Music health early warning method and device based on volume and frequency monitoring

Abstract

The invention relates to the field of music health early warning, and discloses a music health early warning method and device based on volume and frequency monitoring, which are used for solving the problems that the distance between a user and equipment and the attenuation degree are dynamically changed, early warning is carried out only according to the volume and frequency played by the equipment, and mistaken touch can be caused. The method comprises the following steps: acquiring a distance between equipment and a user in real time through an infrared sensor, acquiring initial playing volume and initial frequency distribution of the equipment, calculating to obtain initial receiving volume according to the distance between the equipment and the user and the initial playing volume, acquiring environment data in real time, and evaluating to obtain an environment attenuation factor according to the environment data; and the actual receiving volume and the actual receiving frequency distribution are calculated, the health degree is evaluated, and early warning reminding is performed according to the health degree, so that the problem of false touch early warning caused by dynamic change between the user and the equipment is effectively solved, and the accuracy of the early warning device and the user experience are improved.

Description

Technical Field

[0001] The present invention relates to the field of music health warning, and more specifically to a music health warning method and device based on volume and frequency monitoring. Background Art

[0002] With the widespread use of personal electronic devices such as headphones, speakers, and smart speakers, people are frequently exposed to various audio environments in their daily lives. However, prolonged exposure to high volume or specific frequency sounds can cause potential damage to the hearing system and mental health. The volume warning method of the prior art monitors the volume and frequency output by the device. When the volume and frequency played by the device exceed the threshold, it is judged to be harmful to health and an early warning prompt is issued.

[0003] For example, the invention patent announcement with announcement number: CN110148280B discloses an intelligent nursing headset for epilepsy patients and the epilepsy warning method it adopts, including: a control system, a functional unit, a sensing unit, and an output unit. It utilizes the characteristic of auditory hallucinations before an epileptic attack to test the hearing status of the headset wearer, analyze the test result information, determine whether there is a hidden danger of epileptic attack, and issue warning information in time, which is conducive to epileptic patients to take subsequent treatment measures in time, etc., and reduce the safety risks brought to patients by epileptic attacks.

[0004] For example, the invention patent announcement with announcement number: CN106448050B announces a method and system for warning traffic hazards based on vehicle noise using a smart phone, including: a data acquisition module, a feature extraction module, a central processing unit, a background database, a control module, and a warning module. The collected training samples are used to establish matching relationships and models in the background database, and the vehicle noise data group is collected in real time through the smart phone, and the feature extraction of the vehicle noise data group is performed, and the matching relationship and model output results stored in the background database are called, and the results are analyzed and judged, and the smart phone is controlled to trigger the initial warning and emergency warning, so as to timely remind people with hearing impairments, those who are addicted to looking at their mobile phones while walking, and those who listen to music on their mobile phones with headphones, thereby improving the safety of road travelers and effectively reducing the accident rate on the road.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] In actual application scenarios, users may not necessarily be close to the device, and there may be interference factors in the environment. In addition, the distance between the user and the device and the interference factors change dynamically, resulting in the volume and frequency received by the human ear not being the volume and frequency played by the device. If an early warning is only given based on the volume and frequency played by the device, it may cause a false alarm, causing unnecessary disturbance to the user and reducing the accuracy of the early warning device and the user's experience. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a music health warning method and device based on volume and frequency monitoring to solve the problems existing in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The music health warning method based on volume and frequency monitoring includes the following steps: Step 1: collecting the distance between the device and the user in real time through an infrared sensor; Step 2: obtaining the device playback volume and frequency distribution, recorded as the initial playback volume and the initial frequency distribution, the initial frequency distribution includes the energy of each frequency point, and the initial receiving volume of the human ear is calculated using the inverse square law according to the distance between the device and the user and the initial playback volume; Step 3: acquiring environmental data in real time, and obtaining an environmental attenuation factor based on the environmental data evaluation; Step 4: subtracting the environmental attenuation factor from the energy of each frequency point in the initial reception volume and the initial frequency distribution to obtain the actual reception volume and the actual reception frequency distribution, and evaluating the health level based on the actual reception volume and the actual reception frequency distribution; Step 5: giving an early warning reminder based on the health level.

[0010] Preferably, the step of obtaining the environmental attenuation factor is: obtaining obstacle data of the area between the user and the device, and obtaining the obstacle attenuation factor based on the obstacle data evaluation; obtaining air data of the area between the user and the device, and obtaining the air attenuation factor based on the air information evaluation; normalizing the obstacle attenuation factor and the air attenuation factor, and adding the normalized obstacle attenuation factor and the air attenuation factor to obtain the environmental attenuation factor.

[0011] Preferably, the obstacle attenuation factor acquisition step is: using an infrared sensor to scan obstacles in the space between the user and the device, and counting the number of obstacles; identifying the material of the obstacle by combining a camera with an image processing algorithm; obtaining the sound absorption coefficient and transmission loss of each obstacle material through the ASTM sound absorption coefficient table; and calculating the obstacle attenuation factor according to the sound absorption coefficient and the transmission loss. The specific acquisition method is as follows: Where OA is the obstacle attenuation factor, N is the number of obstacles, and α is i Expressed as the sound absorption coefficient of the ith obstacle, T i It is represented as the transmission loss of the i-th obstacle.

[0012] Preferably, the steps of identifying the material of the obstacle by combining the camera with the image processing algorithm are: using a high-definition camera to capture the surface image of the obstacle, using a filter to remove image noise and converting it into a grayscale image, and using an edge detection algorithm to extract the obstacle area; using a grayscale co-occurrence matrix to extract texture information, and by analyzing the highlight area in the image, judging the glossiness of the object surface, identifying the shape or edge characteristics, and recording them as image features; using a convolutional neural network to automatically learn and classify the image features, and output the obstacle material category.

[0013] Preferably, the air attenuation factor acquisition step is: divide the space area between the user and the device into m sub-areas on average, recorded as space sub-areas; obtain temperature data, humidity data and air pressure data of each space sub-area, and calculate the air absorption coefficient according to the temperature data, humidity data and air pressure data. The specific acquisition method is as follows: Where AB represents the air absorption coefficient, H j represents the humidity data of the jth spatial sub-region, P j Represented as the air pressure data of the jth spatial sub-region, W j It is represented as the temperature data of the jth spatial sub-region; the air absorption coefficient of each spatial sub-region is clustered, and the air attenuation factor is calculated according to the clustering result.

[0014] Preferably, the steps of clustering the air absorption coefficient of each spatial sub-region are as follows: Step 3.1: taking the air absorption coefficient as a clustering feature, taking the air absorption coefficients of all spatial sub-regions as a data set, and each air absorption coefficient in the data set as a data point; Step 3.2: using the elbow method to determine the optimal clustering number K of the data set; Step 3.3: randomly selecting K data points in the data set as initial clustering centers, for each data point, calculating its Euclidean distance to each initial clustering center, for each data point, traversing the K initial clustering centers, and assigning it to the clustering cluster corresponding to the nearest initial clustering center; Step 3.4: after traversing all data points, obtaining initial clustering clusters, for each initial clustering cluster, calculating the mean of the data points therein to obtain a new clustering center; Step 3.5: repeating steps 3.3 and 3.4 until the clustering center no longer changes, and obtaining the final clustering cluster and the final clustering center.

[0015] Preferably, the step of calculating the air attenuation factor according to the clustering results is: calculating the ratio of the number of data points in each final cluster to the total number in the data set to obtain the weight of each final cluster; and performing weighted summation of the weight of each final cluster and the final cluster center to obtain the air attenuation factor.

[0016] Preferably, the health level acquisition step is: setting a healthy and safe volume threshold, acquiring the total time the user receives music in real time, calculating the ratio of the initial received volume to the healthy and safe volume threshold to obtain the volume influence coefficient; obtaining the reference frequency energy, calculating the ratio of the energy of each frequency point to the reference frequency energy and then summing them up to obtain the frequency distribution influence coefficient; normalizing the total time the user receives music, the volume influence coefficient and the frequency distribution influence coefficient, and obtaining the health level according to the normalized total time the user receives music, the volume influence coefficient and the frequency distribution influence coefficient. The specific acquisition method is as follows: In the formula, HY represents the health level, Sc 总 is the total time the user receives music, VE is the volume influence coefficient, FD is the frequency distribution influence coefficient, b1, b2, and b3 represent the weight coefficients of the total time the user receives music, the volume influence coefficient, and the frequency distribution influence coefficient.

[0017] Preferably, the step of issuing an early warning reminder based on the health level is: setting a health threshold, comparing the health level with the health threshold, if the health level is greater than or equal to the health threshold, it is determined that the current music playback does little harm to the user's health, and no early warning reminder is needed, and return to step 1 to re-acquire data and perform a health assessment; if the health level is less than the health threshold, it is determined that the current music playback will cause great harm to the user's health, and an early warning reminder is issued.

[0018] Preferably, a music health warning device based on volume and frequency monitoring includes: an initial playback data acquisition module, which is used to acquire the initial playback volume and initial frequency distribution in real time through a sensor, transmit the initial playback volume to the initial reception volume acquisition module, and transmit the initial frequency distribution to the actual reception data acquisition module; the initial reception volume acquisition module is used to acquire the distance between the device and the user in real time through a sensor, calculate the initial reception volume according to the initial playback volume and the distance between the device and the user, and transmit the initial reception volume to the actual reception data acquisition module; an environmental data evaluation module is used to collect environmental information, and obtain the environmental attenuation factor according to the environmental information evaluation, and transmit the environmental attenuation factor to the actual reception data acquisition module; the actual reception data acquisition module is used to calculate the actual reception volume and the actual reception frequency distribution according to the initial reception volume, the initial frequency distribution and the attenuation factor, and transmit the actual reception volume and the actual reception frequency distribution to the warning module; the warning module is used to evaluate the health level according to the actual reception volume and the actual reception frequency distribution, and give a warning reminder to the user according to the health level.

[0019] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0020] 1. Based on the distance between the device and the user and the initial playback volume, the inverse square law is used to calculate the initial receiving volume of the human ear. Using the inverse square law to calculate the initial receiving volume of the human ear can provide an accurate estimate of the sound pressure level, which can objectively reflect the energy attenuation law of sound waves as they propagate over distance, and avoid discomfort to users caused by excessive volume.

[0021] 2. Real-time acquisition of environmental data, evaluation of environmental attenuation factors based on environmental data, and actual received volume and actual received frequency distribution based on environmental attenuation factors can more accurately predict the attenuation effect of sound during propagation, taking into account the impact of humidity, temperature, and obstacles on volume and frequency components, thereby optimizing the sound quality received by users. This not only improves the accuracy of sound propagation and auditory experience, but also helps devices save energy and reduce consumption, especially in complex or changeable propagation environments, significantly enhancing the adaptability and intelligence of audio systems.

[0022] 3. Evaluating the health status based on the total length of time the user receives music, the actual received volume, and the actual received frequency distribution can achieve scientific monitoring and protection of the user's hearing health. The advantage of this method is that it takes into account the sound intensity, frequency distribution, and contact time, so as to accurately evaluate whether the user's auditory system is overstimulated and reduce the risk of hearing damage caused by long-term exposure to high volume or specific frequencies. This evaluation method can also provide a basis for personalized volume recommendations or reminders, helping users develop healthier listening habits, improving the music experience while protecting hearing health.

[0023] 4. Early warning reminders based on health status can promptly remind users of potential risks that volume or listening time may cause to hearing health, thereby helping users to actively adjust their listening behavior. The benefit of this method is that through real-time intervention, it can avoid irreversible damage to the auditory system caused by long-term high volume exposure or uneven frequency stimulation, while cultivating users' healthy listening habits. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flow chart of a music health warning method based on volume and frequency monitoring provided in an embodiment of the present application.

[0025] Figure 2 This is a structural diagram of a music health warning device based on volume and frequency monitoring provided in an embodiment of the present application.

[0026] Figure 3 Schematic diagram of the total energy of each frequency band in the embodiment of the present application. DETAILED DESCRIPTION

[0027] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The music health warning method and device based on volume and frequency monitoring involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0028] The present invention provides a music health warning method based on volume and frequency monitoring, such as Figure 1 As shown, the following steps are included:

[0029] Step 1: Use infrared sensors to collect the distance between the device and the user in real time;

[0030] During actual use, the distance between the device and the ear is not fixed. By dynamically capturing these distance changes with infrared sensors, the volume assessment value can be updated in real time to adapt to different usage scenarios, making health warnings more flexible and scientific. The propagation attenuation characteristics of sound at different frequencies are closely related to distance. By obtaining the real-time distance between the device and the user with infrared sensors, the frequency distribution correction of the sound can be further optimized to improve the accuracy of the assessment of the frequency components actually received by the user, thereby more scientifically judging health risks.

[0031] Step 2: Obtain the device playback volume and frequency distribution, recorded as the initial playback volume and initial frequency distribution, and use the inverse square law to calculate the initial receiving volume of the human ear according to the distance between the device and the user and the initial playback volume;

[0032] The inverse square law is the basic principle that describes the attenuation of sound intensity during propagation. It states that sound gradually weakens as the distance increases. Specifically, when sound propagates outward from the sound source, the intensity of the sound is inversely proportional to the square of the propagation distance, that is, when the distance doubles, the intensity of the sound decreases to one-fourth of the original. This law means that the farther away from the sound source, the smaller the volume received by the human ear, and this attenuation effect is an important factor that must be considered when evaluating the actual intensity of the sound heard.

[0033] In the transmission of sound waves, distance mainly affects the attenuation of volume, but has a smaller effect on frequency distribution. This is because the geometric diffusion of sound waves (such as spherical wave propagation) has a uniform effect on all frequency components, resulting in the overall amplitude decreasing with increasing distance, but the relative proportion of frequency components remains unchanged. At the same time, within a short distance, the attenuation difference of different frequencies due to atmospheric absorption and dielectric damping is not significant, so the frequency distribution will not be significantly changed. Only in long-distance propagation, the high-frequency part may gradually weaken due to more significant absorption, but in general, this effect is relatively minor compared to geometric diffusion, and the frequency distribution remains basically stable. This makes distance the factor that mainly affects the sound wave volume rather than the frequency distribution, so in this embodiment, only the attenuation of volume due to distance is evaluated.

[0034] In this embodiment, it should be specifically explained that the steps of obtaining the device playback volume and frequency distribution are:

[0035] The sound signal of the playback device is collected in real time through the sensor, the sound signal is time-domain audio signal data, and the sensor can be a microphone array, an ultrasonic sensor, and a sound pressure sensor;

[0036] Perform RMS calculation on the time domain audio signal data to obtain the RMS value of the audio signal. The initial playback volume is obtained according to the RMS value of the audio signal. The specific acquisition method is as follows:

[0037]

[0038] Where, L SPL It is represented as the initial playback volume, RMS is the root mean square value of the audio signal, P ref Expressed as reference sound pressure level, usually 20μPa;

[0039] Use fast Fourier transform to convert the time domain audio signal data into frequency domain signal. The frequency domain signal is composed of frequency domain signals of multiple frequency points. The energy of each frequency point is calculated. The specific acquisition method is as follows:

[0040]

[0041] Where P[q] represents the energy at the qth frequency point, X[q] is the frequency domain signal corresponding to the qth frequency point, and N represents the number of sampling points of the fast Fourier transform, that is, the total number of data points used when performing the fast Fourier transform on the time domain signal;

[0042] Fast Fourier transform is an efficient algorithm for calculating discrete Fourier transform and its inverse transform. The basic idea of ​​Fourier transform is to decompose the time domain signal into multiple sinusoidal components of different frequencies to reveal the frequency characteristics of the signal.

[0043] The frequency points are divided according to the energy to obtain multiple frequency bands. In this embodiment, the frequency is divided into a low frequency band (20 Hz-250 Hz), a medium frequency band (250 Hz-4 kHz) and a high frequency band (>4 kHz), as shown in Table 1. The energy of the frequency points in each frequency band is counted, and the total energy of each frequency band is obtained by summing up.

[0044] Table 1 Total energy in each frequency band

[0045] Frequency band Total Energy Low frequency band 1500 Mid-band 9600 High frequency band 5500

[0046] As shown in Table 1, in a specific embodiment, the actual changes in frequency distribution are demonstrated by statistics and comparison of the total energy in different frequency bands. By analyzing the differences in the energy of these frequency bands, abnormal characteristics that are inconsistent with the reference sound distribution can be identified, such as excessive energy in the low frequency band or significant attenuation in the high frequency band. These energy changes can also be used to assess the potential impact of the sound environment on hearing health. In the scenarios of sound health monitoring or noise control, analyzing the distribution of energy in these frequency bands can effectively capture sound overload or imbalance, thereby timely adjusting the sound source characteristics or optimizing the propagation environment to ensure balanced distribution and health and safety of the sound.

[0047] like Figure 3 As shown, the total energy of each frequency band is displayed in a bar graph to obtain the actual frequency distribution.

[0048] In this embodiment, it should be specifically explained that the initial receiving volume of the human ear is calculated using the inverse square law according to the distance between the device and the user and the initial playback volume. The specific acquisition method is as follows:

[0049] L 初始 =L SPL -20×log 10 di;

[0050] Where, L 初始 is the initial receiving volume, L SPL It is expressed as the initial playback volume, di is the distance between the device and the user, and 20 is a logarithmic scaling factor related to the physical definition of volume.

[0051] Step 3: Obtain environmental data in real time and obtain the environmental attenuation factor based on the environmental data evaluation;

[0052] In this embodiment, it should be specifically explained that the steps for obtaining the environmental attenuation factor are:

[0053] Obtain obstacle data of the area between the user and the device, and obtain an obstacle attenuation factor based on the obstacle data evaluation;

[0054] Obtain air data of the area between the user and the device, and obtain the air attenuation factor based on the air information evaluation;

[0055] The obstacle attenuation factor and the air attenuation factor are normalized, and the normalized obstacle attenuation factor and the air attenuation factor are added to obtain the environmental attenuation factor. The specific acquisition method is: EA = OA + AT;

[0056] Where EA is the environmental attenuation factor, OA is the obstacle attenuation factor, and AT is the air attenuation factor.

[0057] In this embodiment, it should be specifically explained that the step of obtaining the obstacle attenuation factor is:

[0058] Use infrared sensors to scan obstacles in the space between the user and the device and count the number of obstacles;

[0059] Identify the material of obstacles through the combination of cameras and image processing algorithms;

[0060] Obtain the sound absorption coefficient and transmission loss of each obstacle material through the ASTM sound absorption coefficient table;

[0061] The obstacle attenuation factor is calculated based on the sound absorption coefficient and transmission loss. The specific method of obtaining it is as follows:

[0062]

[0063] Where OA is the obstacle attenuation factor, N is the number of obstacles, and α is i Expressed as the sound absorption coefficient of the ith obstacle, T i It is represented as the transmission loss of the i-th obstacle.

[0064] The ASTM sound absorption coefficient table is a material acoustic performance data table generated according to the standard test method of the American Society for Testing and Materials. It is mainly used to describe the sound absorption capacity and transmission loss of different materials at specific frequencies. The sound absorption coefficient (usually between 0 and 1) indicates the proportion of the material's absorption of incident sound waves. The larger the value, the stronger the sound absorption capacity; the transmission loss (in decibels) indicates the energy attenuation when the sound wave penetrates the material. The larger the value, the better the sound insulation performance. This table is widely used in architectural acoustics, environmental noise control and acoustic optimization design, providing a scientific basis for evaluating the acoustic performance of materials within a specific frequency range.

[0065] In this embodiment, it should be specifically explained that the steps of identifying the material of the obstacle by combining the camera with the image processing algorithm are as follows:

[0066] Use a high-definition camera to capture the surface image of the obstacle, use a filter to remove image noise, convert it into a grayscale image to simplify subsequent processing, and use an edge detection algorithm to extract the obstacle area;

[0067] Edge detection algorithm is an image processing technique used to identify areas in an image where the intensity changes significantly, usually corresponding to the boundaries or contours of objects. By calculating the gradient changes in grayscale values ​​or colors between pixels, edge detection algorithms can extract the most structured information in an image. Common edge detection methods include the Canny algorithm, Sobel operator, and Prewitt operator.

[0068] Use the gray-level co-occurrence matrix to extract texture information, such as contrast and uniformity, and extract the color histogram of the image to distinguish the color characteristics of the material. By analyzing the highlight area in the image, the glossiness of the object surface is determined, and the shape or edge characteristics are identified and recorded as image features, which are further classified in combination with the material characteristics.

[0069] Gray-level co-occurrence matrix is ​​a texture feature extraction method in image processing, which is used to describe the spatial distribution relationship of pixel gray values ​​in an image. By counting the gray-level combination frequency between pixel pairs with specific relative positions (such as distance and direction) in the image, the gray-level co-occurrence matrix generates a matrix in which each element represents the number of co-occurrences of the corresponding gray-level value pair. Based on the gray-level co-occurrence matrix, texture features such as contrast, energy, correlation, and entropy can be calculated to distinguish different materials or surface structures.

[0070] Use convolutional neural networks to automatically learn and classify image features. For example, use a pre-trained ResNet or MobileNet model and fine-tune it for material classification. The classification model outputs the obstacle material category.

[0071] Convolutional neural network is a deep learning model designed for processing data with spatial structure such as images. Convolutional neural network extracts low-level features (such as edges, textures) and high-level features (such as shapes, objects) of images through local perception and weight sharing convolution operations, and combines pooling layers to reduce data dimensions, thereby improving computational efficiency and feature expression capabilities.

[0072] In this embodiment, it should be specifically explained that the steps for obtaining the air attenuation factor are:

[0073] Divide the space area between the user and the device into m sub-areas evenly, denoted as space sub-areas;

[0074] The temperature data, humidity data and air pressure data of each spatial sub-area are obtained, and the air absorption coefficient is calculated based on the temperature data, humidity data and air pressure data. It should be specifically noted that the temperature data, humidity data and air pressure data are all normalized before calculation. The specific acquisition method is as follows:

[0075]

[0076] Where AB represents the air absorption coefficient, H j represents the humidity data of the jth spatial sub-region, P j Represented as the air pressure data of the jth spatial sub-region, W j It is represented as the temperature data of the j-th spatial sub-region, 0.1068 is an empirical coefficient used to describe the effect of humidity on the air absorption coefficient, and 0.0025 is an empirical coefficient used to describe the effect of temperature on the air absorption coefficient;

[0077] The air absorption coefficient of each spatial sub-region is clustered, and the air attenuation factor is calculated based on the clustering results.

[0078] In this embodiment, it should be specifically explained that the steps of clustering the air absorption coefficient of each spatial sub-region are:

[0079] Step 3.1: Take the air absorption coefficient as the clustering feature, take the air absorption coefficients of all spatial sub-regions as the data set, and each air absorption coefficient in the data set as a data point;

[0080] Step 3.2: Use the elbow method to determine the optimal number of clusters K for the data set;

[0081] The elbow method is a method for determining the optimal number of clusters in cluster analysis. By calculating the total intra-group squared error under different numbers of clusters, a relationship curve between the optimal number of clusters and the total intra-group squared error is plotted. When the number of clusters increases, the total intra-group squared error will gradually decrease. When the optimal number of clusters reaches a certain value, the rate of decrease of the total intra-group squared error decreases significantly, forming an inflection point similar to an "elbow". The optimal number of clusters corresponding to this inflection point is the optimal number of clusters;

[0082] Step 3.3: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center. The specific method is: Where d(DP,cr) represents the Euclidean distance from the data point to the cluster center, where DP represents the data point and cr represents the initial cluster center. For each data point, K initial cluster centers are traversed and assigned to the cluster corresponding to the nearest initial cluster center.

[0083] Euclidean distance is a method used to measure the degree of difference between data points, which represents the straight-line distance between two points in space. It calculates the difference between each dimension to get the overall distance. The smaller the distance, the more similar the data points are. Euclidean distance is widely used in cluster analysis to determine the proximity of data points to the cluster center.

[0084] Step 3.4: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center.

[0085] Step 3.5: Repeat steps 3.3 and 3.4 until the cluster center no longer changes, and obtain the final cluster and the final cluster center.

[0086] In this embodiment, it should be specifically explained that the steps of calculating the air attenuation factor according to the clustering result are:

[0087] The weight of each final cluster is calculated by calculating the ratio of the number of data points in each final cluster to the total number of data points in the data set;

[0088] The air attenuation factor is obtained by weighting and summing the weight of each final cluster and the final cluster center.

[0089] Step 4: Subtract the environmental attenuation factor from the energy of each frequency point in the initial receiving volume and the initial frequency distribution to obtain the actual receiving volume and the actual receiving frequency distribution, and evaluate the health level based on the actual receiving volume and the actual receiving frequency distribution;

[0090] In this embodiment, it should be specifically explained that the steps for obtaining the health level are:

[0091] Set a healthy and safe volume threshold, obtain the total duration of music received by the user in real time, calculate the volume influence coefficient by comparing the initial received volume with the healthy and safe volume threshold, and in this embodiment, the healthy and safe volume threshold is 85db;

[0092] Obtain reference frequency energy, which is usually the frequency distribution value recommended for healthy hearing. Calculate the ratio of the energy of each frequency point to the reference frequency energy and sum them up to obtain the frequency distribution influence coefficient.

[0093] The total duration of music received by the user, the volume influence coefficient, and the frequency distribution influence coefficient are normalized, and the health level is obtained according to the normalized total duration of music received by the user, the volume influence coefficient, and the frequency distribution influence coefficient. The specific acquisition method is as follows:

[0094]

[0095] In the formula, HY represents the health level, Sc总 The total length of time that users receive music. As users are exposed to music for longer, their health will gradually decrease. Even if the volume is moderate and the frequency distribution is reasonable, long-term exposure to the sound environment will cause fatigue in the auditory organs, thereby increasing the risk of hearing damage. Excessive exposure to music may also cause tinnitus, temporary hearing loss, and even permanent hearing loss. In addition, long-term high-intensity music exposure may have adverse effects on the psychological and physical health of users, such as headaches, decreased attention, and mood swings. VE is the volume influence coefficient. A higher volume will increase the burden on the hair cells and auditory nerves in the cochlea, leading to overstimulation of the auditory system. Long-term exposure may cause tinnitus, temporary hearing loss, and even permanent hearing damage. The louder the volume, the more significant the risk of stress and damage to the human body. FD is the frequency distribution influence coefficient. If the frequency distribution is too unbalanced, especially when the high-frequency component is significantly higher than the reference frequency distribution, the impact on the auditory system will be aggravated. High-frequency sound energy is concentrated, and the stimulation to the hair cells of the basilar membrane of the cochlea is stronger. Long-term exposure may cause damage to the hair cells, thereby causing high-frequency hearing loss or permanent hearing loss. At the same time, low-frequency components that deviate from the standard may trigger body resonance effects, leading to headaches, chest tightness and fatigue, while broadband or noise components may increase auditory fatigue and psychological pressure. b1, b2, and b3 represent the weight coefficients of the total time the user receives music, the volume influence coefficient, and the frequency distribution influence coefficient, and b1+b2+b3=1. The specific values ​​of b1, b2, and b3 are determined by professionals based on actual conditions. For example, b1, b2, and b3 can be 0.1, 0.4, and 0.5, respectively.

[0096] Normalization is an important step in data preprocessing. By converting the total duration of music received by users, the volume influence coefficient, and the frequency distribution influence coefficient to the same numerical range (such as [0,1]), the dimension differences between different indicators are eliminated, ensuring that each factor can fairly reflect its impact on health when comprehensively calculating the health level. Normalization not only improves the accuracy and rationality of the calculation, but also avoids the excessive influence of certain indicators with large values ​​on the results.

[0097] Step 5: Issue early warning reminders based on health status;

[0098] In this embodiment, it should be specifically explained that the steps of providing early warning reminders according to health status are:

[0099] Set a health threshold and compare the health level with the health threshold. If the health level is greater than or equal to the health threshold, it is determined that the current music playback does little harm to the user's health and no early warning reminder is needed. Return to step 1 to reacquire data and perform a health assessment. If the health level is less than the health threshold, it is determined that the current music playback will cause great harm to the user's health, and an early warning reminder will be issued to remind the user to lower the volume or increase the distance from the device.

[0100] In this embodiment, it should be specifically explained that Figure 2 As shown, a music health warning device based on volume and frequency monitoring includes:

[0101] An initial playback data acquisition module is used to acquire the initial playback volume and initial frequency distribution in real time through a sensor, transmit the initial playback volume to the initial reception volume acquisition module, and transmit the initial frequency distribution to the actual reception data acquisition module;

[0102] An initial receiving volume acquisition module is used to obtain the distance between the device and the user in real time through a sensor, calculate the initial receiving volume according to the initial playback volume and the distance between the device and the user, and transmit the initial receiving volume to the actual receiving data acquisition module;

[0103] The environmental data evaluation module is used to collect environmental information, obtain environmental attenuation factors based on the environmental information evaluation, and transmit the environmental attenuation factors to the actual receiving data acquisition module;

[0104] An actual receiving data acquisition module is used to calculate the actual receiving volume and the actual receiving frequency distribution according to the initial receiving volume, the initial frequency distribution and the attenuation factor, and transmit the actual receiving volume and the actual receiving frequency distribution to the early warning module;

[0105] The early warning module is used to evaluate the health level based on the actual received volume and the actual received frequency distribution, and to give early warning reminders to users based on the health level, reminding them that the current music playback will damage their health.

[0106] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A music health warning method and device based on volume and frequency monitoring, characterized in that: The following steps are involved: Step 1: Use infrared sensors to collect the distance between the device and the user in real time; Step 2: Obtain the device playback volume and frequency distribution, recorded as the initial playback volume and initial frequency distribution, the initial frequency distribution includes the energy of each frequency point, and the initial receiving volume of the human ear is calculated using the inverse square law according to the distance between the device and the user and the initial playback volume; Step 3: Obtain environmental data in real time and obtain the environmental attenuation factor based on the environmental data evaluation; Step 4: Subtract the environmental attenuation factor from the energy of each frequency point in the initial receiving volume and the initial frequency distribution to obtain the actual receiving volume and the actual receiving frequency distribution, and evaluate the health level based on the actual receiving volume and the actual receiving frequency distribution; Step 5: Provide early warning reminders based on health status.

2. The music health warning method based on volume and frequency monitoring according to claim 1 is characterized in that: The steps for obtaining the environmental attenuation factor are: Obtain obstacle data of the area between the user and the device, and obtain an obstacle attenuation factor based on the obstacle data evaluation; Obtain air data of the area between the user and the device, and obtain the air attenuation factor based on the air information evaluation; The obstacle attenuation factor and the air attenuation factor are normalized, and the normalized obstacle attenuation factor and the air attenuation factor are added to obtain the environmental attenuation factor.

3. The music health warning method based on volume and frequency monitoring according to claim 2 is characterized in that: The obstacle attenuation factor acquisition steps are: Use infrared sensors to scan obstacles in the space between the user and the device and count the number of obstacles; Identify the material of obstacles through the combination of cameras and image processing algorithms; Obtain the sound absorption coefficient and transmission loss of each obstacle material through the ASTM sound absorption coefficient table; The obstacle attenuation factor is calculated based on the sound absorption coefficient and transmission loss. The specific method of obtaining it is as follows: Where OA is the obstacle attenuation factor, N is the number of obstacles, and α is i Expressed as the sound absorption coefficient of the ith obstacle, T i It is represented as the transmission loss of the i-th obstacle.

4. The music health warning method based on volume and frequency monitoring according to claim 3 is characterized in that: The steps of identifying the material of obstacles by combining the camera with the image processing algorithm are as follows: Use a high-definition camera to capture the surface image of the obstacle, use a filter to remove image noise, convert it into a grayscale image, and use an edge detection algorithm to extract the obstacle area; Use the gray-level co-occurrence matrix to extract texture information, and by analyzing the highlight area in the image, determine the glossiness of the object surface, identify the shape or edge characteristics, and record them as image features; Use convolutional neural networks to automatically learn and classify image features and output obstacle material categories.

5. The music health warning method based on volume and frequency monitoring according to claim 2 is characterized in that: The steps for obtaining the air attenuation factor are: Divide the space area between the user and the device into m sub-areas evenly, denoted as space sub-areas; The temperature data, humidity data and air pressure data of each spatial sub-area are obtained, and the air absorption coefficient is calculated based on the temperature data, humidity data and air pressure data. The specific acquisition method is as follows: Where AB represents the air absorption coefficient, H j represents the humidity data of the jth spatial sub-region, P j Represented as the air pressure data of the jth spatial sub-region, W j Represented as the temperature data of the jth spatial sub-region; The air absorption coefficient of each spatial sub-region is clustered, and the air attenuation factor is calculated based on the clustering results.

6. The music health warning method based on volume and frequency monitoring according to claim 5 is characterized in that: The steps of clustering the air absorption coefficient of each spatial sub-region are: Step 3.1: Take the air absorption coefficient as the clustering feature, take the air absorption coefficients of all spatial sub-regions as the data set, and each air absorption coefficient in the data set as a data point; Step 3.2: Use the elbow method to determine the optimal number of clusters K for the data set; Step 3.3: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center. For each data point, traverse the K initial cluster centers and assign it to the cluster corresponding to the nearest initial cluster center. Step 3.4: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center. Step 3.5: Repeat steps 3.3 and 3.4 until the cluster center no longer changes, and obtain the final cluster and the final cluster center.

7. The music health warning method based on volume and frequency monitoring according to claim 5 is characterized in that: The step of calculating the air attenuation factor according to the clustering result is: The weight of each final cluster is calculated by calculating the ratio of the number of data points in each final cluster to the total number of data points in the data set; The air attenuation factor is obtained by weighting and summing the weight of each final cluster and the final cluster center.

8. The music health warning method based on volume and frequency monitoring according to claim 1 is characterized by: The steps for obtaining the health level are: Set a healthy and safe volume threshold, obtain the total time the user receives music in real time, and calculate the volume impact coefficient by comparing the initial received volume with the healthy and safe volume threshold; Obtain reference frequency energy, calculate the ratio of the energy of each frequency point to the reference frequency energy and then sum them up to obtain the frequency distribution influence coefficient; The total duration of music received by the user, the volume influence coefficient, and the frequency distribution influence coefficient are normalized, and the health level is obtained according to the normalized total duration of music received by the user, the volume influence coefficient, and the frequency distribution influence coefficient. The specific acquisition method is as follows: In the formula, HY represents the health level, Sc 总 is the total time the user receives music, VE is the volume influence coefficient, FD is the frequency distribution influence coefficient, b1, b2, and b3 represent the weight coefficients of the total time the user receives music, the volume influence coefficient, and the frequency distribution influence coefficient.

9. The music health warning method based on volume and frequency monitoring according to claim 1 is characterized in that: The steps of providing early warning reminders according to health status are as follows: Set a health threshold and compare the health level with the health threshold. If the health level is greater than or equal to the health threshold, it is determined that the current music playback does little harm to the user's health and no early warning is needed. Return to step 1 to reacquire data and perform a health assessment. If the health level is less than the health threshold, it is determined that the current music playback will cause great harm to the user's health and an early warning is issued.

10. A music health warning device based on volume and frequency monitoring, used to implement the music health warning method based on volume and frequency monitoring according to any one of claims 1 to 9, characterized in that: The device comprises: An initial playback data acquisition module is used to acquire the initial playback volume and initial frequency distribution in real time through a sensor, transmit the initial playback volume to the initial reception volume acquisition module, and transmit the initial frequency distribution to the actual reception data acquisition module; An initial receiving volume acquisition module is used to obtain the distance between the device and the user in real time through a sensor, calculate the initial receiving volume according to the initial playback volume and the distance between the device and the user, and transmit the initial receiving volume to the actual receiving data acquisition module; The environmental data evaluation module is used to collect environmental information, obtain environmental attenuation factors based on the environmental information evaluation, and transmit the environmental attenuation factors to the actual receiving data acquisition module; An actual receiving data acquisition module is used to calculate the actual receiving volume and the actual receiving frequency distribution according to the initial receiving volume, the initial frequency distribution and the attenuation factor, and transmit the actual receiving volume and the actual receiving frequency distribution to the early warning module; The early warning module is used to evaluate the health level based on the actual receiving volume and the actual receiving frequency distribution, and to issue early warning reminders to users based on the health level.

Images