Wind instrument and matched device, equipment and medium thereof
By combining airflow sensors and audio acquisition devices, the airflow and audio data in wind instruments are analyzed, solving the problem of low accuracy in lung capacity detection and enabling precise assessment of breath in musical expression and comprehensive analysis of performance quality.
Patent Information
- Application Number
- CN202511673396.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-14
- Publication Date
- 2026-02-24
AI Technical Summary
Existing wind instruments have low accuracy in lung capacity testing and cannot deeply integrate breath data with musical expression, resulting in an inability to accurately reflect the actual efficiency and effectiveness of breath in musical expression.
By combining airflow sensors and audio acquisition devices, airflow parameters and performance audio data are detected in real time. By analyzing beat points, peak and valley values and segmented processing, lung capacity indicators and performance intensity weights are calculated to achieve weighted summation.
It improves the accuracy of lung capacity testing, enabling it to more accurately reflect the actual efficiency and effectiveness of breath in musical expression and provide a comprehensive assessment of performance quality.
Smart Images
Figure CN121549802A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data analysis technology, and in particular to a wind instrument and its supporting devices, equipment and media. Background Technology
[0002] In traditional instrumental performance teaching and health monitoring, the assessment of a performer's lung capacity and breath control ability typically relies on independent and separate measurement methods. On the one hand, some existing technologies use airflow sensor-based monitoring devices that can measure basic physical parameters such as airflow velocity and pressure during playing and attempt to estimate airflow based on these parameters. However, these methods often have significant limitations: their measurement process is disconnected from the musical content itself, failing to deeply integrate breath data with specific musical expressions (such as rhythm, phrasing, and performance intensity). This results in the calculated lung capacity index being merely a physical total, unable to accurately reflect the actual efficiency and effectiveness of breath in musical expression, leading to difficulties in achieving sufficient calculation accuracy. For example, it cannot distinguish between effective airflow used to produce stable sustained notes and airflow wasted due to improper control. On the other hand, while existing audio analysis techniques can extract information such as rhythm, note onset, and intensity changes from performance recordings, these analyses are usually independent of physiological parameters and cannot directly serve as a quantitative assessment and optimization guide for a performer's breathing techniques. Summary of the Invention
[0003] This invention provides a wind instrument and its supporting device, computer equipment and medium to solve the problem of low detection accuracy of existing wind instruments used for lung capacity testing on the market.
[0004] In a first aspect, a wind instrument is provided, characterized in that the wind instrument comprises: Memory is used to store computer programs that can be accessed and executed by the processor. An audio acquisition device is used to collect audio data of a user playing the wind instrument. An airflow sensor is installed in the airflow channel of the wind instrument to detect preset type airflow parameters of the airflow flowing through the airflow channel. The preset type airflow parameters refer to the airflow parameters corresponding to each detection time point. The airflow parameters include pressure, temperature and velocity. A processor, communicatively connected to the audio acquisition unit, the airflow sensor, and the memory, is used to invoke and execute the computer program to perform the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the performance intensity weight set to obtain the final lung capacity parameter. Secondly, a lung capacity detection device is provided, comprising: The data acquisition module uses the airflow sensor to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and uses the audio collector to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data collection of the audio collector work synchronously. The peak-valley value recognition module is used to analyze the beat points played by the user based on the performance audio data, obtain beat point sequence data, identify multiple peaks and multiple valleys in the performance audio data, and obtain peak-valley value sequence. The data segmentation module is used to segment the preset type of airflow parameters according to the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. The index calculation module is used to calculate the vital capacity index of each group of airflow parameters in the segmented airflow parameter set, so as to obtain the vital capacity index set. The weighted summation module is used to calculate the performance intensity weight of each group of airflow parameters in the segmented airflow parameter set according to the peak-valley value sequence, to obtain the performance intensity weight set, and to perform weighted summation on the lung capacity index set according to the performance intensity weight set to obtain the final lung capacity parameter.
[0005] Thirdly, a computer device is provided for use with a wind instrument, the wind instrument including an audio acquisition device and an airflow sensor, characterized in that the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the steps to be executed when the computer program stored in the processor of the wind instrument is invoked.
[0006] Fourthly, a computer-readable storage medium is provided for use with a wind instrument, the wind instrument including an audio acquisition device and an airflow sensor, characterized in that the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps to be executed when the computer program stored in the processor of the wind instrument is invoked.
[0007] The aforementioned wind instrument and its associated devices, computer equipment, and storage medium enable the use of sensors embedded in the wind instrument to acquire preset airflow parameters and audio data from a user's performance. Based on the audio data, the beat points of the user's playing are analyzed to obtain a beat point sequence. Multiple peaks and troughs in the audio data are identified to obtain a peak-trough value sequence. The preset airflow parameters are segmented according to the beat point sequence and the peak-trough value sequence to obtain a set of segmented airflow parameters. The vital capacity index for each group of airflow parameters in the segmented airflow parameter set is calculated to obtain a set of vital capacity indicators. The performance intensity weight for each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-trough value sequence to obtain a set of performance intensity weights. Finally, the set of vital capacity indicators is weighted and summed according to the performance intensity weights to obtain the final vital capacity parameter. This improves the accuracy of vital capacity detection. Attached Figure Description
[0008] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0009] Figure 1 This is a flowchart illustrating the execution steps of a computer program stored in a processor of a wind instrument when it is invoked, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a lung capacity detection device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a wind instrument according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a computer device used in conjunction with a wind instrument, according to one embodiment of the present invention. Detailed Implementation
[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0011] Please see Figure 3 The diagram shown is a structural schematic of a wind instrument provided in this embodiment, including a processor 10, a memory 20, an airflow sensor 30, and an audio acquisition unit 40.
[0012] It should be noted that the wind instruments mentioned refer to instruments equipped with airflow channels that can produce sound when played by the user, such as electric wind instruments, melodicas, harmonicas, suonas, flutes, saxophones, oboes, bassoons, piccolo, cornets, tubas and trumpets, French horns, xiao, sheng, hulusi, and other Chinese and Western wind instruments, which will not be elaborated here.
[0013] This invention provides a wind instrument, characterized in that the wind instrument comprises: Memory is used to store computer programs that can be accessed and executed by the processor. An audio acquisition device is used to collect audio data of a user playing the wind instrument. An airflow sensor is installed in the airflow channel of the wind instrument to detect preset type airflow parameters of the airflow flowing through the airflow channel. The preset type airflow parameters refer to the airflow parameters corresponding to each detection time point. The airflow parameters include pressure, temperature and velocity. A processor, communicatively connected to the audio acquisition unit, the airflow sensor, and the memory, is used to invoke and execute the computer program to perform the following steps: Please see Figure 1 The diagram shown illustrates the execution steps of a computer program stored in a processor in a wind instrument when it is invoked, according to this embodiment.
[0014] S1. The airflow sensor is used to detect the preset type of airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the performance audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously.
[0015] In this embodiment of the invention, the preset type of airflow parameters includes airflow velocity data and air pressure data.
[0016] In this embodiment of the invention, the sensors include a pressure sensor and an airflow sensor, which are embedded in the mouthpiece or airflow channel of the instrument to monitor the airflow characteristics during real-time playing. Simultaneously, audio data is collected via a built-in microphone or contact microphone. Before playing, the user can select an operating mode via buttons on the instrument, a mobile application, or a graphical interface, including a playing-only mode or a lung capacity simultaneous detection mode. The system adjusts the sensor activation status and data processing flow according to the user's selection to optimize energy consumption and functionality.
[0017] In this embodiment of the invention, the audio acquisition device may be a pickup, microphone, or any other suitable audio acquisition unit.
[0018] In this embodiment of the invention, the airflow sensor is installed in the airflow channel of the wind instrument to detect airflow parameters, including pressure, temperature and speed, in real time or at regular intervals. These parameters are collected synchronously with the audio acquisition device to provide basic data for subsequent processing.
[0019] In this embodiment of the invention, the user selects an operating mode via a physical button, touchscreen, or accompanying application. For example, there is a playing-only mode: the system only activates the audio sensor to collect performance audio data, while simultaneously turning off or reducing the sampling rate of the airflow sensor (e.g., entering a low-power sleep state), and does not perform lung capacity-related calculations. This mode is suitable for ordinary practice or performance, significantly reducing instrument power consumption and extending battery standby time. Another mode is the lung capacity simultaneous detection mode: the system simultaneously activates the airflow sensor and audio sensor, collecting preset types of airflow parameters (including airflow velocity data and air pressure data) and performance audio data in full-function mode, and performing all subsequent processing steps. This mode is suitable for training or health monitoring scenarios.
[0020] In this embodiment of the invention, before data acquisition, the system automatically executes a sensor calibration procedure, including zero-point calibration (eliminating ambient air pressure deviation) and sensitivity calibration (adjusting the slope using a standard air source) to improve data accuracy.
[0021] S2. Analyze the beat points of the user's performance based on the performance audio data to obtain beat point sequence data.
[0022] In this embodiment of the invention, the step of analyzing the beat points of the user's performance based on the performance audio data to obtain beat point sequence data includes: The performance audio data is subjected to amplitude normalization and frame segmentation to obtain preprocessed audio data. Extract the time-domain features, frequency-domain features, and time-frequency-domain features from the preprocessed audio data to obtain a multi-dimensional feature vector matrix; Based on the multidimensional feature vector matrix, the onset point, spectral abruptness point and phase discontinuity point in the preprocessed audio data are detected to obtain a list of transient point time positions; Based on the list of transient point time positions, rhythm periodicity analysis is performed to obtain the basic beat period value and the theoretical beat time grid. Align the list of transient point time locations with the theoretical beat time grid to obtain an aligned relational mapping table; Based on the aligned relational mapping table, candidate beat points in the theoretical beat time grid are found to obtain a sequence of candidate beat points. Calculate the consistency between the time interval of each beat point in the candidate beat point sequence and the beat points before and after it to obtain a consistency score set; The valid beat points in the candidate beat point sequence are selected based on the consistency score set to obtain beat point sequence data.
[0023] In detail, the amplitude normalization and frame segmentation of the performance audio data are performed to obtain preprocessed audio data. Amplitude normalization unifies audio at different volume levels to the same amplitude range, eliminating the influence of differences in recording conditions. Frame segmentation divides the continuous audio signal into short time periods for analysis, transforming the non-stationary audio signal into multiple short-term stationary signal segments.
[0024] In detail, the extraction of time-domain features, frequency-domain features, and time-frequency-domain features from the preprocessed audio data to obtain a multidimensional feature vector matrix involves extracting time-domain features (such as short-time energy, zero-crossing rate, and amplitude envelope slope), frequency-domain features (such as spectral centroid, spectral roll-off point, and frequency band energy distribution obtained through fast Fourier transform), and time-frequency-domain features (such as Mel frequency cepstral coefficients calculated through short-time Fourier transform and Mel filter bank) from each frame of the preprocessed audio data. Finally, these feature values are combined into a multidimensional feature vector corresponding to each frame, and the feature vectors of all frames are arranged in order to form a multidimensional feature vector matrix.
[0025] In detail, the step of detecting the onset point, spectral abrupt change point, and phase discontinuity point in the preprocessed audio data based on the multidimensional feature vector matrix to obtain a transient point time position list is achieved by analyzing the multidimensional feature vector matrix. First, the onset point is detected by the sharp rise of time-domain features (such as short-time energy and amplitude envelope slope), corresponding to the start time of the note. Second, spectral abrupt change points are identified based on the sudden changes in frequency-domain features (such as spectral flux and harmonic energy distribution), reflecting jumps in timbre or pitch. At the same time, phase discontinuity is analyzed by time-frequency domain features (such as instantaneous phase difference or group delay) to capture signal phase jump events. Finally, the results of these three types of detection are combined, duplicates are removed, and points with similar times are merged to generate a timestamp list containing all significant transient events, i.e., the transient point time position list.
[0026] In detail, the step of performing rhythmic periodicity analysis based on the list of transient point time positions to obtain the basic beat cycle value and the theoretical beat time grid is achieved by calculating the time interval sequence between adjacent transient points, and then using statistical methods (such as histograms or cluster analysis) to find the time interval with the highest frequency as the basic beat cycle value; then, starting from the first transient point, expanding at equal intervals according to the basic beat cycle value, a theoretical beat time grid covering the entire audio duration is generated, which represents an idealized uniform rhythmic framework.
[0027] In detail, the step of finding candidate beat points in the theoretical beat time grid according to the aligned relational mapping table to obtain a candidate beat point sequence involves searching for the corresponding actual transient point within the time window specified in the mapping table for each beat position in the theoretical beat time grid. By comparing the time deviation and confidence level of these transient points with the theoretical beat, the best-matching transient point is selected as a candidate beat point. If there is no corresponding transient point for a certain theoretical position, interpolation is performed based on adjacent beat points to complete the sequence. Finally, all candidate points are arranged in chronological order to form a candidate beat point sequence.
[0028] In detail, the consistency score set is obtained by calculating the consistency of the time interval between each beat point in the candidate beat point sequence and the beat points before and after it. This is done by calculating the time interval between each beat point (excluding the first and last beat points) and the previous beat point (forward interval) and the time interval between each beat point and the next beat point (backward interval). Then, with the basic beat period value as a reference, the consistency is evaluated by comparing the deviation (such as absolute difference or relative error) between the forward and backward intervals and the basic period.
[0029] In detail, the step of filtering valid beat points in the candidate beat point sequence based on the consistency score set to obtain beat point sequence data refers to filtering beat points in the candidate beat point sequence whose consistency score is greater than a preset threshold.
[0030] S3. Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence.
[0031] In this embodiment of the invention, the step of identifying multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence is achieved by detecting local maxima and minima using a sliding window to identify the peaks and valleys in multiple audio signals.
[0032] S4. Based on the beat point sequence data and the peak-valley value sequence, the preset type of airflow parameters are segmented to obtain a set of segmented airflow parameters.
[0033] In this embodiment of the invention, the step of segmenting the preset type of airflow parameters according to the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set includes: After aligning the beat point sequence data and the peak-valley value sequence with the preset type of airflow parameters in a multi-dimensional time series and combining them, a time-aligned multimodal data matrix is obtained. Perform joint beat intensity segmentation point detection on the time-aligned multimodal data matrix to obtain a candidate segmentation point list; Based on the peak-valley value sequence, the intensity change pattern of the audio data is identified, and the beat point density of the beat point sequence data is identified; Based on the intensity change pattern and the beat point density, identify the music segment boundary points of the candidate segment point list to obtain a segment boundary point sequence; Based on the segmented boundary point sequence, the preset type of airflow parameters are processed in a multi-scale segmentation to obtain a segmented airflow parameter set.
[0034] In detail, the step of aligning and combining the beat point sequence data and the peak-valley value sequence with the preset type of airflow parameters in a multi-dimensional time series to obtain a time-aligned multimodal data matrix involves timestamp matching of the three data streams, using cubic spline interpolation to unify data with different sampling rates onto the time axis of the highest sampling rate; then, a dynamic time warping algorithm is used to solve the time offset problem caused by playing free rhythms; finally, the aligned beat markers, intensity values, and airflow parameters are combined into a multi-column data matrix according to time points.
[0035] In detail, the step of performing joint beat intensity segmentation point detection on the time-aligned multimodal data matrix to obtain a candidate segmentation point list is achieved by identifying the overlapping positions of beat points and intensity peaks and valleys, which have the highest segmentation priority; then, analyzing the density variation regions of beat points and detecting auxiliary segmentation points at density abrupt changes; simultaneously considering stable segments with continuous intensity changes, adding segmentation points at positions where the intensity gradient change exceeds a threshold; finally, verifying the local significance of each candidate point through a sliding window to generate a candidate segmentation point list with confidence scores.
[0036] In detail, the step of identifying the intensity change pattern of the audio data based on the peak-valley value sequence and identifying the beat density of the beat density sequence data involves extracting the intensity change pattern from the peak-valley value sequence, using a sliding window to calculate the intensity mean, variance, and gradient features, and identifying patterns such as stable intensity segments, gradually increasing and decreasing intensity segments, and abrupt change segments. Simultaneously, the beat density sequence is analyzed, and the beat density is calculated through time interval statistics and cluster analysis to identify segments with uniform density, sparse density, and dense density. These two patterns are then correlated to establish an intensity-beat density correspondence model, providing feature basis for segment boundary identification.
[0037] In detail, the step of identifying music segment boundary points from the candidate segmentation point list based on the intensity change pattern and the beat density to obtain a segmentation boundary point sequence uses rule-based and machine learning methods to identify music segment boundaries. First, obvious boundary points are determined based on abrupt changes in intensity and beat density changes; then, the transition probability of the feature sequence is analyzed using a Hidden Markov Model to identify potential boundaries that conform to the music's development logic; finally, contextual consistency checks are performed on the boundary points to ensure that each boundary point has maximum feature difference within a certain time range before and after, generating a segmentation boundary point sequence that conforms to the music structure.
[0038] In detail, the step of performing multi-scale segmentation processing on the preset type of airflow parameters based on the segmentation boundary point sequence to obtain a segmented airflow parameter set employs a multi-scale segmentation strategy, dynamically adjusting the segmentation granularity according to the complexity of the music. Larger segmentation scales are used for sections with regular rhythms and stable intensity; finer segmentation is used for sections with complex rhythms and varying intensity. Transition buffers are set at the start and end boundaries of each segment to avoid hard cutting at key points of change in the airflow data.
[0039] S5. Calculate the vital capacity index of each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set.
[0040] In this embodiment of the invention, calculating the vital capacity index of each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set includes: Calculate the airflow rate for each set of airflow parameters in the segmented airflow parameter set; Calculate the effectiveness coefficient of each group of airflow parameters in the segmented airflow parameter set; The product of airflow rate and effectiveness coefficient for each group of airflow parameters in the segmented airflow parameter set is calculated to obtain the vital capacity index for each group of airflow parameters.
[0041] In detail, the calculation of the airflow rate of each group of airflow parameters in the segmented airflow parameter set is to first integrate the airflow velocity data over time and then dynamically correct it in combination with the air pressure data.
[0042] In detail, the calculation of the effectiveness coefficient of each group of airflow parameters in the segmented airflow parameter set is achieved by analyzing the stability of the airflow velocity within each segment (by calculating the standard deviation and coefficient of variation), and simultaneously evaluating the stability of the air pressure control (by observing the pressure fluctuation range and frequency). Then, combined with the sound quality characteristics of the corresponding audio segment (such as harmonic distortion, signal-to-noise ratio, etc.), an airflow-audio efficiency mapping model is established. Finally, through a multi-factor weighted fusion algorithm, the airflow stability index (weight 0.4), air pressure control quality (weight 0.3), and sound energy conversion efficiency (weight 0.3) are comprehensively calculated to generate an effectiveness coefficient in the range of 0-1. The higher the coefficient, the better the airflow utilization efficiency.
[0043] In this embodiment of the invention, calculating the airflow rate of each set of airflow parameters in the segmented airflow parameter set includes: The basic airflow rate of each set of airflow parameters is calculated based on the airflow velocity data and air pressure data contained in the preset type of airflow parameters, and a basic airflow rate set is obtained. Based on the air pressure data, obtain the air pressure corresponding to each group of airflow parameters in the segmented airflow parameter set to obtain the segmented air pressure set; Calculate the difference between the segmented air pressure in each segmented air pressure set and the preset reference air pressure to obtain the air pressure difference value; The ratio of the pressure difference to the reference pressure is calculated and added to a preset pressure sensitivity coefficient to obtain a correction term; The correction term is calculated and the sum of the preset first constant is used to obtain the correction coefficient for each group of airflow parameters in the segmented airflow parameter set; Calculate the product of each group of airflow in the basic airflow set and the correction coefficient to obtain the corrected airflow for each group of airflow parameters in the segmented airflow parameter set; The sound energy conversion weighting of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set is performed based on the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set.
[0044] In detail, the calculation of the basic airflow rate of each set of airflow parameters based on the airflow velocity data and air pressure data contained in the preset type of airflow parameters, and the resulting basic airflow rate set, is achieved by calculating the integral of the airflow velocity with respect to time in each segment using a numerical integration method. That is, the product of the airflow velocity values of all sampling points in the segment and the corresponding time interval is accumulated and summed to obtain the uncorrected basic airflow rate value. This process is essentially the calculation of the original gas volume passing through the musical instrument.
[0045] In detail, the preset reference pressure may refer to one standard atmosphere.
[0046] Specifically, the preset pressure sensitivity coefficient can be 0.2.
[0047] Specifically, the preset first constant can be 1.
[0048] In detail, the step of weighting the acoustic energy conversion of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set according to the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set is based on the efficiency of airflow conversion into acoustic energy in each segment by analyzing the audio data, and finally obtaining an effective airflow rate index that takes into account both physical characteristics and acoustic efficiency.
[0049] In this embodiment of the invention, the step of weighting the acoustic energy conversion of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set based on the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set includes: The audio intensity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained based on the audio data. The airflow velocity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained according to the preset type of airflow parameters; The airflow velocity corresponding to each set of airflow parameters is multiplied sequentially by the preset air density scalar and the preset sound speed scalar to obtain the product term; The sound energy efficiency factor of each set of airflow parameters is obtained by dividing the audio intensity corresponding to each set of airflow parameters by the product term. Calculate the ratio of the acoustic energy efficiency factor to the preset reference efficiency threshold to obtain the efficiency ratio; Calculate the product of the corrected airflow rate and the efficiency ratio for each group of airflow parameters in the segmented airflow parameter set to obtain the flow rate for each group of airflow parameters in the segmented airflow parameter set.
[0050] In detail, the audio intensity corresponding to each set of airflow parameters in the segmented airflow parameter set is obtained based on the audio data. For each segment of audio data, the audio intensity is quantified by calculating the root mean square value of the audio signal. Specifically, the sliding window analysis technique is used to extract the squared average value of the audio amplitude within the segment time, thereby obtaining a numerical index representing the overall sound intensity of the segment.
[0051] Specifically, the preset air density scalar can be 1.225, and the preset sound speed scalar can be 340.
[0052] In this embodiment of the invention, the basic airflow rate after pressure correction is multiplied by the standardized efficiency ratio to achieve sound energy efficiency weighting of airflow. The final airflow rate value not only reflects the physical gas volume, but also reflects the actual utility value of these gases in musical expression, thus completing the transformation from "physical air volume" to "effective air volume".
[0053] S6. Calculate the performance intensity weight of each group of airflow parameters in the segmented airflow parameter set according to the peak-valley value sequence, and obtain the performance intensity weight set.
[0054] In this embodiment of the invention, the step of calculating the performance intensity weight of each group of airflow parameters in the segmented airflow parameter set based on the peak-valley value sequence to obtain the performance intensity weight set is achieved by extracting peak-valley value data within the corresponding time window of each segment, calculating the intensity characteristics of that segment (such as peak average, peak-valley difference, or intensity fluctuation rate) to quantify the dynamic changes in performance; then, these intensity characteristics are normalized and mapped to a preset weight range (such as 0.5 to 1.5), where high-intensity segments receive higher weights (reflecting greater breath demand) and low-intensity segments receive lower weights; finally, specific performance intensity weights are assigned to each segment based on the normalization results, forming a weight set corresponding to the segmented airflow parameter set, which is used for subsequent weighted calculation of vital capacity indicators.
[0055] S7. The lung capacity index set is weighted and summed according to the performance intensity weight set to obtain the final lung capacity parameter.
[0056] In this embodiment of the invention, after performing a weighted summation of the lung capacity index set based on the performance intensity weight set to obtain the final lung capacity parameter, the method further includes: The audio data is segmented based on the timestamps of the segmented airflow parameter set to obtain a segmented audio set. Based on the segmented airflow parameter set and the segmented audio set, a synergistic matrix containing breath features and musical features is constructed for each segment to obtain the segmented feature matrix; Based on the pre-acquired music structure information, the segmented feature matrix is dynamically and adaptively weighted to obtain the segmented dynamic weight configuration. The breath coordination degree is calculated based on the segmented feature matrix and the segmented dynamic weight configuration. Based on the breath coordination, the segmented feature matrix, and the segmented dynamic weight configuration, the performance quality of each segment of the audio data in the segmented audio set is analyzed to obtain a segmented comprehensive quality score set.
[0057] In detail, the audio data is segmented based on the timestamps of the segmented airflow parameter set to obtain segmented audio sets. First, breath features are extracted from the airflow data of each segment, including vital capacity, airflow stability (by calculating the standard deviation and coefficient of variation of airflow velocity), air pressure control accuracy (air pressure fluctuation range), and airflow efficiency (based on sound energy conversion rate). Simultaneously, musical features are extracted from the audio data of the corresponding segments, including pitch deviation (based on fundamental frequency detection), rhythm accuracy (alignment with the beat grid), dynamic range (audio intensity variation), and timbre quality (through spectral centroid and harmonic analysis). Then, these features are standardized to eliminate the influence of dimensions, and principal component analysis (PCA) is used for dimensionality reduction and redundancy removal. Finally, the breath features and musical features are combined into a feature vector for each segment. The feature vectors of all segments together constitute a segmented feature matrix for subsequent collaborative analysis.
[0058] In detail, the step of dynamically and adaptively allocating weights to the segmented feature matrix based on the pre-acquired musical structure information to obtain the segmented dynamic weight configuration is as follows: for technical segments (such as fast scales), the weights of pitch and rhythm are increased; for expressive segments (such as melodic themes), the weights of dynamic control and timbre are enhanced; and for long musical phrases, the weights of breath stability and efficiency are increased.
[0059] In detail, the music structure information is the information contained in the pre-selected performance piece by the user, including musical phrases and sections.
[0060] In detail, the step of calculating breath coordination based on the segmented feature matrix and the segmented dynamic weight configuration first involves weighting the feature matrix based on the dynamic weights to highlight the key features of the current musical segment; then, the temporal correlation between the breath feature sequence (such as changes in vital capacity and airflow stability) and the musical feature sequence (such as dynamic changes and rhythmic patterns) is calculated, and a dynamic time warping algorithm is used to solve the temporal alignment problem caused by playing free rhythms; finally, a coordination score in the range of 0-1 is generated by combining linear correlation analysis (Pearson coefficient) and nonlinear correlation analysis (mutual information entropy).
[0061] In detail, the analysis of the performance quality of each segment of audio data in the segmented audio set based on breath coordination, the segmented feature matrix, and the segmented dynamic weight configuration to obtain a segmented comprehensive quality score set can be obtained through weighted fusion.
[0062] As can be seen, in the above embodiments, air pressure and airflow sensors embedded in the instrument's mouthpiece or airflow channel collect airflow velocity and air pressure data in real time. Simultaneously, a built-in microphone or contact microphone collects performance audio data. Users can select operating modes, such as a playing-only mode or a lung capacity synchronous detection mode, via physical buttons, a touchscreen, or a companion application to adapt to different scenarios, such as ordinary practice or health monitoring. Before data acquisition, the system automatically performs sensor calibration to improve data accuracy. Subsequently, the system processes the performance audio data, including amplitude normalization and frame preprocessing, extracting time-domain features, frequency-domain features, and time-frequency-domain features to form a multi-dimensional feature vector matrix. It then detects the onset point, spectral abrupt change points, and phase discontinuities to generate a list of transient point time positions. Through rhythmic periodicity analysis, it obtains the basic beat cycle value and theoretical beat time grid, and after alignment and consistency filtering, obtains beat point sequence data. Simultaneously, it identifies multiple peaks and valleys in the audio data to form a peak-valley value sequence. By utilizing beat point sequences and peak-valley value sequences, the system performs multi-dimensional time series alignment and combination of preset airflow parameters to obtain a multimodal data matrix. It then generates segment boundary point sequences through beat intensity joint segment point detection and music segment boundary recognition, followed by multi-scale segmentation processing to obtain a set of segmented airflow parameters. For each segment of airflow data, airflow rate and effectiveness coefficient are calculated and multiplied to obtain a set of vital capacity indicators. Simultaneously, the performance intensity weight for each segment of airflow data is calculated based on the peak-valley value sequence. Finally, the vital capacity parameter is obtained by weighted summation of the vital capacity indicator set using the performance intensity weights. The system can further evaluate performance quality based on segmented data by constructing a coordination matrix using segmented audio and airflow data, dynamically allocating weights according to musical structure information, calculating breath coordination and segmented comprehensive quality scores, thereby comprehensively analyzing playing performance.
[0063] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0064] In one embodiment, a lung capacity detection device is provided for use with a wind instrument, the wind instrument including an audio acquisition unit and an airflow sensor. Figure 2 As shown, the lung capacity detection device includes a data acquisition module 101, a peak-to-trough value identification module 102, a data segmentation module 103, an index calculation module 104, and a weighted summation module 105. Detailed descriptions of each functional module are as follows: The data acquisition module 101 is used to acquire preset type airflow parameters and performance audio data when the user plays the wind instrument using sensors preset in the wind instrument. The peak-valley value identification module 102 is used to analyze the beat points played by the user based on the performance audio data to obtain beat point sequence data, and to identify multiple peaks and multiple valleys in the performance audio data to obtain a peak-valley value sequence. The data segmentation module 103 is used to segment the preset type of airflow parameters according to the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. The index calculation module 104 is used to calculate the vital capacity index of each group of airflow parameters in the segmented airflow parameter set, so as to obtain the vital capacity index set. The weighted summation module 105 is used to calculate the performance intensity weight of each group of airflow parameters in the segmented airflow parameter set according to the peak-valley value sequence, to obtain the performance intensity weight set, and to perform weighted summation on the lung capacity index set according to the performance intensity weight set to obtain the final lung capacity parameter.
[0065] In one embodiment, the peak-valley value recognition module 102, when performing the step point analysis based on the performance audio data to obtain the step point sequence data, is specifically used for: The performance audio data is subjected to amplitude normalization and frame segmentation to obtain preprocessed audio data. Extract the time-domain features, frequency-domain features, and time-frequency-domain features from the preprocessed audio data to obtain a multi-dimensional feature vector matrix; Based on the multidimensional feature vector matrix, the onset point, spectral abruptness point and phase discontinuity point in the preprocessed audio data are detected to obtain a list of transient point time positions; Based on the list of transient point time positions, rhythm periodicity analysis is performed to obtain the basic beat period value and the theoretical beat time grid. Align the list of transient point time locations with the theoretical beat time grid to obtain an aligned relational mapping table; Based on the aligned relational mapping table, candidate beat points in the theoretical beat time grid are found to obtain a sequence of candidate beat points. Calculate the consistency between the time interval of each beat point in the candidate beat point sequence and the beat points before and after it to obtain a consistency score set; The valid beat points in the candidate beat point sequence are selected based on the consistency score set to obtain beat point sequence data.
[0066] In one embodiment, the peak-valley value identification module 102, when performing the segmented processing of the preset type airflow parameters based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set, is specifically used for: After aligning the beat point sequence data and the peak-valley value sequence with the preset type of airflow parameters in a multi-dimensional time series and combining them, a time-aligned multimodal data matrix is obtained. Perform joint beat intensity segmentation point detection on the time-aligned multimodal data matrix to obtain a candidate segmentation point list; Based on the peak-valley value sequence, the intensity change pattern of the audio data is identified, and the beat point density of the beat point sequence data is identified; Based on the intensity change pattern and the beat point density, identify the music segment boundary points of the candidate segment point list to obtain a segment boundary point sequence; Based on the segmented boundary point sequence, the preset type of airflow parameters are processed in a multi-scale segmentation to obtain a segmented airflow parameter set.
[0067] In one embodiment, the index calculation module 104, when performing the calculation of the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set, is specifically used for: Calculate the airflow rate for each set of airflow parameters in the segmented airflow parameter set; Calculate the effectiveness coefficient of each group of airflow parameters in the segmented airflow parameter set; The product of airflow rate and effectiveness coefficient for each group of airflow parameters in the segmented airflow parameter set is calculated to obtain the vital capacity index for each group of airflow parameters.
[0068] In one embodiment, the index calculation module 104, when performing the calculation of the airflow rate of each group of airflow parameters in the segmented airflow parameter set, is specifically used for: The basic airflow rate of each set of airflow parameters is calculated based on the airflow velocity data and air pressure data contained in the preset type of airflow parameters, and a basic airflow rate set is obtained. Based on the air pressure data, obtain the air pressure corresponding to each group of airflow parameters in the segmented airflow parameter set to obtain the segmented air pressure set; Calculate the difference between the segmented air pressure in each segmented air pressure set and the preset reference air pressure to obtain the air pressure difference value; The ratio of the pressure difference to the reference pressure is calculated and added to a preset pressure sensitivity coefficient to obtain a correction term; The correction term is calculated and the sum of the preset first constant is used to obtain the correction coefficient for each group of airflow parameters in the segmented airflow parameter set; Calculate the product of each group of airflow in the basic airflow set and the correction coefficient to obtain the corrected airflow for each group of airflow parameters in the segmented airflow parameter set; The sound energy conversion weighting of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set is performed based on the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set.
[0069] In one embodiment, the index calculation module 104, when performing the sound energy conversion weighting of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set based on the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set, is specifically used for: The audio intensity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained based on the audio data. The airflow velocity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained according to the preset type of airflow parameters; The airflow velocity corresponding to each set of airflow parameters is multiplied sequentially by the preset air density scalar and the preset sound speed scalar to obtain the product term; The sound energy efficiency factor of each set of airflow parameters is obtained by dividing the audio intensity corresponding to each set of airflow parameters by the product term. Calculate the ratio of the acoustic energy efficiency factor to the preset reference efficiency threshold to obtain the efficiency ratio; Calculate the product of the corrected airflow rate and the efficiency ratio for each group of airflow parameters in the segmented airflow parameter set to obtain the flow rate for each group of airflow parameters in the segmented airflow parameter set.
[0070] In one embodiment, after performing the weighted summation of the lung capacity index set according to the performance intensity weight set to obtain the final lung capacity parameter, the weighted summation module 105 is further configured to: The audio data is segmented based on the timestamps of the segmented airflow parameter set to obtain a segmented audio set. Based on the segmented airflow parameter set and the segmented audio set, a synergistic matrix containing breath features and musical features is constructed for each segment to obtain the segmented feature matrix; Based on the pre-acquired music structure information, the segmented feature matrix is dynamically and adaptively weighted to obtain the segmented dynamic weight configuration. The breath coordination degree is calculated based on the segmented feature matrix and the segmented dynamic weight configuration. Based on the breath coordination, the segmented feature matrix, and the segmented dynamic weight configuration, the performance quality of each segment of the audio data in the segmented audio set is analyzed to obtain a segmented comprehensive quality score set.
[0071] This invention provides a lung capacity detection device. It collects airflow velocity and pressure data in real time using air pressure and airflow sensors embedded in the mouthpiece or airflow channel of a musical instrument. Simultaneously, it collects performance audio data via a built-in microphone or contact microphone. Users can select operating modes, such as a playing-only mode or a lung capacity simultaneous detection mode, via physical buttons, a touchscreen, or a companion application, to adapt to different scenarios such as ordinary practice or health monitoring. Before data acquisition, the system automatically performs sensor calibration to improve data accuracy. Subsequently, the system processes the performance audio data, including amplitude normalization and frame preprocessing, extracting time-domain, frequency-domain, and time-frequency-domain features to form a multi-dimensional feature vector matrix. It then detects the onset point, spectral abrupt changes, and phase discontinuities to generate a list of transient point time positions. Through rhythmic periodicity analysis, it obtains the basic beat cycle value and theoretical beat time grid, and after alignment and consistency filtering, obtains beat point sequence data. Simultaneously, it identifies multiple peaks and troughs in the audio data to form a peak-trough sequence. By utilizing beat point sequences and peak-valley value sequences, the system performs multi-dimensional time series alignment and combination of preset airflow parameters to obtain a multimodal data matrix. It then generates segment boundary point sequences through beat intensity joint segment point detection and music segment boundary recognition, followed by multi-scale segmentation processing to obtain a set of segmented airflow parameters. For each segment of airflow data, airflow rate and effectiveness coefficient are calculated and multiplied to obtain a set of vital capacity indicators. Simultaneously, the performance intensity weight for each segment of airflow data is calculated based on the peak-valley value sequence. Finally, the vital capacity parameter is obtained by weighted summation of the vital capacity indicator set using the performance intensity weights. The system can further evaluate performance quality based on segmented data by constructing a coordination matrix using segmented audio and airflow data, dynamically allocating weights according to musical structure information, calculating breath coordination and segmented comprehensive quality scores, thereby comprehensively analyzing playing performance.
[0072] Specific limitations regarding the lung capacity testing device can be found in the above description of the steps executed when the computer program stored in the processor of a wind instrument is invoked; these will not be repeated here. Each module in the aforementioned lung capacity testing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can invoke and execute the operations corresponding to each module.
[0073] In one embodiment, a computer device is provided for use with a wind instrument, the wind instrument including an audio acquisition unit and an airflow sensor, characterized in that the computer device can be a client, and its internal structure diagram can be as follows. Figure 3As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external servers via a network connection.
[0074] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the set of performance intensity weights to obtain the final lung capacity parameter.
[0075] In one embodiment, a computer-readable storage medium is provided for use with a wind instrument, the wind instrument including an audio acquisition unit and an airflow sensor, characterized in that the computer-readable storage medium stores a computer program that, when executed by a processor, performs the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the set of performance intensity weights to obtain the final lung capacity parameter.
[0076] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the aforementioned wind instrument embodiments. To avoid repetition, they will not be described one by one here.
[0077] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes described in the above embodiments. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0079] Finally, it should be noted that if any software tools or components not belonging to this company appear in the embodiments of the application, they are merely illustrative examples and do not represent actual use. The embodiments described above are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A wind instrument, characterized in that, The wind instruments include: Memory is used to store computer programs that can be accessed and executed by the processor. An audio acquisition device is used to collect audio data of a user playing the wind instrument. An airflow sensor is installed in the airflow channel of the wind instrument to detect preset type airflow parameters of the airflow flowing through the airflow channel. The preset type airflow parameters refer to the airflow parameters corresponding to each detection time point. The airflow parameters include pressure, temperature and velocity. A processor, communicatively connected to the audio acquisition unit, the airflow sensor, and the memory, is used to invoke and execute the computer program to perform the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the set of performance intensity weights to obtain the final lung capacity parameter.
2. The wind instrument as described in claim 1, characterized in that, The step of analyzing the beat points of the user's performance based on the performance audio data to obtain beat point sequence data includes: The performance audio data is subjected to amplitude normalization and frame segmentation to obtain preprocessed audio data. Extract the time-domain features, frequency-domain features, and time-frequency-domain features from the preprocessed audio data to obtain a multi-dimensional feature vector matrix; Based on the multidimensional feature vector matrix, the onset point, spectral abruptness point and phase discontinuity point in the preprocessed audio data are detected to obtain a list of transient point time positions; Based on the list of transient point time positions, rhythm periodicity analysis is performed to obtain the basic beat period value and the theoretical beat time grid. Align the list of transient point time locations with the theoretical beat time grid to obtain an aligned relational mapping table; Based on the aligned relational mapping table, candidate beat points in the theoretical beat time grid are found to obtain a sequence of candidate beat points. Calculate the consistency between the time interval of each beat point in the candidate beat point sequence and the beat points before and after it to obtain a consistency score set; The valid beat points in the candidate beat point sequence are selected based on the consistency score set to obtain beat point sequence data.
3. The wind instrument as described in claim 1, characterized in that, The step of segmenting the preset type of airflow parameters according to the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set includes: After aligning the beat point sequence data and the peak-valley value sequence with the preset type of airflow parameters in a multi-dimensional time series and combining them, a time-aligned multimodal data matrix is obtained. Perform joint beat intensity segmentation point detection on the time-aligned multimodal data matrix to obtain a candidate segmentation point list; Based on the peak-valley value sequence, the intensity change pattern of the audio data is identified, and the beat point density of the beat point sequence data is identified; Based on the intensity change pattern and the beat point density, identify the music segment boundary points of the candidate segment point list to obtain a segment boundary point sequence; Based on the segmented boundary point sequence, the preset type of airflow parameters are processed in a multi-scale segmentation to obtain a segmented airflow parameter set.
4. The wind instrument as described in claim 1, characterized in that, The step of calculating the vital capacity index of each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set includes: Calculate the airflow rate for each set of airflow parameters in the segmented airflow parameter set; Calculate the effectiveness coefficient of each group of airflow parameters in the segmented airflow parameter set; The product of airflow rate and effectiveness coefficient for each group of airflow parameters in the segmented airflow parameter set is calculated to obtain the vital capacity index for each group of airflow parameters.
5. The wind instrument as described in claim 4, characterized in that, The step of calculating the airflow rate of each set of airflow parameters in the segmented airflow parameter set includes: The basic airflow rate of each set of airflow parameters is calculated based on the airflow velocity data and air pressure data contained in the preset type of airflow parameters, and a basic airflow rate set is obtained. Based on the air pressure data, obtain the air pressure corresponding to each group of airflow parameters in the segmented airflow parameter set to obtain the segmented air pressure set; Calculate the difference between the segmented air pressure in each segmented air pressure set and the preset reference air pressure to obtain the air pressure difference value; The ratio of the pressure difference to the reference pressure is calculated and added to a preset pressure sensitivity coefficient to obtain a correction term; The correction term is calculated and the sum of the preset first constant is used to obtain the correction coefficient for each group of airflow parameters in the segmented airflow parameter set; Calculate the product of each group of airflow in the basic airflow set and the correction coefficient to obtain the corrected airflow for each group of airflow parameters in the segmented airflow parameter set; The sound energy conversion weighting of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set is performed based on the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set.
6. The wind instrument as described in claim 5, characterized in that, The step of weighting the acoustic energy conversion of the corrected airflow volume of each group of airflow parameters in the segmented airflow parameter set according to the audio data to obtain the airflow rate of each group of airflow parameters in the segmented airflow parameter set includes: The audio intensity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained based on the audio data. The airflow velocity corresponding to each group of airflow parameters in the segmented airflow parameter set is obtained according to the preset type of airflow parameters; The airflow velocity corresponding to each set of airflow parameters is multiplied sequentially by the preset air density scalar and the preset sound speed scalar to obtain the product term; The sound energy efficiency factor of each set of airflow parameters is obtained by dividing the audio intensity corresponding to each set of airflow parameters by the product term. Calculate the ratio of the acoustic energy efficiency factor to the preset reference efficiency threshold to obtain the efficiency ratio; Calculate the product of the corrected airflow rate and the efficiency ratio for each group of airflow parameters in the segmented airflow parameter set to obtain the flow rate for each group of airflow parameters in the segmented airflow parameter set.
7. The wind instrument as described in claim 1, characterized in that, After the step of weighted summation of the lung capacity index set according to the performance intensity weight set to obtain the final lung capacity parameter, the method further includes: The audio data is segmented based on the timestamps of the segmented airflow parameter set to obtain a segmented audio set. Based on the segmented airflow parameter set and the segmented audio set, a synergistic matrix containing breath features and musical features is constructed for each segment to obtain the segmented feature matrix; Based on the pre-acquired music structure information, the segmented feature matrix is dynamically and adaptively weighted to obtain the segmented dynamic weight configuration. The breath coordination degree is calculated based on the segmented feature matrix and the segmented dynamic weight configuration. Based on the breath coordination, the segmented feature matrix, and the segmented dynamic weight configuration, the performance quality of each segment of the audio data in the segmented audio set is analyzed to obtain a segmented comprehensive quality score set.
8. A lung capacity detection device, used in conjunction with a wind instrument, the wind instrument comprising an audio acquisition unit and an airflow sensor, characterized in that, The lung capacity detection device includes: The data acquisition module uses the airflow sensor to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and uses the audio collector to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data collection of the audio collector work synchronously. The peak-valley value recognition module is used to analyze the beat points played by the user based on the performance audio data, obtain beat point sequence data, identify multiple peaks and multiple valleys in the performance audio data, and obtain peak-valley value sequence. The data segmentation module is used to segment the preset type of airflow parameters according to the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. The index calculation module is used to calculate the vital capacity index of each group of airflow parameters in the segmented airflow parameter set, so as to obtain the vital capacity index set. The weighted summation module is used to calculate the performance intensity weight of each group of airflow parameters in the segmented airflow parameter set according to the peak-valley value sequence, to obtain the performance intensity weight set, and to perform weighted summation on the lung capacity index set according to the performance intensity weight set to obtain the final lung capacity parameter.
9. A computer device for use with a wind instrument, the wind instrument comprising an audio acquisition unit and an airflow sensor, characterized in that, The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when invoking and executing the computer program, performs the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the set of performance intensity weights to obtain the final lung capacity parameter.
10. A computer-readable storage medium for use with a wind instrument, the wind instrument comprising an audio acquisition unit and an airflow sensor, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the following steps: The airflow sensor is used to detect preset airflow parameters when the user plays the wind instrument in real time or at regular intervals, and the audio acquisition device is used to collect the audio data of the user playing the wind instrument. The parameter detection of the airflow sensor and the audio data acquisition of the audio acquisition device are carried out synchronously. Based on the performance audio data, the beat points of the user's performance are analyzed to obtain beat point sequence data; Identify multiple peaks and valleys in the performance audio data to obtain a peak-valley value sequence; The preset type of airflow parameters are segmented based on the beat point sequence data and the peak-valley value sequence to obtain a segmented airflow parameter set. Calculate the vital capacity index for each group of airflow parameters in the segmented airflow parameter set to obtain the vital capacity index set; The performance intensity weight of each group of airflow parameters in the segmented airflow parameter set is calculated based on the peak-valley value sequence to obtain the performance intensity weight set; The lung capacity index set is weighted and summed according to the set of performance intensity weights to obtain the final lung capacity parameter.