Ai-based music classification system with tiered rating mechanism

Abstract

The present specification describes a method for a terminal to provide a music classification service through an artificial intelligence model, comprising: receiving input of a specific grade and a number of music from a user; transmitting the specific grade and number of music data to an operating server of the music classification service; and receiving music data having the specific grade based on the number of music from the operating server, wherein the operating server may request the generation of the music data from an artificial intelligence module for music generation and receive the music data classified by grade through an artificial intelligence module for music grade classification.

Description

Technology Field

[0001] This specification relates to a system and method for collecting music data and providing labeling considering commercial value, classification model training, and real-time rating classification services. Background Technology

[0003] To date, the analysis and classification of music data have primarily relied on manual methods and basic feature-based approaches. Existing methods involve humans manually labeling music data or performing classification based on the characteristics of simple acoustic signals. This approach struggles to reflect the diversity and complexity of music data and faces limitations in terms of analysis speed and scalability. In particular, the difficulty of efficient management and precise analysis in large-scale data environments results in limited potential for industrial application.

[0004] Existing music analysis technologies primarily focus on measuring low-dimensional characteristics of acoustic signals, such as physical elements like pitch, volume, and tempo. While these characteristics are useful for understanding the basic structure of music, they have limitations in evaluating its artistic quality or commercial value. High-dimensional and abstract characteristics, such as genre color, harmonic structure, and emotional impact, play a significant role in music, yet existing technologies are often lacking in their ability to quantitatively evaluate these elements.

[0005] Therefore, a new technological approach is required to analyze music data more sophisticatedly and simultaneously consider both artistic value and commercial utility. To this end, a system is needed that combines high-dimensional embedding technology with deep neural network models to analyze music data from multiple perspectives. The problem to be solved

[0007] The purpose of this specification is to provide a system and method for collecting music data and providing labeling considering commercial value, classification model training, and real-time rating classification services.

[0008] The technical problems that this specification aims to solve are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this specification belongs from the detailed description of the specification below. means of solving the problem

[0010] One aspect of the present specification is a method for a terminal to provide a music classification service through an artificial intelligence model, comprising: receiving input of a specific grade and a number of music from a user; transmitting the specific grade and number of music data to an operating server of the music classification service; and receiving music data having the specific grade based on the number of music from the operating server, wherein the operating server may request the generation of the music data from an artificial intelligence module for music generation and receive the music data classified by grade through an artificial intelligence module for music grade classification.

[0011] In addition, the artificial intelligence module for generating the music can generate the music data based on a request received from the operating server for the generation of the music data, and transmit the generated music data to the artificial intelligence module for classifying the music grade.

[0012] In addition, the artificial intelligence module for classifying the music grade can analyze the music data received from the artificial intelligence module for generating the music and classify it into one of grades S, A, B, or C based on commercial value.

[0013] In addition, the operating server may request the artificial intelligence module for music generation to terminate the generation of the music data based on the fact that the number of music data classified by the specific grade is equal to the number of music.

[0014] In addition, the artificial intelligence module for generating the music can repeatedly generate the music data and transmit it to the artificial intelligence module for classifying the music until it receives a request to terminate the generation of the music data.

[0015] Another aspect of the present specification is a method for an operating server to provide a music classification service through an artificial intelligence model, comprising: receiving information regarding a specific grade and the number of music from a terminal; requesting the creation of music data from an artificial intelligence module for music creation in response to the information regarding the specific grade and the number of music; wherein the artificial intelligence module for music creation creates the music data based on the request for music data creation and transmits it to an artificial intelligence module for grade classification; receiving music data classified by grade from the artificial intelligence module for grade classification; and transmitting music data having the specific grade to the terminal based on the fact that the number of music data classified by the specific grade is equal to the number of music.

[0016] Additionally, it may further include the step of requesting the artificial intelligence module for music generation to terminate the generation of the music data based on the fact that the number of music data classified into the specific grade is equal to the number of music.

[0017] Additionally, the method further includes the step of calculating a cost based on the specific grade or the number of music pieces; and the step of transmitting music data having the specific grade to the terminal may be performed when payment of the cost is completed. Effects of the invention

[0019] According to the embodiments of the present specification, a system and method can be provided that collect music data and provide labeling considering commercial value, classification model training, and real-time rating classification services.

[0020] The effects obtainable in this specification are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which this specification belongs from the description below. Brief explanation of the drawing

[0022] FIG. 1 is a block diagram for illustrating an electronic device related to the present specification. FIG. 2 is a block diagram of an AI device according to one embodiment of the present specification. FIG. 3 illustrates an AI-based music classification system to which the present specification may be applied. FIG. 4 illustrates a method of training a music classification AI model (220) to which the present specification can be applied. FIG. 5 is an example of an AI-based music classification service to which the present specification may be applied. The accompanying drawings, included as part of the detailed description to aid in understanding the present specification, provide embodiments of the present specification and explain the technical features of the present specification together with the detailed description. Specific details for implementing the invention

[0023] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols are assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not have distinct meanings or roles in themselves. Furthermore, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the concept and technical scope of this specification.

[0024] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0025] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0026] A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0027] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0028] FIG. 1 is a block diagram for illustrating an electronic device related to the present specification.

[0029] The above electronic device (100) may include a wireless communication unit (110), an input unit (120), a sensing unit (140), an output unit (150), an interface unit (160), a memory (170), a control unit (180), and a power supply unit (190), etc. Since the components illustrated in FIG. 1 are not essential for implementing the electronic device, the electronic device described herein may have more or fewer components than those listed above.

[0030] More specifically, among the above components, the wireless communication unit (110) may include one or more modules that enable wireless communication between the electronic device (100) and a wireless communication system, between the electronic device (100) and another electronic device (100), or between the electronic device (100) and an external server. Additionally, the wireless communication unit (110) may include one or more modules that connect the electronic device (100) to one or more networks.

[0031] This wireless communication unit (110) may include at least one of a broadcast receiving module (111), a mobile communication module (112), a wireless internet module (113), a short-range communication module (114), and a location information module (115).

[0032] The input unit (120) may include a camera (121) or video input unit for inputting a video signal, a microphone (122) or audio input unit for inputting an audio signal, and a user input unit (123, e.g., a touch key, a mechanical key, etc.) for receiving information from a user. Voice data or image data collected from the input unit (120) may be analyzed and processed into a control command by the user.

[0033] The sensing unit (140) may include one or more sensors for sensing at least one of information within the electronic device, information about the surrounding environment surrounding the electronic device, and user information. For example, the sensing unit (140) may include at least one of a proximity sensor (141), an illumination sensor (142), a touch sensor, an acceleration sensor, a magnetic sensor, a gravity sensor (G-sensor), a gyroscope sensor, a motion sensor, an RGB sensor, an infrared sensor (IR sensor: infrared sensor), a fingerprint sensor (finger scan sensor), an ultrasonic sensor, an optical sensor (e.g., see camera (121)), a microphone (see 122), a battery gauge, an environmental sensor (e.g., a barometer, a hygrometer, a thermometer, a radiation detection sensor, a heat detection sensor, a gas detection sensor, etc.), and a chemical sensor (e.g., an electronic nose, a healthcare sensor, a biometric sensor, etc.). Meanwhile, the electronic device disclosed in this specification can utilize information sensed by at least two of these sensors in combination.

[0034] The output unit (150) is intended to generate output related to sight, hearing, or touch, and may include at least one of a display unit (151), an audio output unit (152), a haptic module (153), and an optical output unit (154). The display unit (151) may form a layered structure with a touch sensor or be formed integrally to implement a touch screen. Such a touch screen functions as a user input unit (123) that provides an input interface between the electronic device (100) and the user, and at the same time can provide an output interface between the electronic device (100) and the user.

[0035] The interface section (160) serves as a passage for various types of external devices connected to the electronic device (100). This interface section (160) may include at least one of a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, a port for connecting a device equipped with an identification module, an audio I / O (Input / Output) port, a video I / O (Input / Output) port, and an earphone port. In response to an external device being connected to the interface section (160), the electronic device (100) can perform appropriate control related to the connected external device.

[0036] Additionally, the memory (170) stores data that supports various functions of the electronic device (100). The memory (170) can store a number of application programs (or applications) running on the electronic device (100), data for the operation of the electronic device (100), and commands. At least some of these application programs may be downloaded from an external server via wireless communication. Also, at least some of these application programs may exist on the electronic device (100) from the time of shipment for the basic functions of the electronic device (100) (e.g., phone incoming and outgoing functions, message receiving and outgoing functions). Meanwhile, the application programs may be stored in the memory (170), installed on the electronic device (100), and driven by the control unit (180) to perform the operation (or function) of the electronic device.

[0037] In addition to operations related to the application program, the control unit (180) typically controls the overall operation of the electronic device (100). The control unit (180) can provide or process appropriate information or functions to the user by processing signals, data, information, etc. that are input or output through the components described above, or by running an application program stored in memory (170).

[0038] Additionally, the control unit (180) can control at least some of the components examined together with FIG. 1 in order to run an application program stored in memory (170). Furthermore, the control unit (180) can operate at least two or more of the components included in the electronic device (100) in combination with each other to run the application program.

[0039] The power supply unit (190) receives external power and internal power under the control of the control unit (180) and supplies power to each component included in the electronic device (100). This power supply unit (190) includes a battery, and the battery may be a built-in battery or a replaceable battery.

[0040] At least some of the above components may operate in cooperation with each other to implement the operation, control, or control method of an electronic device according to various embodiments described below. Additionally, the operation, control, or control method of the electronic device may be implemented on the electronic device by running at least one application program stored in the memory (170).

[0041] In this specification, the electronic device (100) may be collectively referred to as a server, and the server may include a cloud server. Additionally, the terminal may include all or part of the configuration of the electronic device (100), and may include a tablet PC.

[0042] FIG. 2 is a block diagram of an AI device according to one embodiment of the present specification.

[0043] The AI ​​device (20) may include an electronic device including an AI module capable of performing AI processing, or a terminal including the AI ​​module. Additionally, the AI ​​device (20) may be configured to be included as at least a part of the configuration of the electronic device (100) shown in FIG. 1 to perform at least a part of the AI ​​processing together.

[0044] The above AI device (20) may include an AI processor (21), memory (25) and / or a communication unit (27).

[0045] The above AI device (20) is a computing device capable of learning a neural network and can be implemented as various electronic devices such as a terminal, desktop PC, laptop PC, tablet PC, etc.

[0046] The AI ​​processor (21) can train a neural network using a program stored in memory (25). In particular, the AI ​​processor (21) may include a music generation AI model capable of generating music data using complex deep learning models such as GAN, RNN, and Transformer, and / or a music classification AI model capable of analyzing large-scale music data, performing feature vectorization, and classifying grades (e.g., S, A, B, C) in real time.

[0047] Meanwhile, the AI ​​processor (21) that performs the functions described above may be a general-purpose processor (e.g., CPU), but may be an AI-dedicated processor for artificial intelligence learning (e.g., GPU, graphics processing unit).

[0048] The memory (25) can store various programs and data required for the operation of the AI ​​device (20). The memory (25) can be implemented as non-volatile memory, volatile memory, flash memory, hard disk drive (HDD), or solid-state drive (SDD). The memory (25) is accessed by the AI ​​processor (21), and the AI ​​processor (21) can perform reading / writing / modification / deletion / updating of data. Additionally, the memory (25) can store a neural network model (e.g., a deep learning model) generated through a learning algorithm for data classification / recognition according to one embodiment of the present specification.

[0049] Meanwhile, the AI ​​processor (21) may include a data learning unit that learns a neural network for data classification / recognition. For example, the data learning unit may learn a deep learning model by acquiring training data to be used for learning and applying the acquired training data to a deep learning model.

[0050] The communication unit (27) can transmit the AI ​​processing results by the AI ​​processor (21) to an external electronic device.

[0051] Here, external electronic devices may include other terminals.

[0052] Meanwhile, although the AI ​​device (20) illustrated in FIG. 2 is described by functionally separating it into an AI processor (21), memory (25), and communication unit (27), the aforementioned components may be integrated into a single module and referred to as an AI module or an artificial intelligence (AI) model.

[0053] FIG. 3 illustrates an AI-based music classification system to which the present specification may be applied.

[0054] Referring to FIG. 3, the AI-based music classification system (200) includes an operating server (not shown), It may include a music classification AI model (220) and a music generation AI model (230), and may provide a real-time music rating classification service to the user through the user terminal (210). Alternatively, the music generation AI model (230) may be implemented as a separate service not included in the AI-based music classification system (200). For example, the AI-based music classification system (200) may be configured as a cloud server.

[0055] The terminal (210) serves as an interface through which a user interacts with the system. It can be implemented as a device such as a smartphone, tablet, or computer, and receives user input (e.g., requests for ratings and music counts), transmits it to the system (200), receives a result (e.g., a list of rated music) from the system (200), and outputs it to the user. The user can receive a music rating classification service from the system (200) via the web through the terminal (210), or receive a music rating classification service from the system (200) through a separate application installed on the terminal (210).

[0056] The music classification AI model (220) is an artificial intelligence module that analyzes and classifies music data received through the music generation AI model (230). This module processes acoustic data in multiple stages and utilizes spectrum analysis techniques such as FFT (Fast Fourier Transform) and Mel spectrogram, as well as deep neural networks (DNN), to identify low-dimensional features (pitch, volume, etc.) and high-dimensional features (genre, commercial value, etc.) of the music. For example, the classified music data may include grades (S, A, B, C) and related probability values.

[0057] The music generation AI model (230) is an AI module that automatically generates new music data by utilizing various artificial intelligence algorithms. For example, this module can use various music generation models such as GAN (Generative Adversarial Network), RNN (Recurrent Neural Network), and Transformer-based models. GAN is a method of generating new music data through a generator and a discriminator, and is suitable for creating songs with original and creative styles. RNN is advantageous for generating music sequences where time order is important and can learn melody continuity and rhythm patterns well. Transformer-based models can generate music with more complex structures by learning large-scale data and have strengths in understanding long-term musical patterns.

[0058] The music generation AI model (230) can be initialized to generate music of a specific genre or style that meets user requirements. The generated music can be adjusted according to user-specified conditions, and specific musical characteristics (e.g., tempo, key, mood, etc.) can be controlled during the generation process. Additionally, the generated music data is passed to the music classification AI model (220) to evaluate its commercial value through grades (S, A, B, C), and the classified result can be provided to the user.

[0059] Through this, the AI-based music classification system (200) can provide new music data in real time and support various industrial applications.

[0060] FIG. 4 illustrates a method of training a music classification AI model (220) to which the present specification can be applied.

[0061] Referring to FIG. 4, the AI-based music classification system (200) can use music data generated through the music generation AI model (230) as training data to train the music classification AI model (220) to classify the commercial value of the music data into grades.

[0062] The AI-based music classification system (200) collects and preprocesses music data generated through a music generation AI model (230) (S4010). For example, music data can be collected without restriction through the music generation AI model (230). The music generation AI can automatically generate new music data by utilizing various algorithms such as GAN (Generative Adversarial Network), RNN (Recurrent Neural Network), and Transformer-based models. These models can generate customized music data that reflects specific genres, styles, tempos, moods, etc., and through this, even specific types of data that are difficult to collect in the past can be secured. Data collection using the music generation AI model (230) has the characteristic of being able to continuously secure large-scale data sets because there are no physical or temporal constraints.

[0063] The collected music data can be managed to maintain uniform quality through a preprocessing process. For example, the quality of the data can be improved through operations such as noise removal, sound quality correction, and volume normalization, and the music signal can be converted into spectrum data through Fast Fourier Transform (FFT), Mel-Spectrogram, and Constant-Q Transform (CQT) transformations. By generating standardized data suitable for learning through this preprocessing process, the learning accuracy of the music classification AI model (220) can be improved.

[0064] The AI-based music classification system (200) receives the labeling of music data based on commercial value (S4020). The collected music data can be labeled based on commercial value. For example, it can be classified into grades S, A, B, and C according to the license cost of each song. This commercial value can be used as an indicator to evaluate how high the economic potential of the music is in the actual industry.

[0065] Grade classification may be based on the industry group in which the music data can be used. For example, music with high potential for use in various commercial applications such as advertising, movies, and games, and high licensing costs, may be labeled as Grade S, while music with low potential for use may be classified as Grade C. To classify these industry groups, a music classification AI model (220) may be pre-trained by clustering music data used in a specific industry group, and an AI-based music classification system (200) may first classify the industry group of the music data through the music classification AI model (220) during the aforementioned preprocessing process.

[0066] Furthermore, the labeling process can be performed by experts with over 20 years of experience in advertising music production, allowing labeling standards to be established based on practical experience and actual market data. For example, the labeling process can be carried out by a single expert to ensure accuracy. This incorporates the expert's subjective judgment criteria and over 20 years of experience in advertising music production, providing reliable labeling results.

[0067] Labeled data is used as a primary input for training an AI model and can play a key role in training a music classification AI model (220) that can reflect not only simple acoustic features but also commercial value. The music classification AI model (220) can be trained to precisely evaluate the economic value of music.

[0068] The AI-based music classification system (200) extracts and vectorizes features of labeled music data (S4030). For example, the labeled music data may undergo a detailed feature extraction process for the training of a music classification AI model (220). This process can analyze the music data in detail, including low-dimensional features (e.g., pitch, volume, tempo, etc.) and high-dimensional features (e.g., genre color, harmonic structure, emotional impact, etc.). These features are learned step-by-step through a deep neural network (DNN) structure, and various features extracted at each step can be converted into high-dimensional vectors.

[0069] For example, feature vectors can be converted into 1024 dimensions and stored in a vector database. This vectorization process can represent music data in a mathematical space, providing a basis for quickly searching for similar music data or utilizing it for clustering tasks. Additionally, high-dimensional vector representation ensures robustness against data deformation or noise, and can help the music classification AI model (220) achieve more stable and generalized performance.

[0070] An AI-based music classification system (200) trains a music classification AI model (220) using labeled music data (S4040). The labeled data can be separated into training data (e.g., 80%) and validation data (e.g., 20%) and used to train the music classification AI model (220). The music classification AI model (220) is based on a deep neural network (DNN) structure and can perform gradual learning from low-dimensional characteristics to high-dimensional characteristics. In this process, input data such as FFT, Mel spectrogram, and CQT are utilized, and high-dimensional features such as genre characteristics, harmonic structure, and emotional impact can be learned in the intermediate layer. In particular, since the S, A, B, and C grades included in the labeled data are based on commercial value (e.g., license fees), the music classification AI model (220) can have the ability to evaluate not only the artistic characteristics of the music but also its commercial potential.

[0071] In addition, during the learning process, the K-fold cross-validation technique can be applied to minimize data bias and maximize the generalization performance of the music classification AI model (220). Furthermore, the performance of the music classification AI model (220) can be continuously improved by optimizing hyperparameters such as the learning rate, network depth, and normalization parameters.

[0072] In addition, by further utilizing various music data provided by the music generation AI model (230), the music classification AI model (220) can be enabled to maintain high classification accuracy even for new types of music. The trained music classification AI model (220) can be used for real-time rating classification and commercial value prediction.

[0073] FIG. 5 is an example of an AI-based music classification service to which the present specification may be applied.

[0074] Referring to FIG. 5, the user can receive an AI-based music classification service from an AI-based music classification system (200) through a terminal (210). To this end, the music classification AI model (220) may be a model that has completed the aforementioned training.

[0075] S5010: Enter grade and music count

[0076] The user inputs the desired music grade (e.g., S, A, B, C) and the required number of music through the terminal (210). The information entered by the user is transmitted to an AI-based music classification system (200), and in a subsequent step, suitable music data can be generated and filtered based on this information. During this process, the terminal (210) collects input through a user interface (UI) and can set initial data to provide customized services according to the entered grade and number of music.

[0077] For example, information input from the terminal (210) can be transmitted to an operating server to trigger the main operation of the system (200). Here, the input "grade" refers to the criteria for music data classified according to commercial value, and the "number of songs" may refer to the number of songs of the corresponding grade to be provided to the user. Through this, the AI-based music classification system (200) can efficiently prepare data that meets user requirements.

[0078] S5020: Transmit grade and music count information

[0079] The grade and music count information entered from the terminal (210) is transmitted to the operation server. The operation server can initiate a process to collect and process music data that meets user requirements. For example, the operation server can transmit the received information to a music classification AI model (220) and / or a music generation AI model (230) to prepare for generating and classifying appropriate data. More specifically, the operation server performs a central role in controlling the data flow between each module within the system and can distribute necessary tasks according to user requests.

[0080] S5030~S5050: Music data generation request and collection

[0081] The operating server requests the music generation AI model (230) to generate music data (S5030). The music generation AI model (230) begins to generate new music data (S5040). For example, the music generation AI model (230) can automatically generate new music by utilizing various models such as GAN, RNN, and Transformer. In addition, it can reflect specific conditions requested by the user (e.g., genre, style, tempo, etc.). To do this, the user can additionally input specific conditions through the terminal (210).

[0082] When music data is generated, the music generation AI model (230) transmits it to the music classification AI model (220) (S5050). For example, the generated music data undergoes a preprocessing process to ensure uniform quality, and is converted into an FFT, Mel spectrogram, etc., so that it can be prepared for classification by the music classification AI model (220) in the future.

[0083] If necessary, the music generation AI model (230) can also predict the industry group in which the generated music data will be used, and this can be transmitted to the music classification AI model (220) along with the music data and used to classify grades in the music classification AI model (220).

[0084] S5060: Classification

[0085] The music classification AI model (220) performs a grade classification task on the received music data (S5060). For example, the music classification AI model (220) can analyze the input music data and classify it into grades S, A, B, and C. The music data with completed grade classification can be transmitted to the operation server. The operation server classifies the music data by grade, reviews it once again to see if it meets user requirements, and completes preparations to provide it to the user. The music classification AI model (220) can perform a classification task based on learned commercial value criteria.

[0086] S5070~S5090: Verification and provision of music data for the requested grade

[0087] After receiving music data classified by grade from the music classification AI model (220) (S5070), the operation server checks whether it matches the number of music data of the grade requested by the user (S5080). In this process, the operation server selects only music data that meets the conditions entered by the user, and can repeat the tasks of music data generation by the music generation AI model (230), grade classification by the music classification AI model (220), and receiving the graded music data until the number of music data of the grade requested by the user is reached. Afterwards, when the number of music data of the grade requested by the user is secured, the operation server requests the music generation AI model (230) to stop generating music data (S5090). Through this, the user can receive only the music data of the grade exactly desired, and unnecessary resource waste of the music generation AI model (230) and the music classification AI model (220) can be minimized.

[0088] When all processes are completed, the operating server provides music data of the requested grade to the terminal (210) (S5100). The user terminal (210) outputs the received music data and can provide an environment for the user to display or play a list of music by grade. Through this, the user can use a high-quality music classification service in real time and can also process additional requests as needed.

[0089] The operation server can calculate costs based on the grade and / or quantity of music requested by the user and charge the user. For example, if a user requests S or A grade music with high commercial value, or requests a large quantity of music data, the corresponding cost can be automatically calculated and charged. To this end, the operation server manages payment information for each user and can guarantee the stability and profitability of service provision by providing music data only after payment is completed.

[0090] In addition, the operations server can perform user authentication to support membership plans. For example, the operations server can authenticate user accounts and check membership status to apply benefits available based on specific membership tiers (e.g., providing a fixed quantity of free music, music discounts for specific tiers, etc.). This enables the provision of personalized services and allows for the expectation of continuous customer retention and additional revenue generation through the membership program.

[0091] Based on the aforementioned operation, the AI-based music classification system can automatically collect various types of music data without limitation through music generation AI and analyze it using music classification AI to classify grades in real time based on commercial value. In particular, by assigning grades of S, A, B, and C based on commercial value (license fees), it is possible to provide customized music to users, and technical effects can be achieved to immediately provide high-quality music data suitable for various industrial applications such as advertising, movies, and games.

[0092] Furthermore, the AI-based music classification system maximizes operational efficiency by automating the entire process of music data collection, preprocessing, labeling, classification, and result delivery. By utilizing music-generating AI, it is possible to generate data that was previously difficult to collect, thereby enabling the continuous acquisition of large-scale datasets. Additionally, high-accuracy classification is possible through high-dimensional vector analysis that incorporates diverse musical characteristics. This automated system reduces data processing time and costs, and facilitates the establishment of a standardized music evaluation framework within the industry.

[0093] In particular, AI-based music classification systems can significantly improve the efficiency of music production and utilization by providing high-quality music data that can be immediately used in various fields such as advertising, marketing, and content creation.

[0094] The foregoing specification may be implemented as computer-readable code on a medium on which a program is recorded. A computer-readable medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include Hard Disk Drives (HDDs), Solid State Disks (SSDs), Silicon Disk Drives (SDDs), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, etc., and also include implementations in the form of carrier waves (e.g., transmission over the Internet). Accordingly, the above detailed description should not be interpreted restrictively in all respects and should be considered exemplary. The scope of this specification should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of this specification are included within the scope of this specification.

[0095] Furthermore, although the above description has focused on the services and embodiments, this is merely illustrative and does not limit the scope of this specification. Those skilled in the art will understand that various modifications and applications not exemplified above are possible without departing from the essential characteristics of the services and embodiments. For example, each component specifically shown in the embodiments may be modified and implemented. Differences related to such modifications and applications should be interpreted as being included within the scope of this specification as defined in the appended claims.

Claims

Claim 1 delete Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 A method for an operating server to provide a music classification service through an artificial intelligence model comprises: receiving information from a terminal regarding a specific grade and the number of songs classified based on commercial value; requesting an artificial intelligence module for music generation to generate music data as a response to the information regarding the specific grade and the number of songs, wherein the artificial intelligence module for music generation generates the music data based on the request for music data generation and transmits it to an artificial intelligence module for grade classification; and receiving from the artificial intelligence module for grade classification music data classified into one of grades S, A, B, or C based on commercial value according to license costs and industry group of use, through spectrum analysis using at least one of FFT (Fast Fourier Transform), Mel-Spectrogram, and CQT (Constant-Q Transform) and deep neural network analysis. A method of providing, comprising: a step of repeating 1) generating music data through an artificial intelligence module for music generation, 2) classifying grades through an artificial intelligence module for grade classification, and 3) receiving the grade-classified music data until the number of music data classified into the specific grade reaches the number of music; a step of requesting the artificial intelligence module for music generation to terminate the generation of the music data when, based on the reception of the grade-classified music data, the number of music data classified into the specific grade reaches the number of music; and a step of transmitting music data corresponding to the number of music among the music data classified into the specific grade to the terminal. Claim 7 delete Claim 8 A method of provision according to claim 6, further comprising the step of calculating a cost based on the specific grade or the number of music; wherein the step of transmitting music data having the specific grade to the terminal is performed when payment of the cost is completed.

Images