data transmission

[1002] The recorded voice data and emotion data are sent to the server via the network, where the server receives the data and begins analyzing it.

[1003] 3. Data Analysis

[1004] The server uses a generative AI model to analyze the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The results of the emotion analysis performed by the emotion engine are also taken into account in the evaluation.

[1005] Creation and delivery of training plans

[1006] Based on the analysis results, the server evaluates the user's singing ability and extracts an optimal vocal training plan from the database based on the evaluation. The training plan includes exercises that address the user's specific weaknesses (e.g., pitch, rhythm) and emotional state (relaxation, concentration).

[1007] The generated training plan is sent from the server to the user's device and displayed within the app. The user can then begin practicing according to the plan and monitor their progress within the application.

[1008] Specific examples

[1009] For example, a user launches the app and records a passage from a "famous song." The recording is made through the smartphone's microphone, while the camera in the head-mounted display captures the user's facial expressions and analyzes their emotional state. Once the recording is complete, the audio data and emotional data are sent to the server. The server analyzes this data and provides a detailed evaluation of pitch and rhythm, as well as the emotional state the user felt while singing. A training plan is automatically generated based on the results and sent to the user's device. The user can view the generated plan and begin practicing.

[1010] Example of input prompt for generative AI model

[1011] The following prompt sentences are used to provide examples of input to a generative artificial intelligence model:

[1012] "Based on the following audio data and its emotional analysis results, please evaluate the user's singing ability and generate the optimal vocal training plan.

[1013] Audio data: (attached audio file)

[1014] Emotion analysis results: "Emotion: Tension, Confidence: 0.85"

[1015] Expected output: Evaluation of pitch, rhythm, pronunciation, and emotional expression, and a training plan based on the evaluation. For example, specific practice methods to improve the causes of pitch instability and suggestions for relaxation exercises to reduce tension.

[1016] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1017] Step 1:

[1018] The user starts the application using a smartphone or a head-mounted display and records their singing.

[1019] Input: User's voice and facial expression data

[1020] Specific operation: The user presses the record button, finishes singing, and then presses the stop button. The application saves the voice data and facial expression data to local storage.

[1021] Step 2:

[1022] The device sends the recorded voice data and the emotion data analyzed by the emotion engine to the server.

[1023] Input: Voice and emotion data in local storage

[1024] Specific operation: The application uploads voice data and emotion data to a server via an internet connection.

[1025] Step 3:

[1026] The server inputs the received voice data and emotion data into a generative artificial intelligence model for analysis.

[1027] Input: Voice data and emotion data uploaded to the server

[1028] Specific operation: Run the script and input data into a generative artificial intelligence model (e.g., Python and pydub, EmotionEngine, SingingEvaluation) for analysis.

[1029] Step 4:

[1030] The server generates analysis results and evaluates the user's singing ability.

[1031] Input: Analysis results from a generative artificial intelligence model

[1032] Output: A detailed assessment of the user's pitch, rhythm, pronunciation, and emotional expression.

[1033] Specific operation: Based on the analysis results, an evaluation is generated in the form of a score and comments, and the emotional state is also reflected along with the evaluation.

[1034] Step 5:

[1035] Based on the evaluation results, the server extracts the optimal voice training plan from the database and customizes and generates it.

[1036] Input: User evaluation results and emotion data

[1037] Output: Personalized voice training plan

[1038] Specific operation: Extract appropriate practice methods and exercises from the database and generate an optimal plan based on the user's evaluation results and emotional state.

[1039] Step 6:

[1040] The server transmits the generated voice training plan to the user terminal.

[1041] Enter: a customized voice training plan.

[1042] Output: Sending the training plan to the user's device

[1043] Specific operation: The server sends the training plan to the user's device via the Internet, where it is displayed within the application.

[1044] Step 7:

[1045] The user follows the voice training plan sent to them and begins practicing.

[1046] Input: Training plan displayed on user's device

[1047] What it does: The user follows a training plan within the app, practicing with audio guidance and videos, and the app provides feedback on their progress and emotional state during practice.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] [Fourth embodiment]

[1052] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1053] 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.

[1054] 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).

[1055] 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.

[1056] 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.

[1057] 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).

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] 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.

[1064] 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."

[1065] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate an individual's singing ability and provide an optimal voice training plan.

[1066] Collecting user voice data

[1067] Users record their singing through a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device then stores the audio data in its local storage.

[1068] Sending and analyzing voice data

[1069] The device then sends the recorded voice data over the internet to a server. The server receives the voice data and inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[1070] Singing ability evaluation

[1071] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "unstable pitch and weak sense of rhythm." The server saves the evaluation results and uses them in the next step.

[1072] Extract and generate the best voice training plan

[1073] The server references the evaluation results and extracts the optimal vocal training plan from a database of past training. The selected training plan is tailored to the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[1074] Training plan distribution and implementation

[1075] The generated training plan is sent from the server to the device. The device displays the received training plan within the app so that the user can view it. The user can then begin practicing according to the training plan.

[1076] Specific examples

[1077] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data to the server, which analyzes it. The analysis results in an evaluation that "your pitch is somewhat unstable and your rhythm tends to lag." Based on this evaluation, the server generates a training plan that includes pitch practice and rhythm strengthening exercises and sends it to the device. By following this plan and starting to practice, User A can effectively improve their singing ability.

[1078] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan at low cost.

[1079] The processing flow will be explained below.

[1080] Step 1:

[1081] The user launches the app and goes to the recording screen. The device displays the recording interface.

[1082] Step 2:

[1083] The user presses the record button. The device activates the microphone and starts collecting audio data. The user starts singing.

[1084] Step 3:

[1085] When the user finishes singing, they press the stop button, and the device stops recording and saves the audio file to local storage.

[1086] Step 4:

[1087] The device sends the recorded voice data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data.

[1088] Step 5:

[1089] The server receives the voice data and inputs it into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[1090] Step 6:

[1091] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[1092] Step 7:

[1093] The server evaluates the user's singing ability based on the analysis results, and the evaluation is in the form of a score and comments, indicating specific weaknesses and strengths.

[1094] Step 8:

[1095] Based on the evaluation results, the server extracts the optimal voice training plan from the database, and selects a training plan tailored to the user's specific weaknesses.

[1096] Step 9:

[1097] The server then customizes the training plan for the user, including adding specific exercises and improvements.

[1098] Step 10:

[1099] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[1100] Step 11:

[1101] Users can review the training plan and follow the instructions to begin practicing, which includes videos, audio guides, and exercises.

[1102] Step 12:

[1103] After a certain period of training, the user records again to check their progress, and the device sends the new recording to the server for re-evaluation.

[1104] By proceeding step by step in this way, the user can effectively improve their singing ability. The specific operations at each step demonstrate that the entire system functions smoothly.

[1105] Example 1

[1106] 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."

[1107] Conventional singing ability evaluation systems have had the problem of being difficult to accurately evaluate a user's singing ability and provide an individually customized vocal training plan. Furthermore, the means for efficiently providing evaluation results and training plans to users are limited, leaving users with a lack of effective ways to improve their weaknesses. This has led to the problem that it is difficult for users to effectively improve their singing ability in a short period of time.

[1108] 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.

[1109] In this invention, the server includes a means for uploading a user's voice data to the server, a means for inputting the data into a generative artificial intelligence model for analysis, a means for extracting an optimal vocal training plan from a database based on the evaluation results, and a means for customizing the training plan to suit the user's specific weaknesses. This makes it possible to accurately evaluate a user's singing ability and provide an optimal vocal training plan that addresses each weakness. Furthermore, the training plan includes specific practice methods and areas for improvement and is delivered to the user's terminal using an encrypted protocol, allowing the user to train safely and efficiently.

[1110] "User voice data" refers to recorded voice data collected by a user using a dedicated device.

[1111] A "generative artificial intelligence model" is an artificial intelligence model that learns from large amounts of data and performs appropriate processing and analysis on given input data.

[1112] A "server" is a central computer system that stores, processes, and distributes data to other devices over a network.

[1113] The "evaluation means" is a means for evaluating the user's singing ability in the form of numerical values ​​or comments based on data analyzed by the generative artificial intelligence model.

[1114] A "database" is a system configured to efficiently manage, store, and search large amounts of data.

[1115] A "voice training plan" is a plan that specifies practice methods and training steps designed to improve a user's singing ability.

[1116] The "customization means" is a means for individually adjusting the optimal training plan based on the user's evaluation results, and changing the plan to suit the user's specific weaknesses and needs.

[1117] An "encrypted protocol" is a communication method used to protect the contents of data when it is sent and received, and is a technology that prevents third parties from reading the contents.

[1118] A "user terminal" is a device that can be directly operated by a user, such as a smartphone or tablet.

[1119] The "practice method" indicates the specific practice content and procedures that the user should follow in order to improve their singing ability.

[1120] This invention relates to a system that uses voice recognition technology and generative AI models to evaluate a user's singing ability and provide an individually customized vocal training plan. The following describes specific embodiments of the invention.

[1121] Collecting user voice data

[1122] The user launches a dedicated application on a device such as a smartphone or tablet. The application displays an interface for recording audio. The user presses the record button to start singing and the stop button to end recording. The device saves the recorded audio data in local storage. This temporarily saves the audio data.

[1123] Sending and analyzing voice data

[1124] The device uploads the saved voice data to a server via the internet. The data is securely transmitted using an encrypted protocol (e.g., HTTPS). The server receives the voice data and inputs it into a generative AI model (e.g., OpenAI's GPT-3, Google's BERT, etc.). The generative AI model analyzes the voice data and extracts features such as pitch, rhythm, pronunciation, and emotional expression. The analysis results are returned to the server.

[1125] Singing ability evaluation

[1126] The server evaluates the user's singing ability based on the data analyzed by the generative AI model. The evaluation is provided in the form of a number (e.g., 0-100 points) or a comment. For example, the evaluation result may be displayed as "unstable pitch and weak sense of rhythm." The server then stores the evaluation results in a database.

[1127] Extract and generate the best voice training plan

[1128] The server then references the evaluation results and extracts the optimal vocal training plan from its database. The training plan addresses the user's specific weaknesses (e.g., improving pitch stability or rhythmic sense). The server then customizes the plan and generates it in a format (e.g., PDF or video) that includes specific practice methods and areas for improvement.

[1129] Training plan distribution and implementation

[1130] The server sends the generated training plan to the device. The plan is sent using an encrypted protocol, ensuring secure data delivery. The device displays the training plan within the app so that the user can review it. The user then begins practicing according to the plan. The application displays a metronome and pitch guide, allowing the user to practice according to the appropriate guide.

[1131] Specific examples

[1132] For example, User A starts the application and records a passage from "Let It Be." The device uploads the recorded audio data to the server, which analyzes it using a generative AI model. The analysis results indicate that "the pitch is somewhat unstable and the rhythm tends to lag." Based on this evaluation, the server generates a training plan including pitch practice and rhythm strengthening exercises and sends it to the device. User A follows this plan and begins practicing using the metronome and pitch guide provided within the app.

[1133] Prompt Sentence Examples

[1134] Analyze the user's singing voice data and evaluate it based on pitch, rhythm, pronunciation, and emotional expression. Also, propose the optimal vocal training plan based on the evaluation results.

[1135] In this way, the system accurately evaluates the user's singing ability and provides an optimal, individually tailored vocal training plan, enabling the user to effectively improve their singing ability in a short period of time.

[1136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1137] Step 1:

[1138] The user launches the application and moves to the recording screen. The application displays the recording interface, and the user presses the record button to begin singing. The input is the user's singing voice, and the device records that voice and collects audio data from the time the record button is pressed to the time the stop button is pressed. The output is the recorded audio data, which is saved in the device's local storage. Specifically, the audio signal is input to the device through the microphone and saved as digital data.

[1139] Step 2:

[1140] The device uploads the recorded audio data to the server via the Internet. The input is the recorded audio data, and the output is the data sent to the server. This involves encrypting the data (e.g., using SSL / TLS) and sending it. Specifically, the device sends the audio data via the network to the server's API endpoint using the POST method.

[1141] Step 3:

[1142] The server inputs the received voice data into a generative artificial intelligence model. The input is voice data, which the AI ​​model analyzes. The output is the analysis results for pitch, rhythm, pronunciation, emotional expression, etc. The server sends prompt sentences to the model to analyze these characteristics. Specifically, the voice data is passed to the input layer of the AI ​​model, where it undergoes computational processing and characteristic data is output.

[1143] Step 4:

[1144] The server evaluates the user's singing ability based on the analysis results of the generated AI model. The evaluation includes pitch accuracy, rhythmic stability, and pronunciation clarity. The input is the analysis results, and the output is the user's singing ability evaluation score and feedback in the form of comments. Specifically, the evaluation algorithm converts the characteristic data into a numerical score and generates feedback based on that score.

[1145] Step 5:

[1146] The server references the evaluation results and extracts the optimal voice training plan from the database. The input is the user's evaluation results, and the output is the optimal training plan. The server takes into account past training data and evaluation results to select a plan tailored to specific weaknesses (e.g., improving pitch stability or rhythmic sense). Specifically, it issues a query to the database and extracts relevant training data.

[1147] Step 6:

[1148] The server further customizes the selected training plan. The input is the extracted training plan and the user's evaluation results, and the output is a customized training plan. Specifically, the training content is adjusted and modified based on the evaluation results, and a training plan tailored to the user is created.

[1149] Step 7:

[1150] The server sends a customized voice training plan to the user's device. The input is the customized training plan, and the output is the data sent to the device. The transmission uses an encrypted protocol. Specifically, the server sends data to the device using an authentication token.

[1151] Step 8:

[1152] The voice training plan received by the device is displayed within the app. The input is the training plan sent from the server, and the output is the display content that the user can visually confirm. Specifically, the application constructs an interface based on the data acquired and presents the user with appropriate practice methods.

[1153] Step 9:

[1154] The user begins practicing according to the training plan. The input is the training plan displayed in the application, and the output is the practice results and feedback. Specifically, the user uses the metronome and pitch guide within the application to perform the instructed practice. The user's practice data is used in the subsequent evaluation process.

[1155] (Application example 1)

[1156] 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."

[1157] Traditional voice training often requires individual instruction from a professional instructor, which entails high costs and time constraints. While online instruction is becoming more common, few systems exist that provide detailed evaluations tailored to individual singing abilities or generate and provide appropriate training plans. Furthermore, there is a lack of systems that automatically collect and analyze users' singing data and provide effective training plans based on the results, making it difficult for users to efficiently improve their singing abilities.

[1158] 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.

[1159] In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for transmitting the voice data to the server via the Internet, means for customizing the training plan based on the user's singing ability evaluation results, and means for displaying the generated training plan on the user terminal. This allows users to receive training plans to efficiently improve their singing ability at home or elsewhere without relying on professional instructors.

[1160] "User" refers to an individual who uses the system to provide voice data and whose singing ability is evaluated.

[1161] "Audio Data" refers to a digital audio file of a user's singing recording.

[1162] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes input data and generates the analysis results.

[1163] "Analysis results" refers to evaluation information resulting from analyzing voice data using a generative artificial intelligence model.

[1164] "Singing ability" refers to the user's singing abilities, such as pitch, rhythm, pronunciation, and emotional expression.

[1165] A "database" refers to a collection of information that stores past training data and evaluation data.

[1166] A "voice training plan" refers to a plan that includes specific practice content and improvement methods created to improve a user's singing ability.

[1167] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1168] "Server" refers to a computer system used to analyze audio data and generate training plans.

[1169] "Customization" refers to individualizing a training plan based on a user's specific needs and assessment results.

[1170] "Internet" refers to the global network used to transmit audio data to servers.

[1171] About the system program

[1172] Hardware and software used

[1173] This system is implemented using the following hardware and software.

[1174] Hardware: Smartphones, personal computers, servers

[1175] Software: Flask (web server framework), Pytorch or Tensorflow (for building and training AI models), Requests (for handling HTTP requests)

[1176] Natural language description of the process

[1177] 1. Collecting user voice data

[1178] The user records any singing using a smartphone or personal computer.

[1179] For example, 30 seconds of singing is recorded as a digital audio file and saved to local storage.

[1180] 2. Transmission of data to a server over the Internet

[1181] The device uploads the recorded audio data to a server via the Internet as an HTTP POST request.

[1182] Send data using the Requests library.

[1183] 3. Analysis of audio data

[1184] The server inputs the received voice data into a generative artificial intelligence model and analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[1185] This is done by an AI model using Pytorch or Tensorflow.

[1186] 4. Singing ability evaluation

[1187] The server evaluates the user's singing ability based on the analysis results of the generative AI model. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag."

[1188] 5. Extract and generate a voice training plan

[1189] Based on the evaluation results, the server extracts and generates an optimal voice training plan from the database tailored to the user's specific weaknesses.

[1190] It references a database of past training sessions and generates a customized training plan for each user.

[1191] 6. Delivering and implementing training plans

[1192] The generated training plan is sent from the server to the user's device, which then displays the received training plan in the application, allowing the user to view and practice it.

[1193] Specific examples

[1194] For example, User A records a passage of "Let It Be" using a smartphone. User A presses the record button on the device and completes singing for 30 seconds. The device then sends the recorded audio data to the server, which analyzes it. The generative AI model analyzes pitch, rhythm, pronunciation, and emotional expression, and evaluates the result as "slightly unstable pitch and prone to delays in rhythm." Based on this evaluation, the server generates a customized training plan including pitch practice and rhythm strengthening exercises and sends it to the user's device. User A can effectively improve their singing ability by checking and practicing the training plan on their smartphone.

[1195] Prompt Sentence Examples

[1196] An example of a prompt for a generative AI model is:

[1197] "Please analyze user A's singing recording. Evaluate pitch, rhythm, pronunciation, and emotional expression, and provide a score. Generate an optimal training plan based on the evaluation results."

[1198] This makes it possible for the system to provide training plans that allow users to efficiently improve their singing ability at home, without relying on professional instructors.

[1199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1200] Step 1:

[1201] Users collect audio data using a smartphone or personal computer. Specifically, they press the record button on the application and sing a song of their choice. When recording is complete, they press the stop button and save the recorded data to local storage. The input is the user's singing voice, and the output is a digital audio file (e.g., user_recording.wav).

[1202] Step 2:

[1203] The device uploads recorded audio data to the server. The user device sends the recorded audio file to the server as an HTTP POST request. The input is a digital audio file, and the output is the audio data received by the server. The specific operation is to use the Requests library to send the data.

[1204] Step 3:

[1205] The server inputs the received audio data into a generative AI model for analysis. The input is the received audio data, and the output is the analysis results. The AI ​​model uses Pytorch or Tensorflow to analyze the audio data to analyze features such as pitch, rhythm, pronunciation, and emotional expression.

[1206] Step 4:

[1207] The server evaluates the user's singing ability based on the analysis results. The input is the analysis results obtained from the generative AI model, and the output is an evaluation score and comments on the user's singing ability. The evaluation results are expressed in concrete terms, such as "your pitch is a little unstable and your rhythm tends to lag."

[1208] Step 5:

[1209] The server extracts and generates the optimal vocal training plan from the database based on the evaluation results. The input is the singing ability evaluation score and comments, and the output is a customized vocal training plan. Specifically, it references the past training database and selects training methods that address the user's specific weaknesses.

[1210] Step 6:

[1211] The server sends the generated training plan to the user terminal. The input is the generated voice training plan, and the output is the training plan delivered to the user terminal. Specifically, the training plan is sent to the user terminal using an HTTP request.

[1212] Step 7:

[1213] The training plan received by the user's device is displayed within the application, allowing the user to view and practice. The input is the received voice training plan, and the output is the display of the training plan on the application. Specifically, the contents of the plan are displayed on the application UI, and the user begins practicing according to them.

[1214] This allows users to receive training plans to improve their singing ability efficiently at home, etc., without relying on professional instructors.

[1215] 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.

[1216] This invention relates to a system that combines voice recognition technology, a generative artificial intelligence model, and an emotion engine to evaluate the singing ability of each user and provide an optimal voice training plan.

[1217] User voice data collection and emotion recognition

[1218] Users record themselves singing using a dedicated application. The device displays a recording interface, and the user presses the record button and sings. When they finish singing, they press the stop button to complete the recording. The device saves this audio data in local storage and uses an emotion engine to analyze the user's emotions during recording.

[1219] Transmission and analysis of voice and emotion data

[1220] The device then sends the recorded voice data and the emotional data analyzed by the emotion engine to a server via the internet. The server receives the voice data and emotional data and inputs them into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the analysis results to the server.

[1221] Singing ability evaluation

[1222] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The evaluation is then corrected based on the emotion recognition results. For example, if the user is emotionally unstable or nervous, this effect can be reflected in the singing ability evaluation, providing more accurate feedback.

[1223] Extract and generate the best voice training plan

[1224] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotion recognition results. The selected training plan addresses the user's specific weaknesses (e.g., improving pitch stability, strengthening rhythmic sense) as well as their emotional state (relaxation, improving concentration). The server then customizes this plan for the user and generates a training plan that includes specific practice methods and areas for improvement.

[1225] Training plan distribution and implementation

[1226] The generated training plan is sent from the server to the device. The device displays the received training plan within the app for the user to view. The user then begins practicing according to the training plan. The plan includes video and audio guides, practice tasks, as well as advice and exercises tailored to the user's emotional state.

[1227] Specific examples

[1228] For example, User A starts the app and records a passage from "Let It Be." The device sends this audio data, along with the emotional data analyzed by the emotion engine during recording, to the server. The server analyzes the data and determines that the user's pitch is somewhat unstable and the rhythm tends to lag behind, and that the emotional analysis indicates a high level of tension. Based on these results, the server generates a training plan that includes pitch practice, rhythm strengthening exercises, and relaxation exercises, and sends it to the device. User A can start practicing according to this plan and effectively improve their singing ability by practicing the relaxation exercises suggested during practice.

[1229] In this way, the present invention realizes a system that objectively evaluates a user's singing ability and provides an individualized training plan that takes into account the user's emotional state at low cost.

[1230] The processing flow will be explained below.

[1231] Step 1:

[1232] The user launches the app and goes to the recording screen. The device displays the recording interface.

[1233] Step 2:

[1234] The user presses the record button. The device activates the microphone and starts collecting voice data. At the same time, the emotion engine also activates and begins analyzing the user's emotional state.

[1235] Step 3:

[1236] When the user finishes singing, they press the stop button. The device stops recording and saves the audio file in local storage. The emotion engine also finishes analyzing the data and saves the emotion data.

[1237] Step 4:

[1238] The device transmits the recorded voice data and emotion data to the server via the Internet. The device initiates the transmission process, and the server prepares to receive the voice data and emotion data.

[1239] Step 5:

[1240] The server receives the voice data and emotion data and inputs them into the generative AI model. The server then invokes the AI ​​model and begins analyzing the voice data.

[1241] Step 6:

[1242] The AI ​​model analyzes the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The analysis results are then returned to the server.

[1243] Step 7:

[1244] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, such as "Your pitch is a little unstable and you tend to be behind the rhythm." The evaluation is corrected based on the analysis results of the emotion engine. For example, it may include feedback such as "Your pitch became more unstable because you were nervous."

[1245] Step 8:

[1246] The server extracts the optimal voice training plan from the database based on the evaluation results and emotion recognition results. The server selects a training plan that takes into account the user's specific weaknesses as well as their emotional state.

[1247] Step 9:

[1248] The server then customizes the training plan for the user, including specific practice methods and areas for improvement, as well as exercises that address emotional states.

[1249] Step 10:

[1250] The server sends the customized training plan to the device, which then displays the received training plan in the app.

[1251] Step 11:

[1252] Users can view and follow the instructions for their training plan, which includes video and audio guides, practice exercises, and advice and exercises tailored to the user's emotional state.

[1253] Step 12:

[1254] After a certain period of training, the user records again to check their progress, and the device sends the new recording and emotional data to the server for re-evaluation.

[1255] In this way, through detailed processing steps, users can objectively evaluate their singing ability and receive a training plan that takes into account their emotional state. Through the specific operations of each step, it can be seen that the entire system functions smoothly.

[1256] Example 2

[1257] 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."

[1258] Conventional voice data analysis systems do not take into account a user's emotional state when evaluating their singing ability, resulting in poor evaluation accuracy and making it difficult to provide an individually customized training plan based on the user's specific weaknesses and emotional state.

[1259] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results and the user's emotional data, means for extracting an optimal voice training plan from a database based on the evaluation results and the emotional data, and means for providing the voice training plan to the user terminal. This enables accurate evaluation of singing ability taking into account the user's emotional state and provides an individually customized training plan.

[1260] "User's voice data" refers to data that represents voice information such as singing or conversation recorded by a user in digital format.

[1261] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that learns from large amounts of data and analyzes and predicts new data.

[1262] "Analysis" is the process of analyzing features and patterns based on input data and extracting the results.

[1263] "User emotion data" is data that analyzes the emotional state of the user while recording the voice and expresses it as numerical values ​​or categories.

[1264] "Evaluating singing ability" means evaluating elements of the user's singing, such as pitch, rhythm, pronunciation, and emotional expression, as scores or comments.

[1265] A "database" is a system for efficiently storing, managing, and searching data, or a collection of accumulated information.

[1266] A "voice training plan" is a written plan that includes practice methods, exercises, and improvements designed to improve a user's singing ability.

[1267] A "user terminal" is a digital device used by a user, such as a computer, smartphone, or tablet.

[1268] This invention relates to a system that combines voice recognition technology, a generative AI model, and an emotion engine to evaluate the singing ability of individual users and provide an optimal vocal training plan. This system collects the user's voice data, analyzes it using a generative AI model, and provides an evaluation and training plan based on the results.

[1269] User voice data collection and emotion recognition

[1270] The user launches the dedicated application, and the recording interface appears on the device. The user presses the record button and sings, recording the audio data. After recording is complete, the device saves the audio data in local storage. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and extract emotion data.

[1271] Transmission and analysis of voice and emotion data

[1272] The device sends the stored voice and emotion data to a server via the internet. When the server receives this data, it inputs it into a generative AI model. The AI ​​model analyzes characteristics such as pitch, rhythm, pronunciation, and emotional expression, and provides the results to the server.

[1273] Singing ability evaluation

[1274] The server evaluates the user's singing ability based on the analysis results. The evaluation is in the form of a score and comments, and the evaluation is also corrected by taking into account the emotion recognition results. For example, if the emotional state is "nervous," this influence is reflected in the evaluation and detailed feedback is provided.

[1275] Generate and deliver optimal voice training plans

[1276] The server extracts an optimal vocal training plan from the database based on the evaluation results and emotional data. This plan addresses the user's specific weaknesses and emotional state. A customized training plan including specific practice methods, areas for improvement, and exercises is generated and sent to the device.

[1277] Implementing your training plan

[1278] The device receives a training plan, which is then displayed in the app for the user to view. The user can then begin practicing according to the plan and periodically check their progress. The plan may include video and audio guides, practice assignments, relaxation exercises, and more.

[1279] Specific examples

[1280] For example, User A launches the app and records a passage from "Let It Be." The device sends the audio data and emotional data indicating "high tension" to the server. The server then analyzes the audio data using a generative AI model and produces an evaluation result indicating "your pitch is somewhat unstable and your rhythm tends to lag." It then corrects the evaluation based on the emotional data and provides specific feedback. The server then generates a training plan that includes improving pitch stability, strengthening your sense of rhythm, and relaxation exercises, and sends it to the device. User A follows this plan and begins practicing, including the suggested relaxation exercises.

[1281] Examples of prompt statements

[1282] Below are some example prompts to input to a generative AI model:

[1283] 1. "Write a script that analyzes a user's voice data and evaluates their singing ability. Evaluation criteria should include pitch, rhythm, pronunciation, and emotional expression."

[1284] 2. "Based on the emotion recognition results, please design an algorithm to correct the singing ability evaluation and create a program that outputs the results in the form of a score and comments."

[1285] In this way, the present invention realizes a system that provides an objective evaluation of singing ability that also takes into account the user's emotional state, and an individualized training plan at low cost.

[1286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1287] Step 1:

[1288] The user launches the dedicated app and the recording interface appears on the device. The user taps the record button and starts singing. When the user finishes recording, the device saves the audio data to local storage. At the same time, the device uses an emotion engine to analyze the user's emotional state and extract emotion data.

[1289] Input: User's singing voice

[1290] Output: Audio data (recorded file) and emotion data (analysis results)

[1291] Step 2:

[1292] The device transmits the stored voice data and emotion data to a server via the Internet, which receives the data and stores it in a database.

[1293] Input: Voice data, emotion data

[1294] Output: Storage of voice data and emotion data on the server

[1295] Step 3:

[1296] The server inputs the audio data into a generative AI model. The AI ​​model analyzes pitch, rhythm, pronunciation, emotional expression, and other factors to extract various characteristics. For example, it evaluates the stability of pitch and the accuracy of rhythm. At the same time, emotional data is also analyzed, resulting in a comprehensive analysis result.

[1297] Input: Voice data, emotion data

[1298] Output: Analysis results (pitch, rhythm, pronunciation, emotional expression)

[1299] Step 4:

[1300] The server evaluates the user's singing ability based on the analysis results. The evaluation is displayed in the form of a score and comments, such as "Your pitch is a little unstable and your rhythm tends to lag." The server then corrects the emotion recognition results and generates detailed feedback.

[1301] Input: Analysis results (pitch, rhythm, pronunciation, emotional expression), emotional data

[1302] Output: Evaluation results (score, comments)

[1303] Step 5:

[1304] The server extracts the optimal vocal training plan from the database based on the evaluation results and emotional data. This plan includes improving pitch stability, strengthening rhythmic sense, and relaxation exercises. The plan is customized for each user, and specific practice methods are provided.

[1305] Input: Evaluation results, emotion data

[1306] Output: Voice Training Plan (Customized Plan)

[1307] Step 6:

[1308] The server sends the generated voice training plan to the device. The device receives the plan and displays it within the app. The user begins practicing according to the plan, and the app records the practice progress.

[1309] Enter: Voice Training Plan

[1310] Output: Plan display and practice record to user

[1311] In this way, the user, the terminal, and the server cooperate to carry out the process at each step, thereby providing an accurate singing ability evaluation and an individualized training plan that takes into account the user's emotional state.

[1312] (Application example 2)

[1313] 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."

[1314] While conventional vocal training systems provide technical evaluations of pitch and rhythm, they struggle to provide feedback and training plans that take the user's emotional state into account. As a result, users often practice singing while experiencing emotional issues such as tension or anxiety, resulting in ineffective training. Furthermore, there has been a lack of methods for accurately evaluating a user's singing ability and providing a customized training plan tailored to their individual needs.

[1315] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1316] In this invention, the server includes means for collecting a user's voice data, means for inputting the voice data into a generative artificial intelligence model for analysis, means for evaluating the user's singing ability based on the analysis results, means for extracting an optimal voice training plan from a database based on the evaluation results, means for providing the voice training plan to a user terminal, means for analyzing the user's emotional state, means for reflecting the emotional state in the evaluation results, means for generating a training plan according to the user's emotional state, means for uploading the voice data and emotional state data to the server, and means for including specific practice methods and areas for improvement in the voice training plan, as well as exercises according to the user's emotional state. This enables more effective and customized voice training that takes into account not only the user's technical ability but also their emotional state.

[1317] "Audio data" is digital data that includes audio signals such as singing recorded by a user.

[1318] A "generative artificial intelligence model" is a system that includes an artificial intelligence algorithm that analyzes audio data as input and evaluates characteristics such as pitch, rhythm, pronunciation, and emotional expression.

[1319] The "evaluation results" are data including scores and comments on the user's singing ability analyzed by the generative artificial intelligence model, as well as an evaluation of the user's emotional state.

[1320] A "voice training plan" is a teaching program that includes specific practice methods, areas for improvement, and exercises to improve the user's singing ability.

[1321] "Emotional state" is data that indicates the psychological state, such as tension, anxiety, or relaxation, that the user feels while singing.

[1322] "Means for analyzing" refers to methods and apparatus that use generative artificial intelligence models to evaluate audio data and emotional states.

[1323] The "means for extracting" refers to a method and apparatus for extracting an optimal voice training plan from a database based on the user's evaluation results.

[1324] The "means for providing" refers to a method and device for displaying and distributing the extracted voice training plan on the user's terminal.

[1325] "Uploading means" refers to a method and apparatus for transmitting a user's voice data and emotional state data to a server over the Internet.

[1326] The "means for analyzing emotional state" refers to a method and device for analyzing the psychological state of a user from the user's voice data and facial expression data.

[1327] The "reflecting means" refers to a method and device for incorporating the analyzed emotional state into the evaluation of the user's singing ability.

[1328] The "means for generating" refers to a method and apparatus for creating a customized training plan for a user based on the assessment results and emotional state.

[1329] The present invention is a system for users to evaluate their singing ability and provide a personalized vocal training plan. The system collects the user's voice data and emotional state data, and generates personalized feedback and training plans based on the analysis results.

[1330] System Configuration

[1331] The system consists of the following main components:

[1332] 1. User Device

[1333] The user terminals are smartphones and head-mounted displays, which are devices that allow users to record their singing and capture their emotional state.

[1334] It provides an audio recording interface and stores the recording data in local storage.

[1335] An emotion engine is used to analyze the user's emotional state.

[1336] 2. Server

[1337] The system receives voice data and emotion data and analyzes them using a generative AI model, such as Python, pydub, EmotionEngine, and SingingEvaluation.

[1338] The system evaluates the user's singing ability and extracts and generates a voice training plan from a database based on the evaluation results.

[1339] This training plan includes specific drills, areas for improvement, and even exercises tailored to your emotional state.

[1340] 3. Network Infrastructure

[1341] It supports data communication between the user device and the server. Voice data and emotion data are uploaded to the server via an internet connection, and analysis results and training plans are sent to the user device.

[1342] Data collection and analysis

[1343] 1. Collection of audio data

[1344] The user uses the application to record themselves singing. Once the recording is complete, the audio data is saved to local storage. At that time, the emotion engine analyzes the user's emotional state, and the emotional data is also saved.

[1345] 2. Data transmission

[1346] The recorded voice data and emotion data are sent to the server via the network, where the server receives the data and begins analyzing it.

[1347] 3. Data Analysis

[1348] The server uses a generative AI model to analyze the audio data, focusing on pitch, rhythm, pronunciation, and emotional expression. The results of the emotion analysis performed by the emotion engine are also taken into account in the evaluation.

[1349] Creation and delivery of training plans

[1350] Based on the analysis results, the server evaluates the user's singing ability and extracts an optimal vocal training plan from the database based on the evaluation. The training plan includes exercises that address the user's specific weaknesses (e.g., pitch, rhythm) and emotional state (relaxation, concentration).

[1351] The generated training plan is sent from the server to the user's device and displayed within the app. The user can then begin practicing according to the plan and monitor their progress within the application.

[1352] Specific examples

[1353] For example, a user launches the app and records a passage from a "famous song." The recording is made through the smartphone's microphone, while the camera in the head-mounted display captures the user's facial expressions and analyzes their emotional state. Once the recording is complete, the audio data and emotional data are sent to the server. The server analyzes this data and provides a detailed evaluation of pitch and rhythm, as well as the emotional state the user felt while singing. A training plan is automatically generated based on the results and sent to the user's device. The user can view the generated plan and begin practicing.

[1354] Example of input prompt for generative AI model

[1355] The following prompt sentences are used to provide examples of input to a generative artificial intelligence model:

[1356] "Based on the following audio data and its emotional analysis results, please evaluate the user's singing ability and generate the optimal vocal training plan.

[1357] Audio data: (attached audio file)

[1358] Emotion analysis results: "Emotion: Tension, Confidence: 0.85"

[1359] Expected output: Evaluation of pitch, rhythm, pronunciation, and emotional expression, and a training plan based on the evaluation. For example, specific practice methods to improve the causes of pitch instability and suggestions for relaxation exercises to reduce tension.

[1360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1361] Step 1:

[1362] The user starts the application using a smartphone or a head-mounted display and records their singing.

[1363] Input: User's voice and facial expression data

[1364] Specific operation: The user presses the record button, finishes singing, and then presses the stop button. The application saves the voice data and facial expression data to local storage.

[1365] Step 2:

[1366] The device sends the recorded voice data and the emotion data analyzed by the emotion engine to the server.

[1367] Input: Voice and emotion data in local storage

[1368] Specific operation: The application uploads voice data and emotion data to a server via an internet connection.

[1369] Step 3:

[1370] The server inputs the received voice data and emotion data into a generative artificial intelligence model for analysis.

[1371] Input: Voice data and emotion data uploaded to the server

[1372] Specific operation: Run the script and input data into a generative artificial intelligence model (e.g., Python and pydub, EmotionEngine, SingingEvaluation) for analysis.

[1373] Step 4:

[1374] The server generates analysis results and evaluates the user's singing ability.

[1375] Input: Analysis results from a generative artificial intelligence model

[1376] Output: A detailed assessment of the user's pitch, rhythm, pronunciation, and emotional expression.

[1377] Specific operation: Based on the analysis results, an evaluation is generated in the form of a score and comments, and the emotional state is also reflected along with the evaluation.

[1378] Step 5:

[1379] Based on the evaluation results, the server extracts the optimal voice training plan from the database and customizes and generates it.

[1380] Input: User evaluation results and emotion data

[1381] Output: Personalized voice training plan

[1382] Specific operation: Extract appropriate practice methods and exercises from the database and generate an optimal plan based on the user's evaluation results and emotional state.

[1383] Step 6:

[1384] The server transmits the generated voice training plan to the user terminal.

[1385] Enter: a customized voice training plan.

[1386] Output: Sending the training plan to the user's device

[1387] Specific operation: The server sends the training plan to the user's device via the Internet, where it is displayed within the application.

[1388] Step 7:

[1389] The user follows the voice training plan sent to them and begins practicing.

[1390] Input: Training plan displayed on user's device

[1391] What it does: The user follows a training plan within the app, practicing with audio guidance and videos, and the app provides feedback on their progress and emotional state during practice.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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).

[1399] 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.

[1400] 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."

[1401] 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.

[1402] 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).

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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.

[1412] 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.

[1413] The following is further disclosed regarding the above embodiment.

[1414] (Claim 1)

[1415] means for collecting user voice data;

[1416] means for inputting the voice data into a generative artificial intelligence model for analysis;

[1417] means for evaluating the singing ability of the user based on the analysis results;

[1418] A means for extracting an optimal voice training plan from a database based on the evaluation results;

[1419] A system including means for providing the voice training plan to a user terminal.

[1420] (Claim 2)

[1421] 10. The system of claim 1, further comprising means for uploading the audio data to a server.

[1422] (Claim 3)

[1423] 10. The system of claim 1, further comprising means for including specific practice methods and improvements in said vocal training plan.

[1424] "Example 1"

[1425] (Claim 1)

[1426] means for collecting user voice data;

[1427] means for uploading the audio data to a server;

[1428] means for inputting the voice data into a generative artificial intelligence model for analysis;

[1429] means for evaluating the singing ability of the user based on the analysis results;

[1430] A means for extracting an optimal voice training plan from a database based on the evaluation results;

[1431] means for customizing said training plan to a user's particular weaknesses;

[1432] means for providing the customized voice training plan to a user terminal;

[1433] The system includes a means for a user to begin practicing with a training plan.

[1434] (Claim 2)

[1435] 10. The system of claim 1, further comprising means for including specific exercises and improvements in said training plan.

[1436] (Claim 3)

[1437] 10. The system of claim 1, further comprising means for transmitting the training plan using an encrypted protocol.

[1438] "Application Example 1"

[1439] (Claim 1)

[1440] means for collecting user voice data;

[1441] means for inputting the voice data into a generative artificial intelligence model for analysis;

[1442] means for evaluating the singing ability of the user based on the analysis results;

[1443] A means for extracting an optimal voice training plan from a database based on the evaluation results;

[1444] means for providing the voice training plan to a user terminal;

[1445] means for transmitting the voice data to a server via the Internet;

[1446] A means for customizing a training plan based on the user's singing ability evaluation results;

[1447] The system includes a means for displaying the generated training plan on a user terminal.

[1448] (Claim 2)

[1449] 10. The system of claim 1, further comprising means for uploading the audio data to a server.

[1450] (Claim 3)

[1451] 10. The system of claim 1, further comprising means for including specific practice methods and improvements in said vocal training plan.

[1452] "Example 2: Combining Emotion Engines"

[1453] (Claim 1)

[1454] means for collecting user voice data;

[1455] means for inputting the voice data into a generative artificial intelligence model for analysis;

[1456] means for evaluating the singing ability of the user based on the analysis results and the user's emotion data;

[1457] means for extracting an optimal voice training plan from a database based on the evaluation results and the emotion data;

[1458] A system including means for providing the voice training plan to a user terminal.

[1459] (Claim 2)

[1460] The system of claim 1 , further comprising means for uploading the voice data and emotion data to a server.

[1461] (Claim 3)

[1462] 10. The system of claim 1, further comprising means for including specific practice methods, exercises, and improvements in said vocal training plan.

[1463] "Application example 2 when combining emotion engines"

[1464] (Claim 1)

[1465] means for collecting user voice data;

[1466] means for inputting the voice data into a generative artificial intelligence model for analysis;

[1467] means for evaluating the singing ability of the user based on the analysis results;

[1468] A means for extracting an optimal voice training plan from a database based on the evaluation results;

[1469] means for providing the voice training plan to a user terminal;

[1470] means for analyzing the emotional state of a user;

[1471] a means for reflecting the emotional state in an evaluation result;

[1472] A system including means for generating a training plan according to a user's emotional state.

[1473] (Claim 2)

[1474] 10. The system of claim 1, further comprising means for uploading the voice data and emotional state data to a server.

[1475] (Claim 3)

[1476] 10. The system of claim 1, further comprising means for including in the vocal training plan specific practice methods and improvements, and exercises that respond to the user's emotional state. [Explanation of symbols]

[1477] 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. means for collecting user voice data; means for inputting the voice data into a generative artificial intelligence model for analysis; means for evaluating the singing ability of the user based on the analysis results; A means for extracting an optimal voice training plan from a database based on the evaluation results; A system including means for providing the voice training plan to a user terminal.

2. The system of claim 1 further comprising means for uploading the audio data to a server.

3. 10. The system of claim 1, further comprising means for including specific practice methods and improvements in said vocal training plan.

Images