Square dance noise data processing method

Abstract

The invention relates to a square dance noise data processing method, and relates to the field of smart cities, and the method comprises the steps: obtaining a resident at-home probability set of a noise coverage area according to the matching of a current playing interval; by utilizing a noise region simulation space, according to the current meteorological data and the resident at-home probability set, performing sound layout parameter iterative optimization by taking a sound movable region range as an optimization space and taking the minimum overall noise influence as a target, and outputting an optimal position and an optimal angle; and placing the sound in the current playing interval according to the optimal position and the optimal angle, and continuing to optimize the sound placement. According to the invention, the technical problem that the regional noise influence is difficult to effectively control because the traditional method cannot reasonably select the activity field and sound layout of the square dance in combination with the actual scene can be solved; scientific and reasonable arrangement of a square dance activity site and sound equipment layout can be improved, regional noise pollution is reduced to the greatest extent, and intelligent and scientific urban noise management is realized.

Description

Technical Field

[0001] The present invention relates to the field of smart cities, and in particular to a square dance noise data processing method. Background Art

[0002] Square dancing, as a widely popular mass fitness activity, has strong social attributes and fitness value. However, due to the high-decibel noise generated by its audio equipment, it can easily cause interference to surrounding residents, especially in open spaces such as residential areas, parks, and squares.

[0003] The existing square dance noise management methods mainly rely on passive management measures such as fixed volume limits, manual inspections, and resident complaints and feedback, which make it difficult to achieve scientific, accurate, and efficient noise optimization management. Summary of the invention

[0004] The present invention aims to solve the technical problem that traditional methods cannot reasonably select square dance activity venues and sound layouts in combination with actual scenarios, resulting in difficulty in effectively controlling regional noise impacts, and provides a square dance noise data processing method to solve the problem.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: The present invention provides a square dance noise data processing method, comprising: dividing the scheduled activity time period of square dance into multiple playback intervals, and obtaining the probability set of residents being at home in the noise coverage area according to the current playback interval matching; constructing a noise area simulation space according to the architectural characteristics of the noise coverage area and the location coordinates of several households; utilizing the noise area simulation space, based on current meteorological data and the probability set of residents being at home, taking the range of the movable area of ​​the audio as the optimization space, and iteratively optimizing the audio layout parameters with the goal of minimizing the overall noise impact, and outputting the current optimal layout parameters, wherein the current optimal layout parameters include the optimal position and the optimal angle; placing the audio in the current playback interval according to the optimal position and the optimal angle, and continuing to optimize the audio placement in the order of the playback intervals until the square dance activity ends.

[0006] Optionally, the square dance noise data processing method also includes: performing noise diffusion coverage simulation based on the maximum noise intensity of the square dance within a preset time period and the characteristics of the surrounding buildings to determine the noise coverage area, wherein the default regional wind speed is 0 during the noise diffusion simulation; dividing the scheduled activity time period of the square dance according to a predetermined time step to determine multiple playback intervals; separately counting the historical proportion of residents at home of several households in the noise coverage area under the multiple playback intervals, setting them as the historical resident at home probability, obtaining multiple historical resident at home probability sets, and establishing a probability mapping relationship between the playback interval and the historical resident at home probability set; obtaining the resident at home probability set based on matching the current playback interval and the probability mapping relationship.

[0007] Optionally, the square dance noise data processing method also includes: obtaining the range of the movable audio area for square dancing in the area, and randomly selecting multiple audio placement positions within the movable audio area; configuring multiple audio placement angles at predetermined angle intervals, and randomly combining the multiple audio placement angles and several audio placement positions to generate several initial layout parameters; utilizing the noise area simulation space, based on current meteorological data and the probability set of residents being at home, with the goal of minimizing the overall noise impact, iteratively optimizing the audio layout parameters based on the several initial layout parameters, and outputting the current optimal layout parameters.

[0008] Optionally, the square dance noise data processing method also includes: utilizing the noise area simulation space and combining it with a BP neural network to construct a noise diffusion simulator; monitoring and acquiring current meteorological data, wherein the meteorological data includes wind speed and wind direction; inputting the current meteorological data and a number of initial layout parameters into the noise diffusion simulator, and outputting a number of noise simulation intensity sets, wherein each noise simulation intensity set includes a number of noise simulation intensities of a number of households; calculating a number of overall influence coefficients based on the number of noise simulation intensity sets and the probability sets of residents being at home; iteratively optimizing the sound layout parameters based on the number of initial layout parameters and a number of overall influence coefficients, and outputting the current optimal layout parameters.

[0009] Optionally, the square dance noise data processing method also includes: based on the noise area simulation space, constructing an initial noise diffusion simulator using the BP neural network as the prediction logic; collecting sample meteorological data sets and sample audio layout parameter sets according to regional noise monitoring records, and statistically analyzing a number of noise intensities of a number of households under different sample meteorological data and sample audio layout parameters to obtain multiple sample noise intensity sets; using the sample meteorological data sets and sample audio layout parameter sets as input and the multiple sample noise intensity sets as supervision to train the initial noise diffusion simulator until convergence to obtain the noise diffusion simulator.

[0010] Optionally, the square dance noise data processing method also includes: establishing a location mapping association between the probability of residents being at home and the noise simulation intensity; based on the location mapping association, taking the probability of residents being at home as a weight, performing weighted calculations on the several noise simulation intensity sets respectively according to the resident home probability sets, and outputting several overall impact coefficients.

[0011] Optionally, the square dance noise data processing method further includes: based on the several overall influence coefficients, mapping and arranging the several initial layout parameters according to the coefficients from small to large to generate an initial parameter sequence; setting the initial parameters as the initial solution, and setting the first N initial solutions of the initial parameter sequence as the optimal solution, and setting the last M initial solutions as the inferior solution, wherein M is K times N, and K is an integer greater than 10 and less than 50; randomly clustering the M inferior solutions with the N optimal solutions as the center to generate N solution sets, and calculating N adjustment step sets; within the N solution sets, taking the optimal solution as the adjustment direction, according to the N adjustment step sets The inferior solutions in the solution set are optimized and adjusted, and N updated solution sets are output, wherein if the adjusted inferior solution exceeds the range of the movable area of ​​the audio system, no adjustment is performed; the overall influence coefficients of the inferior solutions in the N updated solution sets are calculated, and the N updated solution sets are identified, and if the overall influence coefficient of the inferior solution is less than the overall influence coefficient of the superior solution in the same updated solution set, the superior solution is replaced by the inferior solution; iterative optimization is continued until a predetermined number of optimization searches is reached, N current updated solution sets are output, and the current updated solution set with the smallest sum of the overall influence coefficients is selected as the optimal solution set, and the superior solution of the optimal solution set is set as the current optimal layout parameter.

[0012] Optionally, the square dance noise data processing method also includes: configuring an initial adjustment step, wherein the initial adjustment step includes a position adjustment amplitude and an angle adjustment amplitude; randomly selecting a first solution set, and obtaining a first optimal solution overall influence coefficient of a first optimal solution in the first solution set, and multiple first inferior solution overall influence coefficients of multiple inferior solutions; respectively calculating the deviation ratio between the multiple first inferior solution overall influence coefficients and the first optimal solution overall influence coefficient, and setting multiple first correction weights according to the deviation ratio, wherein the deviation ratio and the correction weight are positively correlated; optimizing and correcting the initial adjustment step according to the multiple first correction weights to obtain a first adjustment step set, and adding it to the N adjustment step sets.

[0013] The beneficial effects of the present invention are as follows: by dividing the scheduled activity time period of square dancing into multiple playback intervals, the probability set of residents being at home in the noise coverage area is obtained according to the current playback interval matching; then a noise area simulation space is constructed according to the architectural features of the noise coverage area and the location coordinates of several families; further utilizing the noise area simulation space, according to the current meteorological data and the probability set of residents being at home, taking the range of the movable area of ​​the audio as the optimization space, and taking the overall noise impact as the goal to iteratively optimize the audio layout parameters, and outputting the current optimal layout parameters, wherein the current optimal layout parameters include the optimal position and the optimal angle; finally, the audio is placed in the current playback interval according to the optimal position and the optimal angle, and the audio placement optimization is continued in the order of the playback intervals until the square dance activity ends; the above method can improve the scientificity and rationality of the square dance activity venue and audio layout settings, so that while ensuring the entertainment experience, the regional square dance noise pollution can be minimized to achieve intelligent and scientific urban noise management. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic flow chart of a square dance noise data processing method provided by the present invention; Figure 2 A schematic diagram of a flow chart of obtaining a probability set of residents being at home in a square dance noise data processing method provided by the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0016] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0017] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0018] Examples, such as Figure 1 As shown, the embodiment of the present invention provides a square dance noise data processing method, which specifically includes the following steps: S100: Divide the scheduled activity time period of square dancing into multiple playing intervals, and obtain a set of probabilities of residents in the noise coverage area being at home according to the current playing interval matching.

[0019] Further, if Figure 2 As shown, step S100 of the present invention further includes: S110: Perform noise diffusion coverage simulation based on the maximum noise intensity of square dancing within a preset time period and the characteristics of surrounding buildings to determine the noise coverage area, wherein the default regional wind speed is 0 during the noise diffusion simulation process; S120: Divide the scheduled activity time period of square dancing according to the predetermined time step to determine multiple playback intervals; S130: Count the historical proportions of residents at home of several families in the noise coverage area under the multiple playback intervals, set them as the historical resident at home probability, obtain multiple historical resident at home probability sets, and establish a probability mapping relationship between the playback interval and the historical resident at home probability set; S140: Obtain the resident at home probability set based on the current playback interval and the probability mapping relationship.

[0020] Specifically, first, based on the square dance noise monitoring records within a preset time period (such as the last month), such as using noise monitoring equipment to record noise data during square dance activities, the maximum noise intensity of square dance is obtained; then the building characteristics around the square dance activity area are obtained, including building geometric characteristics (building height, building density, etc.) and vegetation information (tree height, etc.). Then, the noise diffusion simulation conditions are set, in which the default regional wind speed is 0 during the noise diffusion simulation process, that is, the influence of wind speed and wind direction is not considered; and based on the noise diffusion simulation conditions, the noise diffusion coverage simulation is performed according to the maximum noise intensity and the surrounding building characteristics, such as simulating the propagation path of noise in the building environment through ray tracing, and using the noise attenuation model to calculate the noise coverage range to obtain the noise coverage area.

[0021] On the other hand, the scheduled activity time period of square dancing is obtained, such as the square dancing activity time period is usually from 06:00 to 08:00 and from 18:00 to 22:00; then the scheduled time step is set, usually with a value of 10 to 30 minutes, to ensure that the optimization calculation is sufficiently precise while reducing the calculation burden, such as setting the scheduled time step to 15 minutes; then the scheduled activity time period of square dancing is divided according to the scheduled time step, as shown in Table 1, to obtain multiple playback intervals.

[0022] Table 1 Then, according to the square dance noise monitoring records, the historical proportion of residents at home of several families in the noise coverage area in the multiple playback intervals is counted respectively, such as by questionnaire survey, and based on the statistical data, the proportion of residents at home in each playback interval is calculated. The proportion of residents at home is the ratio of the number of times at home to the total number of statistical times. For example, the number of times residents are at home in the same playback interval every day is counted to obtain the historical proportion of residents at home, which is set as the historical probability of residents at home, and multiple sets of historical probability of residents at home are obtained, and a probability mapping relationship between the playback interval and the set of historical probability of residents at home is established. Then the current playback interval (such as 06:00 to 06:15) is read, and the set of resident at home probability corresponding to the current playback interval is matched according to the probability mapping relationship.

[0023] S200: Constructing a noise area simulation space according to the architectural features of the noise coverage area and the location coordinates of a plurality of households.

[0024] Specifically, the architectural feature information of the noise coverage area is obtained, including data such as building geometric features, building density and vegetation information, and the location coordinates of several households in the noise coverage area are obtained; then three-dimensional simulation modeling is performed based on the architectural feature information and the location coordinates of several households, such as defining a three-dimensional coordinate system, setting the square dance activity location as the origin, importing building data, generating a three-dimensional noise propagation environment, and loading household location data, mapping it into three-dimensional space, and generating a noise area simulation space.

[0025] S300: Utilizing the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, taking the movable area of ​​the audio system as the optimization space, and taking the overall noise impact as the goal, iteratively optimizing the audio layout parameters, and outputting the current optimal layout parameters, wherein the current optimal layout parameters include the optimal position and the optimal angle.

[0026] Furthermore, step S300 of the present invention further includes: S310: Obtain the movable area range of the audio system for square dancing in the area, and randomly select multiple audio placement positions within the movable area range; S320: Configure multiple audio placement angles according to predetermined angle intervals, randomly combine the multiple audio placement angles and multiple audio placement positions, and generate multiple initial layout parameters.

[0027] Specifically, first, the range of the movable audio area for square dancing in the area is obtained, and the movable audio area refers to the area within the square dance activity area where the audio can be effectively placed; then, a plurality of audio placement positions are randomly selected within the movable audio area, such as dividing the movable audio area into several small units, and randomly selecting a plurality of placement positions from the divided small units, and determining a reasonable number of random selections based on the size of the venue to ensure that within the movable audio area, the selected audio positions have sufficient diversity to optimize the selection of the best layout.

[0028] Then, a preset angle interval is configured, which can be set according to the actual scenario, such as configuring a placement angle every 15° to ensure that the sound can cover different areas; and multiple speaker placement angles are configured according to the preset angle interval, that is, a speaker placement angle is set every 15°; then the multiple speaker placement angles and several speaker placement positions are randomly combined to generate several initial layout parameters. Considering the limitations of site conditions, some unreasonable placement angles can be eliminated according to the speaker placement position. For example, if there are buildings or other obstacles near the speaker placement position, it will affect the propagation direction of the sound waves. Therefore, placement positions at certain angles should be eliminated to ensure that the generated initial layout parameters are reasonable and practical.

[0029] S330: Utilizing the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, with the goal of minimizing the overall noise impact, iteratively optimizing the sound layout parameters according to the several initial layout parameters, and outputting the current optimal layout parameters.

[0030] Further, step S330 of the present invention further includes: S331: Utilize the noise region simulation space and combine it with the BP neural network to construct a noise diffusion simulator.

[0031] Further, step S331 of the present invention further includes: S3311: Based on the noise area simulation space, an initial noise diffusion simulator is constructed using the BP neural network as the prediction logic; S3312: According to the regional noise monitoring records, sample meteorological data sets and sample audio layout parameter sets are collected, and statistics are collected on several noise intensities of several households under different sample meteorological data and sample audio layout parameters to obtain multiple sample noise intensity sets; S3313: Using the sample meteorological data sets and sample audio layout parameter sets as inputs and the multiple sample noise intensity sets as supervision, the initial noise diffusion simulator is trained until convergence to obtain the noise diffusion simulator.

[0032] Specifically, based on the noise area simulation space, an initial noise diffusion simulator is constructed using the BP neural network as the prediction logic, that is, the BP neural network (back propagation neural network) is used as a prediction model, combined with the noise area simulation space, and the diffusion of noise is simulated through training, wherein the initial noise diffusion simulator includes an input layer, multiple hidden layers (for learning the nonlinear relationship between input and output) and an output layer, the input data of the input layer are meteorological data (wind speed and wind direction) and audio layout parameters (placement position and placement angle), and the output data of the output layer are the noise intensity of several households in the noise coverage area.

[0033] Next, based on the regional noise monitoring records, sample meteorological data sets and sample sound layout parameter sets are collected, where each change in the sound position or angle will affect the diffusion range of the noise, and the wind speed and wind direction will also have an impact on the noise diffusion; then, the noise intensities of several households under different sample meteorological data and sample sound layout parameters are statistically analyzed to obtain multiple sample noise intensity sets. Then, the sample meteorological data and sample sound layout parameters are used as inputs, the sample noise intensity set is used as supervision, and the sample meteorological data sets, sample sound layout parameter set and sample noise intensity set are used as training data to perform supervised training on the initial noise diffusion simulator. First, the sample meteorological data and sample sound layout parameters are passed into the neural network as inputs. The network generates predicted values ​​through calculations at each layer, predicts the noise intensity, and calculates the difference between the predicted noise intensity and the actual noise intensity as the model error; then, a loss function (such as mean square error MSE) is used to calculate the error between the noise intensity output by the model and the actual noise intensity, and the error is calculated by inverse The forward propagation algorithm calculates the gradient of the error for each layer of network parameters (weights and biases), and uses the gradient descent algorithm (or other optimization algorithms) to update the parameters in the network so that the model output error is minimized as much as possible; then, based on the results of the back propagation, the optimization algorithm (such as gradient descent, Adam, etc.) is used to update the network weights and biases, and the network parameters are adjusted so that the predicted value is closer to the actual noise intensity; the above process (forward propagation, error calculation, back propagation, weight update) is repeated for multiple rounds of training. When the training error reaches the set minimum value or the number of training iterations reaches the predetermined upper limit, the training process stops and a trained noise diffusion simulator is obtained. The trained noise diffusion simulator can intelligently predict the intensity and diffusion range of noise based on given meteorological conditions and sound layout parameters, thereby providing a scientific basis for sound layout optimization.

[0034] S332: Monitor and obtain current meteorological data, wherein the meteorological data includes wind speed and wind direction; S333: Input the current meteorological data and a number of initial layout parameters into the noise diffusion simulator, and output a number of noise simulation intensity sets, wherein each noise simulation intensity set includes a number of noise simulation intensities of a number of households.

[0035] Specifically, the current meteorological data is obtained through the monitoring tool, including wind speed data (wind speed in the current area, usually in meters per second) and wind direction (wind direction, usually expressed as an angle, with 0° in the north direction and increasing in the clockwise direction). Then the current meteorological data and several initial layout parameters are combined to obtain multiple input data (including the current meteorological data and any initial layout parameter) and input into the noise diffusion simulator, and output several noise simulation intensity sets, wherein each noise simulation intensity set includes several noise simulation intensities of several households.

[0036] S334: Calculate a plurality of overall impact coefficients according to the plurality of noise simulation intensity sets and the plurality of resident at-home probability sets.

[0037] Further, step S334 of the present invention further includes: S3341: Establish a location mapping association between the probability of residents being at home and the noise simulation intensity; S3342: Based on the location mapping association, take the probability of residents being at home as the weight, perform weighted calculations on the several noise simulation intensity sets according to the sets of resident home probabilities, and output several overall impact coefficients.

[0038] Specifically, for each family's noise simulation intensity and the probability of the family being at home, a location mapping association is established. The noise simulation intensity of each family can be associated with the noise simulation intensity through the family's location coordinates (such as longitude and latitude) to obtain the noise impact value of each family. The noise simulation intensity value of each family will be adjusted according to the probability of the family being at home, with the purpose of improving the assessment of the impact of residents' actual exposure to noise. Then, based on the location mapping association, the probability of residents being at home is used as the weight, and the several noise simulation intensity sets are weighted according to the set of residents at home probabilities. That is, for each playback interval (such as a certain period of time every day), the weighted noise intensity of all families in the area is summed up. The weighted noise intensity of each family is obtained by multiplying the noise simulation intensity and the probability of residents being at home, and the overall impact coefficient of the period is calculated. The overall impact coefficient reflects the comprehensive noise impact of square dance activities on all families in a specific playback interval.

[0039] By weighting the probability of residents being at home and the noise simulation intensity, the noise impact value of each household in a specific playback range can be obtained, and the overall impact coefficient can be calculated. This process can help evaluate the actual impact of different playback ranges and audio layout schemes on square dance noise, and provide a scientific basis for the optimization of audio placement.

[0040] S335: Iteratively optimizing the acoustic layout parameters according to the plurality of initial layout parameters and the plurality of overall influence coefficients, and outputting the current optimal layout parameters.

[0041] Further, step S335 of the present invention further includes: S3351: Based on the several overall influence coefficients, the several initial layout parameters are mapped and arranged according to the coefficients from small to large to generate an initial parameter sequence; S3352: The initial parameters are set as the initial solutions, and the first N initial solutions of the initial parameter sequence are set as optimal solutions, and the last M initial solutions are set as inferior solutions, where M is K times N, and K is an integer greater than 10 and less than 50; S3353: Randomly cluster the M inferior solutions with the N optimal solutions as the center to generate N solution sets, and calculate N adjustment step sets.

[0042] Specifically, based on the several overall influence coefficients, the several initial layout parameters are mapped and arranged from small to large coefficients to generate an initial parameter sequence. The smaller the influence coefficient, the lower the noise impact and the better the layout; the larger the influence coefficient, the greater the noise impact of the layout scheme and the need for optimization and adjustment. Then, the initial parameters are set as the initial solution, and the first N initial solutions of the initial parameter sequence are set as the optimal solution, and the last M initial solutions are set as the inferior solution, where M and N are both positive integers, M is K times N, and K is an integer greater than 10 and less than 50, which can be set according to actual conditions, such as setting K to 20; then, the M inferior solutions are randomly clustered with the N optimal solutions as the center to generate N solution sets, with the same number of inferior solutions in each solution set, and N adjustment step sets of the N solution sets are calculated.

[0043] Further, step S3353 of the present invention also includes: S33531: Configure the initial adjustment step, wherein the initial adjustment step includes the position adjustment amplitude and the angle adjustment amplitude; S33532: Randomly select the first solution set, and obtain the first optimal solution overall influence coefficient of the first optimal solution in the first solution set, and multiple first inferior solution overall influence coefficients of multiple inferior solutions; S33533: Calculate the deviation ratio of the multiple first inferior solution overall influence coefficients to the first optimal solution overall influence coefficient respectively, and set multiple first correction weights according to the deviation ratio, wherein the deviation ratio and the correction weight are positively correlated; S33534: Optimize and correct the initial adjustment step according to the multiple first correction weights to obtain a first adjustment step set, and add it to the N adjustment step sets.

[0044] Specifically, the initial adjustment step is configured, wherein the initial adjustment step includes the position adjustment amplitude and the angle adjustment amplitude. The position adjustment amplitude is used to change the placement of the speaker to ensure that the speaker gradually moves closer to the optimal solution during the optimization process. It can be set according to actual conditions, such as setting the position adjustment amplitude to 0.2 meters; the angle adjustment amplitude is used to optimize the pointing angle of the speaker and reduce unnecessary noise diffusion, such as setting the angle adjustment amplitude to 5°. Then, any solution set is randomly selected from the N solution sets as the first solution set, and the first optimal solution overall influence coefficient of the first optimal solution in the first solution set and the first inferior solution overall influence coefficients of multiple inferior solutions are obtained.

[0045] Then, the deviation ratios of the overall influence coefficients of the multiple first inferior solutions and the overall influence coefficients of the first optimal solution are calculated respectively. The deviation ratio is the ratio of the difference between the overall influence coefficients of the first inferior solution and the overall influence coefficients of the first optimal solution to the overall influence coefficient of the first optimal solution, which indicates the increase in the noise influence degree of a certain inferior solution compared with the optimal solution. Multiple first correction weights are set according to the deviation ratio, wherein the deviation ratio and the correction weight are positively correlated, that is, the smaller the deviation ratio, the lower the weight, the smaller the adjustment step length, and the optimization accuracy is improved; the larger the deviation ratio, the higher the weight, the larger the adjustment step length, and the optimization efficiency is improved; the correction weight determines the step length of each inferior solution in the optimization adjustment, so that the optimization process takes into account both accuracy and efficiency. By calculating the deviation ratio of the overall influence coefficient and setting the correction weight, the optimization process can be made more intelligent, and both efficient and accurate parameter optimization can be achieved.

[0046] The initial adjustment step length is further optimized and corrected according to the multiple first correction weights, that is, the first correction weight is multiplied by the initial adjustment step length, and the product of the two is used as the first adjustment step length to obtain the first adjustment step length set, and the N adjustment step length sets of the N solution sets are calculated using the same method. By optimizing the adjustment step length with correction weights, intelligent and dynamic sound layout optimization is achieved, so that the optimization process can converge quickly and ensure the high accuracy of the final layout, thereby improving the scientificity and rationality of square dance noise management.

[0047] S3354: within the N solution sets, taking the best solution as the adjustment direction, optimizing and adjusting the inferior solutions within the solution set according to the N adjustment step sets, and outputting N updated solution sets, wherein if the adjusted inferior solution exceeds the range of the movable area of ​​the audio system, no adjustment is performed; S3355: calculating the overall influence coefficient of the inferior solutions within the N updated solution sets, and identifying the N updated solution sets, and if within the same updated solution set, the overall influence coefficient of the inferior solution is less than the overall influence coefficient of the superior solution, replacing the superior solution with the inferior solution; S3356: continuing to iterate and optimize until a predetermined number of optimization searches is reached, outputting N current updated solution sets, and selecting the current updated solution set with the smallest sum of the overall influence coefficients as the optimal solution set, and setting the superior solution of the optimal solution set as the current optimal layout parameter.

[0048] Specifically, in the N solution sets, the optimal solution is used as the adjustment direction, and the inferior solution in the solution set is optimized and adjusted according to the N adjustment step sets. At the same time, if the adjusted inferior solution exceeds the range of the movable area of ​​the audio system, this adjustment is not performed to avoid unreasonable audio layout due to excessive adjustment, and N updated solution sets are obtained. Then, the overall influence coefficient of the inferior solution in the N updated solution sets is calculated, and the N updated solution sets are identified. If the overall influence coefficient of the inferior solution is less than the overall influence coefficient of the superior solution in the same updated solution set, the superior solution is replaced by the inferior solution, that is, to ensure that the optimized superior solution is always the layout with the least noise impact; the same method is used to continue iterative optimization, and the optimization is repeated until the predetermined number of optimizations is reached, and N current updated solution sets are output, and the current updated solution set with the smallest sum of the overall influence coefficients is selected as the optimal solution set, and the optimal solution of the optimal solution set is set as the current optimal layout parameter.

[0049] The above optimization algorithm adopts a correction weight mechanism to dynamically adjust the step size, avoiding the local optimal stagnation problem caused by a fixed step size and making the optimization more accurate; it adopts an optimal solution replacement mechanism to automatically screen the optimal solution within the solution set to improve the optimization efficiency; in addition, in each iteration, multiple solution sets are optimized at the same time to ensure that the optimization schemes under different scenarios have higher adaptability, thereby improving the accuracy and efficiency of optimizing the sound layout parameters.

[0050] S400: placing the speakers in the current playback interval according to the optimal position and the optimal angle, and continuing to optimize the speaker placement in the order of the playback intervals until the square dance activity ends.

[0051] Specifically, the speakers are placed in the current playback interval according to the optimal position and the optimal angle, that is, the speakers are placed at the optimal coordinate point according to the calculated optimal position, and the speaker angle is adjusted to point to the optimal direction to reduce the noise impact on the residential area; the same method is used to continue to optimize the speaker placement in the order of the playback intervals, that is, after entering a new playback interval, the latest meteorological data, the probability of residents being at home and other information are obtained, and recalculated and adjusted according to the optimization algorithm, and the speaker layout is continuously optimized to ensure that the noise impact is minimized during the entire activity until the square dance activity ends. This method is based on the dynamic speaker placement optimization strategy of the optimal solution to ensure that the square dance speakers are in the optimal state in each playback interval, thereby minimizing the impact of noise on residents and improving the intelligent management level of square dance activities.

[0052] The square dance noise data processing method provided by the embodiment of the present invention has at least the following technical effects: The scheduled activity time period of square dancing is divided into multiple playback intervals, and the probability set of residents being at home in the noise coverage area is obtained according to the current playback interval matching; then a noise area simulation space is constructed according to the architectural features of the noise coverage area and the location coordinates of several families; the noise area simulation space is further utilized, and according to the current meteorological data and the probability set of residents being at home, the audio movable area range is used as the optimization space, and the audio layout parameters are iteratively optimized with the goal of minimizing the overall noise impact, and the current optimal layout parameters are output, wherein the current optimal layout parameters include the optimal position and the optimal angle; finally, the audio is placed in the current playback interval according to the optimal position and the optimal angle, and the audio placement optimization is continued in the order of the playback intervals until the square dance activity ends; the above method can improve the scientificity and rationality of the square dance activity venue and audio layout setting, so that the regional square dance noise pollution can be minimized while ensuring the entertainment experience, and intelligent and scientific urban noise management can be realized.

[0053] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0054] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A square dance noise data processing method, characterized in that: Methods include: The scheduled activity time period of square dancing is divided into multiple playing intervals, and the probability set of residents at home in the noise coverage area is obtained according to the current playing interval matching; Constructing a noise area simulation space according to the architectural features of the noise coverage area and the location coordinates of several households; Using the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, taking the movable area of ​​the sound system as the optimization space, and taking the overall noise impact as the goal, iterative optimization of the sound system layout parameters is performed, and the current optimal layout parameters are output, wherein the current optimal layout parameters include the optimal position and the optimal angle; The speakers are placed in the current playback interval according to the optimal position and optimal angle, and the speaker placement optimization is continued in the order of the playback intervals until the square dance activity ends.

2. A square dance noise data processing method according to claim 1, characterized in that: The scheduled activity time period of square dancing is divided into multiple play intervals, and the probability set of residents at home in the noise coverage area is obtained according to the current play interval matching, including: The noise diffusion coverage simulation is performed based on the maximum noise intensity of square dancing within a preset time period and the characteristics of surrounding buildings to determine the noise coverage area. In the noise diffusion simulation process, the default regional wind speed is 0; Divide the scheduled activity time period of the square dance according to the scheduled time step, and determine multiple play intervals; Counting the historical proportions of residents at home of several households in the noise coverage area in the multiple playback intervals respectively, setting them as historical resident at home probabilities, obtaining multiple historical resident at home probability sets, and establishing a probability mapping relationship between the playback intervals and the historical resident at home probability sets; The probability set of the resident being at home is obtained by matching the current playback interval with the probability mapping relationship.

3. A square dance noise data processing method according to claim 1, characterized in that: By using the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, taking the movable area of ​​the sound system as the optimization space, and taking the overall noise impact as the minimum as the goal, the sound system layout parameters are iteratively optimized, and the current optimal layout parameters are output, including: Obtaining a movable area range of the speakers for square dancing in the area, and randomly selecting a plurality of speaker placement positions within the movable area range of the speakers; Arrange a plurality of speaker placement angles according to a predetermined angle interval, randomly combine the plurality of speaker placement angles and a plurality of speaker placement positions, and generate a plurality of initial layout parameters; By using the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, with the goal of minimizing the overall noise impact, the sound layout parameters are iteratively optimized according to the several initial layout parameters, and the current optimal layout parameters are output.

4. A square dance noise data processing method according to claim 3, characterized in that: By using the noise area simulation space, according to the current meteorological data and the probability set of the residents being at home, with the goal of minimizing the overall noise impact, the sound layout parameters are iteratively optimized according to the several initial layout parameters, and the current optimal layout parameters are output, including: Using the noise region simulation space and combining it with a BP neural network, a noise diffusion simulator is constructed; Monitor and obtain current meteorological data, including wind speed and wind direction; Inputting the current meteorological data and a plurality of initial layout parameters into the noise diffusion simulator, and outputting a plurality of noise simulation intensity sets, wherein each noise simulation intensity set includes a plurality of noise simulation intensities of a plurality of households; Calculate a plurality of overall impact coefficients according to the plurality of noise simulation intensity sets and the plurality of resident at-home probability sets; The acoustic layout parameters are iteratively optimized according to the several initial layout parameters and the several overall influence coefficients, and the current optimal layout parameters are output.

5. A square dance noise data processing method according to claim 4, characterized in that: The noise diffusion simulator is constructed by using the noise region simulation space and combining with the BP neural network, including: Based on the noise region simulation space, an initial noise diffusion simulator is constructed using a BP neural network as a prediction logic; According to the regional noise monitoring records, a sample meteorological data set and a sample sound layout parameter set are collected, and a number of noise intensities of a number of households under different sample meteorological data and sample sound layout parameters are counted to obtain a plurality of sample noise intensity sets; The sample meteorological data set and the sample acoustic layout parameter set are used as inputs, and the multiple sample noise intensity sets are used as supervision to train the initial noise diffusion simulator until convergence, thereby obtaining the noise diffusion simulator.

6. A square dance noise data processing method according to claim 4, characterized in that: Several overall impact coefficients are calculated based on the several noise simulation intensity sets and the resident at home probability sets, including: Establish a location mapping relationship between the probability of residents being at home and the noise simulation intensity; Based on the location mapping association, taking the probability of residents being at home as a weight, weighted calculations are performed on the several noise simulation intensity sets according to the probability sets of residents being at home, and several overall impact coefficients are output.

7. A square dance noise data processing method according to claim 4, characterized in that: Iteratively optimizing the acoustic layout parameters according to the plurality of initial layout parameters and the plurality of overall influence coefficients, and outputting the current optimal layout parameters, including: Based on the plurality of overall influence coefficients, mapping and arranging the plurality of initial layout parameters according to the coefficients from small to large, to generate an initial parameter sequence; The initial parameters are set as the initial solutions, and the first N initial solutions of the initial parameter sequence are set as the optimal solutions, and the last M initial solutions are set as the inferior solutions, where M is K times N, and K is an integer greater than 10 and less than 50; Randomly cluster the M inferior solutions with N optimal solutions as the center, generate N solution sets, and calculate N adjustment step sets; In the N solution sets, taking the best solution as the adjustment direction, optimizing and adjusting the inferior solutions in the solution set according to the N adjustment step sets, and outputting N updated solution sets, wherein if the inferior solution after adjustment exceeds the range of the movable area of ​​the speaker, no adjustment is performed; Calculate the overall influence coefficient of the inferior solution in the N updated solution sets, and identify the N updated solution sets. If the overall influence coefficient of the inferior solution is less than the overall influence coefficient of the superior solution in the same updated solution set, replace the superior solution with the inferior solution; Continue to iterate and optimize until the predetermined number of optimization times is reached, output N current update solution sets, select the current update solution set with the smallest sum of overall influence coefficients as the optimal solution set, and set the optimal solution of the optimal solution set as the current optimal layout parameter.

8. A square dance noise data processing method according to claim 7, characterized in that: N adjustment step sets are calculated, including: Configure an initial adjustment step, wherein the initial adjustment step includes a position adjustment amplitude and an angle adjustment amplitude; Randomly select a first solution set, and obtain a first optimal solution overall influence coefficient of a first optimal solution in the first solution set, and multiple first inferior solution overall influence coefficients of multiple inferior solutions; Respectively calculating the deviation ratios of the first inferior solution overall influence coefficients and the first superior solution overall influence coefficient, and setting a plurality of first correction weights according to the deviation ratios, wherein the deviation ratios are positively correlated with the correction weights; The initial adjustment step length is optimized and corrected according to the multiple first correction weights to obtain a first adjustment step length set, which is added to the N adjustment step length sets.

Images