Electronic organ dynamic music score generation and key highlight guiding method and system

Abstract

The invention discloses an electronic organ dynamic music score generation and key highlight guiding method and system, and the method comprises the steps: receiving music and difficulty parameters inputted by a user, and carrying out the preprocessing; a multi-track separation and chord reasoning algorithm based on deep learning is adopted, and music features including melody, chord and rhythm in the preprocessed music are extracted; generating a dynamic electronic organ music score according to the music characteristics and the difficulty parameters by adopting a multi-mode Transform model, and adjusting the content of the music score according to the note density and the rhythm complexity; according to the electronic organ music score, a lighting system on the electronic organ is used for indicating keys needing to be played; the skill level of the user is evaluated by collecting the key pressing speed and accuracy of the user, and the electronic organ music score difficulty is adjusted in real time according to the evaluation result; a music generation Transform technology is adopted to generate an accompaniment note sequence, and various accompaniment instrument options and style adjustment options are provided according to user preferences. According to the invention, full-process automation and personalized learning can be realized.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to a method and system for generating dynamic music scores and guiding key highlighting of an electronic keyboard. Background Art

[0002] With the popularity of smart electronic keyboards in the field of music education, users' requirements for their functions and learning experience are constantly increasing. However, the existing technology has many shortcomings, which limit its teaching effect. First, the light guidance of the smart electronic keyboard only supports preset repertoires, and users cannot choose new repertoires to learn. In addition, the repertoire updates slowly, making it difficult to meet diverse needs. The lighting function is also limited to prompting the position of the keys, and lacks rhythm and strength guidance. Secondly, the difficulty of the repertoire is fixed and cannot be adjusted according to the user's skills, making it difficult to adapt to beginners and advanced users. In addition, the system lacks personalized arrangement, and user interests and creative needs are not supported. Learning feedback is insufficient, and it is difficult for users to correct errors or track progress in real time. In summary, the existing technology has defects in dynamic music score generation, difficulty adaptation, personalization and feedback, and is in urgent need of improvement. Summary of the Invention

[0003] In response to the above problems, the present invention provides a method and system for generating dynamic music scores and highlighting keys for an electronic keyboard. The method aims to utilize artificial intelligence models for music analysis and adaptive difficulty grading, and combines real-time light guidance technology to provide electronic keyboard users with intelligent repertoire teaching and personalized learning experience.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for generating dynamic music scores and guiding key highlighting of an electronic keyboard is provided, the method comprising the following steps: Receive music and difficulty parameters input by the user and perform preprocessing; Using a deep learning-based multi-track separation and chord inference algorithm, we extract musical features including melody, chords, and rhythm from pre-processed music. Using a multimodal Transformer model, a dynamic electronic piano score is generated according to the musical characteristics and difficulty parameters, and the score content is adjusted according to the note density and rhythm complexity; According to the electronic keyboard music score, use the light system on the electronic keyboard to indicate the keys to be played; Assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; The music generation Transformer technology is used to generate accompaniment note sequences, and a variety of accompaniment instrument options and style adjustment options are provided according to user preferences.

[0005] In some embodiments, the method further includes recording the user's performance audio, comparing it with the standard musical notation, evaluating the pitch and rhythm, and generating improvement suggestions.

[0006] In some embodiments, the difficulty parameters include note density and rhythm complexity, and according to thresholds of note density and rhythm complexity, qualified segments are extracted from the parsed music.

[0007] In some embodiments, extracting music features including melody, chords, and rhythm from the pre-processed music comprises the following steps: The Music Transformer based on the Transformer pre-trained model is used to process audio time series data using the self-attention mechanism; Use the Melody RNN model to convert audio into MIDI format and extract the main melody note sequence; Use the Chord Recognition CNN model to analyze chords in audio; The onset detection algorithm is used to detect the note starting points and calculate the rhythm pattern.

[0008] In some embodiments, a multimodal Transformer model is used to generate a dynamic electronic piano score based on the music features and difficulty parameters, including the following steps: Using a multimodal Transformer model, the audio feature vector m and the difficulty parameter vector d are fused through vector concatenation to generate a feature vector x. Use the Transformer encoder to process the fused feature vector x and generate the context representation h; The Transformer decoder is used to generate the next note based on the context representation and the previously generated note sequence, ultimately forming a dynamic electronic organ score.

[0009] In some embodiments, the light system on the electronic keyboard is used to indicate the keys to be played according to the electronic keyboard music score, specifically including: setting the light brightness proportional to the note strength; setting the light color ,in , Indicates the interval between notes. is the color mapping function.

[0010] In some embodiments, by recording the user's performance audio, and using a convolutional neural network to play the audio signal, and comparing it with the standard music score, the pitch and rhythm are evaluated, and improvement suggestions are generated. The specific expression is: pitch evaluation ; Rhythm assessment , Indicates the temperament played by the user. Indicates standard musical temperament. Indicates the rhythm played by the user, Indicates standard rhythm, comprehensive score ,in 、 represents the weight, Represents the tolerance threshold, and uses the rule engine to generate personalized recommendations based on the deviation results and the comprehensive score.

[0011] According to a second aspect of an embodiment of the present disclosure, a system for generating dynamic music scores and guiding key highlights of an electronic keyboard is provided, the system comprising: Music input module, used to receive music and difficulty parameters input by users and perform preprocessing; A feature extraction module, which uses a deep learning-based multi-track separation and chord inference algorithm to extract musical features including melody, chords, and rhythm from the preprocessed music; A dynamic music score generation module, configured to generate a dynamic electronic organ music score based on the music characteristics and difficulty parameters using a multimodal Transformer model, and to adjust the music score content based on note density and rhythm complexity; The key highlight guidance module is used to indicate the keys to be played based on the electronic keyboard music score using the lighting system on the electronic keyboard; The difficulty adaptation module is used to assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; The personalized arrangement module uses music generation Transformer technology to generate accompaniment note sequences and provides multiple accompaniment instrument options and style adjustment options based on user preferences.

[0012] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned method for generating dynamic music scores and guiding key highlights of an electronic piano are implemented.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the above-mentioned electronic piano dynamic music score generation and key highlighting guidance method are implemented.

[0014] The disclosed embodiments provide a method, system, electronic device, and storage medium for generating dynamic music scores and guiding key highlighting for an electronic piano. Users upload or record music, and deep learning technology is used to perform multi-track separation and chord analysis to extract music features. Based on the features, electronic piano scores of various difficulty levels are generated, and the difficulty of the scores is adjusted in real time by evaluating the user's skill level. Lights are used to indicate key positions, rhythm, and dynamics, and the method also provides accompaniment and style adjustment options. The method, system, electronic device, and storage medium of the present invention realize full-process automation and personalized learning, enhance the flexibility and fun of music teaching, and are suitable for users with different skills and interests.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] Figure 1 This is a flow chart of a method for generating dynamic music scores and guiding key highlights on an electronic keyboard according to an embodiment of the present invention; Figure 2 1 is a schematic diagram of a feature extraction process in an embodiment of the present invention; Figure 3 This is a schematic diagram of the process of generating dynamic electronic piano music scores in an embodiment of the present invention; Figure 4 1. It is a schematic structural diagram of a system for generating dynamic music scores and highlighting keys of an electronic keyboard according to an embodiment of the present invention; Figure 5 It is a schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0019] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0020] The present invention provides a method, system, electronic device, and storage medium for generating dynamic music scores and highlighting keys for an electronic keyboard. These methods aim to address technical deficiencies in existing electronic keyboard teaching systems and enhance the user learning experience. Prior art guidance functions for intelligent electronic keyboards are typically limited to pre-set tracks, lacking flexibility and unable to adjust difficulty based on user needs or provide personalized arrangement support. The present invention provides the following embodiments: A method for generating dynamic music scores and guiding keyboard key highlights of an electronic keyboard, such as Figure 1 As shown, the method includes the following steps: S1, receiving music and difficulty parameters input by the user and performing pre-processing; Specifically, it supports audio file uploads and microphone recording, and pre-processes the input music, including noise reduction and standardization, to ensure accurate analysis. Users can upload music and set the learning difficulty, and the system generates personalized teaching content based on the input.

[0021] In one embodiment, users can upload music files (e.g., MP3, WAV format) or record audio through a microphone and set the learning difficulty level (elementary, intermediate, advanced). Based on the difficulty level selected by the user, music fragments that meet the requirements are filtered or generated.

[0022] Difficulty Presets: After receiving the difficulty selection through the User Interface (UI), the system filters scores based on the following thresholds: primary: , , intermediate: , , advanced: , , Feature calculation: Note density: ; Rhythm complexity: ; Music score screening: Select the difficulty threshold above based on the user's difficulty level, extract qualified fragments from the parsed music, or generate corresponding teaching content.

[0023] At the same time, for music clips or teaching content, the specific expression for complexity evaluation is: ,in: 、 Dynamically adjusted weights based on music style. , , , Statistical means and standard deviations of note density and rhythmic complexity.

[0024] S2, using a deep learning-based multi-track separation and chord inference algorithm to extract musical features including melody, chords, and rhythm from the pre-processed music; Specifically, S2 includes track separation, melody extraction, chord analysis, and rhythm analysis, which are used to separate the input music into different tracks, extract the main melody, analyze the chord progression, and detect the rhythm pattern, respectively. This provides a basis for subsequent music score generation.

[0025] In a specific embodiment, input music is analyzed through artificial intelligence technology to extract key features such as melody, chords, and rhythm, providing a data basis for subsequent processing.

[0026] Model selection: Music Transformer (a pre-trained model based on Transformer) is used to efficiently process audio time series data using the self-attention mechanism.

[0027] Feature extraction: Melody extraction: Use the Melody RNN model to convert the audio into MIDI format and extract the main melody note sequence; Chord recognition: Use the Chord Recognition CNN model to analyze the chord progression in the audio; Rhythm analysis: Use the Onset Detection algorithm to detect the starting point of the note and calculate the rhythm pattern.

[0028] Self-attention mechanism of Transformer model: ,in are query, key, and value matrices respectively, The dimension of the key.

[0029] S3. Using a multimodal Transformer model, generating a dynamic electronic piano score based on the music characteristics and difficulty parameters, and adjusting the score content based on note density and rhythm complexity; Specifically, it supports the generation of music scores of various difficulty levels, including simplified, standard and advanced versions, and adjusts the music score content according to note density and rhythm complexity.

[0030] In a specific embodiment, a dynamic music score is generated based on the music characteristics and the difficulty set by the user, and a key lighting guidance scheme is designed. The brightness and color changes of the lights are used to indicate the rhythm and playing strength.

[0031] Model selection: A multimodal Transformer model is used to fuse the audio feature vector m and the difficulty parameter vector d through vector concatenation. The fused input is represented as: ,in Represents vector concatenation operation, is the audio feature vector (dimension n), is the difficulty parameter vector (dimension ).

[0032] Music score generation: Input: fused feature vector x. Output: music score note sequence ,in Indicates the The pitch and duration of each note.

[0033] The Transformer encoder processes the input x and generates a contextual representation h: h=TransformerEncoder(x); Transformer decoder based on h and the previous note sequence s t-1 Generate the next note s t :s t =TransformerDecoder(h,s t-1 ); Light brightness and note velocity Proportional to: ,in is the note velocity, is the proportionality coefficient.

[0034] Light color: ,in , is the note interval time, is a color mapping function. For example, fast tempo is indicated by red and slow tempo is indicated by blue. The unit is "notes per second".

[0035] S4. Use the light system on the electronic keyboard to indicate the keys to be played according to the electronic keyboard music score; Specifically, the key positions are indicated by lights, and visual cues for rhythm and dynamics are provided. The brightness of the lights is proportional to the dynamics of the notes, and the color of the lights changes according to the tempo. This generates a musical score and guides the user through the key lights (including varying brightness levels).

[0036] S5. Assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; S6. Use music generation Transformer technology to generate accompaniment note sequences and provide multiple accompaniment instrument options and style adjustment options based on user preferences.

[0037] Specifically, adjust the accompaniment and music style to meet the user's creation and learning needs.

[0038] The embodiment of the present invention aims to break through the limitations of traditional electronic keyboard teaching through intelligent and personalized design, and to enhance the flexibility, interest and efficiency of learning.

[0039] In a specific embodiment, the accompaniment content or music style is adjusted according to user needs, such as adding different instrument accompaniment or implementing style transfer. Specifically, the music generation Transformer technology is used to support conditional generation. and user-selected style tags , output accompaniment note sequence ,pass For example, if the user selects a pop style, the system will add drum and bass accompaniment to the melody.

[0040] The method further includes S7, recording the user's performance audio, comparing it with standard musical notation, evaluating the pitch and rhythm, and generating improvement suggestions. That is, recording the user's performance and providing targeted suggestions to help the user improve his or her skills.

[0041] Specifically, the difficulty parameters in S1 include note density and rhythm complexity. According to the thresholds of note density and rhythm complexity, qualified fragments are extracted from the parsed music.

[0042] Specifically, S2 extracts the music features including melody, chords and rhythm from the pre-processed music, such as Figure 2 As shown, the following steps are included: S21, using the Music Transformer based on the Transformer pre-trained model and the self-attention mechanism to process audio time series data; S22. Use the Melody RNN model to convert the audio into MIDI format and extract the main melody note sequence; S23, using the Chord Recognition CNN model to analyze chords in audio; S24. Detect the note starting point using an Onset Detection algorithm and calculate the rhythm pattern.

[0043] S3 uses a multimodal Transformer model to generate dynamic electronic piano music scores based on the music features and difficulty parameters, such as Figure 3 As shown, the following steps are included: S31, using the multimodal Transformer model, fusing audio feature vectors through vector concatenation and the difficulty parameter vector , generating the feature vector ; S32, use the Transformer encoder to process the fused feature vector x and generate the context representation h; S33. Use the Transformer decoder to generate the next note based on the context representation and the previously generated note sequence, and finally form a dynamic electronic piano score.

[0044] In S4, the light system on the electronic keyboard is used to indicate the keys to be played according to the electronic keyboard music score, including: setting the light brightness proportional to the note strength; setting the light color ,in , Indicates the interval between notes. is the color mapping function.

[0045] S7 records the user's performance audio and uses a convolutional neural network to perform the audio signal, compares it with the standard music score, evaluates the pitch and rhythm, and generates improvement suggestions. The specific expression is: Pitch evaluation ; Rhythm assessment , Indicates the temperament played by the user. Indicates standard musical temperament. Indicates the rhythm played by the user, Indicates standard rhythm, comprehensive score ,in 、 represents the weight, Represents the tolerance threshold, and uses the rule engine to generate personalized recommendations based on the deviation results and the comprehensive score.

[0046] In a specific embodiment, the following steps are performed: Input and initialization: The user uploads a music file or records audio and selects a difficulty level. The system decodes the audio and initializes the difficulty parameters.

[0047] Feature extraction: Use Music Transformer to analyze music and extract melody, chord, and rhythm features.

[0048] Music score and guidance generation: Integrate music features and difficulty parameters to generate dynamic music scores and lighting control signals.

[0049] Performance and Evaluation: Users record audio based on guided performance, difficulty rating, and feedback modules. CNN evaluates pitch and rhythm, and generates improvement suggestions.

[0050] Personalized adjustment: Users select accompaniment or style, and Transformer is used to generate personalized accompaniment content.

[0051] Here's a specific example: Application scenario: Users upload music files (such as MP3 and WAV formats) or record audio through a microphone and select the learning difficulty level (such as beginner, intermediate, and advanced) based on their skill level.

[0052] Users upload music files or record audio through the user interface (UI), and the system decodes the input using audio processing techniques. For example, open source libraries such as Librosa are used to convert audio files into analyzable waveform data, ensuring high-fidelity reading.

[0053] Provides a difficulty selection interface. After the user selects, the difficulty level is mapped to a quantitative parameter: Note density ( ): Indicates the number of notes per unit time, notes / second.

[0054] Rhythm complexity ( ): reflects the complexity of rhythm changes.

[0055] The optimization examples are as follows: primary: , ; intermediate: , ; advanced: , .

[0056] The teaching process is initialized based on the user's selected difficulty level, ensuring that the subsequently generated music scores and guidance content match the user's needs. Through audio decoding and difficulty presets, the system supports multiple audio input formats and flexibly adjusts teaching content based on the user's skill level, enhancing the personalized and adaptable learning experience.

[0057] Perform intelligent analysis on the music input by the user, extract key features such as melody, chords and rhythm, and provide data support for subsequent music score generation.

[0058] Track separation and melody extraction: Use artificial intelligence technology (Music Transformer model) to process audio data, analyze audio timing features through the self-attention mechanism, convert the input audio into MIDI format, and extract the main melody note sequence.

[0059] Chord Analysis: This system uses a convolutional neural network (CNN) model (Chord Recognition CNN) to identify chord progressions in audio. For example, if a user uploads an MP3 file, the system separates the main melody from the accompaniment and outputs a chord sequence (e.g., CG-Am-F).

[0060] Rhythm analysis: Detect the note starting point through the Onset Detection algorithm, calculate the rhythm pattern, and generate the rhythm feature vector.

[0061] Through deep learning technology, the system can efficiently and accurately extract music features, laying the foundation for dynamic music score generation and key guidance.

[0062] Dynamic music score generation and key highlight guidance: Based on the extracted music features and the difficulty set by the user, dynamic music scores are generated, and the user's performance is guided in real time through the lighting system on the electronic keyboard.

[0063] Multimodal fusion: Using the multimodal Transformer model, the music feature vector (including melody, chords, rhythm) and difficulty parameters Fusion, generating comprehensive feature vector .

[0064] Music score generation: Transformer encoder processes input , generating contextual representation : , the decoder is based on Generate note sequence , supports multiple difficulty versions: ; Simplified version: Reduce the number of chords and reduce the rhythmic complexity.

[0065] Standard version: retains the original melody and chords.

[0066] Advanced version: Adds ornaments and complex rhythms.

[0067] Key highlight guide: Light brightness: ,in It is The velocity of each note (range [0,127], based on the MIDI standard), is the scaling factor (e.g. k=0.01 maps intensity to the brightness range [0, 1]), Light color: According to the rhythm speed change, Defined as the time interval between adjacent notes The reciprocal of: , color mapping function The specific form is a piecewise function: , in The unit is "notes per second".

[0068] Through multimodal fusion and lighting control technology, music scores that match the user's difficulty level are generated, and intuitive key guidance is provided to improve teaching interactivity and accuracy.

[0069] Performance and evaluation: users play the electronic keyboard according to the music score and light guidance. The system records the performance audio, evaluates the performance, and provides improvement suggestions.

[0070] Collect user performance audio and use the CNN model to analyze pitch and rhythm: Pitch evaluation: calculate the frequency deviation between the user's performance and the standard note: Errorpitch=|fuser−fstandard|; Rhythm evaluation: calculate the deviation of the note start time: Errorrhythm=|tuser−tstandard|; Comprehensive score: ,in and is the weight, The threshold for tolerance is given. Feedback is generated based on the scoring results, such as “pay attention to the pitch in the high notes” or “strengthen the rhythm stability.”

[0071] Dynamic adjustment: If the user makes continuous mistakes , the system automatically switches to the simplified version of the music score.

[0072] The real-time evaluation and feedback mechanism helps users identify problems in a timely manner and improve their playing skills, thereby improving learning efficiency.

[0073] Personalized composing: Users select an accompaniment type (e.g., guitar, drums) or musical style (e.g., pop, jazz) to generate personalized accompaniment content. This uses Transformer music generation technology and supports conditional generation.

[0074] Accompaniment generation: Input: main melody and style tags ; Output: Accompaniment note sequence . Model architecture: Transformer encoder processes the main melody, and decoder generates accompaniment.

[0075] Style transfer: through style embedding vectors Control the generation style.

[0076] Conditional generation: The personalized arrangement function enhances the creative flexibility of the system and improves the fun of users' learning and playing.

[0077] The embodiments of the present invention are based on artificial intelligence and multimodal fusion technology. The implementation principles, logic, and conduction methods are as follows: The system uses deep learning models (such as Transformers and CNNs) to process audio data, extract musical features, and generate musical scores and guidance signals. The system uses mathematical modeling to quantify difficulty parameters and performance, ensuring accurate and consistent output.

[0078] It adopts a modular design, including five core modules: music input, feature extraction, score generation, performance evaluation and personalized arrangement. The modules work together in sequence to form a closed-loop teaching process.

[0079] Users input music and preferences through the UI. After processing, the system interacts with the user through dynamic music scores and key lights. After the user plays, the system further optimizes and guides through audio feedback to achieve a human-computer collaborative teaching experience.

[0080] The preset parameters in the above formula (such as weight coefficients, difficulty thresholds, etc.) are set and optimized by those skilled in the art according to actual application requirements and music characteristics to ensure the accuracy and practicality of the system functions. The above content shows the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the embodiments and descriptions are only for illustrating the principles of the technical solutions of the present invention. Without departing from the spirit and scope of the present invention, the present invention can also be subjected to various changes and improvements, such as adjusting the music analysis algorithm, expanding the lighting guidance mode or optimizing the personalized arrangement function, etc. These changes and improvements all fall within the scope of protection claimed by the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

[0081] Another embodiment is used to illustrate a system for generating dynamic music scores and highlighting keys of an electronic keyboard. Figure 4 As shown, the system includes: a music input module 410 for receiving music and difficulty parameters input by a user and performing preprocessing; a feature extraction module 420 for extracting music features including melody, chords and rhythm from the preprocessed music using a multi-track separation and chord inference algorithm based on deep learning; a dynamic score generation module 430 for generating a dynamic electronic piano score based on the music features and difficulty parameters using a multimodal Transformer model, and adjusting the score content according to the note density and rhythm complexity; a key highlight guidance module 440 for indicating the keys to be played based on the electronic piano score using the lighting system on the electronic piano; a difficulty adaptation module 450 for evaluating the user's skill level by collecting the user's keystroke speed and accuracy, and adjusting the difficulty of the electronic piano score in real time according to the evaluation results; a personalized arrangement module 460 for generating an accompaniment note sequence using music generation Transformer technology, and providing a variety of accompaniment instrument options and style adjustment options according to user preferences.

[0082] In addition to the above modules, the system may also include other components. However, since these components are irrelevant to the content of the embodiments of the present disclosure, their illustration and description are omitted here.

[0083] The other specific working processes of the electronic keyboard dynamic music score generation and key highlight guidance system are described in the above-mentioned electronic keyboard dynamic music score generation and key highlight guidance method embodiment, which will not be repeated here.

[0084] Another embodiment is used to illustrate that the system of the present invention can also be used with the help of Figure 5 The architecture of the computing device shown is implemented. Figure 5 The architecture of the computing device is shown in FIG. Figure 5 As shown, a computer system 510, a system bus 530, one or more CPUs 540, an input / output 520, a memory 550, etc. The memory 550 can store various data or files used for computer processing and / or communication, as well as program instructions executed by the CPU, including the method for generating dynamic music scores and guiding key highlights of an electronic keyboard. Figure 5 The architecture shown is only exemplary and may be adjusted based on actual needs when implementing different devices. Figure 5 One or more components in the system. The memory 550, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the electronic keyboard dynamic music score generation and key highlight guidance method in the embodiment of the present invention (for example, the music input module 410, feature extraction module 420, dynamic music score generation module 430, key highlight guidance module 440, difficulty adaptation module 450 and personalized arrangement module 460 in the electronic keyboard dynamic music score generation and key highlight guidance system). One or more CPUs 540 execute various functional applications and data processing of the system of the present invention by running the software programs, instructions and modules stored in the memory 550, that is, to implement the above-mentioned electronic keyboard dynamic music score generation and key highlight guidance method, which includes the following steps: Receive music and difficulty parameters input by the user and perform preprocessing; Using a deep learning-based multi-track separation and chord inference algorithm, we extract musical features including melody, chords, and rhythm from pre-processed music. Using a multimodal Transformer model, a dynamic electronic piano score is generated according to the musical characteristics and difficulty parameters, and the score content is adjusted according to the note density and rhythm complexity; According to the electronic keyboard music score, use the light system on the electronic keyboard to indicate the keys to be played; Assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; The music generation Transformer technology is used to generate accompaniment note sequences, and a variety of accompaniment instrument options and style adjustment options are provided according to user preferences.

[0085] Of course, the processor of the server provided by the embodiment of the present invention is not limited to executing the method operations described above, and can also execute related operations in the electronic piano dynamic music score generation and key highlighting guidance method provided by any embodiment of the present invention.

[0086] The memory 550 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. Furthermore, the memory 550 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the memory 550 may further include memory remotely located relative to one or more CPUs 540, and these remote memories may be connected to the device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] The input / output 520 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The input / output 520 may also include a display device such as a display screen.

[0088] Embodiments of the present invention also provide a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the electronic keyboard dynamic score generation and key highlighting guidance methods described in the above embodiments. The computer-readable storage medium of the embodiments of the present invention may be any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0089] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0090] The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0091] In addition, other specific working processes of a non-transitory computer-readable storage medium refer to the description of the above-mentioned electronic piano dynamic music score generation and key highlight guidance method embodiment, and will not be repeated here.

[0092] In this document, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a step or method that comprises a series of elements includes not only those elements, but also includes other elements not expressly listed, or also includes elements inherent to such step or method.

[0093] The above is a further detailed description of the present invention in conjunction with specific preferred embodiments, and the specific implementation of the present invention should not be considered to be limited to these descriptions. For those skilled in the art of the present invention, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should be considered to fall within the scope of protection of the present invention.

Claims

1. A method for generating dynamic music scores and guiding key highlighting of an electronic keyboard, characterized in that: The method comprises the following steps: Receive music and difficulty parameters input by the user and perform preprocessing; Using a deep learning-based multi-track separation and chord inference algorithm, we extract musical features including melody, chords, and rhythm from pre-processed music. Using a multimodal Transformer model, a dynamic electronic piano score is generated according to the musical characteristics and difficulty parameters, and the score content is adjusted according to the note density and rhythm complexity; According to the electronic keyboard music score, use the light system on the electronic keyboard to indicate the keys to be played; Assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; The music generation Transformer technology is used to generate accompaniment note sequences, and a variety of accompaniment instrument options and style adjustment options are provided according to user preferences.

2. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 1, wherein: The method also includes recording the user's performance audio, comparing it with the standard musical score, evaluating the pitch and rhythm, and generating improvement suggestions.

3. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 1, characterized in that: The difficulty parameters include note density and rhythm complexity. According to the thresholds of note density and rhythm complexity, qualified fragments are extracted from the parsed music.

4. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 1, wherein: The method of extracting music features including melody, chords and rhythm from the pre-processed music comprises the following steps: The Music Transformer based on the Transformer pre-trained model is used to process audio time series data using the self-attention mechanism; Use the Melody RNN model to convert audio into MIDI format and extract the main melody note sequence; Use the Chord Recognition CNN model to analyze chords in audio; The onset detection algorithm is used to detect the note starting points and calculate the rhythm pattern.

5. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 1, characterized in that: A multimodal Transformer model is used to generate dynamic electronic piano music scores according to the music features and difficulty parameters, including the following steps: Using a multimodal Transformer model, the audio feature vector m and the difficulty parameter vector d are fused through vector concatenation to generate a feature vector x. Use the Transformer encoder to process the fused feature vector x and generate the context representation h; The Transformer decoder is used to generate the next note based on the context representation and the previously generated note sequence, ultimately forming a dynamic electronic organ score.

6. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 1, characterized in that: According to the electronic keyboard music score, use the light system on the electronic keyboard to indicate the keys to be played, including: setting the light brightness proportional to the note strength; setting the light color ,in , Indicates the interval between notes. is the color mapping function.

7. The method for generating dynamic music scores and guiding key highlights of an electronic keyboard according to claim 2, characterized in that: By recording the user's performance audio, and using a convolutional neural network to play the audio signal, and comparing it with the standard music score, the pitch and rhythm are evaluated, and improvement suggestions are generated. The specific expression is: pitch evaluation ; Rhythm assessment , Indicates the temperament played by the user. Indicates standard musical temperament. Indicates the rhythm played by the user, Indicates standard rhythm, comprehensive score ,in 、 represents the weight, Represents the tolerance threshold, and uses the rule engine to generate personalized recommendations based on the deviation results and the comprehensive score.

8. An electronic keyboard dynamic music score generation and key highlighting guidance system, characterized in that: The system comprises: Music input module, used to receive music and difficulty parameters input by users and perform preprocessing; A feature extraction module, which uses a deep learning-based multi-track separation and chord inference algorithm to extract musical features including melody, chords, and rhythm from the preprocessed music; A dynamic music score generation module, configured to generate a dynamic electronic organ music score based on the music characteristics and difficulty parameters using a multimodal Transformer model, and to adjust the music score content based on note density and rhythm complexity; The key highlighting guide module is used to indicate the keys to be played based on the electronic keyboard music score using the lighting system on the electronic keyboard; The difficulty adaptation module is used to assess the user's skill level by collecting the user's keystroke speed and accuracy, and adjust the difficulty of the electronic keyboard score in real time based on the assessment results; The personalized arrangement module uses music generation Transformer technology to generate accompaniment note sequences and provides multiple accompaniment instrument options and style adjustment options based on user preferences.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for generating dynamic music scores and guiding key highlights of an electronic keyboard as claimed in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of the electronic keyboard dynamic music score generation and key highlighting guidance method as described in any one of claims 1 to 7 are implemented.

Images