System

Abstract

A system is provided.SOLUTION: A system includes means for collecting information from a user, means for analyzing the collected information and diagnosing a behavior pattern and a psychological state of the user, means for generating an optimal musical characteristic on the basis of an analysis result, means for distributing the generated musical characteristic to a terminal of the user, and means for collecting feedback from the user and updating a machine learning model.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] In modern society, factors such as a declining birthrate and aging population, an increase in single-person households, and smartphone dependency are causing physical and mental fatigue to accumulate. Labor shortages in the service industry and copyright issues regarding music use are also prominent. While appropriate solutions to these issues are needed, conventional methods have not been sufficiently effective. In particular, it has been difficult to provide an effective music experience while addressing the needs of individual users and avoiding copyright issues. Therefore, the present invention aims to provide a new system that uses AI to generate optimal music that influences people's awareness and behavior, thereby improving the quality of their lives. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, it includes a means for collecting information from users. This information includes age, gender, lifestyle patterns, music preferences, etc. Next, it includes a means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state. This analysis utilizes a machine learning model to grasp the user's individual characteristics in detail. Next, it includes a means for generating optimal music characteristics based on the analysis results. The generated music characteristics are then distributed to the user's device. It also includes a means for collecting feedback from users and updating the machine learning model. This cycle provides a system that provides an optimal sound experience for each user and enables effective music use while avoiding copyright issues.

[0006] "User" refers to an individual or company that uses this system.

[0007] "Information" refers to data such as the user's age, gender, lifestyle, and musical preferences.

[0008] "Collecting" refers to the process of obtaining information from users and storing it in a database or server.

[0009] "Analyzing" refers to the process of diagnosing a user's behavioral patterns and psychological state based on collected information using machine learning models and statistical methods.

[0010] "Behavioral patterns" refer to the sequence of actions and habits of a user in their daily life.

[0011] "Mental state" refers to the user's emotional and mood state.

[0012] "Musical characteristics" refers to the tempo, frequency, melody, tone, etc. of music.

[0013] "Distributing" refers to the process of transferring the generated music characteristics to a user's terminal so that they can be played.

[0014] "Terminal" refers to a device such as a smartphone, tablet, or PC that a user uses to access the system.

[0015] "Feedback" refers to the evaluation of satisfaction and effectiveness provided by users after use.

[0016] A "machine learning model" refers to an algorithm that learns from collected data and improves the performance of analytical and generation processes.

[0017] "Updating" refers to the process of incorporating new feedback and data to improve the performance of a machine learning model.

[0018] "Sound experience" refers to the sensations and emotions that users get through music, especially the comfort and relaxation effects.

[0019] "Copyright issues" refer to legal issues and troubles regarding the right to use music.

[0020] "System" refers to the entire system, including all processes related to collecting information from users, analyzing it, generating music, distributing it, and collecting and learning from feedback, as well as all related technical elements. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is a system that provides an optimal music experience based on user information, and is specifically implemented as follows.

[0043] Data Collection Phase

[0044] Users install the smartphone app and enter their age, gender, wake-up time, bedtime, and preferred music genre. The app can also connect to health devices (e.g., smartwatches) to obtain more detailed lifestyle data (e.g., heart rate, sleep patterns, etc.). This information is sent from the device to the server via a secure protocol.

[0045] Data analysis phase

[0046] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. The analysis provides a detailed diagnosis of the user's behavioral patterns and psychological state. For example, a time series analysis of the user's past sleep data can be performed to predict the optimal music characteristics for the next wake-up time.

[0047] Sound Generation Phase

[0048] Based on the analysis results, the server uses a music generation algorithm (e.g., MusicVAE) to generate optimal music. This music generation algorithm inputs parameters such as tempo and frequency to generate optimized sound. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library and temporarily stored on the server.

[0049] Sound Distribution Phase

[0050] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio, gradually increasing the volume to wake up the user, for example, to promote natural waking.

[0051] Feedback gathering and learning phase

[0052] After experiencing the sound, users enter feedback within the app about the effect, including their assessment of the quality of their awakening and the relaxing effect before sleep. The device then sends this feedback to the server, which stores the new data in a database. This feedback data is used to update the performance of the machine learning model and is reflected in future music generation.

[0053] Specific examples

[0054] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and gradually play classical music-based sounds with a relaxing effect starting 15 minutes (6:45am) before waking up. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation.

[0055] As described above, the present invention is a system that provides an optimal sound experience that meets the user's needs in each phase and enables continuous improvement of service performance through feedback.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user installs the smartphone app and launches it. An initial setup screen appears, prompting the user to enter information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device (such as a smartwatch) and enter more detailed lifestyle data (heart rate, sleep patterns, etc.).

[0059] Step 2:

[0060] The terminal sends the data entered by the user to the server using a secure protocol (e.g., HTTPS). The sent data is encrypted to maintain security.

[0061] Step 3:

[0062] The server receives the user information sent from the terminal and stores it in a database.

[0063] Step 4:

[0064] The server uses Python's Pandas and Scikit-learn libraries to analyze user information stored in the database. The analysis diagnoses the user's past behavioral patterns and psychological state. For example, it analyzes past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0065] Step 5:

[0066] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. This music data (e.g., MIDI file) is then converted into an audio file (e.g., mp3) using a voice synthesis library.

[0067] Step 6:

[0068] The server temporarily stores the generated audio file and checks the user's schedule information. For example, when it is 15 minutes before the user's wake-up time, the server prepares to deliver the audio file in real time.

[0069] Step 7:

[0070] At a specific time, the server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0071] Step 8:

[0072] The device receives the audio data sent from the server, plays the audio data, and, for example, gradually increases the volume to wake up the user naturally.

[0073] Step 9:

[0074] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings for the quality of their awakening and the relaxing effect.

[0075] Step 10:

[0076] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0077] Step 11:

[0078] The server stores the new feedback data in a database and updates the machine learning model. Using the SciPy library, it applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize future music generation.

[0079] Example 1

[0080] 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."

[0081] Conventional music distribution systems have difficulty providing music tailored to individual users' lifestyle patterns and preferences, and can only provide a uniform music experience. Furthermore, there is no mechanism for improving the system based on user feedback, making it difficult to provide a music experience optimized for each individual user. Therefore, there is a need for an advanced system that can provide a music experience that takes into account the user's health data and lifestyle rhythm.

[0082] 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.

[0083] In this invention, the server includes means for collecting personal information from users, means for integrating the collected personal information and health data and transmitting the integrated data to the server, means for storing the collected information in a database on the server and performing data analysis, means for generating optimal musical characteristics based on the analysis results, means for converting the generated musical characteristics into an audio file and delivering it to the user's device in real time, and means for collecting feedback from users and updating the machine learning model, thereby enabling the provision of an optimal music experience tailored to the user's individual lifestyle patterns and preferences.

[0084] "Means for collecting personal information from users" refers to a function for acquiring information such as the user's age, gender, wake-up time, bedtime, and favorite music genre.

[0085] "Means for integrating collected personal information and health data and sending it to a server" refers to a function that integrates data obtained from the user's smartphone or health device, encrypts it, and sends it to a server via a secure protocol.

[0086] "Means of storing information collected on the server in a database and performing data analysis" refers to a function that stores received data in a database and performs data analysis using Python's Pandas library and Scikit-learn library.

[0087] "Means for generating optimal musical characteristics based on analysis results" refers to a function that extracts parameters such as the tempo and frequency of music that are optimal for the user from the data analysis results, and generates music using a music generation algorithm.

[0088] The "means for converting the generated musical characteristics into an audio file and distributing it to the user's terminal in real time" is a function for converting the generated MIDI data into an audio file and distributing it to the user's terminal in real time using a streaming protocol.

[0089] "Means of collecting user feedback and updating the machine learning model" refers to a function that collects ratings and opinions entered by users within the app, updates the machine learning model based on that information, and reflects it in future music generation.

[0090] The present invention is a system that provides an optimal music experience based on a user's personal information and health data. Specific embodiments of the system are described below.

[0091] (Data collection phase)

[0092] First, a user installs and launches the application on their smartphone. The application prompts the user to enter personal information such as age, gender, wake-up time, bedtime, and preferred music genre. The application then connects to the user's health device (e.g., a smartwatch) via Bluetooth or Wi-Fi to collect information such as heart rate and sleep patterns. This data is temporarily stored on the device and then transmitted to a server via a secure protocol (e.g., HTTPS).

[0093] (Data analysis phase)

[0094] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. The server then preprocesses the data using Python's Pandas library and trains a machine learning model using the Scikit-learn library. This analysis allows for a detailed diagnosis of the user's behavioral patterns and psychological state, and derives optimal musical characteristics (e.g., tempo, frequency).

[0095] As a concrete example, let's say a 30-year-old man has a daily rhythm of waking up at 7am and going to bed at 10pm, and likes classical music. In this case, the server analyzes past sleep data and recommends classical music with a high relaxing effect, starting 15 minutes before waking up (6:45am). From the analysis results, specific musical characteristics such as "high tempo is effective for waking up in the morning" can be derived.

[0096] (Sound generation phase)

[0097] The server inputs the necessary parameters into a music generation algorithm (e.g., MusicVAE) based on the analysis results, generating optimal music. This algorithm makes maximum use of parameters such as tempo and frequency to generate music suited to each individual user. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted audio file is temporarily stored on the server.

[0098] (Sound distribution phase)

[0099] The server sets the delivery time of the audio file based on the user's schedule. For example, if the user wakes up at 7:00 a.m., the server can schedule the audio file to play from 6:45 a.m. Streaming protocols such as RTP and RTSP are used to deliver the audio file, and it is sent to the device in real time. The device then plays the received audio file, gradually increasing the volume, for example, to encourage a natural awakening.

[0100] (Feedback collection and learning phase)

[0101] After listening to the music, users can enter feedback within the app, including their evaluation of the quality of their wake-up experience and the relaxing effect before sleep. The device then sends this feedback data to the server, which then stores the new data in a database. This feedback data is used to update the machine learning model and is reflected in future music generation, continuously improving the overall system performance.

[0102] This allows the present invention to provide an optimal music experience tailored to each user's individual lifestyle patterns and preferences, and to continuously improve the performance of the service through feedback.

[0103] Prompt Sentence Examples

[0104] "If a user prefers classical music, what is the best tempo and frequency to use for the music generation algorithm?"

[0105] "If a user prefers high-tempo music to wake them up in the morning, generate the appropriate music."

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

[0107] Step 1:

[0108] The user installs the application on their smartphone and launches it. As an initial setting, they enter personal information such as their age, gender, wake-up time, bedtime, and preferred music genre. This entered data is temporarily saved on the device in the form of "age," "gender," "wake-up time," "bedtime," and "music genre."

[0109] Step 2:

[0110] The device syncs with the user's health devices, such as smartwatches and fitness trackers, via Bluetooth or Wi-Fi. This operation collects health data such as heart rate and sleep patterns. The health data is stored on the device as "heart rate" and "sleep patterns."

[0111] Step 3:

[0112] This collected data (personal information and health data) is sent from the device to the server using a secure protocol (e.g., HTTPS). The data sent is encrypted and protected from access by third parties. The input at this stage is the collected "personal information" and "health data," and the output is "sent data" to the server.

[0113] Step 4:

[0114] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used as the database. At this stage, the input is "sent data" and the output is "stored data." The server then adds the data to the database.

[0115] Step 5:

[0116] The server uses Python's Pandas library to preprocess the data. Specifically, it performs operations such as filling in missing values ​​and normalizing the data. Next, it uses the Scikit-learn library to train a machine learning model to analyze the user's behavioral patterns and psychological state. The input for this process is the "stored data," and the output is the "analysis results." The server preprocesses the data and trains and analyzes the machine learning model.

[0117] Step 6:

[0118] The server generates optimal musical characteristics based on the analysis results. Specifically, it inputs parameters such as tempo and frequency obtained from the analysis results into a music generation algorithm such as MusicVAE to generate optimal music. At this stage, the input is the "analysis results" and the output is "music data (MIDI file)." The server uses MusicVAE to generate music.

[0119] Step 7:

[0120] The generated music data (MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted file is temporarily stored on the server. At this stage, the input is "music data (MIDI file)" and the output is "audio file (mp3)." The server performs the conversion process using a voice synthesis library.

[0121] Step 8:

[0122] The server sets the delivery time of the audio file based on the user's schedule (wake-up time, etc.). Specifically, if the user wakes up at 7:00 AM, the schedule is set to play the audio file from 6:45 AM. At this stage, the input is "schedule information" and the output is "delivery schedule." The server sets the schedule.

[0123] Step 9:

[0124] The server sends audio files to the terminal in real time according to the distribution schedule using streaming protocols such as RTP or RTSP. The inputs are "audio files (mp3)" and "distribution schedule," and the output is "sent audio files." The server performs streaming distribution.

[0125] Step 10:

[0126] The device plays the received audio file, gradually increasing the volume, for example, to allow the user to wake up naturally. At this stage, the input is the "transmitted audio file" and the output is the "music experience." The device plays the audio file.

[0127] Step 11:

[0128] After experiencing the music, users can enter feedback about the effect in the app. Evaluation items include the quality of awakening and the relaxation effect. This input feedback data is saved on the device as "feedback."

[0129] Step 12:

[0130] The device sends the collected feedback data to the server. This data is encrypted and transmitted using a secure protocol. The input is "feedback" and the output is "sent feedback" to the server.

[0131] Step 13:

[0132] The server stores the new feedback data in a database. It then updates the machine learning model and reflects this in future music generation. The input is the "submitted feedback" and the output is the "updated machine learning model." The server stores the feedback data and updates the machine learning model.

[0133] The above has described the specific operation of a system that processes and calculates input data at each processing step to provide the user with an optimal music experience.

[0134] (Application example 1)

[0135] 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."

[0136] With conventional music distribution systems, it was difficult to provide an optimal music experience based on the individual lifestyle and psychological state of each user, and there was a lack of mechanisms for continuously improving the service by utilizing user feedback. Furthermore, the technology for delivering personalized music in real time was not well developed, and there were limited means to improve user satisfaction.

[0137] 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.

[0138] In this invention, the server includes a means for collecting information from users, a means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, and a means for generating optimal music characteristics based on the analysis results. This enables optimal music to be generated based on individual user data and distributed in real time. The quality of the service is continuously improved by a means for converting the generated music characteristics into an audio file and distributing it to the user's device, and a means for collecting user feedback and updating the machine learning model. Furthermore, by providing a means for inputting the user's lifestyle data, such as sleep patterns and heart rate, and preferred music genres, an even more accurate music experience can be provided. The real-time distribution of audio files enables an optimal music experience that matches the user's lifestyle.

[0139] "Means for collecting information from users" refers to mechanisms for comprehensively obtaining individual information such as the user's age, gender, and biometric data provided by the device used.

[0140] "Means for analyzing collected information" refers to algorithms or analytical tools that process the acquired data and evaluate the user's behavioral patterns and psychological state.

[0141] "Means for diagnosing a user's behavioral patterns and psychological state" refers to a method for identifying a user's behavioral tendencies and emotional state based on analyzed data and responding to individual needs.

[0142] The "means for generating optimal musical characteristics based on the analysis results" is a mechanism that sets musical parameters that are optimal for the user's preferences and health condition based on the results of data analysis, and creates music using a music generation algorithm.

[0143] The "means for converting the generated musical characteristics into an audio file" is a speech synthesis system for converting the generated musical parameters into an actual audio format (e.g., MP3).

[0144] The "means for delivering to the user's device" refers to streaming technology or communication protocols for transmitting the generated audio file to the user's device and playing it at the appropriate time.

[0145] "Means for collecting user feedback" refers to an interface for obtaining users' evaluations and impressions of their musical experiences and reflecting them in future music generation.

[0146] The "means for updating the machine learning model" is a machine learning technique that uses collected feedback data to improve the performance of the music generation algorithm.

[0147] "User device" refers to a device such as a smartphone, tablet, or personal computer that a user uses to input information or receive or play music.

[0148] "Sleep pattern" is information about the user's sleep, including the user's sleep duration, sleep depth, and movements during sleep.

[0149] "Life data such as heart rate" is data that indicates the user's life rhythm, including biometric information, and is usually obtained from a wearable device.

[0150] "Favorite music genre" refers to the type or style of music that the user particularly likes, and includes categories such as classical, jazz, and pop.

[0151] "Feedback" refers to the ratings and impressions users provide about their music experience, and this data helps improve and personalize the system.

[0152] The invention is a system designed to provide a user-personalized sound experience, and includes the following phases:

[0153] Data collection phase:

[0154] Users install a smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre. Additionally, detailed lifestyle data (e.g., heart rate and sleep patterns) is collected using health devices such as smartwatches. This data is then transmitted to a server via a secure protocol.

[0155] Data analysis phase:

[0156] The server stores the transmitted data in a database and analyzes it using Python's Pandas and Scikit-learn libraries. The analysis diagnoses the user's behavioral patterns and psychological state, specifically by analyzing past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0157] Sound generation phase:

[0158] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimal music. The generated music is an optimized sound based on input parameters such as tempo and frequency, and is generated as a MIDI file. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library and temporarily stored on the server.

[0159] Sound Delivery Phase:

[0160] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio and gradually increases the volume to wake up the user, for example.

[0161] Feedback gathering and learning phase:

[0162] After experiencing the sound, users enter feedback about the effect in the app. This feedback includes an evaluation of the quality of waking them up and the relaxing effect before sleep. This data is sent from the device to the server, which stores the feedback data in a database. This feedback is used to update the performance of the machine learning model and is reflected in future music generation.

[0163] Examples:

[0164] For example, assume that a user has a lifestyle where they wake up at 7:00 a.m. every morning and go to bed at 10:00 p.m. If the user prefers classical music when they want to relax, the server will analyze their past sleep data and gradually play classical music-based music with a high relaxing effect starting at 6:45 a.m. before they wake up.

[0165] Example prompt sentence:

[0166] 1. "Write a code that generates music appropriate for improving daytime focus based on the user's age and gender."

[0167] 2. "Write code for an algorithm that analyzes sleep data and generates music to help you wake up comfortably."

[0168] This invention is a system that provides a personalized music experience based on the user's lifestyle and preferences, and can continuously improve the quality of the service through feedback.

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

[0170] Step 1:

[0171] The server receives basic information (age, gender, wake-up time, bedtime, preferred music genre) sent from the user's smartphone app. It also collects detailed lifestyle data such as heart rate and sleep patterns from health devices such as smartwatches. This data is transmitted using a secure protocol and stored in a database.

[0172] Input: User information (age, gender, wake-up time, bedtime, music genre, heart rate, sleep pattern)

[0173] Output: Stored user data

[0174] Step 2:

[0175] The server analyzes the user information stored in the database. It preprocesses the data using Python's Pandas library and diagnoses the user's behavioral patterns and psychological state using the Scikit-learn library. This analysis allows it to predict future behavior and state based on the user's past data.

[0176] Input: User data stored in the database

[0177] Output: Diagnosis of user's behavioral patterns and psychological state

[0178] Step 3:

[0179] The server uses a generative AI model (e.g., MusicVAE) to generate optimal musical characteristics based on the analysis results. Parameters such as tempo and frequency obtained from the analysis are input into MusicVAE to generate optimal music. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library.

[0180] Input: Behavioral patterns and psychological state diagnosis results, parameters such as tempo and frequency

[0181] Output: Generated audio file (MP3)

[0182] Step 4:

[0183] The server references the user's schedule and delivers the generated audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for music delivery, and the audio is sent to the user's device without delay. The device then plays the received audio file, improving the user experience.

[0184] Input: Generated audio file, user schedule information

[0185] Output: Streamed audio file

[0186] Step 5:

[0187] After experiencing the music, users enter feedback within the app, including their evaluation of the quality and effectiveness of the music. The device then sends this feedback to the server, which stores the received feedback data in a database and updates the machine learning model to include new data.

[0188] Input: User feedback data

[0189] Output: An updated machine learning model

[0190] The above processing steps realize a system that provides an optimal music experience tailored to the individual needs of users and continuously improves the quality of service by incorporating feedback.

[0191] 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.

[0192] This invention is a system that provides an optimal music experience based on user information, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate emotion recognition and music personalization.

[0193] Data Collection Phase

[0194] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The app also connects to a health device (such as a smartwatch) to obtain more detailed lifestyle data (heart rate, sleep patterns, etc.). The smartphone's camera and microphone are also used to capture the user's facial expressions and voice data.

[0195] Data transmission phase

[0196] The device sends the data entered by the user and the acquired facial and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and transmitted securely.

[0197] Data analysis phase

[0198] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial and voice data to identify the user's emotional state in real time. For example, it can infer emotions (joy, anger, sadness, etc.) from the user's facial expressions captured on camera and the tone of voice picked up by the microphone.

[0199] Sound Generation Phase

[0200] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. It is also possible to adjust the characteristics of the generated music in real time based on the emotional state obtained from the emotion engine.

[0201] Sound Distribution Phase

[0202] The server checks the user's schedule information and prepares to deliver the audio file in real time at a specific time. The delivery uses streaming protocols such as RTP and RTSP to stream the audio to the terminal without delay.

[0203] Music Playback Phase

[0204] The device receives and plays the audio data sent from the server. The received audio data can, for example, gradually increase the volume to wake the user up naturally, while providing a pleasant musical experience with music characteristics that correspond to the user's emotional state.

[0205] Feedback gathering and learning phase

[0206] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0207] Feedback Analysis Phase

[0208] The server stores the new feedback data in the database and updates the machine learning model and emotion engine model. Using the SciPy library, the server applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize music generation and emotion recognition for future sessions.

[0209] Specific examples

[0210] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0211] Through the above processing, a system is realized that aims to improve the quality of life of users and, by combining it with an emotion engine, provides a more personalized music experience.

[0212] The processing flow will be explained below.

[0213] Step 1:

[0214] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters their age, gender, wake-up time, bedtime, and preferred music genre. By connecting a health device (such as a smartwatch), more detailed lifestyle data (heart rate, sleep patterns, etc.) can be obtained.

[0215] Step 2:

[0216] The terminal sends the data entered by the user and the acquired data to the server using a secure protocol (e.g., HTTPS). The transmitted data is encrypted and communicated in a secure manner.

[0217] Step 3:

[0218] The server receives the user information sent from the terminal and stores it in a database.

[0219] Step 4:

[0220] The user provides facial and voice data using the smartphone camera and microphone. In this process, the data necessary for emotion recognition (e.g., smile, tone of voice) is acquired.

[0221] Step 5:

[0222] The device transmits the captured facial and voice data to a server in real time, allowing the user's emotional state to be instantly analyzed.

[0223] Step 6:

[0224] The emotion engine of the server analyzes the facial expression data and voice data to identify the user's emotional state. For example, if the user is smiling, the emotion engine determines that the user is in a "joy" state.

[0225] Step 7:

[0226] The server analyzes the user information stored in the database and the emotional data from the emotion engine using Python's Pandas and Scikit-learn libraries, and diagnoses the user's behavioral patterns and psychological state based on the analysis results.

[0227] Step 8:

[0228] The server generates musical characteristics (tempo, frequency, melody, timbre, etc.) using a music generation algorithm (e.g., MusicVAE) based on the analysis results. The generated musical characteristics are dynamically adjusted based on the emotional state obtained from the emotion engine.

[0229] Step 9:

[0230] The server converts the generated music data (e.g., MIDI file) into an audio file (e.g., mp3) using a voice synthesis library. The converted audio file is temporarily stored on the server.

[0231] Step 10:

[0232] The server checks the user's schedule and prepares to stream the audio file in real time at the specified time. For example, the server starts streaming the audio file in real time 15 minutes before the user wakes up.

[0233] Step 11:

[0234] The server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0235] Step 12:

[0236] The device receives the audio data sent from the server and starts playing it. For example, it gradually increases the volume to wake you up naturally.

[0237] Step 13:

[0238] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings of the quality of their awakening, relaxation, and emotional changes.

[0239] Step 14:

[0240] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0241] Step 15:

[0242] The server stores the feedback data in a database and updates the machine learning model and emotion engine model. For example, it uses the SciPy library to adapt the new data to the existing model and re-evaluate the model's performance. This will further improve the accuracy of music generation and emotion recognition in future runs.

[0243] Example 2

[0244] 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."

[0245] Conventional music experience systems were unable to fully grasp the user's emotional state and behavioral patterns, making it difficult to provide optimal music for each individual user. Furthermore, the system's ability to improve the system by incorporating user feedback was insufficient, making it impossible to increase user satisfaction. Furthermore, data security was often not ensured, creating a risk of personal information leaks.

[0246] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0247] In this invention, the server includes means for collecting information from users, means for encrypting and transmitting the collected information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal musical characteristics using a generative AI model based on the analysis results, means for converting the generated musical characteristics into an audio file, means for streaming the generated audio file to the user's device, and means for collecting feedback from users and updating the machine learning model and emotion recognition model. This not only enables optimal music to be provided based on the user's emotional state and behavioral patterns, but also allows the system to be continuously improved by reflecting the feedback and ensures data security.

[0248] "User" means a person who uses the system and provides their information and feedback.

[0249] The "information collection means" is a means for acquiring basic information from the user, such as age, gender, wake-up time, bedtime, and preferred music genre, as well as lifestyle data acquired from health devices, and the user's facial expressions and voice data.

[0250] The "encryption transmission means" is a means for encrypting collected user information and transmitting it to a server using a secure protocol.

[0251] The "data analysis means" is a means for storing the user information received by the server in a database and diagnosing the user's behavioral patterns and psychological state using a Python data analysis library.

[0252] A "generative AI model" is an artificial intelligence model that uses a music generation algorithm to generate optimal musical characteristics based on the results of data analysis.

[0253] The "audio file conversion means" is a means for converting the music data generated by the generative AI model into an audio file using a voice synthesis library.

[0254] The "streaming delivery means" is a means for streaming the generated audio file to the user's terminal in real time.

[0255] The "feedback collection means" is a means for collecting user evaluations and impressions regarding the music experience provided.

[0256] "Model updating means" refers to a means of updating machine learning models and emotion recognition models based on collected feedback to improve system performance.

[0257] An "emotion recognition model" is an artificial intelligence model that analyzes a user's facial expressions and voice data to identify emotional states such as joy, anger, and sadness.

[0258] This invention is a system that provides an optimal music experience based on user information, and by combining emotion recognition technology, it achieves more accurate emotion analysis and music personalization. The system operates through a process in which the user uses a smartphone app, collects and analyzes user information, and generates and delivers optimal music.

[0259] Data Collection Phase

[0260] The user installs and launches the smartphone app. On the initial setup screen, the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device such as a smartwatch to collect more detailed lifestyle data (e.g., heart rate and sleep patterns). Furthermore, the smartphone's camera and microphone are used to capture the user's facial expressions and voice data.

[0261] Data transmission phase

[0262] The device sends the data entered by the user and the acquired facial expression and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted to ensure security.

[0263] Data analysis phase

[0264] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. The emotion engine analyzes facial and voice data to identify the user's emotional state in real time. This emotion recognition technology infers emotions such as joy, anger, and sadness from the user's facial expressions captured by the camera and tone of voice picked up from the microphone.

[0265] Sound Generation Phase

[0266] Based on the analysis results, the server uses music generation algorithms such as MusicVAE to generate optimal musical characteristics. Specific parameters (tempo, frequency, melody, timbre, etc.) are set and the music is customized based on the emotional state obtained from the emotion engine. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library.

[0267] Sound Distribution Phase

[0268] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, ensuring audio is sent to the terminal without delay.

[0269] Music Playback Phase

[0270] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it can gradually increase the volume to wake up the user, encouraging them to wake up naturally, while also providing music with musical characteristics that correspond to the user's emotional state, creating a pleasant music experience.

[0271] Feedback gathering phase

[0272] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0273] Feedback Analysis Phase

[0274] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and re-evaluate their performance. The updated models are then used to further optimize music generation and emotion recognition for future iterations.

[0275] Specific examples

[0276] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, making it possible to provide an even more accurate service.

[0277] This invention utilizes user information to provide a personalized music experience and combines emotion recognition technology to improve the user's quality of life.

[0278] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0279] Step 1:

[0280] Users install the smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre on the initial setup screen. The information entered at this time is saved in the app as text data.

[0281] Step 2:

[0282] Users connect their health devices, such as smartwatches, to the app, which then collects detailed lifestyle data, such as heart rate and sleep patterns, in real time. The collected data is then stored in the app as numerical data.

[0283] Step 3:

[0284] Users use their smartphone's camera and microphone to collect facial and voice data. The facial data is saved as an image file, and the voice data is saved as an audio file. These data are used to analyze the user's emotional state in real time.

[0285] Step 4:

[0286] The device sends the basic information entered by the user, the acquired lifestyle data, facial expression data, and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and stored on the server as encrypted data after transmission.

[0287] Step 5:

[0288] The server stores the received information in a database. The stored data is classified by user ID and saved in the following data formats: text, numeric, image, and audio.

[0289] Step 6:

[0290] The server uses Python's Pandas and Scikit-learn libraries to analyze the information in the database. The analysis diagnoses the user's behavioral patterns and psychological state. Specifically, it analyzes sleep quality and heart rate fluctuations from lifestyle data to identify behavioral patterns. In addition, an emotion engine analyzes facial expression data and voice data to identify the user's emotional state. The analysis results are output as text data representing behavioral patterns and emotional states.

[0291] Step 7:

[0292] The server then uses music generation algorithms such as MusicVAE to generate optimal musical characteristics based on the analysis results. Specific parameters (tempo, frequency, melody, timbre, etc.) are set, and the music is customized based on the emotional state obtained from the emotion engine. The generated music data is output in MIDI file format.

[0293] Step 8:

[0294] The server converts the generated music data (MIDI file) into an audio file (mp3 format) using a voice synthesis library, and the converted audio file is stored on the server in preparation for distribution.

[0295] Step 9:

[0296] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, and audio data is sent to the terminal in real time. The transmitted audio data is then received by the terminal as a real-time streaming file.

[0297] Step 10:

[0298] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it gradually increases the volume to wake up the user naturally, and provides music with musical characteristics that correspond to the user's emotional state. The played audio is output as an MP3 audio file.

[0299] Step 11:

[0300] After listening to the music, users can enter feedback about the effects of the music in the app. This feedback includes an evaluation of the quality of awakening, relaxation, and emotional changes. The input feedback data is stored in the app as numerical and text data.

[0301] Step 12:

[0302] The device sends the collected feedback data to the server. The feedback data is encrypted and sent using a secure protocol (e.g., HTTPS). After sending, the data is stored on the server as encrypted data.

[0303] Step 13:

[0304] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and reevaluate their performance. The updated models are used for music generation and emotion recognition from the next time onwards. The updated model information is saved as text data on the server.

[0305] (Application example 2)

[0306] 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."

[0307] Existing music distribution services have difficulty providing a personalized music experience based on the user's emotions and behavioral patterns. Therefore, there is a need for a system that can provide music optimized for the user's psychological state and emotions in real time. Furthermore, a mechanism is also needed that effectively utilizes user feedback to continuously improve the quality of the music experience.

[0308] 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.

[0309] In this invention, the server includes means for collecting user information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal music characteristics based on the analysis results, means for generating music characteristics using an emotion engine that recognizes the user's emotional state in real time, means for delivering the generated music characteristics to the user's device, means for collecting user feedback and updating the machine learning model, and means for using a streaming protocol to deliver the generated music in real time, thereby enabling the provision of a personalized music experience based on the user's emotions and behavioral patterns.

[0310] "Means of collecting information from users" refers to functions that obtain data such as the user's age, gender, sleep patterns, preferred music genres, heart rate, facial expressions, and voice via smartphones or wearable devices.

[0311] "Means of analyzing collected information and diagnosing the user's behavioral patterns and psychological state" refers to a function that analyzes changes in the user's daily rhythm and emotions based on collected data, and identifies behavioral patterns and psychological state.

[0312] The "means for generating optimal musical characteristics" is a function that determines musical elements such as tempo, frequency, melody, and tone based on analyzed user data, and creates music that is optimal for the user.

[0313] The "means for delivering the generated music characteristics to the user's terminal" is a function for transmitting the generated music data to the user's terminal in streaming or download format.

[0314] "Musical characteristic generation means using an emotion engine that recognizes the user's emotional state in real time" is a function that grasps the user's emotions in real time through facial expression recognition and voice analysis, and generates musical characteristics that are adapted to those emotions.

[0315] "Means for collecting user feedback and updating the machine learning model" refers to a function that collects feedback on users' music experiences and updates the machine learning model based on that feedback, adapting it to the latest data.

[0316] "Means for using a streaming protocol to deliver the generated music in real time" refers to a function that uses a streaming protocol such as RTP or RTSP to deliver the generated music to users without delay.

[0317] This invention is a system that provides an optimal music experience based on the user's emotions and behavioral patterns. Specifically, it includes a series of processes for collecting and analyzing user information, and generating and distributing music based on the analysis results.

[0318] The system collects various data using the user's smartphone and wearable devices such as a smartwatch. Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. By linking the app to a smartwatch, the system also collects heart rate and sleep patterns. Furthermore, the system uses the smartphone's camera and microphone to collect facial expressions and voice data.

[0319] This data is sent to a server using a secure protocol such as HTTPS. The server then analyzes the data using Python libraries such as Pandas and Scikit-learn. This analysis identifies the user's behavioral patterns and psychological state. Furthermore, an emotion engine is used to analyze the user's emotional state in real time.

[0320] Based on the analysis results, a music generation algorithm (e.g., MusicVAE) is used to generate music that is optimal for the user. This generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a speech synthesis library. The music is then delivered to the user's device without delay using a streaming protocol such as RTP or RTSP.

[0321] After playing the provided music, users enter feedback within the app. This feedback data is also sent to the server and used to update the machine learning model. Using the SciPy library, the new data is adapted to the existing model to further optimize music generation and emotion recognition in future trials.

[0322] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0323] An example of a prompt sentence to input to the generative AI model is as follows:

[0324] "Analyze facial expressions and voice data to indicate that the user is stressed. Explain the process of generating and delivering relaxing music to the user."

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Step 1:

[0327] Data Collection Phase

[0328] Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. Furthermore, by connecting a smartwatch, heart rate and sleep patterns can also be obtained. The smartphone's camera and microphone are also used to collect facial expressions and voice data. The input is the user's profile information and biometric data, and the collected data is output.

[0329] Step 2:

[0330] Data transmission phase

[0331] The terminal sends the collected data to the server using the HTTPS protocol. Specifically, the user data is converted into JSON format, encrypted, and then sent to the server. The input is the collected user data, and the output is the data securely sent to the server.

[0332] Step 3:

[0333] Data analysis phase

[0334] The server stores the received information in a database and analyzes it using Pandas and Scikit-learn. The analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial expressions and voice data to identify the user's emotional state in real time. The input is the user data sent to the server, and the output is the analysis results (behavioral patterns, psychological state, and emotional state).

[0335] Step 4:

[0336] Sound Generation Phase

[0337] The server uses a music generation algorithm such as MusicVAE to generate optimized sounds based on input parameters such as tempo, frequency, melody, and timbre. The generated data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. The input is the analysis result, and the output is the generated music file.

[0338] Step 5:

[0339] Sound Distribution Phase

[0340] The server uses streaming protocols such as RTP and RTSP to deliver music files generated in real time to users' devices. The input is the music file, and the output is real-time streaming.

[0341] Step 6:

[0342] Music Playback Phase

[0343] The device plays the received music data. Specifically, it plays the received audio file using a media player. The input is the distributed music file, and the output is the music playback.

[0344] Step 7:

[0345] Feedback gathering and learning phase

[0346] After experiencing the sound, the user inputs feedback within the app. The device sends this feedback to the server. The input is the user feedback, and the output is the feedback data sent to the server.

[0347] Step 8:

[0348] Feedback Analysis Phase

[0349] The server stores the new feedback data in a database and updates the machine learning model and the emotion engine model using the SciPy library. The input is the feedback data and the output is the updated machine learning model.

[0350] 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.

[0351] 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.

[0352] 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.

[0353] [Second embodiment]

[0354] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0355] 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.

[0356] 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).

[0357] 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.

[0358] 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.

[0359] 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).

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] 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."

[0366] The present invention is a system that provides an optimal music experience based on user information, and is specifically implemented as follows.

[0367] Data Collection Phase

[0368] Users install the smartphone app and enter their age, gender, wake-up time, bedtime, and preferred music genre. The app can also connect to health devices (e.g., smartwatches) to obtain more detailed lifestyle data (e.g., heart rate, sleep patterns, etc.). This information is sent from the device to the server via a secure protocol.

[0369] Data analysis phase

[0370] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. The analysis provides a detailed diagnosis of the user's behavioral patterns and psychological state. For example, a time series analysis of the user's past sleep data can be performed to predict the optimal music characteristics for the next wake-up time.

[0371] Sound Generation Phase

[0372] Based on the analysis results, the server uses a music generation algorithm (e.g., MusicVAE) to generate optimal music. This music generation algorithm inputs parameters such as tempo and frequency to generate optimized sound. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library and temporarily stored on the server.

[0373] Sound Distribution Phase

[0374] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio, gradually increasing the volume to wake up the user, for example, to promote natural waking.

[0375] Feedback gathering and learning phase

[0376] After experiencing the sound, users enter feedback within the app about the effect, including their assessment of the quality of their awakening and the relaxing effect before sleep. The device then sends this feedback to the server, which stores the new data in a database. This feedback data is used to update the performance of the machine learning model and is reflected in future music generation.

[0377] Specific examples

[0378] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and gradually play classical music-based sounds with a relaxing effect starting 15 minutes (6:45am) before waking up. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation.

[0379] As described above, the present invention is a system that provides an optimal sound experience that meets the user's needs in each phase and enables continuous improvement of service performance through feedback.

[0380] The processing flow will be explained below.

[0381] Step 1:

[0382] The user installs the smartphone app and launches it. An initial setup screen appears, prompting the user to enter information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device (such as a smartwatch) and enter more detailed lifestyle data (heart rate, sleep patterns, etc.).

[0383] Step 2:

[0384] The terminal sends the data entered by the user to the server using a secure protocol (e.g., HTTPS). The sent data is encrypted to maintain security.

[0385] Step 3:

[0386] The server receives the user information sent from the terminal and stores it in a database.

[0387] Step 4:

[0388] The server uses Python's Pandas and Scikit-learn libraries to analyze user information stored in the database. The analysis diagnoses the user's past behavioral patterns and psychological state. For example, it analyzes past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0389] Step 5:

[0390] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. This music data (e.g., MIDI file) is then converted into an audio file (e.g., mp3) using a voice synthesis library.

[0391] Step 6:

[0392] The server temporarily stores the generated audio file and checks the user's schedule information. For example, when it is 15 minutes before the user's wake-up time, the server prepares to deliver the audio file in real time.

[0393] Step 7:

[0394] At a specific time, the server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0395] Step 8:

[0396] The device receives the audio data sent from the server, plays the audio data, and, for example, gradually increases the volume to wake up the user naturally.

[0397] Step 9:

[0398] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings for the quality of their awakening and the relaxing effect.

[0399] Step 10:

[0400] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0401] Step 11:

[0402] The server stores the new feedback data in a database and updates the machine learning model. Using the SciPy library, it applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize future music generation.

[0403] Example 1

[0404] 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."

[0405] Conventional music distribution systems have difficulty providing music tailored to individual users' lifestyle patterns and preferences, and can only provide a uniform music experience. Furthermore, there is no mechanism for improving the system based on user feedback, making it difficult to provide a music experience optimized for each individual user. Therefore, there is a need for an advanced system that can provide a music experience that takes into account the user's health data and lifestyle rhythm.

[0406] 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.

[0407] In this invention, the server includes means for collecting personal information from users, means for integrating the collected personal information and health data and transmitting the integrated data to the server, means for storing the collected information in a database on the server and performing data analysis, means for generating optimal musical characteristics based on the analysis results, means for converting the generated musical characteristics into an audio file and delivering it to the user's device in real time, and means for collecting feedback from users and updating the machine learning model, thereby enabling the provision of an optimal music experience tailored to the user's individual lifestyle patterns and preferences.

[0408] "Means for collecting personal information from users" refers to a function for acquiring information such as the user's age, gender, wake-up time, bedtime, and favorite music genre.

[0409] "Means for integrating collected personal information and health data and sending it to a server" refers to a function that integrates data obtained from the user's smartphone or health device, encrypts it, and sends it to a server via a secure protocol.

[0410] "Means of storing information collected on the server in a database and performing data analysis" refers to a function that stores received data in a database and performs data analysis using Python's Pandas library and Scikit-learn library.

[0411] "Means for generating optimal musical characteristics based on analysis results" refers to a function that extracts parameters such as the tempo and frequency of music that are optimal for the user from the data analysis results, and generates music using a music generation algorithm.

[0412] The "means for converting the generated musical characteristics into an audio file and distributing it to the user's terminal in real time" is a function for converting the generated MIDI data into an audio file and distributing it to the user's terminal in real time using a streaming protocol.

[0413] "Means of collecting user feedback and updating the machine learning model" refers to a function that collects ratings and opinions entered by users within the app, updates the machine learning model based on that information, and reflects it in future music generation.

[0414] The present invention is a system that provides an optimal music experience based on a user's personal information and health data. Specific embodiments of the system are described below.

[0415] (Data collection phase)

[0416] First, a user installs and launches the application on their smartphone. The application prompts the user to enter personal information such as age, gender, wake-up time, bedtime, and preferred music genre. The application then connects to the user's health device (e.g., a smartwatch) via Bluetooth or Wi-Fi to collect information such as heart rate and sleep patterns. This data is temporarily stored on the device and then transmitted to a server via a secure protocol (e.g., HTTPS).

[0417] (Data analysis phase)

[0418] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. The server then preprocesses the data using Python's Pandas library and trains a machine learning model using the Scikit-learn library. This analysis allows for a detailed diagnosis of the user's behavioral patterns and psychological state, and derives optimal musical characteristics (e.g., tempo, frequency).

[0419] As a concrete example, let's say a 30-year-old man has a daily rhythm of waking up at 7am and going to bed at 10pm, and likes classical music. In this case, the server analyzes past sleep data and recommends classical music with a high relaxing effect, starting 15 minutes before waking up (6:45am). From the analysis results, specific musical characteristics such as "high tempo is effective for waking up in the morning" can be derived.

[0420] (Sound generation phase)

[0421] The server inputs the necessary parameters into a music generation algorithm (e.g., MusicVAE) based on the analysis results, generating optimal music. This algorithm makes maximum use of parameters such as tempo and frequency to generate music suited to each individual user. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted audio file is temporarily stored on the server.

[0422] (Sound distribution phase)

[0423] The server sets the delivery time of the audio file based on the user's schedule. For example, if the user wakes up at 7:00 a.m., the server can schedule the audio file to play from 6:45 a.m. Streaming protocols such as RTP and RTSP are used to deliver the audio file, and it is sent to the device in real time. The device then plays the received audio file, gradually increasing the volume, for example, to encourage a natural awakening.

[0424] (Feedback collection and learning phase)

[0425] After listening to the music, users can enter feedback within the app, including their evaluation of the quality of their wake-up experience and the relaxing effect before sleep. The device then sends this feedback data to the server, which then stores the new data in a database. This feedback data is used to update the machine learning model and is reflected in future music generation, continuously improving the overall system performance.

[0426] This allows the present invention to provide an optimal music experience tailored to each user's individual lifestyle patterns and preferences, and to continuously improve the performance of the service through feedback.

[0427] Prompt Sentence Examples

[0428] "If a user prefers classical music, what is the best tempo and frequency to use for the music generation algorithm?"

[0429] "If a user prefers high-tempo music to wake them up in the morning, generate the appropriate music."

[0430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0431] Step 1:

[0432] The user installs the application on their smartphone and launches it. As an initial setting, they enter personal information such as their age, gender, wake-up time, bedtime, and preferred music genre. This entered data is temporarily saved on the device in the form of "age," "gender," "wake-up time," "bedtime," and "music genre."

[0433] Step 2:

[0434] The device syncs with the user's health devices, such as smartwatches and fitness trackers, via Bluetooth or Wi-Fi. This operation collects health data such as heart rate and sleep patterns. The health data is stored on the device as "heart rate" and "sleep patterns."

[0435] Step 3:

[0436] This collected data (personal information and health data) is sent from the device to the server using a secure protocol (e.g., HTTPS). The data sent is encrypted and protected from access by third parties. The input at this stage is the collected "personal information" and "health data," and the output is "sent data" to the server.

[0437] Step 4:

[0438] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used as the database. At this stage, the input is "sent data" and the output is "stored data." The server then adds the data to the database.

[0439] Step 5:

[0440] The server uses Python's Pandas library to preprocess the data. Specifically, it performs operations such as filling in missing values ​​and normalizing the data. Next, it uses the Scikit-learn library to train a machine learning model to analyze the user's behavioral patterns and psychological state. The input for this process is the "stored data," and the output is the "analysis results." The server preprocesses the data and trains and analyzes the machine learning model.

[0441] Step 6:

[0442] The server generates optimal musical characteristics based on the analysis results. Specifically, it inputs parameters such as tempo and frequency obtained from the analysis results into a music generation algorithm such as MusicVAE to generate optimal music. At this stage, the input is the "analysis results" and the output is "music data (MIDI file)." The server uses MusicVAE to generate music.

[0443] Step 7:

[0444] The generated music data (MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted file is temporarily stored on the server. At this stage, the input is "music data (MIDI file)" and the output is "audio file (mp3)." The server performs the conversion process using a voice synthesis library.

[0445] Step 8:

[0446] The server sets the delivery time of the audio file based on the user's schedule (wake-up time, etc.). Specifically, if the user wakes up at 7:00 AM, the schedule is set to play the audio file from 6:45 AM. At this stage, the input is "schedule information" and the output is "delivery schedule." The server sets the schedule.

[0447] Step 9:

[0448] The server sends audio files to the terminal in real time according to the distribution schedule using streaming protocols such as RTP or RTSP. The inputs are "audio files (mp3)" and "distribution schedule," and the output is "sent audio files." The server performs streaming distribution.

[0449] Step 10:

[0450] The device plays the received audio file, gradually increasing the volume, for example, to allow the user to wake up naturally. At this stage, the input is the "transmitted audio file" and the output is the "music experience." The device plays the audio file.

[0451] Step 11:

[0452] After experiencing the music, users can enter feedback about the effect in the app. Evaluation items include the quality of awakening and the relaxation effect. This input feedback data is saved on the device as "feedback."

[0453] Step 12:

[0454] The device sends the collected feedback data to the server. This data is encrypted and transmitted using a secure protocol. The input is "feedback" and the output is "sent feedback" to the server.

[0455] Step 13:

[0456] The server stores the new feedback data in a database. It then updates the machine learning model and reflects this in future music generation. The input is the "submitted feedback" and the output is the "updated machine learning model." The server stores the feedback data and updates the machine learning model.

[0457] The above has described the specific operation of a system that processes and calculates input data at each processing step to provide the user with an optimal music experience.

[0458] (Application example 1)

[0459] 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."

[0460] With conventional music distribution systems, it was difficult to provide an optimal music experience based on the individual lifestyle and psychological state of each user, and there was a lack of mechanisms for continuously improving the service by utilizing user feedback. Furthermore, the technology for delivering personalized music in real time was not well developed, and there were limited means to improve user satisfaction.

[0461] 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.

[0462] In this invention, the server includes a means for collecting information from users, a means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, and a means for generating optimal music characteristics based on the analysis results. This enables optimal music to be generated based on individual user data and distributed in real time. The quality of the service is continuously improved by a means for converting the generated music characteristics into an audio file and distributing it to the user's device, and a means for collecting user feedback and updating the machine learning model. Furthermore, by providing a means for inputting the user's lifestyle data, such as sleep patterns and heart rate, and preferred music genres, an even more accurate music experience can be provided. The real-time distribution of audio files enables an optimal music experience that matches the user's lifestyle.

[0463] "Means for collecting information from users" refers to mechanisms for comprehensively obtaining individual information such as the user's age, gender, and biometric data provided by the device used.

[0464] "Means for analyzing collected information" refers to algorithms or analytical tools that process the acquired data and evaluate the user's behavioral patterns and psychological state.

[0465] "Means for diagnosing a user's behavioral patterns and psychological state" refers to a method for identifying a user's behavioral tendencies and emotional state based on analyzed data and responding to individual needs.

[0466] The "means for generating optimal musical characteristics based on the analysis results" is a mechanism that sets musical parameters that are optimal for the user's preferences and health condition based on the results of data analysis, and creates music using a music generation algorithm.

[0467] The "means for converting the generated musical characteristics into an audio file" is a speech synthesis system for converting the generated musical parameters into an actual audio format (e.g., MP3).

[0468] The "means for delivering to the user's device" refers to streaming technology or communication protocols for transmitting the generated audio file to the user's device and playing it at the appropriate time.

[0469] "Means for collecting user feedback" refers to an interface for obtaining users' evaluations and impressions of their musical experiences and reflecting them in future music generation.

[0470] The "means for updating the machine learning model" is a machine learning technique that uses collected feedback data to improve the performance of the music generation algorithm.

[0471] "User device" refers to a device such as a smartphone, tablet, or personal computer that a user uses to input information or receive or play music.

[0472] "Sleep pattern" is information about the user's sleep, including the user's sleep duration, sleep depth, and movements during sleep.

[0473] "Life data such as heart rate" is data that indicates the user's life rhythm, including biometric information, and is usually obtained from a wearable device.

[0474] "Favorite music genre" refers to the type or style of music that the user particularly likes, and includes categories such as classical, jazz, and pop.

[0475] "Feedback" refers to the ratings and impressions users provide about their music experience, and this data helps improve and personalize the system.

[0476] The invention is a system designed to provide a user-personalized sound experience, and includes the following phases:

[0477] Data collection phase:

[0478] Users install a smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre. Additionally, detailed lifestyle data (e.g., heart rate and sleep patterns) is collected using health devices such as smartwatches. This data is then transmitted to a server via a secure protocol.

[0479] Data analysis phase:

[0480] The server stores the transmitted data in a database and analyzes it using Python's Pandas and Scikit-learn libraries. The analysis diagnoses the user's behavioral patterns and psychological state, specifically by analyzing past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0481] Sound generation phase:

[0482] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimal music. The generated music is an optimized sound based on input parameters such as tempo and frequency, and is generated as a MIDI file. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library and temporarily stored on the server.

[0483] Sound Delivery Phase:

[0484] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio and gradually increases the volume to wake up the user, for example.

[0485] Feedback gathering and learning phase:

[0486] After experiencing the sound, users enter feedback about the effect in the app. This feedback includes an evaluation of the quality of waking them up and the relaxing effect before sleep. This data is sent from the device to the server, which stores the feedback data in a database. This feedback is used to update the performance of the machine learning model and is reflected in future music generation.

[0487] Examples:

[0488] For example, assume that a user has a lifestyle where they wake up at 7:00 a.m. every morning and go to bed at 10:00 p.m. If the user prefers classical music when they want to relax, the server will analyze their past sleep data and gradually play classical music-based music with a high relaxing effect starting at 6:45 a.m. before they wake up.

[0489] Example prompt sentence:

[0490] 1. "Write a code that generates music appropriate for improving daytime focus based on the user's age and gender."

[0491] 2. "Write code for an algorithm that analyzes sleep data and generates music to help you wake up comfortably."

[0492] This invention is a system that provides a personalized music experience based on the user's lifestyle and preferences, and can continuously improve the quality of the service through feedback.

[0493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0494] Step 1:

[0495] The server receives basic information (age, gender, wake-up time, bedtime, preferred music genre) sent from the user's smartphone app. It also collects detailed lifestyle data such as heart rate and sleep patterns from health devices such as smartwatches. This data is transmitted using a secure protocol and stored in a database.

[0496] Input: User information (age, gender, wake-up time, bedtime, music genre, heart rate, sleep pattern)

[0497] Output: Stored user data

[0498] Step 2:

[0499] The server analyzes the user information stored in the database. It preprocesses the data using Python's Pandas library and diagnoses the user's behavioral patterns and psychological state using the Scikit-learn library. This analysis allows it to predict future behavior and state based on the user's past data.

[0500] Input: User data stored in the database

[0501] Output: Diagnosis of user's behavioral patterns and psychological state

[0502] Step 3:

[0503] The server uses a generative AI model (e.g., MusicVAE) to generate optimal musical characteristics based on the analysis results. Parameters such as tempo and frequency obtained from the analysis are input into MusicVAE to generate optimal music. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library.

[0504] Input: Behavioral patterns and psychological state diagnosis results, parameters such as tempo and frequency

[0505] Output: Generated audio file (MP3)

[0506] Step 4:

[0507] The server references the user's schedule and delivers the generated audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for music delivery, and the audio is sent to the user's device without delay. The device then plays the received audio file, improving the user experience.

[0508] Input: Generated audio file, user schedule information

[0509] Output: Streamed audio file

[0510] Step 5:

[0511] After experiencing the music, users enter feedback within the app, including their evaluation of the quality and effectiveness of the music. The device then sends this feedback to the server, which stores the received feedback data in a database and updates the machine learning model to include new data.

[0512] Input: User feedback data

[0513] Output: An updated machine learning model

[0514] The above processing steps realize a system that provides an optimal music experience tailored to the individual needs of users and continuously improves the quality of service by incorporating feedback.

[0515] 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.

[0516] This invention is a system that provides an optimal music experience based on user information, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate emotion recognition and music personalization.

[0517] Data Collection Phase

[0518] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The app also connects to a health device (such as a smartwatch) to obtain more detailed lifestyle data (heart rate, sleep patterns, etc.). The smartphone's camera and microphone are also used to capture the user's facial expressions and voice data.

[0519] Data transmission phase

[0520] The device sends the data entered by the user and the acquired facial and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and transmitted securely.

[0521] Data analysis phase

[0522] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial and voice data to identify the user's emotional state in real time. For example, it can infer emotions (joy, anger, sadness, etc.) from the user's facial expressions captured on camera and the tone of voice picked up by the microphone.

[0523] Sound Generation Phase

[0524] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. It is also possible to adjust the characteristics of the generated music in real time based on the emotional state obtained from the emotion engine.

[0525] Sound Distribution Phase

[0526] The server checks the user's schedule information and prepares to deliver the audio file in real time at a specific time. The delivery uses streaming protocols such as RTP and RTSP to stream the audio to the terminal without delay.

[0527] Music Playback Phase

[0528] The device receives and plays the audio data sent from the server. The received audio data can, for example, gradually increase the volume to wake the user up naturally, while providing a pleasant musical experience with music characteristics that correspond to the user's emotional state.

[0529] Feedback gathering and learning phase

[0530] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0531] Feedback Analysis Phase

[0532] The server stores the new feedback data in the database and updates the machine learning model and emotion engine model. Using the SciPy library, the server applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize music generation and emotion recognition for future sessions.

[0533] Specific examples

[0534] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0535] Through the above processing, a system is realized that aims to improve the quality of life of users and, by combining it with an emotion engine, provides a more personalized music experience.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters their age, gender, wake-up time, bedtime, and preferred music genre. By connecting a health device (such as a smartwatch), more detailed lifestyle data (heart rate, sleep patterns, etc.) can be obtained.

[0539] Step 2:

[0540] The terminal sends the data entered by the user and the acquired data to the server using a secure protocol (e.g., HTTPS). The transmitted data is encrypted and communicated in a secure manner.

[0541] Step 3:

[0542] The server receives the user information sent from the terminal and stores it in a database.

[0543] Step 4:

[0544] The user provides facial and voice data using the smartphone camera and microphone. In this process, the data necessary for emotion recognition (e.g., smile, tone of voice) is acquired.

[0545] Step 5:

[0546] The device transmits the captured facial and voice data to a server in real time, allowing the user's emotional state to be instantly analyzed.

[0547] Step 6:

[0548] The emotion engine of the server analyzes the facial expression data and voice data to identify the user's emotional state. For example, if the user is smiling, the emotion engine determines that the user is in a "joy" state.

[0549] Step 7:

[0550] The server analyzes the user information stored in the database and the emotional data from the emotion engine using Python's Pandas and Scikit-learn libraries, and diagnoses the user's behavioral patterns and psychological state based on the analysis results.

[0551] Step 8:

[0552] The server generates musical characteristics (tempo, frequency, melody, timbre, etc.) using a music generation algorithm (e.g., MusicVAE) based on the analysis results. The generated musical characteristics are dynamically adjusted based on the emotional state obtained from the emotion engine.

[0553] Step 9:

[0554] The server converts the generated music data (e.g., MIDI file) into an audio file (e.g., mp3) using a voice synthesis library. The converted audio file is temporarily stored on the server.

[0555] Step 10:

[0556] The server checks the user's schedule and prepares to stream the audio file in real time at the specified time. For example, the server starts streaming the audio file in real time 15 minutes before the user wakes up.

[0557] Step 11:

[0558] The server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0559] Step 12:

[0560] The device receives the audio data sent from the server and starts playing it. For example, it gradually increases the volume to wake you up naturally.

[0561] Step 13:

[0562] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings of the quality of their awakening, relaxation, and emotional changes.

[0563] Step 14:

[0564] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0565] Step 15:

[0566] The server stores the feedback data in a database and updates the machine learning model and emotion engine model. For example, it uses the SciPy library to adapt the new data to the existing model and re-evaluate the model's performance. This will further improve the accuracy of music generation and emotion recognition in future runs.

[0567] Example 2

[0568] 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."

[0569] Conventional music experience systems were unable to fully grasp the user's emotional state and behavioral patterns, making it difficult to provide optimal music for each individual user. Furthermore, the system's ability to improve the system by incorporating user feedback was insufficient, making it impossible to increase user satisfaction. Furthermore, data security was often not ensured, creating a risk of personal information leaks.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0571] In this invention, the server includes means for collecting information from users, means for encrypting and transmitting the collected information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal musical characteristics using a generative AI model based on the analysis results, means for converting the generated musical characteristics into an audio file, means for streaming the generated audio file to the user's device, and means for collecting feedback from users and updating the machine learning model and emotion recognition model. This not only enables optimal music to be provided based on the user's emotional state and behavioral patterns, but also allows the system to be continuously improved by reflecting the feedback and ensures data security.

[0572] "User" means a person who uses the system and provides their information and feedback.

[0573] The "information collection means" is a means for acquiring basic information from the user, such as age, gender, wake-up time, bedtime, and preferred music genre, as well as lifestyle data acquired from health devices, and the user's facial expressions and voice data.

[0574] The "encryption transmission means" is a means for encrypting collected user information and transmitting it to a server using a secure protocol.

[0575] The "data analysis means" is a means for storing the user information received by the server in a database and diagnosing the user's behavioral patterns and psychological state using a Python data analysis library.

[0576] A "generative AI model" is an artificial intelligence model that uses a music generation algorithm to generate optimal musical characteristics based on the results of data analysis.

[0577] The "audio file conversion means" is a means for converting the music data generated by the generative AI model into an audio file using a voice synthesis library.

[0578] The "streaming delivery means" is a means for streaming the generated audio file to the user's terminal in real time.

[0579] The "feedback collection means" is a means for collecting user evaluations and impressions regarding the music experience provided.

[0580] "Model updating means" refers to a means of updating machine learning models and emotion recognition models based on collected feedback to improve system performance.

[0581] An "emotion recognition model" is an artificial intelligence model that analyzes a user's facial expressions and voice data to identify emotional states such as joy, anger, and sadness.

[0582] This invention is a system that provides an optimal music experience based on user information, and by combining emotion recognition technology, it achieves more accurate emotion analysis and music personalization. The system operates through a process in which the user uses a smartphone app, collects and analyzes user information, and generates and delivers optimal music.

[0583] Data Collection Phase

[0584] The user installs and launches the smartphone app. On the initial setup screen, the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device such as a smartwatch to collect more detailed lifestyle data (e.g., heart rate and sleep patterns). Furthermore, the smartphone's camera and microphone are used to capture the user's facial expressions and voice data.

[0585] Data transmission phase

[0586] The device sends the data entered by the user and the acquired facial expression and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted to ensure security.

[0587] Data analysis phase

[0588] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. The emotion engine analyzes facial and voice data to identify the user's emotional state in real time. This emotion recognition technology infers emotions such as joy, anger, and sadness from the user's facial expressions captured by the camera and tone of voice picked up from the microphone.

[0589] Sound Generation Phase

[0590] Based on the analysis results, the server uses music generation algorithms such as MusicVAE to generate optimal musical characteristics. Specific parameters (tempo, frequency, melody, timbre, etc.) are set and the music is customized based on the emotional state obtained from the emotion engine. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library.

[0591] Sound Distribution Phase

[0592] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, ensuring audio is sent to the terminal without delay.

[0593] Music Playback Phase

[0594] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it can gradually increase the volume to wake up the user, encouraging them to wake up naturally, while also providing music with musical characteristics that correspond to the user's emotional state, creating a pleasant music experience.

[0595] Feedback gathering phase

[0596] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0597] Feedback Analysis Phase

[0598] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and re-evaluate their performance. The updated models are then used to further optimize music generation and emotion recognition for future iterations.

[0599] Specific examples

[0600] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, making it possible to provide an even more accurate service.

[0601] This invention utilizes user information to provide a personalized music experience and combines emotion recognition technology to improve the user's quality of life.

[0602] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0603] Step 1:

[0604] Users install the smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre on the initial setup screen. The information entered at this time is saved in the app as text data.

[0605] Step 2:

[0606] Users connect their health devices, such as smartwatches, to the app, which then collects detailed lifestyle data, such as heart rate and sleep patterns, in real time. The collected data is then stored in the app as numerical data.

[0607] Step 3:

[0608] Users use their smartphone's camera and microphone to collect facial and voice data. The facial data is saved as an image file, and the voice data is saved as an audio file. These data are used to analyze the user's emotional state in real time.

[0609] Step 4:

[0610] The device sends the basic information entered by the user, the acquired lifestyle data, facial expression data, and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and stored on the server as encrypted data after transmission.

[0611] Step 5:

[0612] The server stores the received information in a database. The stored data is classified by user ID and saved in the following data formats: text, numeric, image, and audio.

[0613] Step 6:

[0614] The server uses Python's Pandas and Scikit-learn libraries to analyze the information in the database. The analysis diagnoses the user's behavioral patterns and psychological state. Specifically, it analyzes sleep quality and heart rate fluctuations from lifestyle data to identify behavioral patterns. In addition, an emotion engine analyzes facial expression data and voice data to identify the user's emotional state. The analysis results are output as text data representing behavioral patterns and emotional states.

[0615] Step 7:

[0616] The server then uses music generation algorithms such as MusicVAE to generate optimal musical characteristics based on the analysis results. Specific parameters (tempo, frequency, melody, timbre, etc.) are set, and the music is customized based on the emotional state obtained from the emotion engine. The generated music data is output in MIDI file format.

[0617] Step 8:

[0618] The server converts the generated music data (MIDI file) into an audio file (mp3 format) using a voice synthesis library, and the converted audio file is stored on the server in preparation for distribution.

[0619] Step 9:

[0620] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, and audio data is sent to the terminal in real time. The transmitted audio data is then received by the terminal as a real-time streaming file.

[0621] Step 10:

[0622] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it gradually increases the volume to wake up the user naturally, and provides music with musical characteristics that correspond to the user's emotional state. The played audio is output as an MP3 audio file.

[0623] Step 11:

[0624] After listening to the music, users can enter feedback about the effects of the music in the app. This feedback includes an evaluation of the quality of awakening, relaxation, and emotional changes. The input feedback data is stored in the app as numerical and text data.

[0625] Step 12:

[0626] The device sends the collected feedback data to the server. The feedback data is encrypted and sent using a secure protocol (e.g., HTTPS). After sending, the data is stored on the server as encrypted data.

[0627] Step 13:

[0628] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and reevaluate their performance. The updated models are used for music generation and emotion recognition from the next time onwards. The updated model information is saved as text data on the server.

[0629] (Application example 2)

[0630] 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."

[0631] Existing music distribution services have difficulty providing a personalized music experience based on the user's emotions and behavioral patterns. Therefore, there is a need for a system that can provide music optimized for the user's psychological state and emotions in real time. Furthermore, a mechanism is also needed that effectively utilizes user feedback to continuously improve the quality of the music experience.

[0632] 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.

[0633] In this invention, the server includes means for collecting user information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal music characteristics based on the analysis results, means for generating music characteristics using an emotion engine that recognizes the user's emotional state in real time, means for delivering the generated music characteristics to the user's device, means for collecting user feedback and updating the machine learning model, and means for using a streaming protocol to deliver the generated music in real time, thereby enabling the provision of a personalized music experience based on the user's emotions and behavioral patterns.

[0634] "Means of collecting information from users" refers to functions that obtain data such as the user's age, gender, sleep patterns, preferred music genres, heart rate, facial expressions, and voice via smartphones or wearable devices.

[0635] "Means of analyzing collected information and diagnosing the user's behavioral patterns and psychological state" refers to a function that analyzes changes in the user's daily rhythm and emotions based on collected data, and identifies behavioral patterns and psychological state.

[0636] The "means for generating optimal musical characteristics" is a function that determines musical elements such as tempo, frequency, melody, and tone based on analyzed user data, and creates music that is optimal for the user.

[0637] The "means for delivering the generated music characteristics to the user's terminal" is a function for transmitting the generated music data to the user's terminal in streaming or download format.

[0638] "Musical characteristic generation means using an emotion engine that recognizes the user's emotional state in real time" is a function that grasps the user's emotions in real time through facial expression recognition and voice analysis, and generates musical characteristics that are adapted to those emotions.

[0639] "Means for collecting user feedback and updating the machine learning model" refers to a function that collects feedback on users' music experiences and updates the machine learning model based on that feedback, adapting it to the latest data.

[0640] "Means for using a streaming protocol to deliver the generated music in real time" refers to a function that uses a streaming protocol such as RTP or RTSP to deliver the generated music to users without delay.

[0641] This invention is a system that provides an optimal music experience based on the user's emotions and behavioral patterns. Specifically, it includes a series of processes for collecting and analyzing user information, and generating and distributing music based on the analysis results.

[0642] The system collects various data using the user's smartphone and wearable devices such as a smartwatch. Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. By linking the app to a smartwatch, the system also collects heart rate and sleep patterns. Furthermore, the system uses the smartphone's camera and microphone to collect facial expressions and voice data.

[0643] This data is sent to a server using a secure protocol such as HTTPS. The server then analyzes the data using Python libraries such as Pandas and Scikit-learn. This analysis identifies the user's behavioral patterns and psychological state. Furthermore, an emotion engine is used to analyze the user's emotional state in real time.

[0644] Based on the analysis results, a music generation algorithm (e.g., MusicVAE) is used to generate music that is optimal for the user. This generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a speech synthesis library. The music is then delivered to the user's device without delay using a streaming protocol such as RTP or RTSP.

[0645] After playing the provided music, users enter feedback within the app. This feedback data is also sent to the server and used to update the machine learning model. Using the SciPy library, the new data is adapted to the existing model to further optimize music generation and emotion recognition in future trials.

[0646] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0647] An example of a prompt sentence to input to the generative AI model is as follows:

[0648] "Analyze facial expressions and voice data to indicate that the user is stressed. Explain the process of generating and delivering relaxing music to the user."

[0649] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0650] Step 1:

[0651] Data Collection Phase

[0652] Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. Furthermore, by connecting a smartwatch, heart rate and sleep patterns can also be obtained. The smartphone's camera and microphone are also used to collect facial expressions and voice data. The input is the user's profile information and biometric data, and the collected data is output.

[0653] Step 2:

[0654] Data transmission phase

[0655] The terminal sends the collected data to the server using the HTTPS protocol. Specifically, the user data is converted into JSON format, encrypted, and then sent to the server. The input is the collected user data, and the output is the data securely sent to the server.

[0656] Step 3:

[0657] Data analysis phase

[0658] The server stores the received information in a database and analyzes it using Pandas and Scikit-learn. The analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial expressions and voice data to identify the user's emotional state in real time. The input is the user data sent to the server, and the output is the analysis results (behavioral patterns, psychological state, and emotional state).

[0659] Step 4:

[0660] Sound Generation Phase

[0661] The server uses a music generation algorithm such as MusicVAE to generate optimized sounds based on input parameters such as tempo, frequency, melody, and timbre. The generated data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. The input is the analysis result, and the output is the generated music file.

[0662] Step 5:

[0663] Sound Distribution Phase

[0664] The server uses streaming protocols such as RTP and RTSP to deliver music files generated in real time to users' devices. The input is the music file, and the output is real-time streaming.

[0665] Step 6:

[0666] Music Playback Phase

[0667] The device plays the received music data. Specifically, it plays the received audio file using a media player. The input is the distributed music file, and the output is the music playback.

[0668] Step 7:

[0669] Feedback gathering and learning phase

[0670] After experiencing the sound, the user inputs feedback within the app. The device sends this feedback to the server. The input is the user feedback, and the output is the feedback data sent to the server.

[0671] Step 8:

[0672] Feedback Analysis Phase

[0673] The server stores the new feedback data in a database and updates the machine learning model and the emotion engine model using the SciPy library. The input is the feedback data and the output is the updated machine learning model.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] [Third embodiment]

[0678] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0679] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0680] 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).

[0681] 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.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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."

[0690] The present invention is a system that provides an optimal music experience based on user information, and is specifically implemented as follows.

[0691] Data Collection Phase

[0692] Users install the smartphone app and enter their age, gender, wake-up time, bedtime, and preferred music genre. The app can also connect to health devices (e.g., smartwatches) to obtain more detailed lifestyle data (e.g., heart rate, sleep patterns, etc.). This information is sent from the device to the server via a secure protocol.

[0693] Data analysis phase

[0694] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. The analysis provides a detailed diagnosis of the user's behavioral patterns and psychological state. For example, a time series analysis of the user's past sleep data can be performed to predict the optimal music characteristics for the next wake-up time.

[0695] Sound Generation Phase

[0696] Based on the analysis results, the server uses a music generation algorithm (e.g., MusicVAE) to generate optimal music. This music generation algorithm inputs parameters such as tempo and frequency to generate optimized sound. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library and temporarily stored on the server.

[0697] Sound Distribution Phase

[0698] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio, gradually increasing the volume to wake up the user, for example, to promote natural waking.

[0699] Feedback gathering and learning phase

[0700] After experiencing the sound, users enter feedback within the app about the effect, including their assessment of the quality of their awakening and the relaxing effect before sleep. The device then sends this feedback to the server, which stores the new data in a database. This feedback data is used to update the performance of the machine learning model and is reflected in future music generation.

[0701] Specific examples

[0702] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and gradually play classical music-based sounds with a relaxing effect starting 15 minutes (6:45am) before waking up. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation.

[0703] As described above, the present invention is a system that provides an optimal sound experience that meets the user's needs in each phase and enables continuous improvement of service performance through feedback.

[0704] The processing flow will be explained below.

[0705] Step 1:

[0706] The user installs the smartphone app and launches it. An initial setup screen appears, prompting the user to enter information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device (such as a smartwatch) and enter more detailed lifestyle data (heart rate, sleep patterns, etc.).

[0707] Step 2:

[0708] The terminal sends the data entered by the user to the server using a secure protocol (e.g., HTTPS). The sent data is encrypted to maintain security.

[0709] Step 3:

[0710] The server receives the user information sent from the terminal and stores it in a database.

[0711] Step 4:

[0712] The server uses Python's Pandas and Scikit-learn libraries to analyze user information stored in the database. The analysis diagnoses the user's past behavioral patterns and psychological state. For example, it analyzes past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0713] Step 5:

[0714] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. This music data (e.g., MIDI file) is then converted into an audio file (e.g., mp3) using a voice synthesis library.

[0715] Step 6:

[0716] The server temporarily stores the generated audio file and checks the user's schedule information. For example, when it is 15 minutes before the user's wake-up time, the server prepares to deliver the audio file in real time.

[0717] Step 7:

[0718] At a specific time, the server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0719] Step 8:

[0720] The device receives the audio data sent from the server, plays the audio data, and, for example, gradually increases the volume to wake up the user naturally.

[0721] Step 9:

[0722] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings for the quality of their awakening and the relaxing effect.

[0723] Step 10:

[0724] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0725] Step 11:

[0726] The server stores the new feedback data in a database and updates the machine learning model. Using the SciPy library, it applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize future music generation.

[0727] Example 1

[0728] 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."

[0729] Conventional music distribution systems have difficulty providing music tailored to individual users' lifestyle patterns and preferences, and can only provide a uniform music experience. Furthermore, there is no mechanism for improving the system based on user feedback, making it difficult to provide a music experience optimized for each individual user. Therefore, there is a need for an advanced system that can provide a music experience that takes into account the user's health data and lifestyle rhythm.

[0730] 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.

[0731] In this invention, the server includes means for collecting personal information from users, means for integrating the collected personal information and health data and transmitting the integrated data to the server, means for storing the collected information in a database on the server and performing data analysis, means for generating optimal musical characteristics based on the analysis results, means for converting the generated musical characteristics into an audio file and delivering it to the user's device in real time, and means for collecting feedback from users and updating the machine learning model, thereby enabling the provision of an optimal music experience tailored to the user's individual lifestyle patterns and preferences.

[0732] "Means for collecting personal information from users" refers to a function for acquiring information such as the user's age, gender, wake-up time, bedtime, and favorite music genre.

[0733] "Means for integrating collected personal information and health data and sending it to a server" refers to a function that integrates data obtained from the user's smartphone or health device, encrypts it, and sends it to a server via a secure protocol.

[0734] "Means of storing information collected on the server in a database and performing data analysis" refers to a function that stores received data in a database and performs data analysis using Python's Pandas library and Scikit-learn library.

[0735] "Means for generating optimal musical characteristics based on analysis results" refers to a function that extracts parameters such as the tempo and frequency of music that are optimal for the user from the data analysis results, and generates music using a music generation algorithm.

[0736] The "means for converting the generated musical characteristics into an audio file and distributing it to the user's terminal in real time" is a function for converting the generated MIDI data into an audio file and distributing it to the user's terminal in real time using a streaming protocol.

[0737] "Means of collecting user feedback and updating the machine learning model" refers to a function that collects ratings and opinions entered by users within the app, updates the machine learning model based on that information, and reflects it in future music generation.

[0738] The present invention is a system that provides an optimal music experience based on a user's personal information and health data. Specific embodiments of the system are described below.

[0739] (Data collection phase)

[0740] First, a user installs and launches the application on their smartphone. The application prompts the user to enter personal information such as age, gender, wake-up time, bedtime, and preferred music genre. The application then connects to the user's health device (e.g., a smartwatch) via Bluetooth or Wi-Fi to collect information such as heart rate and sleep patterns. This data is temporarily stored on the device and then transmitted to a server via a secure protocol (e.g., HTTPS).

[0741] (Data analysis phase)

[0742] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. The server then preprocesses the data using Python's Pandas library and trains a machine learning model using the Scikit-learn library. This analysis allows for a detailed diagnosis of the user's behavioral patterns and psychological state, and derives optimal musical characteristics (e.g., tempo, frequency).

[0743] As a concrete example, let's say a 30-year-old man has a daily rhythm of waking up at 7am and going to bed at 10pm, and likes classical music. In this case, the server analyzes past sleep data and recommends classical music with a high relaxing effect, starting 15 minutes before waking up (6:45am). From the analysis results, specific musical characteristics such as "high tempo is effective for waking up in the morning" can be derived.

[0744] (Sound generation phase)

[0745] The server inputs the necessary parameters into a music generation algorithm (e.g., MusicVAE) based on the analysis results, generating optimal music. This algorithm makes maximum use of parameters such as tempo and frequency to generate music suited to each individual user. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted audio file is temporarily stored on the server.

[0746] (Sound distribution phase)

[0747] The server sets the delivery time of the audio file based on the user's schedule. For example, if the user wakes up at 7:00 a.m., the server can schedule the audio file to play from 6:45 a.m. Streaming protocols such as RTP and RTSP are used to deliver the audio file, and it is sent to the device in real time. The device then plays the received audio file, gradually increasing the volume, for example, to encourage a natural awakening.

[0748] (Feedback collection and learning phase)

[0749] After listening to the music, users can enter feedback within the app, including their evaluation of the quality of their wake-up experience and the relaxing effect before sleep. The device then sends this feedback data to the server, which then stores the new data in a database. This feedback data is used to update the machine learning model and is reflected in future music generation, continuously improving the overall system performance.

[0750] This allows the present invention to provide an optimal music experience tailored to each user's individual lifestyle patterns and preferences, and to continuously improve the performance of the service through feedback.

[0751] Prompt Sentence Examples

[0752] "If a user prefers classical music, what is the best tempo and frequency to use for the music generation algorithm?"

[0753] "If a user prefers high-tempo music to wake them up in the morning, generate the appropriate music."

[0754] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] The user installs the application on their smartphone and launches it. As an initial setting, they enter personal information such as their age, gender, wake-up time, bedtime, and preferred music genre. This entered data is temporarily saved on the device in the form of "age," "gender," "wake-up time," "bedtime," and "music genre."

[0757] Step 2:

[0758] The device syncs with the user's health devices, such as smartwatches and fitness trackers, via Bluetooth or Wi-Fi. This operation collects health data such as heart rate and sleep patterns. The health data is stored on the device as "heart rate" and "sleep patterns."

[0759] Step 3:

[0760] This collected data (personal information and health data) is sent from the device to the server using a secure protocol (e.g., HTTPS). The data sent is encrypted and protected from access by third parties. The input at this stage is the collected "personal information" and "health data," and the output is "sent data" to the server.

[0761] Step 4:

[0762] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used as the database. At this stage, the input is "sent data" and the output is "stored data." The server then adds the data to the database.

[0763] Step 5:

[0764] The server uses Python's Pandas library to preprocess the data. Specifically, it performs operations such as filling in missing values ​​and normalizing the data. Next, it uses the Scikit-learn library to train a machine learning model to analyze the user's behavioral patterns and psychological state. The input for this process is the "stored data," and the output is the "analysis results." The server preprocesses the data and trains and analyzes the machine learning model.

[0765] Step 6:

[0766] The server generates optimal musical characteristics based on the analysis results. Specifically, it inputs parameters such as tempo and frequency obtained from the analysis results into a music generation algorithm such as MusicVAE to generate optimal music. At this stage, the input is the "analysis results" and the output is "music data (MIDI file)." The server uses MusicVAE to generate music.

[0767] Step 7:

[0768] The generated music data (MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted file is temporarily stored on the server. At this stage, the input is "music data (MIDI file)" and the output is "audio file (mp3)." The server performs the conversion process using a voice synthesis library.

[0769] Step 8:

[0770] The server sets the delivery time of the audio file based on the user's schedule (wake-up time, etc.). Specifically, if the user wakes up at 7:00 AM, the schedule is set to play the audio file from 6:45 AM. At this stage, the input is "schedule information" and the output is "delivery schedule." The server sets the schedule.

[0771] Step 9:

[0772] The server sends audio files to the terminal in real time according to the distribution schedule using streaming protocols such as RTP or RTSP. The inputs are "audio files (mp3)" and "distribution schedule," and the output is "sent audio files." The server performs streaming distribution.

[0773] Step 10:

[0774] The device plays the received audio file, gradually increasing the volume, for example, to allow the user to wake up naturally. At this stage, the input is the "transmitted audio file" and the output is the "music experience." The device plays the audio file.

[0775] Step 11:

[0776] After experiencing the music, users can enter feedback about the effect in the app. Evaluation items include the quality of awakening and the relaxation effect. This input feedback data is saved on the device as "feedback."

[0777] Step 12:

[0778] The device sends the collected feedback data to the server. This data is encrypted and transmitted using a secure protocol. The input is "feedback" and the output is "sent feedback" to the server.

[0779] Step 13:

[0780] The server stores the new feedback data in a database. It then updates the machine learning model and reflects this in future music generation. The input is the "submitted feedback" and the output is the "updated machine learning model." The server stores the feedback data and updates the machine learning model.

[0781] The above has described the specific operation of a system that processes and calculates input data at each processing step to provide the user with an optimal music experience.

[0782] (Application example 1)

[0783] 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."

[0784] With conventional music distribution systems, it was difficult to provide an optimal music experience based on the individual lifestyle and psychological state of each user, and there was a lack of mechanisms for continuously improving the service by utilizing user feedback. Furthermore, the technology for delivering personalized music in real time was not well developed, and there were limited means to improve user satisfaction.

[0785] 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.

[0786] In this invention, the server includes a means for collecting information from users, a means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, and a means for generating optimal music characteristics based on the analysis results. This enables optimal music to be generated based on individual user data and distributed in real time. The quality of the service is continuously improved by a means for converting the generated music characteristics into an audio file and distributing it to the user's device, and a means for collecting user feedback and updating the machine learning model. Furthermore, by providing a means for inputting the user's lifestyle data, such as sleep patterns and heart rate, and preferred music genres, an even more accurate music experience can be provided. The real-time distribution of audio files enables an optimal music experience that matches the user's lifestyle.

[0787] "Means for collecting information from users" refers to mechanisms for comprehensively obtaining individual information such as the user's age, gender, and biometric data provided by the device used.

[0788] "Means for analyzing collected information" refers to algorithms or analytical tools that process the acquired data and evaluate the user's behavioral patterns and psychological state.

[0789] "Means for diagnosing a user's behavioral patterns and psychological state" refers to a method for identifying a user's behavioral tendencies and emotional state based on analyzed data and responding to individual needs.

[0790] The "means for generating optimal musical characteristics based on the analysis results" is a mechanism that sets musical parameters that are optimal for the user's preferences and health condition based on the results of data analysis, and creates music using a music generation algorithm.

[0791] The "means for converting the generated musical characteristics into an audio file" is a speech synthesis system for converting the generated musical parameters into an actual audio format (e.g., MP3).

[0792] The "means for delivering to the user's device" refers to streaming technology or communication protocols for transmitting the generated audio file to the user's device and playing it at the appropriate time.

[0793] "Means for collecting user feedback" refers to an interface for obtaining users' evaluations and impressions of their musical experiences and reflecting them in future music generation.

[0794] The "means for updating the machine learning model" is a machine learning technique that uses collected feedback data to improve the performance of the music generation algorithm.

[0795] "User device" refers to a device such as a smartphone, tablet, or personal computer that a user uses to input information or receive or play music.

[0796] "Sleep pattern" is information about the user's sleep, including the user's sleep duration, sleep depth, and movements during sleep.

[0797] "Life data such as heart rate" is data that indicates the user's life rhythm, including biometric information, and is usually obtained from a wearable device.

[0798] "Favorite music genre" refers to the type or style of music that the user particularly likes, and includes categories such as classical, jazz, and pop.

[0799] "Feedback" refers to the ratings and impressions users provide about their music experience, and this data helps improve and personalize the system.

[0800] The invention is a system designed to provide a user-personalized sound experience, and includes the following phases:

[0801] Data collection phase:

[0802] Users install a smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre. Additionally, detailed lifestyle data (e.g., heart rate and sleep patterns) is collected using health devices such as smartwatches. This data is then transmitted to a server via a secure protocol.

[0803] Data analysis phase:

[0804] The server stores the transmitted data in a database and analyzes it using Python's Pandas and Scikit-learn libraries. The analysis diagnoses the user's behavioral patterns and psychological state, specifically by analyzing past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[0805] Sound generation phase:

[0806] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimal music. The generated music is an optimized sound based on input parameters such as tempo and frequency, and is generated as a MIDI file. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library and temporarily stored on the server.

[0807] Sound Delivery Phase:

[0808] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio and gradually increases the volume to wake up the user, for example.

[0809] Feedback gathering and learning phase:

[0810] After experiencing the sound, users enter feedback about the effect in the app. This feedback includes an evaluation of the quality of waking them up and the relaxing effect before sleep. This data is sent from the device to the server, which stores the feedback data in a database. This feedback is used to update the performance of the machine learning model and is reflected in future music generation.

[0811] Examples:

[0812] For example, assume that a user has a lifestyle where they wake up at 7:00 a.m. every morning and go to bed at 10:00 p.m. If the user prefers classical music when they want to relax, the server will analyze their past sleep data and gradually play classical music-based music with a high relaxing effect starting at 6:45 a.m. before they wake up.

[0813] Example prompt sentence:

[0814] 1. "Write a code that generates music appropriate for improving daytime focus based on the user's age and gender."

[0815] 2. "Write code for an algorithm that analyzes sleep data and generates music to help you wake up comfortably."

[0816] This invention is a system that provides a personalized music experience based on the user's lifestyle and preferences, and can continuously improve the quality of the service through feedback.

[0817] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0818] Step 1:

[0819] The server receives basic information (age, gender, wake-up time, bedtime, preferred music genre) sent from the user's smartphone app. It also collects detailed lifestyle data such as heart rate and sleep patterns from health devices such as smartwatches. This data is transmitted using a secure protocol and stored in a database.

[0820] Input: User information (age, gender, wake-up time, bedtime, music genre, heart rate, sleep pattern)

[0821] Output: Stored user data

[0822] Step 2:

[0823] The server analyzes the user information stored in the database. It preprocesses the data using Python's Pandas library and diagnoses the user's behavioral patterns and psychological state using the Scikit-learn library. This analysis allows it to predict future behavior and state based on the user's past data.

[0824] Input: User data stored in the database

[0825] Output: Diagnosis of user's behavioral patterns and psychological state

[0826] Step 3:

[0827] The server uses a generative AI model (e.g., MusicVAE) to generate optimal musical characteristics based on the analysis results. Parameters such as tempo and frequency obtained from the analysis are input into MusicVAE to generate optimal music. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library.

[0828] Input: Behavioral patterns and psychological state diagnosis results, parameters such as tempo and frequency

[0829] Output: Generated audio file (MP3)

[0830] Step 4:

[0831] The server references the user's schedule and delivers the generated audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for music delivery, and the audio is sent to the user's device without delay. The device then plays the received audio file, improving the user experience.

[0832] Input: Generated audio file, user schedule information

[0833] Output: Streamed audio file

[0834] Step 5:

[0835] After experiencing the music, users enter feedback within the app, including their evaluation of the quality and effectiveness of the music. The device then sends this feedback to the server, which stores the received feedback data in a database and updates the machine learning model to include new data.

[0836] Input: User feedback data

[0837] Output: An updated machine learning model

[0838] The above processing steps realize a system that provides an optimal music experience tailored to the individual needs of users and continuously improves the quality of service by incorporating feedback.

[0839] 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.

[0840] This invention is a system that provides an optimal music experience based on user information, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate emotion recognition and music personalization.

[0841] Data Collection Phase

[0842] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The app also connects to a health device (such as a smartwatch) to obtain more detailed lifestyle data (heart rate, sleep patterns, etc.). The smartphone's camera and microphone are also used to capture the user's facial expressions and voice data.

[0843] Data transmission phase

[0844] The device sends the data entered by the user and the acquired facial and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and transmitted securely.

[0845] Data analysis phase

[0846] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial and voice data to identify the user's emotional state in real time. For example, it can infer emotions (joy, anger, sadness, etc.) from the user's facial expressions captured on camera and the tone of voice picked up by the microphone.

[0847] Sound Generation Phase

[0848] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. It is also possible to adjust the characteristics of the generated music in real time based on the emotional state obtained from the emotion engine.

[0849] Sound Distribution Phase

[0850] The server checks the user's schedule information and prepares to deliver the audio file in real time at a specific time. The delivery uses streaming protocols such as RTP and RTSP to stream the audio to the terminal without delay.

[0851] Music Playback Phase

[0852] The device receives and plays the audio data sent from the server. The received audio data can, for example, gradually increase the volume to wake the user up naturally, while providing a pleasant musical experience with music characteristics that correspond to the user's emotional state.

[0853] Feedback gathering and learning phase

[0854] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0855] Feedback Analysis Phase

[0856] The server stores the new feedback data in the database and updates the machine learning model and emotion engine model. Using the SciPy library, the server applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize music generation and emotion recognition for future sessions.

[0857] Specific examples

[0858] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0859] Through the above processing, a system is realized that aims to improve the quality of life of users and, by combining it with an emotion engine, provides a more personalized music experience.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters their age, gender, wake-up time, bedtime, and preferred music genre. By connecting a health device (such as a smartwatch), more detailed lifestyle data (heart rate, sleep patterns, etc.) can be obtained.

[0863] Step 2:

[0864] The terminal sends the data entered by the user and the acquired data to the server using a secure protocol (e.g., HTTPS). The transmitted data is encrypted and communicated in a secure manner.

[0865] Step 3:

[0866] The server receives the user information sent from the terminal and stores it in a database.

[0867] Step 4:

[0868] The user provides facial and voice data using the smartphone camera and microphone. In this process, the data necessary for emotion recognition (e.g., smile, tone of voice) is acquired.

[0869] Step 5:

[0870] The device transmits the captured facial and voice data to a server in real time, allowing the user's emotional state to be instantly analyzed.

[0871] Step 6:

[0872] The emotion engine of the server analyzes the facial expression data and voice data to identify the user's emotional state. For example, if the user is smiling, the emotion engine determines that the user is in a "joy" state.

[0873] Step 7:

[0874] The server analyzes the user information stored in the database and the emotional data from the emotion engine using Python's Pandas and Scikit-learn libraries, and diagnoses the user's behavioral patterns and psychological state based on the analysis results.

[0875] Step 8:

[0876] The server generates musical characteristics (tempo, frequency, melody, timbre, etc.) using a music generation algorithm (e.g., MusicVAE) based on the analysis results. The generated musical characteristics are dynamically adjusted based on the emotional state obtained from the emotion engine.

[0877] Step 9:

[0878] The server converts the generated music data (e.g., MIDI file) into an audio file (e.g., mp3) using a voice synthesis library. The converted audio file is temporarily stored on the server.

[0879] Step 10:

[0880] The server checks the user's schedule and prepares to stream the audio file in real time at the specified time. For example, the server starts streaming the audio file in real time 15 minutes before the user wakes up.

[0881] Step 11:

[0882] The server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[0883] Step 12:

[0884] The device receives the audio data sent from the server and starts playing it. For example, it gradually increases the volume to wake you up naturally.

[0885] Step 13:

[0886] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings of the quality of their awakening, relaxation, and emotional changes.

[0887] Step 14:

[0888] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[0889] Step 15:

[0890] The server stores the feedback data in a database and updates the machine learning model and emotion engine model. For example, it uses the SciPy library to adapt the new data to the existing model and re-evaluate the model's performance. This will further improve the accuracy of music generation and emotion recognition in future runs.

[0891] Example 2

[0892] 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."

[0893] Conventional music experience systems were unable to fully grasp the user's emotional state and behavioral patterns, making it difficult to provide optimal music for each individual user. Furthermore, the system's ability to improve the system by incorporating user feedback was insufficient, making it impossible to increase user satisfaction. Furthermore, data security was often not ensured, creating a risk of personal information leaks.

[0894] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0895] In this invention, the server includes means for collecting information from users, means for encrypting and transmitting the collected information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal musical characteristics using a generative AI model based on the analysis results, means for converting the generated musical characteristics into an audio file, means for streaming the generated audio file to the user's device, and means for collecting feedback from users and updating the machine learning model and emotion recognition model. This not only enables optimal music to be provided based on the user's emotional state and behavioral patterns, but also allows the system to be continuously improved by reflecting the feedback and ensures data security.

[0896] "User" means a person who uses the system and provides their information and feedback.

[0897] The "information collection means" is a means for acquiring basic information from the user, such as age, gender, wake-up time, bedtime, and preferred music genre, as well as lifestyle data acquired from health devices, and the user's facial expressions and voice data.

[0898] The "encryption transmission means" is a means for encrypting collected user information and transmitting it to a server using a secure protocol.

[0899] The "data analysis means" is a means for storing the user information received by the server in a database and diagnosing the user's behavioral patterns and psychological state using a Python data analysis library.

[0900] A "generative AI model" is an artificial intelligence model that uses a music generation algorithm to generate optimal musical characteristics based on the results of data analysis.

[0901] The "audio file conversion means" is a means for converting the music data generated by the generative AI model into an audio file using a voice synthesis library.

[0902] The "streaming delivery means" is a means for streaming the generated audio file to the user's terminal in real time.

[0903] The "feedback collection means" is a means for collecting user evaluations and impressions regarding the music experience provided.

[0904] "Model updating means" refers to a means of updating machine learning models and emotion recognition models based on collected feedback to improve system performance.

[0905] An "emotion recognition model" is an artificial intelligence model that analyzes a user's facial expressions and voice data to identify emotional states such as joy, anger, and sadness.

[0906] This invention is a system that provides an optimal music experience based on user information, and by combining emotion recognition technology, it achieves more accurate emotion analysis and music personalization. The system operates through a process in which the user uses a smartphone app, collects and analyzes user information, and generates and delivers optimal music.

[0907] Data Collection Phase

[0908] The user installs and launches the smartphone app. On the initial setup screen, the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device such as a smartwatch to collect more detailed lifestyle data (e.g., heart rate and sleep patterns). Furthermore, the smartphone's camera and microphone are used to capture the user's facial expressions and voice data.

[0909] Data transmission phase

[0910] The device sends the data entered by the user and the acquired facial expression and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted to ensure security.

[0911] Data analysis phase

[0912] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. The emotion engine analyzes facial and voice data to identify the user's emotional state in real time. This emotion recognition technology infers emotions such as joy, anger, and sadness from the user's facial expressions captured by the camera and tone of voice picked up from the microphone.

[0913] Sound Generation Phase

[0914] Based on the analysis results, the server uses music generation algorithms such as MusicVAE to generate optimal musical characteristics. Specific parameters (tempo, frequency, melody, timbre, etc.) are set and the music is customized based on the emotional state obtained from the emotion engine. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library.

[0915] Sound Distribution Phase

[0916] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, ensuring audio is sent to the terminal without delay.

[0917] Music Playback Phase

[0918] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it can gradually increase the volume to wake up the user, encouraging them to wake up naturally, while also providing music with musical characteristics that correspond to the user's emotional state, creating a pleasant music experience.

[0919] Feedback gathering phase

[0920] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[0921] Feedback Analysis Phase

[0922] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and re-evaluate their performance. The updated models are then used to further optimize music generation and emotion recognition for future iterations.

[0923] Specific examples

[0924] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, making it possible to provide an even more accurate service.

[0925] This invention utilizes user information to provide a personalized music experience and combines emotion recognition technology to improve the user's quality of life.

[0926] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0927] Step 1:

[0928] Users install the smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre on the initial setup screen. The information entered at this time is saved in the app as text data.

[0929] Step 2:

[0930] Users connect their health devices, such as smartwatches, to the app, which then collects detailed lifestyle data, such as heart rate and sleep patterns, in real time. The collected data is then stored in the app as numerical data.

[0931] Step 3:

[0932] Users use their smartphone's camera and microphone to collect facial and voice data. The facial data is saved as an image file, and the voice data is saved as an audio file. These data are used to analyze the user's emotional state in real time.

[0933] Step 4:

[0934] The device sends the basic information entered by the user, the acquired lifestyle data, facial expression data, and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and stored on the server as encrypted data after transmission.

[0935] Step 5:

[0936] The server stores the received information in a database. The stored data is classified by user ID and saved in the following data formats: text, numeric, image, and audio.

[0937] Step 6:

[0938] The server uses Python's Pandas and Scikit-learn libraries to analyze the information in the database. The analysis diagnoses the user's behavioral patterns and psychological state. Specifically, it analyzes sleep quality and heart rate fluctuations from lifestyle data to identify behavioral patterns. In addition, an emotion engine analyzes facial expression data and voice data to identify the user's emotional state. The analysis results are output as text data representing behavioral patterns and emotional states.

[0939] Step 7:

[0940] The server then uses music generation algorithms such as MusicVAE to generate optimal musical characteristics based on the analysis results. Specific parameters (tempo, frequency, melody, timbre, etc.) are set, and the music is customized based on the emotional state obtained from the emotion engine. The generated music data is output in MIDI file format.

[0941] Step 8:

[0942] The server converts the generated music data (MIDI file) into an audio file (mp3 format) using a voice synthesis library, and the converted audio file is stored on the server in preparation for distribution.

[0943] Step 9:

[0944] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, and audio data is sent to the terminal in real time. The transmitted audio data is then received by the terminal as a real-time streaming file.

[0945] Step 10:

[0946] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it gradually increases the volume to wake up the user naturally, and provides music with musical characteristics that correspond to the user's emotional state. The played audio is output as an MP3 audio file.

[0947] Step 11:

[0948] After listening to the music, users can enter feedback about the effects of the music in the app. This feedback includes an evaluation of the quality of awakening, relaxation, and emotional changes. The input feedback data is stored in the app as numerical and text data.

[0949] Step 12:

[0950] The device sends the collected feedback data to the server. The feedback data is encrypted and sent using a secure protocol (e.g., HTTPS). After sending, the data is stored on the server as encrypted data.

[0951] Step 13:

[0952] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and reevaluate their performance. The updated models are used for music generation and emotion recognition from the next time onwards. The updated model information is saved as text data on the server.

[0953] (Application example 2)

[0954] 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."

[0955] Existing music distribution services have difficulty providing a personalized music experience based on the user's emotions and behavioral patterns. Therefore, there is a need for a system that can provide music optimized for the user's psychological state and emotions in real time. Furthermore, a mechanism is also needed that effectively utilizes user feedback to continuously improve the quality of the music experience.

[0956] 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.

[0957] In this invention, the server includes means for collecting user information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal music characteristics based on the analysis results, means for generating music characteristics using an emotion engine that recognizes the user's emotional state in real time, means for delivering the generated music characteristics to the user's device, means for collecting user feedback and updating the machine learning model, and means for using a streaming protocol to deliver the generated music in real time, thereby enabling the provision of a personalized music experience based on the user's emotions and behavioral patterns.

[0958] "Means of collecting information from users" refers to functions that obtain data such as the user's age, gender, sleep patterns, preferred music genres, heart rate, facial expressions, and voice via smartphones or wearable devices.

[0959] "Means of analyzing collected information and diagnosing the user's behavioral patterns and psychological state" refers to a function that analyzes changes in the user's daily rhythm and emotions based on collected data, and identifies behavioral patterns and psychological state.

[0960] The "means for generating optimal musical characteristics" is a function that determines musical elements such as tempo, frequency, melody, and tone based on analyzed user data, and creates music that is optimal for the user.

[0961] The "means for delivering the generated music characteristics to the user's terminal" is a function for transmitting the generated music data to the user's terminal in streaming or download format.

[0962] "Musical characteristic generation means using an emotion engine that recognizes the user's emotional state in real time" is a function that grasps the user's emotions in real time through facial expression recognition and voice analysis, and generates musical characteristics that are adapted to those emotions.

[0963] "Means for collecting user feedback and updating the machine learning model" refers to a function that collects feedback on users' music experiences and updates the machine learning model based on that feedback, adapting it to the latest data.

[0964] "Means for using a streaming protocol to deliver the generated music in real time" refers to a function that uses a streaming protocol such as RTP or RTSP to deliver the generated music to users without delay.

[0965] This invention is a system that provides an optimal music experience based on the user's emotions and behavioral patterns. Specifically, it includes a series of processes for collecting and analyzing user information, and generating and distributing music based on the analysis results.

[0966] The system collects various data using the user's smartphone and wearable devices such as a smartwatch. Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. By linking the app to a smartwatch, the system also collects heart rate and sleep patterns. Furthermore, the system uses the smartphone's camera and microphone to collect facial expressions and voice data.

[0967] This data is sent to a server using a secure protocol such as HTTPS. The server then analyzes the data using Python libraries such as Pandas and Scikit-learn. This analysis identifies the user's behavioral patterns and psychological state. Furthermore, an emotion engine is used to analyze the user's emotional state in real time.

[0968] Based on the analysis results, a music generation algorithm (e.g., MusicVAE) is used to generate music that is optimal for the user. This generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a speech synthesis library. The music is then delivered to the user's device without delay using a streaming protocol such as RTP or RTSP.

[0969] After playing the provided music, users enter feedback within the app. This feedback data is also sent to the server and used to update the machine learning model. Using the SciPy library, the new data is adapted to the existing model to further optimize music generation and emotion recognition in future trials.

[0970] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[0971] An example of a prompt sentence to input to the generative AI model is as follows:

[0972] "Analyze facial expressions and voice data to indicate that the user is stressed. Explain the process of generating and delivering relaxing music to the user."

[0973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0974] Step 1:

[0975] Data Collection Phase

[0976] Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. Furthermore, by connecting a smartwatch, heart rate and sleep patterns can also be obtained. The smartphone's camera and microphone are also used to collect facial expressions and voice data. The input is the user's profile information and biometric data, and the collected data is output.

[0977] Step 2:

[0978] Data transmission phase

[0979] The terminal sends the collected data to the server using the HTTPS protocol. Specifically, the user data is converted into JSON format, encrypted, and then sent to the server. The input is the collected user data, and the output is the data securely sent to the server.

[0980] Step 3:

[0981] Data analysis phase

[0982] The server stores the received information in a database and analyzes it using Pandas and Scikit-learn. The analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial expressions and voice data to identify the user's emotional state in real time. The input is the user data sent to the server, and the output is the analysis results (behavioral patterns, psychological state, and emotional state).

[0983] Step 4:

[0984] Sound Generation Phase

[0985] The server uses a music generation algorithm such as MusicVAE to generate optimized sounds based on input parameters such as tempo, frequency, melody, and timbre. The generated data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. The input is the analysis result, and the output is the generated music file.

[0986] Step 5:

[0987] Sound Distribution Phase

[0988] The server uses streaming protocols such as RTP and RTSP to deliver music files generated in real time to users' devices. The input is the music file, and the output is real-time streaming.

[0989] Step 6:

[0990] Music Playback Phase

[0991] The device plays the received music data. Specifically, it plays the received audio file using a media player. The input is the distributed music file, and the output is the music playback.

[0992] Step 7:

[0993] Feedback gathering and learning phase

[0994] After experiencing the sound, the user inputs feedback within the app. The device sends this feedback to the server. The input is the user feedback, and the output is the feedback data sent to the server.

[0995] Step 8:

[0996] Feedback Analysis Phase

[0997] The server stores the new feedback data in a database and updates the machine learning model and the emotion engine model using the SciPy library. The input is the feedback data and the output is the updated machine learning model.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] [Fourth embodiment]

[1002] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1003] 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.

[1004] 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).

[1005] 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.

[1006] 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.

[1007] 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).

[1008] 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.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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.

[1014] 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."

[1015] The present invention is a system that provides an optimal music experience based on user information, and is specifically implemented as follows.

[1016] Data Collection Phase

[1017] Users install the smartphone app and enter their age, gender, wake-up time, bedtime, and preferred music genre. The app can also connect to health devices (e.g., smartwatches) to obtain more detailed lifestyle data (e.g., heart rate, sleep patterns, etc.). This information is sent from the device to the server via a secure protocol.

[1018] Data analysis phase

[1019] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. The analysis provides a detailed diagnosis of the user's behavioral patterns and psychological state. For example, a time series analysis of the user's past sleep data can be performed to predict the optimal music characteristics for the next wake-up time.

[1020] Sound Generation Phase

[1021] Based on the analysis results, the server uses a music generation algorithm (e.g., MusicVAE) to generate optimal music. This music generation algorithm inputs parameters such as tempo and frequency to generate optimized sound. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library and temporarily stored on the server.

[1022] Sound Distribution Phase

[1023] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio, gradually increasing the volume to wake up the user, for example, to promote natural waking.

[1024] Feedback gathering and learning phase

[1025] After experiencing the sound, users enter feedback within the app about the effect, including their assessment of the quality of their awakening and the relaxing effect before sleep. The device then sends this feedback to the server, which stores the new data in a database. This feedback data is used to update the performance of the machine learning model and is reflected in future music generation.

[1026] Specific examples

[1027] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and gradually play classical music-based sounds with a relaxing effect starting 15 minutes (6:45am) before waking up. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation.

[1028] As described above, the present invention is a system that provides an optimal sound experience that meets the user's needs in each phase and enables continuous improvement of service performance through feedback.

[1029] The processing flow will be explained below.

[1030] Step 1:

[1031] The user installs the smartphone app and launches it. An initial setup screen appears, prompting the user to enter information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device (such as a smartwatch) and enter more detailed lifestyle data (heart rate, sleep patterns, etc.).

[1032] Step 2:

[1033] The terminal sends the data entered by the user to the server using a secure protocol (e.g., HTTPS). The sent data is encrypted to maintain security.

[1034] Step 3:

[1035] The server receives the user information sent from the terminal and stores it in a database.

[1036] Step 4:

[1037] The server uses Python's Pandas and Scikit-learn libraries to analyze user information stored in the database. The analysis diagnoses the user's past behavioral patterns and psychological state. For example, it analyzes past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[1038] Step 5:

[1039] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. This music data (e.g., MIDI file) is then converted into an audio file (e.g., mp3) using a voice synthesis library.

[1040] Step 6:

[1041] The server temporarily stores the generated audio file and checks the user's schedule information. For example, when it is 15 minutes before the user's wake-up time, the server prepares to deliver the audio file in real time.

[1042] Step 7:

[1043] At a specific time, the server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[1044] Step 8:

[1045] The device receives the audio data sent from the server, plays the audio data, and, for example, gradually increases the volume to wake up the user naturally.

[1046] Step 9:

[1047] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings for the quality of their awakening and the relaxing effect.

[1048] Step 10:

[1049] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[1050] Step 11:

[1051] The server stores the new feedback data in a database and updates the machine learning model. Using the SciPy library, it applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize future music generation.

[1052] Example 1

[1053] 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."

[1054] Conventional music distribution systems have difficulty providing music tailored to individual users' lifestyle patterns and preferences, and can only provide a uniform music experience. Furthermore, there is no mechanism for improving the system based on user feedback, making it difficult to provide a music experience optimized for each individual user. Therefore, there is a need for an advanced system that can provide a music experience that takes into account the user's health data and lifestyle rhythm.

[1055] 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.

[1056] In this invention, the server includes means for collecting personal information from users, means for integrating the collected personal information and health data and transmitting the integrated data to the server, means for storing the collected information in a database on the server and performing data analysis, means for generating optimal musical characteristics based on the analysis results, means for converting the generated musical characteristics into an audio file and delivering it to the user's device in real time, and means for collecting feedback from users and updating the machine learning model, thereby enabling the provision of an optimal music experience tailored to the user's individual lifestyle patterns and preferences.

[1057] "Means for collecting personal information from users" refers to a function for acquiring information such as the user's age, gender, wake-up time, bedtime, and favorite music genre.

[1058] "Means for integrating collected personal information and health data and sending it to a server" refers to a function that integrates data obtained from the user's smartphone or health device, encrypts it, and sends it to a server via a secure protocol.

[1059] "Means of storing information collected on the server in a database and performing data analysis" refers to a function that stores received data in a database and performs data analysis using Python's Pandas library and Scikit-learn library.

[1060] "Means for generating optimal musical characteristics based on analysis results" refers to a function that extracts parameters such as the tempo and frequency of music that are optimal for the user from the data analysis results, and generates music using a music generation algorithm.

[1061] The "means for converting the generated musical characteristics into an audio file and distributing it to the user's terminal in real time" is a function for converting the generated MIDI data into an audio file and distributing it to the user's terminal in real time using a streaming protocol.

[1062] "Means of collecting user feedback and updating the machine learning model" refers to a function that collects ratings and opinions entered by users within the app, updates the machine learning model based on that information, and reflects it in future music generation.

[1063] The present invention is a system that provides an optimal music experience based on a user's personal information and health data. Specific embodiments of the system are described below.

[1064] (Data collection phase)

[1065] First, a user installs and launches the application on their smartphone. The application prompts the user to enter personal information such as age, gender, wake-up time, bedtime, and preferred music genre. The application then connects to the user's health device (e.g., a smartwatch) via Bluetooth or Wi-Fi to collect information such as heart rate and sleep patterns. This data is temporarily stored on the device and then transmitted to a server via a secure protocol (e.g., HTTPS).

[1066] (Data analysis phase)

[1067] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. The server then preprocesses the data using Python's Pandas library and trains a machine learning model using the Scikit-learn library. This analysis allows for a detailed diagnosis of the user's behavioral patterns and psychological state, and derives optimal musical characteristics (e.g., tempo, frequency).

[1068] As a concrete example, let's say a 30-year-old man has a daily rhythm of waking up at 7am and going to bed at 10pm, and likes classical music. In this case, the server analyzes past sleep data and recommends classical music with a high relaxing effect, starting 15 minutes before waking up (6:45am). From the analysis results, specific musical characteristics such as "high tempo is effective for waking up in the morning" can be derived.

[1069] (Sound generation phase)

[1070] The server inputs the necessary parameters into a music generation algorithm (e.g., MusicVAE) based on the analysis results, generating optimal music. This algorithm makes maximum use of parameters such as tempo and frequency to generate music suited to each individual user. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted audio file is temporarily stored on the server.

[1071] (Sound distribution phase)

[1072] The server sets the delivery time of the audio file based on the user's schedule. For example, if the user wakes up at 7:00 a.m., the server can schedule the audio file to play from 6:45 a.m. Streaming protocols such as RTP and RTSP are used to deliver the audio file, and it is sent to the device in real time. The device then plays the received audio file, gradually increasing the volume, for example, to encourage a natural awakening.

[1073] (Feedback collection and learning phase)

[1074] After listening to the music, users can enter feedback within the app, including their evaluation of the quality of their wake-up experience and the relaxing effect before sleep. The device then sends this feedback data to the server, which then stores the new data in a database. This feedback data is used to update the machine learning model and is reflected in future music generation, continuously improving the overall system performance.

[1075] This allows the present invention to provide an optimal music experience tailored to each user's individual lifestyle patterns and preferences, and to continuously improve the performance of the service through feedback.

[1076] Prompt Sentence Examples

[1077] "If a user prefers classical music, what is the best tempo and frequency to use for the music generation algorithm?"

[1078] "If a user prefers high-tempo music to wake them up in the morning, generate the appropriate music."

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] The user installs the application on their smartphone and launches it. As an initial setting, they enter personal information such as their age, gender, wake-up time, bedtime, and preferred music genre. This entered data is temporarily saved on the device in the form of "age," "gender," "wake-up time," "bedtime," and "music genre."

[1082] Step 2:

[1083] The device syncs with the user's health devices, such as smartwatches and fitness trackers, via Bluetooth or Wi-Fi. This operation collects health data such as heart rate and sleep patterns. The health data is stored on the device as "heart rate" and "sleep patterns."

[1084] Step 3:

[1085] This collected data (personal information and health data) is sent from the device to the server using a secure protocol (e.g., HTTPS). The data sent is encrypted and protected from access by third parties. The input at this stage is the collected "personal information" and "health data," and the output is "sent data" to the server.

[1086] Step 4:

[1087] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used as the database. At this stage, the input is "sent data" and the output is "stored data." The server then adds the data to the database.

[1088] Step 5:

[1089] The server uses Python's Pandas library to preprocess the data. Specifically, it performs operations such as filling in missing values ​​and normalizing the data. Next, it uses the Scikit-learn library to train a machine learning model to analyze the user's behavioral patterns and psychological state. The input for this process is the "stored data," and the output is the "analysis results." The server preprocesses the data and trains and analyzes the machine learning model.

[1090] Step 6:

[1091] The server generates optimal musical characteristics based on the analysis results. Specifically, it inputs parameters such as tempo and frequency obtained from the analysis results into a music generation algorithm such as MusicVAE to generate optimal music. At this stage, the input is the "analysis results" and the output is "music data (MIDI file)." The server uses MusicVAE to generate music.

[1092] Step 7:

[1093] The generated music data (MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library (e.g., FluidSynth). The converted file is temporarily stored on the server. At this stage, the input is "music data (MIDI file)" and the output is "audio file (mp3)." The server performs the conversion process using a voice synthesis library.

[1094] Step 8:

[1095] The server sets the delivery time of the audio file based on the user's schedule (wake-up time, etc.). Specifically, if the user wakes up at 7:00 AM, the schedule is set to play the audio file from 6:45 AM. At this stage, the input is "schedule information" and the output is "delivery schedule." The server sets the schedule.

[1096] Step 9:

[1097] The server sends audio files to the terminal in real time according to the distribution schedule using streaming protocols such as RTP or RTSP. The inputs are "audio files (mp3)" and "distribution schedule," and the output is "sent audio files." The server performs streaming distribution.

[1098] Step 10:

[1099] The device plays the received audio file, gradually increasing the volume, for example, to allow the user to wake up naturally. At this stage, the input is the "transmitted audio file" and the output is the "music experience." The device plays the audio file.

[1100] Step 11:

[1101] After experiencing the music, users can enter feedback about the effect in the app. Evaluation items include the quality of awakening and the relaxation effect. This input feedback data is saved on the device as "feedback."

[1102] Step 12:

[1103] The device sends the collected feedback data to the server. This data is encrypted and transmitted using a secure protocol. The input is "feedback" and the output is "sent feedback" to the server.

[1104] Step 13:

[1105] The server stores the new feedback data in a database. It then updates the machine learning model and reflects this in future music generation. The input is the "submitted feedback" and the output is the "updated machine learning model." The server stores the feedback data and updates the machine learning model.

[1106] The above has described the specific operation of a system that processes and calculates input data at each processing step to provide the user with an optimal music experience.

[1107] (Application example 1)

[1108] 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."

[1109] With conventional music distribution systems, it was difficult to provide an optimal music experience based on the individual lifestyle and psychological state of each user, and there was a lack of mechanisms for continuously improving the service by utilizing user feedback. Furthermore, the technology for delivering personalized music in real time was not well developed, and there were limited means to improve user satisfaction.

[1110] 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.

[1111] In this invention, the server includes a means for collecting information from users, a means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, and a means for generating optimal music characteristics based on the analysis results. This enables optimal music to be generated based on individual user data and distributed in real time. The quality of the service is continuously improved by a means for converting the generated music characteristics into an audio file and distributing it to the user's device, and a means for collecting user feedback and updating the machine learning model. Furthermore, by providing a means for inputting the user's lifestyle data, such as sleep patterns and heart rate, and preferred music genres, an even more accurate music experience can be provided. The real-time distribution of audio files enables an optimal music experience that matches the user's lifestyle.

[1112] "Means for collecting information from users" refers to mechanisms for comprehensively obtaining individual information such as the user's age, gender, and biometric data provided by the device used.

[1113] "Means for analyzing collected information" refers to algorithms or analytical tools that process the acquired data and evaluate the user's behavioral patterns and psychological state.

[1114] "Means for diagnosing a user's behavioral patterns and psychological state" refers to a method for identifying a user's behavioral tendencies and emotional state based on analyzed data and responding to individual needs.

[1115] The "means for generating optimal musical characteristics based on the analysis results" is a mechanism that sets musical parameters that are optimal for the user's preferences and health condition based on the results of data analysis, and creates music using a music generation algorithm.

[1116] The "means for converting the generated musical characteristics into an audio file" is a speech synthesis system for converting the generated musical parameters into an actual audio format (e.g., MP3).

[1117] The "means for delivering to the user's device" refers to streaming technology or communication protocols for transmitting the generated audio file to the user's device and playing it at the appropriate time.

[1118] "Means for collecting user feedback" refers to an interface for obtaining users' evaluations and impressions of their musical experiences and reflecting them in future music generation.

[1119] The "means for updating the machine learning model" is a machine learning technique that uses collected feedback data to improve the performance of the music generation algorithm.

[1120] "User device" refers to a device such as a smartphone, tablet, or personal computer that a user uses to input information or receive or play music.

[1121] "Sleep pattern" is information about the user's sleep, including the user's sleep duration, sleep depth, and movements during sleep.

[1122] "Life data such as heart rate" is data that indicates the user's life rhythm, including biometric information, and is usually obtained from a wearable device.

[1123] "Favorite music genre" refers to the type or style of music that the user particularly likes, and includes categories such as classical, jazz, and pop.

[1124] "Feedback" refers to the ratings and impressions users provide about their music experience, and this data helps improve and personalize the system.

[1125] The invention is a system designed to provide a user-personalized sound experience, and includes the following phases:

[1126] Data collection phase:

[1127] Users install a smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre. Additionally, detailed lifestyle data (e.g., heart rate and sleep patterns) is collected using health devices such as smartwatches. This data is then transmitted to a server via a secure protocol.

[1128] Data analysis phase:

[1129] The server stores the transmitted data in a database and analyzes it using Python's Pandas and Scikit-learn libraries. The analysis diagnoses the user's behavioral patterns and psychological state, specifically by analyzing past sleep data over time to predict the optimal music characteristics for the next wake-up time.

[1130] Sound generation phase:

[1131] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimal music. The generated music is an optimized sound based on input parameters such as tempo and frequency, and is generated as a MIDI file. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library and temporarily stored on the server.

[1132] Sound Delivery Phase:

[1133] The server checks the user's schedule and delivers the audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for delivery, sending the audio to the device without delay. The device then plays the received audio and gradually increases the volume to wake up the user, for example.

[1134] Feedback gathering and learning phase:

[1135] After experiencing the sound, users enter feedback about the effect in the app. This feedback includes an evaluation of the quality of waking them up and the relaxing effect before sleep. This data is sent from the device to the server, which stores the feedback data in a database. This feedback is used to update the performance of the machine learning model and is reflected in future music generation.

[1136] Examples:

[1137] For example, assume that a user has a lifestyle where they wake up at 7:00 a.m. every morning and go to bed at 10:00 p.m. If the user prefers classical music when they want to relax, the server will analyze their past sleep data and gradually play classical music-based music with a high relaxing effect starting at 6:45 a.m. before they wake up.

[1138] Example prompt sentence:

[1139] 1. "Write a code that generates music appropriate for improving daytime focus based on the user's age and gender."

[1140] 2. "Write code for an algorithm that analyzes sleep data and generates music to help you wake up comfortably."

[1141] This invention is a system that provides a personalized music experience based on the user's lifestyle and preferences, and can continuously improve the quality of the service through feedback.

[1142] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1143] Step 1:

[1144] The server receives basic information (age, gender, wake-up time, bedtime, preferred music genre) sent from the user's smartphone app. It also collects detailed lifestyle data such as heart rate and sleep patterns from health devices such as smartwatches. This data is transmitted using a secure protocol and stored in a database.

[1145] Input: User information (age, gender, wake-up time, bedtime, music genre, heart rate, sleep pattern)

[1146] Output: Stored user data

[1147] Step 2:

[1148] The server analyzes the user information stored in the database. It preprocesses the data using Python's Pandas library and diagnoses the user's behavioral patterns and psychological state using the Scikit-learn library. This analysis allows it to predict future behavior and state based on the user's past data.

[1149] Input: User data stored in the database

[1150] Output: Diagnosis of user's behavioral patterns and psychological state

[1151] Step 3:

[1152] The server uses a generative AI model (e.g., MusicVAE) to generate optimal musical characteristics based on the analysis results. Parameters such as tempo and frequency obtained from the analysis are input into MusicVAE to generate optimal music. The generated MIDI file is then converted into an audio file (e.g., MP3 format) using a voice synthesis library.

[1153] Input: Behavioral patterns and psychological state diagnosis results, parameters such as tempo and frequency

[1154] Output: Generated audio file (MP3)

[1155] Step 4:

[1156] The server references the user's schedule and delivers the generated audio file in real time at the specified time. Streaming protocols such as RTP and RTSP are used for music delivery, and the audio is sent to the user's device without delay. The device then plays the received audio file, improving the user experience.

[1157] Input: Generated audio file, user schedule information

[1158] Output: Streamed audio file

[1159] Step 5:

[1160] After experiencing the music, users enter feedback within the app, including their evaluation of the quality and effectiveness of the music. The device then sends this feedback to the server, which stores the received feedback data in a database and updates the machine learning model to include new data.

[1161] Input: User feedback data

[1162] Output: An updated machine learning model

[1163] The above processing steps realize a system that provides an optimal music experience tailored to the individual needs of users and continuously improves the quality of service by incorporating feedback.

[1164] 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.

[1165] This invention is a system that provides an optimal music experience based on user information, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate emotion recognition and music personalization.

[1166] Data Collection Phase

[1167] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The app also connects to a health device (such as a smartwatch) to obtain more detailed lifestyle data (heart rate, sleep patterns, etc.). The smartphone's camera and microphone are also used to capture the user's facial expressions and voice data.

[1168] Data transmission phase

[1169] The device sends the data entered by the user and the acquired facial and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and transmitted securely.

[1170] Data analysis phase

[1171] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial and voice data to identify the user's emotional state in real time. For example, it can infer emotions (joy, anger, sadness, etc.) from the user's facial expressions captured on camera and the tone of voice picked up by the microphone.

[1172] Sound Generation Phase

[1173] The server uses a music generation algorithm (e.g., MusicVAE) based on the analysis results to generate optimized sounds by inputting parameters such as tempo, frequency, melody, and timbre. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. It is also possible to adjust the characteristics of the generated music in real time based on the emotional state obtained from the emotion engine.

[1174] Sound Distribution Phase

[1175] The server checks the user's schedule information and prepares to deliver the audio file in real time at a specific time. The delivery uses streaming protocols such as RTP and RTSP to stream the audio to the terminal without delay.

[1176] Music Playback Phase

[1177] The device receives and plays the audio data sent from the server. The received audio data can, for example, gradually increase the volume to wake the user up naturally, while providing a pleasant musical experience with music characteristics that correspond to the user's emotional state.

[1178] Feedback gathering and learning phase

[1179] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[1180] Feedback Analysis Phase

[1181] The server stores the new feedback data in the database and updates the machine learning model and emotion engine model. Using the SciPy library, the server applies the new data to the existing model and re-evaluates the model's performance. This updated model is used to further optimize music generation and emotion recognition for future sessions.

[1182] Specific examples

[1183] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[1184] Through the above processing, a system is realized that aims to improve the quality of life of users and, by combining it with an emotion engine, provides a more personalized music experience.

[1185] The processing flow will be explained below.

[1186] Step 1:

[1187] The user installs the smartphone app and launches it. An initial setup screen appears, where the user enters their age, gender, wake-up time, bedtime, and preferred music genre. By connecting a health device (such as a smartwatch), more detailed lifestyle data (heart rate, sleep patterns, etc.) can be obtained.

[1188] Step 2:

[1189] The terminal sends the data entered by the user and the acquired data to the server using a secure protocol (e.g., HTTPS). The transmitted data is encrypted and communicated in a secure manner.

[1190] Step 3:

[1191] The server receives the user information sent from the terminal and stores it in a database.

[1192] Step 4:

[1193] The user provides facial and voice data using the smartphone camera and microphone. In this process, the data necessary for emotion recognition (e.g., smile, tone of voice) is acquired.

[1194] Step 5:

[1195] The device transmits the captured facial and voice data to a server in real time, allowing the user's emotional state to be instantly analyzed.

[1196] Step 6:

[1197] The emotion engine of the server analyzes the facial expression data and voice data to identify the user's emotional state. For example, if the user is smiling, the emotion engine determines that the user is in a "joy" state.

[1198] Step 7:

[1199] The server analyzes the user information stored in the database and the emotional data from the emotion engine using Python's Pandas and Scikit-learn libraries, and diagnoses the user's behavioral patterns and psychological state based on the analysis results.

[1200] Step 8:

[1201] The server generates musical characteristics (tempo, frequency, melody, timbre, etc.) using a music generation algorithm (e.g., MusicVAE) based on the analysis results. The generated musical characteristics are dynamically adjusted based on the emotional state obtained from the emotion engine.

[1202] Step 9:

[1203] The server converts the generated music data (e.g., MIDI file) into an audio file (e.g., mp3) using a voice synthesis library. The converted audio file is temporarily stored on the server.

[1204] Step 10:

[1205] The server checks the user's schedule and prepares to stream the audio file in real time at the specified time. For example, the server starts streaming the audio file in real time 15 minutes before the user wakes up.

[1206] Step 11:

[1207] The server uses a streaming module to stream audio files to the terminal in real time, using streaming protocols such as RTP and RTSP to deliver audio without delay.

[1208] Step 12:

[1209] The device receives the audio data sent from the server and starts playing it. For example, it gradually increases the volume to wake you up naturally.

[1210] Step 13:

[1211] After experiencing the sounds, users can enter feedback within the app about the effects, including ratings of the quality of their awakening, relaxation, and emotional changes.

[1212] Step 14:

[1213] The terminal transmits the user's feedback data to the server, which is also encrypted to ensure secure communication.

[1214] Step 15:

[1215] The server stores the feedback data in a database and updates the machine learning model and emotion engine model. For example, it uses the SciPy library to adapt the new data to the existing model and re-evaluate the model's performance. This will further improve the accuracy of music generation and emotion recognition in future runs.

[1216] Example 2

[1217] 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."

[1218] Conventional music experience systems were unable to fully grasp the user's emotional state and behavioral patterns, making it difficult to provide optimal music for each individual user. Furthermore, the system's ability to improve the system by incorporating user feedback was insufficient, making it impossible to increase user satisfaction. Furthermore, data security was often not ensured, creating a risk of personal information leaks.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1220] In this invention, the server includes means for collecting information from users, means for encrypting and transmitting the collected information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal musical characteristics using a generative AI model based on the analysis results, means for converting the generated musical characteristics into an audio file, means for streaming the generated audio file to the user's device, and means for collecting feedback from users and updating the machine learning model and emotion recognition model. This not only enables optimal music to be provided based on the user's emotional state and behavioral patterns, but also allows the system to be continuously improved by reflecting the feedback and ensures data security.

[1221] "User" means a person who uses the system and provides their information and feedback.

[1222] The "information collection means" is a means for acquiring basic information from the user, such as age, gender, wake-up time, bedtime, and preferred music genre, as well as lifestyle data acquired from health devices, and the user's facial expressions and voice data.

[1223] The "encryption transmission means" is a means for encrypting collected user information and transmitting it to a server using a secure protocol.

[1224] The "data analysis means" is a means for storing the user information received by the server in a database and diagnosing the user's behavioral patterns and psychological state using a Python data analysis library.

[1225] A "generative AI model" is an artificial intelligence model that uses a music generation algorithm to generate optimal musical characteristics based on the results of data analysis.

[1226] The "audio file conversion means" is a means for converting the music data generated by the generative AI model into an audio file using a voice synthesis library.

[1227] The "streaming delivery means" is a means for streaming the generated audio file to the user's terminal in real time.

[1228] The "feedback collection means" is a means for collecting user evaluations and impressions regarding the music experience provided.

[1229] "Model updating means" refers to a means of updating machine learning models and emotion recognition models based on collected feedback to improve system performance.

[1230] An "emotion recognition model" is an artificial intelligence model that analyzes a user's facial expressions and voice data to identify emotional states such as joy, anger, and sadness.

[1231] This invention is a system that provides an optimal music experience based on user information, and by combining emotion recognition technology, it achieves more accurate emotion analysis and music personalization. The system operates through a process in which the user uses a smartphone app, collects and analyzes user information, and generates and delivers optimal music.

[1232] Data Collection Phase

[1233] The user installs and launches the smartphone app. On the initial setup screen, the user enters information such as age, gender, wake-up time, bedtime, and preferred music genre. The user can also connect a health device such as a smartwatch to collect more detailed lifestyle data (e.g., heart rate and sleep patterns). Furthermore, the smartphone's camera and microphone are used to capture the user's facial expressions and voice data.

[1234] Data transmission phase

[1235] The device sends the data entered by the user and the acquired facial expression and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted to ensure security.

[1236] Data analysis phase

[1237] The server stores the received information in a database. The information stored in the database is analyzed using Python's Pandas and Scikit-learn libraries. This analysis diagnoses the user's behavioral patterns and psychological state. The emotion engine analyzes facial and voice data to identify the user's emotional state in real time. This emotion recognition technology infers emotions such as joy, anger, and sadness from the user's facial expressions captured by the camera and tone of voice picked up from the microphone.

[1238] Sound Generation Phase

[1239] Based on the analysis results, the server uses music generation algorithms such as MusicVAE to generate optimal musical characteristics. Specific parameters (tempo, frequency, melody, timbre, etc.) are set and the music is customized based on the emotional state obtained from the emotion engine. The generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library.

[1240] Sound Distribution Phase

[1241] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, ensuring audio is sent to the terminal without delay.

[1242] Music Playback Phase

[1243] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it can gradually increase the volume to wake up the user, encouraging them to wake up naturally, while also providing music with musical characteristics that correspond to the user's emotional state, creating a pleasant music experience.

[1244] Feedback gathering phase

[1245] After experiencing the sound, users can enter feedback within the app about the effect, including ratings of the quality of awakening, relaxation, and emotional changes, and the device then sends this feedback to the server.

[1246] Feedback Analysis Phase

[1247] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and re-evaluate their performance. The updated models are then used to further optimize music generation and emotion recognition for future iterations.

[1248] Specific examples

[1249] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If this user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, making it possible to provide an even more accurate service.

[1250] This invention utilizes user information to provide a personalized music experience and combines emotion recognition technology to improve the user's quality of life.

[1251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1252] Step 1:

[1253] Users install the smartphone app and enter basic information such as age, gender, wake-up time, bedtime, and preferred music genre on the initial setup screen. The information entered at this time is saved in the app as text data.

[1254] Step 2:

[1255] Users connect their health devices, such as smartwatches, to the app, which then collects detailed lifestyle data, such as heart rate and sleep patterns, in real time. The collected data is then stored in the app as numerical data.

[1256] Step 3:

[1257] Users use their smartphone's camera and microphone to collect facial and voice data. The facial data is saved as an image file, and the voice data is saved as an audio file. These data are used to analyze the user's emotional state in real time.

[1258] Step 4:

[1259] The device sends the basic information entered by the user, the acquired lifestyle data, facial expression data, and voice data to the server using a secure protocol (e.g., HTTPS). The data is encrypted and stored on the server as encrypted data after transmission.

[1260] Step 5:

[1261] The server stores the received information in a database. The stored data is classified by user ID and saved in the following data formats: text, numeric, image, and audio.

[1262] Step 6:

[1263] The server uses Python's Pandas and Scikit-learn libraries to analyze the information in the database. The analysis diagnoses the user's behavioral patterns and psychological state. Specifically, it analyzes sleep quality and heart rate fluctuations from lifestyle data to identify behavioral patterns. In addition, an emotion engine analyzes facial expression data and voice data to identify the user's emotional state. The analysis results are output as text data representing behavioral patterns and emotional states.

[1264] Step 7:

[1265] The server then uses music generation algorithms such as MusicVAE to generate optimal musical characteristics based on the analysis results. Specific parameters (tempo, frequency, melody, timbre, etc.) are set, and the music is customized based on the emotional state obtained from the emotion engine. The generated music data is output in MIDI file format.

[1266] Step 8:

[1267] The server converts the generated music data (MIDI file) into an audio file (mp3 format) using a voice synthesis library, and the converted audio file is stored on the server in preparation for distribution.

[1268] Step 9:

[1269] The server prepares to stream audio files at specific times based on the user's schedule information. Streaming protocols such as RTP and RTSP are used for streaming, and audio data is sent to the terminal in real time. The transmitted audio data is then received by the terminal as a real-time streaming file.

[1270] Step 10:

[1271] The device receives the audio data sent from the server and plays it according to the user's schedule. For example, it gradually increases the volume to wake up the user naturally, and provides music with musical characteristics that correspond to the user's emotional state. The played audio is output as an MP3 audio file.

[1272] Step 11:

[1273] After listening to the music, users can enter feedback about the effects of the music in the app. This feedback includes an evaluation of the quality of awakening, relaxation, and emotional changes. The input feedback data is stored in the app as numerical and text data.

[1274] Step 12:

[1275] The device sends the collected feedback data to the server. The feedback data is encrypted and sent using a secure protocol (e.g., HTTPS). After sending, the data is stored on the server as encrypted data.

[1276] Step 13:

[1277] The server stores the new feedback data in a database and updates the machine learning and emotion recognition models. It uses the SciPy library to adapt the new data to the existing models and reevaluate their performance. The updated models are used for music generation and emotion recognition from the next time onwards. The updated model information is saved as text data on the server.

[1278] (Application example 2)

[1279] 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."

[1280] Existing music distribution services have difficulty providing a personalized music experience based on the user's emotions and behavioral patterns. Therefore, there is a need for a system that can provide music optimized for the user's psychological state and emotions in real time. Furthermore, a mechanism is also needed that effectively utilizes user feedback to continuously improve the quality of the music experience.

[1281] 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.

[1282] In this invention, the server includes means for collecting user information, means for analyzing the collected information and diagnosing the user's behavioral patterns and psychological state, means for generating optimal music characteristics based on the analysis results, means for generating music characteristics using an emotion engine that recognizes the user's emotional state in real time, means for delivering the generated music characteristics to the user's device, means for collecting user feedback and updating the machine learning model, and means for using a streaming protocol to deliver the generated music in real time, thereby enabling the provision of a personalized music experience based on the user's emotions and behavioral patterns.

[1283] "Means of collecting information from users" refers to functions that obtain data such as the user's age, gender, sleep patterns, preferred music genres, heart rate, facial expressions, and voice via smartphones or wearable devices.

[1284] "Means of analyzing collected information and diagnosing the user's behavioral patterns and psychological state" refers to a function that analyzes changes in the user's daily rhythm and emotions based on collected data, and identifies behavioral patterns and psychological state.

[1285] The "means for generating optimal musical characteristics" is a function that determines musical elements such as tempo, frequency, melody, and tone based on analyzed user data, and creates music that is optimal for the user.

[1286] The "means for delivering the generated music characteristics to the user's terminal" is a function for transmitting the generated music data to the user's terminal in streaming or download format.

[1287] "Musical characteristic generation means using an emotion engine that recognizes the user's emotional state in real time" is a function that grasps the user's emotions in real time through facial expression recognition and voice analysis, and generates musical characteristics that are adapted to those emotions.

[1288] "Means for collecting user feedback and updating the machine learning model" refers to a function that collects feedback on users' music experiences and updates the machine learning model based on that feedback, adapting it to the latest data.

[1289] "Means for using a streaming protocol to deliver the generated music in real time" refers to a function that uses a streaming protocol such as RTP or RTSP to deliver the generated music to users without delay.

[1290] This invention is a system that provides an optimal music experience based on the user's emotions and behavioral patterns. Specifically, it includes a series of processes for collecting and analyzing user information, and generating and distributing music based on the analysis results.

[1291] The system collects various data using the user's smartphone and wearable devices such as a smartwatch. Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. By linking the app to a smartwatch, the system also collects heart rate and sleep patterns. Furthermore, the system uses the smartphone's camera and microphone to collect facial expressions and voice data.

[1292] This data is sent to a server using a secure protocol such as HTTPS. The server then analyzes the data using Python libraries such as Pandas and Scikit-learn. This analysis identifies the user's behavioral patterns and psychological state. Furthermore, an emotion engine is used to analyze the user's emotional state in real time.

[1293] Based on the analysis results, a music generation algorithm (e.g., MusicVAE) is used to generate music that is optimal for the user. This generated music data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a speech synthesis library. The music is then delivered to the user's device without delay using a streaming protocol such as RTP or RTSP.

[1294] After playing the provided music, users enter feedback within the app. This feedback data is also sent to the server and used to update the machine learning model. Using the SciPy library, the new data is adapted to the existing model to further optimize music generation and emotion recognition in future trials.

[1295] For example, suppose a user has a lifestyle pattern of waking up at 7am every morning and going to bed at 10pm. If the user selects classical music as their preferred music for relaxation, the server will analyze their past sleep data and emotional data obtained from the emotion engine, and generate relaxing sounds based on classical music starting 15 minutes (6:45am) before waking up, and deliver them in real time. If the feedback is that the music has a relaxing effect, this data will be reflected in future music generation and emotional analysis, providing even more accurate services.

[1296] An example of a prompt sentence to input to the generative AI model is as follows:

[1297] "Analyze facial expressions and voice data to indicate that the user is stressed. Explain the process of generating and delivering relaxing music to the user."

[1298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1299] Step 1:

[1300] Data Collection Phase

[1301] Users install a smartphone app and enter basic information such as age, gender, preferred music genre, wake-up time, and bedtime. Furthermore, by connecting a smartwatch, heart rate and sleep patterns can also be obtained. The smartphone's camera and microphone are also used to collect facial expressions and voice data. The input is the user's profile information and biometric data, and the collected data is output.

[1302] Step 2:

[1303] Data transmission phase

[1304] The terminal sends the collected data to the server using the HTTPS protocol. Specifically, the user data is converted into JSON format, encrypted, and then sent to the server. The input is the collected user data, and the output is the data securely sent to the server.

[1305] Step 3:

[1306] Data analysis phase

[1307] The server stores the received information in a database and analyzes it using Pandas and Scikit-learn. The analysis diagnoses the user's behavioral patterns and psychological state. In addition, an emotion engine analyzes facial expressions and voice data to identify the user's emotional state in real time. The input is the user data sent to the server, and the output is the analysis results (behavioral patterns, psychological state, and emotional state).

[1308] Step 4:

[1309] Sound Generation Phase

[1310] The server uses a music generation algorithm such as MusicVAE to generate optimized sounds based on input parameters such as tempo, frequency, melody, and timbre. The generated data (e.g., MIDI file) is converted into an audio file (e.g., mp3) using a voice synthesis library. The input is the analysis result, and the output is the generated music file.

[1311] Step 5:

[1312] Sound Distribution Phase

[1313] The server uses streaming protocols such as RTP and RTSP to deliver music files generated in real time to users' devices. The input is the music file, and the output is real-time streaming.

[1314] Step 6:

[1315] Music Playback Phase

[1316] The device plays the received music data. Specifically, it plays the received audio file using a media player. The input is the distributed music file, and the output is the music playback.

[1317] Step 7:

[1318] Feedback gathering and learning phase

[1319] After experiencing the sound, the user inputs feedback within the app. The device sends this feedback to the server. The input is the user feedback, and the output is the feedback data sent to the server.

[1320] Step 8:

[1321] Feedback Analysis Phase

[1322] The server stores the new feedback data in a database and updates the machine learning model and the emotion engine model using the SciPy library. The input is the feedback data and the output is the updated machine learning model.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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."

[1332] 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.

[1333] 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).

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] The following is further disclosed regarding the above embodiment.

[1345] (Claim 1)

[1346] a means for collecting information from users;

[1347] A means of analyzing the collected information and diagnosing the user's behavioral patterns and psychological state;

[1348] means for generating optimal musical characteristics based on the analysis results;

[1349] means for delivering the generated musical characteristics to a user's terminal;

[1350] a means of collecting user feedback and updating the machine learning model; and

[1351] A system including:

[1352] (Claim 2)

[1353] 10. The system according to claim 1, further comprising means for inputting the user's sleep patterns and preferred music genres at the user's terminal.

[1354] (Claim 3)

[1355] 2. The system according to claim 1, further comprising means for storing user information in a database and performing analysis based on the data.

[1356] "Example 1"

[1357] (Claim 1)

[1358] a means for collecting personal information from users;

[1359] A means for integrating the collected personal information and health data and transmitting the integrated data to a server;

[1360] A means for storing the information collected on the server in a database and performing data analysis;

[1361] means for generating optimal musical characteristics based on the analysis results;

[1362] means for converting the generated musical characteristics into an audio file and delivering it to a user's device in real time;

[1363] a means of collecting user feedback and updating the machine learning model; and

[1364] A system including:

[1365] (Claim 2)

[1366] 10. The system according to claim 1, further comprising means for inputting the user's sleep patterns and preferred music genres at the user's terminal.

[1367] (Claim 3)

[1368] The system of claim 1, further comprising means for storing user information in a database and performing analysis based on the data using the Pandas library and the Scikit-learn library.

[1369] "Application Example 1"

[1370] (Claim 1)

[1371] a means for collecting information from users;

[1372] A means of analyzing the collected information and diagnosing the user's behavioral patterns and psychological state;

[1373] means for generating optimal musical characteristics based on the analysis results;

[1374] means for converting the generated musical characteristics into an audio file and delivering the audio file to a user's terminal;

[1375] a means of collecting user feedback and updating the machine learning model; and

[1376] A system including:

[1377] (Claim 2)

[1378] 2. The system according to claim 1, further comprising means for inputting lifestyle data such as the user's sleep patterns and heart rate, and the user's preferred music genre, in the user's terminal.

[1379] (Claim 3)

[1380] 2. The system according to claim 1, further comprising: means for storing user information in a database and performing analysis based on the data; and means for delivering an audio file in real time based on the analysis results.

[1381] "Example 2: Combining Emotion Engines"

[1382] (Claim 1)

[1383] a means for collecting information from users;

[1384] A means for encrypting the collected information and transmitting it to a server;

[1385] A means of analyzing the collected information and diagnosing the user's behavioral patterns and psychological state;

[1386] A means for generating optimal musical characteristics using a generative AI model based on the analysis results;

[1387] means for converting the generated musical characteristics into an audio file;

[1388] means for streaming the generated audio file to a user's terminal;

[1389] a means for collecting user feedback and updating the machine learning model and emotion recognition model;

[1390] A system including:

[1391] (Claim 2)

[1392] 2. The system according to claim 1, further comprising means for inputting the user's sleep pattern and preferred music genre, and means for acquiring the user's facial expression and voice, in the user's terminal.

[1393] (Claim 3)

[1394] 2. The system according to claim 1, further comprising means for storing user information in a database and performing analysis based on the data.

[1395] "Application example 2 when combining emotion engines"

[1396] (Claim 1)

[1397] a means for collecting information from users;

[1398] A means of analyzing the collected information and diagnosing the user's behavioral patterns and psychological state;

[1399] means for generating optimal musical characteristics based on the analysis results;

[1400] means for delivering the generated musical characteristics to a user's terminal;

[1401] a music characteristic generating means using an emotion engine that recognizes the user's emotional state in real time;

[1402] a means of collecting user feedback and updating the machine learning model; and

[1403] means for using a streaming protocol to deliver the generated music in real time;

[1404] A system including:

[1405] (Claim 2)

[1406] 10. The system according to claim 1, further comprising means for inputting the user's sleep patterns and preferred music genres at the user's terminal.

[1407] (Claim 3)

[1408] 2. The system according to claim 1, further comprising means for storing user information in a database and performing analysis based on the data. [Explanation of symbols]

[1409] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting information from users; A means of analyzing the collected information and diagnosing the user's behavioral patterns and psychological state; means for generating optimal musical characteristics based on the analysis results; means for delivering the generated musical characteristics to a user's terminal; a means of collecting user feedback and updating the machine learning model; and A system including:

2. 2. The system according to claim 1, further comprising means for inputting the user's sleep patterns and preferred music genres at the user's terminal.

3. 2. The system according to claim 1, further comprising means for storing user information in a database and performing analysis based on the data.

Images