Multifunctional digital music teaching system

Abstract

The invention discloses a multifunctional digital music teaching system in the field of digital music teaching, and the system comprises a teaching module which is used for providing music teaching courses and playing skill training, and also providing guidance and feedback according to the learning progress and performance; the creation module is used for providing tools and resources required by music creation, assisting in creating music works and simultaneously providing creative inspiration tools and music materials; the evaluation module is used for collecting multi-source data during playing skill training, recognizing playing postures and actions in combination with deep learning and image processing technologies, and performing analysis and evaluation; and the expansion module is used for guiding and exploring the relationship between music and other art forms. Students' physiology, action and performance data are comprehensively acquired through the multi-modal acquisition unit, the posture and action analysis unit accurately judges whether postures are correct or wrong, and the playing evaluation unit performs multi-dimensional evaluation from performance, style, innovation and the like, so that comprehensive, objective and accurate evaluation results are provided for the students.

Description

Technical Field

[0001] The invention relates to the technical field of digital music teaching, and in particular to a multifunctional digital music teaching system. Background Art

[0002] Digital music teaching is a music teaching activity based on digital technology and carried out with the help of computers, smart devices and other carriers. It transforms traditional music teaching content into digital form, covering multiple aspects such as music theory knowledge explanation, instrument performance teaching, music creation guidance, etc. Through digital means, such as online courses, music teaching software, virtual performance scenes, etc., it provides students with rich and diverse learning resources and highly interactive learning experiences, breaking the limitations of time and space, so that students can learn music knowledge and skills more conveniently and efficiently, and improve their music literacy.

[0003] In traditional digital music teaching, the evaluation method mainly focuses on the surface examination of students' playing skills, such as simple pitch and rhythm judgment, which makes it difficult to comprehensively measure students' musical literacy. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects in the prior art and provide a multifunctional digital music teaching system to solve the problem that it is difficult to comprehensively measure the music literacy of students in traditional digital music teaching.

[0005] The objective of the present invention is achieved in that a multifunctional digital music teaching system comprises:

[0006] Teaching module: used to provide music teaching courses and performance skills training, while providing guidance and feedback based on learning progress and performance;

[0007] Creation module: used to provide the tools and resources required for music creation, assist in the creation of music works, and provide creative inspiration tools and music materials;

[0008] Evaluation module: used to collect multi-source data during performance skill training, combine deep learning and image processing technology to identify performance postures and movements, and conduct analysis and evaluation;

[0009] Extension module: used to guide students to explore the relationship between music and other art forms, plan personalized learning paths, and provide a platform for interactive communication;

[0010] Management module: used to store the data generated by each module and define different operation permissions.

[0011] Preferably, the teaching module includes a course teaching unit and a performance training unit. The course teaching unit is used to teach students basic music theory knowledge through multimedia resources, while providing interactive exercises and providing timely feedback and learning suggestions based on the answers. The basic music theory knowledge includes notes, beats, scales, and chords. The performance training unit is used to provide repertoire exercises of different styles and difficulty levels based on current performance level, learning goals, and past learning records.

[0012] Preferably, the creation module includes a virtual arrangement unit and an inspiration material unit. The virtual arrangement unit is used to provide a variety of virtual musical instruments for simulating musical instrument performances. The inspiration material unit is used to provide a creative inspiration tool and generate different note sequences and chord progressions through a random algorithm to provide a source of inspiration for creation. At the same time, it provides music materials for retrieval and calling according to creation needs. The creative inspiration tool includes a random note generator and a chord progression recommender.

[0013] Preferably, the evaluation module includes a multimodal acquisition unit, a posture and motion analysis unit, and a performance evaluation unit. The multimodal acquisition unit is used to use sensors and cameras to collect multi-source data in the performance skill training or creation process from different modalities. The sensors include heart rate sensors and skin electrical response sensors. The multi-source data include physiological data, motion data, and performance videos. The posture and motion analysis unit is used to analyze the collected multi-source data in combination with deep learning and image processing technology to identify performance postures and movements, determine whether they meet the standards, and analyze and prompt incorrect postures and movements. The performance evaluation unit is used to evaluate the performance, mastery and innovation of the performance style, and at the same time locate and analyze errors in the performance process and provide improvement suggestions.

[0014] Preferably, the performance evaluation unit includes an expressiveness evaluation subunit, a creativity evaluation subunit, and a music comprehension evaluation subunit. The expressiveness evaluation subunit is used to evaluate the expressiveness level of students in various aspects during the performance by analyzing the physiological data and performance videos of students during the performance, combined with audio data, and using a deep learning model. The physiological data includes heart rate variability, and the formula is used. where RR i is the time interval between adjacent heartbeats, is the average heartbeat interval, N is the total number of heartbeats, and the various aspects include emotional expression, timbre control, and stage performance. The creativity evaluation subunit is used to perform cross-modal analysis on the works, including feature extraction and analysis of works that integrate painting and literary elements. Through natural language processing and image recognition technologies such as sentiment analysis and keyword extraction, the degree of innovation of the works in terms of creativity and cultural elements is evaluated, and the operation sequence in the students' creative process is mined. Through the Apriori algorithm, the support Analyze the coherence of students' creative ideas and innovative ideas. The music comprehension assessment subunit is used to collect EEG data of students when listening to music with the help of EEG monitoring equipment, extract EEG features through signal processing and analysis technology, and combine with music knowledge graph to evaluate students' mastery and understanding of music knowledge, including understanding of music theory, culture, and history. At the same time, use machine learning algorithms to comprehensively analyze the level of expressiveness, degree of innovation, coherence of creative ideas, innovative ideas, and mastery and understanding of music knowledge to provide students with music comprehension ability assessment and learning suggestions.

[0015] Preferably, the expansion module includes a music resource unit, a learning path planning unit, a thinking guidance unit, and a music community communication unit. The music resource unit is used to integrate music and cultural resources from various places, present them to students in various forms, and provide interactive learning activities. The music and cultural resources from various places include traditional music works from different countries and regions, introductions to music genres, and the historical development of music. The various forms include audio, video, and text. The learning activities include music style identification and cultural knowledge questions and answers. The learning path planning unit is used to conduct initial tests on students, analyze learning goals and learning style preferences, and use machine learning algorithms to develop learning paths. The thinking guidance unit is used to establish a cross-domain thinking model by showing cases of the integration of music and art forms, and by constructing a color-emotion association matrix. The art forms include painting, dance, and film. The music community communication unit is used to provide an online community, and the popularity of posts is calculated by Popularity=L+2C+3S, where L is the number of likes, C is the number of comments, and S is the number of shares.

[0016] Preferably, the management module includes a data management unit, a permission management unit, and a monitoring and maintenance unit. The data management unit is used to store the data generated by each module and perform data backup through incremental backup and full backup strategies. The permission management unit is used to clarify the user's role and define different operation permissions for each role. The user's operation is made to comply with the scope of his or her permission through the permission verification formula, and permission adjustment and audit functions are provided at the same time. The monitoring and maintenance unit is used to monitor the operating status of each module in real time.

[0017] A multifunctional digital music teaching method comprises the following steps:

[0018] Teaching: The course teaching unit teaches students basic music theory knowledge through multimedia resources, and provides interactive exercises, and provides instant feedback and learning suggestions based on the answers. The performance training unit then provides repertoire exercises of different styles and difficulty levels based on current performance level, learning goals and past learning records;

[0019] Creation: The virtual arrangement unit provides a variety of virtual instruments to simulate instrument performance, and the inspiration material unit provides creative inspiration tools and generates different note sequences and chord progressions through random algorithms to provide inspiration for creation. At the same time, music materials are retrieved and called according to the needs of creation;

[0020] Evaluation: The multimodal acquisition unit uses sensors and cameras to collect multi-source data from different modes during the performance skill training or creation process. The posture and action analysis unit then analyzes the collected multi-source data and combines deep learning and image processing technology to identify the performance posture and action, determine whether it meets the standards, and analyze and prompt incorrect postures and actions. The performance evaluation unit then evaluates the performance, the mastery and innovation of the performance style, and locates and analyzes the errors in the performance process, and provides improvement suggestions;

[0021] Extension: The music resource unit integrates music and cultural resources from all over the world and presents them to students in various forms, while providing interactive learning activities. The learning path planning unit then conducts initial tests on students, analyzes their learning goals and learning style preferences, and uses machine learning algorithms to develop learning paths. The thinking guidance unit then demonstrates examples of the integration of music and art forms, and establishes a cross-domain thinking model by building a color-emotion association matrix. The music community exchange unit provides an online community.

[0022] Management: The data management unit stores the data generated by each module and backs up the data through incremental backup and full backup strategies. The permission management unit clarifies the user's role and defines different operation permissions for each role. The permission verification formula ensures that the user's operation is within the scope of his or her permission. At the same time, it provides permission adjustment and audit functions. The monitoring and maintenance unit monitors the operating status of each module in real time.

[0023] The present invention provides a multifunctional digital music teaching system. It has the following beneficial effects:

[0024] 1. The present invention uses a multimodal acquisition unit to obtain students' physiological, movement, and performance data in all directions. The posture and movement analysis unit accurately determines the correctness of the posture. The performance evaluation unit evaluates from multiple dimensions such as performance, style, and innovation, thereby providing students with comprehensive, objective, and accurate evaluation results, allowing students and teachers to clearly understand the strengths and weaknesses of students, and scientifically quantifying the evaluation of students' music learning outcomes, solving the problem that it is difficult to comprehensively measure students' music literacy in traditional digital music teaching.

[0025] 2. The present invention provides rich music materials by providing a variety of virtual musical instruments for simulated performances, and the inspiration material unit uses random algorithms to generate note sequences and chord progressions. The inspiration material unit generates creative content based on music theory rules, and filters and calls on massive material libraries as needed, thereby stimulating students' creative inspiration, lowering the threshold for creation, providing students with rich creative possibilities, and realizing full-process creative support from creative conception to the formation of works.

[0026] 3. The present invention integrates music and cultural resources from various places through expansion modules, presents and arranges interactive activities in various forms, uses machine learning algorithms to plan personalized learning paths, demonstrates art integration cases to build cross-domain thinking models, and builds a music community communication platform, so that students can have an in-depth understanding of diverse music cultures, cultivate cross-domain innovative thinking, create a good learning and communication atmosphere, and realize the transformation from single music learning to multi-domain integration and all-round expansion. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A system architecture diagram of a multifunctional digital music teaching system proposed by the present invention. DETAILED DESCRIPTION

[0028] like Figure 1 A multifunctional digital music teaching system is shown, comprising:

[0029] Teaching module: used to provide music teaching courses and performance skills training, while providing guidance and feedback based on learning progress and performance; the teaching module includes course teaching units and performance training units. The course teaching unit is used to teach students basic music theory knowledge through multimedia resources, while providing interactive exercises and providing instant feedback and learning suggestions based on the answers. Basic music theory knowledge includes notes, beats, scales, and chords. The performance training unit is used to provide repertoire exercises of different styles and difficulty levels based on current performance level, learning goals, and past learning records.

[0030] Specifically, basic music theory knowledge is imparted to students through multimedia resources, and interactive exercises are provided. In addition, instant feedback and learning suggestions are provided based on the answers, so that abstract basic music theory knowledge can be presented to students in an intuitive and vivid form, enabling students to learn basic music theory knowledge efficiently, and grasping students' learning progress and knowledge mastery in real time. By providing repertoire exercises of different styles and difficulty levels based on current performance level, learning goals and past learning records, the most suitable repertoire for students' current practice can be selected, providing students with personalized and targeted repertoire practice resources to help them gradually improve their performance skills.

[0031] Creation module: used to provide the tools and resources required for music creation, assist in the creation of musical works, and provide creative inspiration tools and music materials; the creation module includes a virtual arrangement unit and an inspiration material unit. The virtual arrangement unit is used to provide a variety of virtual instruments for simulating instrument performances. The inspiration material unit is used to provide creative inspiration tools and generate different note sequences and chord progressions through random algorithms to provide a source of inspiration for creation. At the same time, it provides music materials for retrieval and call according to creation needs. Creative inspiration tools include a random note generator and a chord progression recommender.

[0032] Specifically, by integrating the Web Audio API with efficient audio processing algorithms, a fully functional virtual musical instrument performance environment is built. With the help of JavaScript scripting language, the sound-generating principles of various musical instruments are accurately simulated. For example, when simulating string instruments, relevant parameters are adjusted according to the physical formula of string vibration to present the unique timbre of different string instruments. At the same time, HTML5 and CSS3 are used to build an intuitive interactive interface, and various virtual instruments such as piano, guitar, and drums are displayed as image icons.

[0033] Through the random note generation algorithm, using the random number generation function in the programming language, combined with music theory rules, such as note duration, mode and tonality, creative note sequences are generated. For the chord progression recommender, a huge chord relationship database is built based on the music harmony system. When the user inputs the creation requirements or starting chords, the intelligent matching algorithm is used to screen out the appropriate chord progressions. At the same time, advanced database management technology is used to classify and store massive music materials according to multiple dimensions such as style, rhythm, and instrument, so as to provide creators with a continuous source of inspiration and rich materials.

[0034] Evaluation module: used to collect multi-source data during performance skill training, combine deep learning and image processing technology, identify performance postures and movements, and conduct analysis and evaluation; the evaluation module includes a multimodal acquisition unit, a posture and movement analysis unit, and a performance evaluation unit. The multimodal acquisition unit is used to use sensors and cameras to collect multi-source data in the performance skill training or creation process from different modalities. The sensors include heart rate sensors and skin electrical response sensors. The multi-source data includes physiological data, movement data, and performance videos. The posture and movement analysis unit is used to analyze the collected multi-source data, combine deep learning and image processing technology, identify performance postures and movements, determine whether they meet the standards, and analyze and prompt incorrect postures and movements. The performance evaluation unit is used to evaluate the performance, mastery and innovation of the performance style, and locate and analyze errors in the performance process, and provide improvement suggestions.

[0035] Specifically, by using sensors and cameras, multi-source data from different modalities during performance skill training or creation is collected, so that the heart rate data of students during performance or creation can be collected in real time. This data reflects the physiological state of students such as emotional tension. Based on the characteristics that human skin resistance changes with emotions, the galvanic skin response sensor measures the changes in weak current on the surface of the skin, and then obtains galvanic skin response data to assist in judging students' emotional fluctuations. The camera uses high-definition image acquisition technology to shoot students' performance scenes from different angles and capture movement details. Through these devices, multi-source data such as physiological data, movement data, and performance videos are collected from different modalities. This provides a comprehensive and rich data foundation for subsequent analysis and evaluation.

[0036] The action recognition model is built through a deep learning framework (such as TensorFlow). First, a large number of video samples containing correct and incorrect playing postures and movements are annotated to form a training data set. The model is based on the convolutional neural network (CNN) architecture, and analyzes the collected video data frame by frame to extract the feature points of key parts of the human body. By continuously learning the spatial position relationship and motion trajectory of the feature points, the playing posture and movement are identified. The pre-set standard posture and movement parameters are used as a reference to determine whether the currently identified posture and movement meet the standard. Once an error is detected, the model determines the error type and cause by analyzing the deviation of the feature points. Combined with deep learning and image processing technology, accurate recognition and analysis of playing postures and movements can be achieved.

[0037] By combining audio analysis technology with machine learning algorithms, the performance audio is processed by Fourier transform and other methods, and elements such as pitch, rhythm, and timbre are analyzed to evaluate the performance. Machine learning algorithms such as cluster analysis are used to compare a large number of performance samples of different styles to determine the degree of students' mastery of performance styles. The innovation evaluation algorithm is used to analyze the unique use of musical elements in students' performances and evaluate innovative performance. For errors in the performance process, the time point and specific form of the error are located by comparing with standard performance audio and analyzing the correlation between movement data. Based on the pre-built error cause library and improvement strategy library, targeted improvement suggestions are generated, thereby achieving a comprehensive, objective and accurate evaluation of the performance, thus solving the problem of strong subjectivity, lack of systematicness and specificity in traditional evaluation.

[0038] The performance evaluation unit includes the expressiveness evaluation subunit, the creativity evaluation subunit, and the music comprehension evaluation subunit. The expressiveness evaluation subunit is used to evaluate the students' expressiveness level in various aspects of the performance process by analyzing the students' physiological data and performance videos during the performance, combined with audio data, and using a deep learning model. The physiological data includes heart rate variability, and the formula is used. where RR i is the time interval between adjacent heartbeats, is the average heartbeat interval, N is the total number of heartbeats, and various aspects include emotional expression, timbre control, and stage performance. The creativity evaluation subunit is used to conduct cross-modal analysis of the works, including feature extraction and analysis of works that integrate painting and literary elements. Through natural language processing and image recognition technologies such as sentiment analysis and keyword extraction, the degree of innovation of the works in terms of creativity and cultural elements is evaluated. At the same time, the operation sequence in the students' creative process is explored. Through the Apriori algorithm, the support Analyze the coherence of students' creative ideas and innovative ideas. The music comprehension assessment sub-unit is used to collect students' EEG data when listening to music with the help of EEG monitoring equipment, extract EEG features through signal processing and analysis technology, and combine with the music knowledge graph to evaluate students' mastery and understanding of music knowledge, including their understanding of music theory, culture, and history. At the same time, the machine learning algorithm is used to comprehensively analyze the level of expressiveness, degree of innovation, coherence of creative ideas, innovative ideas, and mastery and understanding of music knowledge to provide students with music comprehension ability assessment and learning suggestions.

[0039] Specifically, by analyzing students' physiological data and performance videos during performance, combined with audio data, a deep learning model is used to evaluate students' expressive levels in various aspects of the performance, thereby conducting a comprehensive evaluation of students' expressive levels in emotional expression, timbre control, stage performance, etc., and achieving objective and accurate measurement of students' performance expressiveness from multiple dimensions.

[0040] By applying natural language processing technology and image recognition technology to creative works that integrate painting and literary elements, for the literary part, keyword extraction is carried out through means such as lexical analysis and syntactic analysis, and the sentiment analysis algorithm is used to judge the sentiment tendency of the work; for the painting part, the image recognition model based on the convolutional neural network is used to extract features such as color, composition, and lines. At the same time, by systematically recording the operation sequences of students' creative process, these sequences are mined using the Apriori algorithm, and the support is calculated to analyze frequently occurring creative patterns and changes in ideas, thereby evaluating the degree of innovation in the use of creative and cultural elements in the works, as well as the coherence and innovation of creative ideas, achieving a quantitative evaluation of students' creativity, and providing data support for cultivating students' innovative ability, thus solving the difficult problem of scientifically judging students' innovative ability in music creation.

[0041] The EEG data of students listening to music is collected through EEG monitoring equipment, and the original EEG signals are converted into frequency domain signals using signal processing technologies such as fast Fourier transform, and features such as alpha waves and beta waves are extracted. At the same time, a music knowledge graph containing music theory, culture, and historical knowledge is constructed, and students' performance in music learning is associated with the knowledge graph. Then, machine learning algorithms are used to conduct a comprehensive analysis of multi-dimensional data such as the level of expressiveness, degree of innovation, coherence of creative ideas, innovative ideas, and the mastery and understanding of music knowledge. Through these steps, students are provided with a comprehensive and scientific assessment of their music comprehension ability, and targeted learning suggestions are generated based on the assessment results, achieving an in-depth analysis of students' music comprehension ability, providing a basis for personalized teaching, and thus systematically assessing students' music comprehension ability and providing effective learning suggestions.

[0042] Extension module: used to guide the exploration of the relationship between music and other art forms, while planning personalized learning paths and providing a platform for interactive communication; the extension module includes a music resource unit, a learning path planning unit, a thinking guidance unit, and a music community communication unit. The music resource unit is used to integrate music and cultural resources from various places and present them to students in various forms, while providing interactive learning activities. Music and cultural resources from various places include traditional music works from different countries and regions, introductions to music genres, and the development of music history. Various forms include audio, video, and text. Learning activities include music style identification and cultural knowledge Q&A. The learning path planning unit is used to conduct initial tests on students, analyze learning goals and learning style preferences, and use machine learning algorithms to develop learning paths. The thinking guidance unit is used to establish a cross-domain thinking model by showing examples of the integration of music and art forms and by constructing a color-emotion association matrix. Art forms include painting, dance, and film. The music community communication unit is used to provide an online community and calculate the popularity of posts through Popularity=L+2C+3S, where L is the number of likes, C is the number of comments, and S is the number of shares.

[0043] Specifically, by integrating music and cultural resources from all over the country and presenting them to students in various forms, while providing interactive learning activities, the diverse music and cultural resources can be vividly presented to students, stimulating their interest in learning and enhancing their cognition and understanding of different music cultures; by conducting initial tests on students, analyzing their learning goals and learning style preferences, and using machine learning algorithms to develop learning paths, the learning content can be divided into different stages according to the characteristics of the students, and appropriate courses, exercises and assessment methods can be matched for each stage, so as to develop personalized, scientific and reasonable learning paths for students, implement teaching in accordance with their aptitude, and improve students' learning efficiency and enthusiasm.

[0044] By showing examples of the integration of music and art forms, and establishing a cross-domain thinking model by constructing a color-emotion association matrix, for dance and music, by analyzing the rhythm, strength of dance movements and the fit with music beats and emotions, students can intuitively feel the commonalities of different art forms, thereby helping students to establish a cross-domain thinking model, broaden their artistic vision and innovative thinking, and achieve deep integration and inspiration of knowledge across art fields, thus solving the problem that students find it difficult to understand the relationship between music and other art forms and lack cross-domain thinking; by providing an online community, it provides students with a space for interactive communication, promotes music communication and cooperation among students, realizes the transformation of students' music learning from individual to group, and creates a good learning atmosphere.

[0045] Management module: used to store the data generated by each module and define different operation permissions; the management module includes a data management unit, a permission management unit, and a monitoring and maintenance unit. The data management unit is used to store the data generated by each module and perform data backup through incremental backup and full backup strategies. The permission management unit is used to clarify the user's role and define different operation permissions for each role. The user's operation is made to comply with the scope of its permission through the permission verification formula, and permission adjustment and audit functions are provided. The monitoring and maintenance unit is used to monitor the operating status of each module in real time.

[0046] Specifically, by using MySQL database to store the data generated by each module, corresponding data table structures are created for different types of data, including student information, teacher information, teaching materials, evaluation data, etc. At the same time, user role tables and permission tables are set up in the database to define roles such as students, teachers, administrators, and their corresponding operating permissions. The permission verification logic is used to ensure that user operations comply with their role permissions. When the user performs an operation, the system queries and verifies in the permission table based on the user role and operation type, thereby achieving orderly data storage and precise management of user operating permissions.

[0047] A multifunctional digital music teaching method comprises the following steps:

[0048] Teaching: The course teaching unit teaches students basic music theory knowledge through multimedia resources, and provides interactive exercises, and provides instant feedback and learning suggestions based on the answers. The performance training unit then provides repertoire exercises of different styles and difficulty levels based on current performance level, learning goals and past learning records;

[0049] Creation: The virtual arrangement unit provides a variety of virtual instruments to simulate instrument performance, and the inspiration material unit provides creative inspiration tools and generates different note sequences and chord progressions through random algorithms to provide inspiration for creation. At the same time, music materials are retrieved and called according to the needs of creation;

[0050] Evaluation: The multimodal acquisition unit uses sensors and cameras to collect multi-source data from different modes during the performance skill training or creation process. The posture and action analysis unit then analyzes the collected multi-source data and combines deep learning and image processing technology to identify the performance posture and action, determine whether it meets the standards, and analyze and prompt incorrect postures and actions. The performance evaluation unit then evaluates the performance, the mastery and innovation of the performance style, and locates and analyzes the errors in the performance process, and provides improvement suggestions;

[0051] Extension: The music resource unit integrates music and cultural resources from all over the world and presents them to students in various forms, while providing interactive learning activities. The learning path planning unit then conducts initial tests on students, analyzes their learning goals and learning style preferences, and uses machine learning algorithms to develop learning paths. The thinking guidance unit then demonstrates examples of the integration of music and art forms, and establishes a cross-domain thinking model by building a color-emotion association matrix. The music community exchange unit provides an online community.

[0052] Management: The data management unit stores the data generated by each module and backs up the data through incremental backup and full backup strategies. The permission management unit clarifies the user's role and defines different operation permissions for each role. The permission verification formula ensures that the user's operation is within the scope of his or her permission. At the same time, it provides permission adjustment and audit functions. The monitoring and maintenance unit monitors the operating status of each module in real time.

[0053] The present invention is not limited to the above-mentioned embodiments. On the basis of the technical solution disclosed in the present invention, technicians in this field can make some substitutions and deformations to some technical features therein according to the disclosed technical content without creative labor, and these substitutions and deformations are all within the protection scope of the present invention.

Claims

1. A multifunctional digital music teaching system, characterized in that: include: Teaching module: used to provide music teaching courses and performance skills training, while providing guidance and feedback based on learning progress and performance; Creation module: used to provide the tools and resources required for music creation, assist in the creation of music works, and provide creative inspiration tools and music materials; Evaluation module: used to collect multi-source data during performance skill training, combine deep learning and image processing technology to identify performance postures and movements, and conduct analysis and evaluation; Extension module: used to guide students to explore the relationship between music and other art forms, plan personalized learning paths, and provide a platform for interactive communication; Management module: used to store the data generated by each module and define different operation permissions.

2. A multifunctional digital music teaching system according to claim 1, characterized in that: The teaching module includes a course teaching unit and a performance training unit. The course teaching unit is used to teach students basic music theory knowledge through multimedia resources, and at the same time provides interactive exercises and provides instant feedback and learning suggestions based on the answers. The basic music theory knowledge includes notes, beats, scales, and chords. The performance training unit is used to provide repertoire exercises of different styles and difficulty levels based on current performance level, learning goals, and past learning records.

3. A multifunctional digital music teaching system according to claim 1, characterized in that: The creation module includes a virtual arrangement unit and an inspiration material unit. The virtual arrangement unit is used to provide a variety of virtual musical instruments for simulating musical instrument performances. The inspiration material unit is used to provide creative inspiration tools and generate different note sequences and chord progressions through random algorithms to provide a source of inspiration for creation. At the same time, it provides music materials for retrieval and calling according to creation needs. The creative inspiration tools include a random note generator and a chord progression recommender.

4. A multifunctional digital music teaching system according to claim 1, characterized in that: The evaluation module includes a multimodal acquisition unit, a posture and motion analysis unit, and a performance evaluation unit. The multimodal acquisition unit is used to use sensors and cameras to collect multi-source data in the performance skill training or creation process from different modalities. The sensors include heart rate sensors and skin electrical response sensors. The multi-source data includes physiological data, motion data, and performance videos. The posture and motion analysis unit is used to analyze the collected multi-source data, combine deep learning and image processing technology, identify the performance posture and motion, determine whether it meets the standards, and analyze and prompt incorrect postures and motions. The performance evaluation unit is used to evaluate the performance, the mastery and innovation of the performance style, and at the same time locate and analyze errors in the performance process and provide improvement suggestions.

5. A multifunctional digital music teaching system according to claim 1, characterized in that: The performance evaluation unit includes an expressiveness evaluation subunit, a creativity evaluation subunit, and a music comprehension evaluation subunit. The expressiveness evaluation subunit is used to evaluate the students' expressiveness level in various aspects of the performance process by analyzing the students' physiological data and performance videos during the performance, combined with audio data, and using a deep learning model. The physiological data includes heart rate variability, and the formula is used. where RR i is the time interval between adjacent heartbeats, is the average heartbeat interval, N is the total number of heartbeats, and the various aspects include emotional expression, timbre control, and stage performance. The creativity evaluation subunit is used to perform cross-modal analysis on the works, including feature extraction and analysis of works that integrate painting and literary elements. Through natural language processing and image recognition technologies such as sentiment analysis and keyword extraction, the degree of innovation of the works in terms of creativity and cultural elements is evaluated, and the operation sequence in the students' creative process is mined. Through the Apriori algorithm, the support Analyze the coherence of students' creative ideas and innovative ideas. The music comprehension assessment subunit is used to collect EEG data of students when listening to music with the help of EEG monitoring equipment, extract EEG features through signal processing and analysis technology, and combine with music knowledge graph to evaluate students' mastery and understanding of music knowledge, including understanding of music theory, culture, and history. At the same time, use machine learning algorithms to comprehensively analyze the level of expressiveness, degree of innovation, coherence of creative ideas, innovative ideas, and mastery and understanding of music knowledge to provide students with music comprehension ability assessment and learning suggestions.

6. A multifunctional digital music teaching system according to claim 1, characterized in that: The expansion module includes a music resource unit, a learning path planning unit, a thinking guidance unit, and a music community communication unit. The music resource unit is used to integrate music and cultural resources from various places, present them to students in various forms, and provide interactive learning activities. The music and cultural resources from various places include traditional music works from different countries and regions, introductions to music genres, and the historical development of music. The various forms include audio, video, and text. The learning activities include music style identification and cultural knowledge questions and answers. The learning path planning unit is used to conduct initial tests on students, analyze learning goals and learning style preferences, and use machine learning algorithms to develop learning paths. The thinking guidance unit is used to establish a cross-domain thinking model by showing cases of the integration of music and art forms, and by constructing a color-emotion association matrix. The art forms include painting, dance, and film. The music community communication unit is used to provide an online community, and the popularity of posts is calculated by Popularity=L+2C+3S, where L is the number of likes, C is the number of comments, and S is the number of shares.

7. A multifunctional digital music teaching system according to claim 1, characterized in that: The management module includes a data management unit, a permission management unit, and a monitoring and maintenance unit. The data management unit is used to store the data generated by each module and perform data backup through incremental backup and full backup strategies. The permission management unit is used to clarify the user's role and define different operation permissions for each role. The user's operation is made to comply with the scope of his or her permission through the permission verification formula, and permission adjustment and audit functions are provided. The monitoring and maintenance unit is used to monitor the operating status of each module in real time.

8. A multifunctional digital music teaching method, characterized in that: A multifunctional digital music teaching system applied to any one of claims 1 to 7, comprising the following steps: Teaching: The course teaching unit teaches students basic music theory knowledge through multimedia resources, and provides interactive exercises, and provides instant feedback and learning suggestions based on the answers. The performance training unit then provides repertoire exercises of different styles and difficulty levels based on current performance level, learning goals and past learning records; Creation: The virtual arrangement unit provides a variety of virtual instruments to simulate instrument performance, and the inspiration material unit provides creative inspiration tools and generates different note sequences and chord progressions through random algorithms to provide inspiration for creation. At the same time, music materials are retrieved and called according to the needs of creation; Evaluation: The multimodal acquisition unit uses sensors and cameras to collect multi-source data from different modes during the performance skill training or creation process. The posture and action analysis unit then analyzes the collected multi-source data and combines deep learning and image processing technology to identify the performance posture and action, determine whether it meets the standards, and analyze and prompt incorrect postures and actions. The performance evaluation unit then evaluates the performance, the mastery and innovation of the performance style, and locates and analyzes the errors in the performance process, and provides improvement suggestions; Extension: The music resource unit integrates music and cultural resources from all over the world and presents them to students in various forms, while providing interactive learning activities. The learning path planning unit then conducts initial tests on students, analyzes their learning goals and learning style preferences, and uses machine learning algorithms to develop learning paths. The thinking guidance unit then demonstrates examples of the integration of music and art forms, and establishes a cross-domain thinking model by building a color-emotion association matrix. The music community exchange unit provides an online community. Management: The data management unit stores the data generated by each module and backs up the data through incremental backup and full backup strategies. The permission management unit clarifies the user's role and defines different operation permissions for each role. The permission verification formula ensures that the user's operation is within the scope of his or her permission. At the same time, it provides permission adjustment and audit functions. The monitoring and maintenance unit monitors the operating status of each module in real time.

Images