Control system and method for stage intelligent sound control sound equipment

Abstract

The invention relates to the technical field of remote volume adjustment, in particular to a control system and method for stage intelligent sound control sound equipment, and aims to accurately capture time distribution and amplitude characteristics of volume fluctuation by collecting environmental noise data in real time and combining a dynamic data analysis method, predict a future volume trend based on historical data, and improve the sound control efficiency. According to the logic based on dynamic prediction, the response capacity to sound changes is enhanced in volume control, the Kriging interpolation method is adopted to accurately analyze sound field requirements, the requirements of different areas are matched by adjusting sound field parameters, the sound field uniformity and the coverage accuracy are improved, and the volume control accuracy is improved. Meanwhile, the intelligence and automation level of the sound system is improved, the output power and frequency distribution of the sound equipment are dynamically adjusted through the particle swarm optimization algorithm, the output volume can be continuously optimized according to the real-time environment and sound field requirements, and the individual requirements of different stage performances are met.

Description

Technical Field

[0001] The present invention relates to the technical field of remote volume adjustment, and in particular to a control system and method for stage intelligent voice-controlled audio. Background Art

[0002] The field of remote volume control technology focuses on remote adjustment and optimization of the volume of audio devices through the combination of wireless communication, control algorithms and audio equipment, aiming to meet the flexible control needs of audio output in various application scenarios.

[0003] The control system of the stage intelligent voice-controlled audio system aims to enhance the intelligence level and remote control capability of the stage audio system, meet the real-time adjustment needs of sound in different performance scenes, realize fast and accurate adjustment of the audio volume, ensure the acoustic effect of stage performances, and improve the overall performance quality.

[0004] Although the existing technology can achieve remote adjustment of volume, it lacks real-time monitoring and prediction of environmental volume fluctuation data, resulting in the system being unable to respond to sudden volume changes in a timely manner. The output adjustment of the audio equipment relies on a single parameter adjustment, and it is difficult to accurately match the sound field requirements in different areas, resulting in excessive sound pressure or insufficient coverage in some areas, reducing the overall sound field uniformity. The existing system lacks analysis of the sound field layout and audience distribution, and it is difficult to adjust according to the actual acoustic requirements of the venue. This can easily lead to an imbalance in sound distribution in changing stage scenes, affecting the audience's auditory experience, limiting the adaptability of the existing system in complex scenes, and failing to meet diverse stage requirements, affecting the overall sound quality of stage performances. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a control system and method for stage intelligent voice-controlled audio.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A control system for stage intelligent voice-controlled audio comprises:

[0007] Real-time volume monitoring module: collects volume fluctuation data through environmental noise sensors, monitors volume data in real time and predicts future volume trends through dynamic data analysis, collects environmental volume changes and performs volume fluctuation analysis to obtain environmental volume predictions;

[0008] Volume adjustment strategy module: based on the environmental volume prediction, the Kriging interpolation method is used to analyze the sound field requirements in combination with the venue layout information and the audience distribution data, the volume parameter adjustment is used to simulate the influence of different sound field arrangements, the volume output parameters are adjusted to match the ideal sound field distribution, and the adjustment strategy parameters are generated;

[0009] Dynamic output adjustment module: through the adjustment strategy parameters, the particle swarm optimization algorithm is used to adjust the output settings of each audio device, the sound field effect is adjusted to match the sound field distribution of the venue through continuous monitoring, and the output of the audio device is adjusted in real time to obtain dynamic adjustment results;

[0010] Volume fine adjustment module: based on the dynamic adjustment result, the volume matching is optimized by adjusting the volume in a small range, the volume output is accurately adjusted to balance the sound field, and a fine adjustment result is generated;

[0011] Volume effect evaluation module: Based on the fine adjustment results, the volume output and sound field effect are continuously monitored through a sound level meter, while the impact of volume adjustment on the audience experience is evaluated and the sound field uniformity is analyzed to obtain an adjustment effect evaluation.

[0012] Preferably, the real-time volume monitoring module includes a volume data acquisition submodule, a dynamic data analysis submodule and a volume trend prediction submodule, wherein:

[0013] Volume data collection submodule: collects volume fluctuation data based on the environmental noise sensor, records the volume fluctuation amplitude and frequency changes through time-sharing sampling, and marks and segments the volume fluctuation data on the time axis to generate volume fluctuation collection data;

[0014] Dynamic data analysis submodule: based on the volume fluctuation collection data, extract the volume change points and statistical data distribution within the continuous time interval, and analyze the volume fluctuation frequency and amplitude characteristics to obtain the volume fluctuation law analysis results;

[0015] Volume trend prediction submodule: Based on the volume fluctuation law analysis results, analyze the volume historical fluctuation data and calculate the volume trend curve, predict the volume change amplitude in the future time interval, and obtain the environmental volume prediction.

[0016] Preferably, the volume adjustment strategy module includes a sound field demand analysis submodule, a volume parameter adjustment simulation submodule and an adjustment strategy parameter generation submodule, wherein:

[0017] Sound field demand analysis submodule: Based on the environmental volume prediction, the Kriging interpolation method is used, the venue layout information and the audience distribution data are combined, and the sound field distribution data at different positions in the venue are calculated to extract the sound field adjustment demand data of a specific area and obtain the sound field demand parameters;

[0018] Volume parameter adjustment simulation submodule: based on the sound field demand parameters, perform volume parameter adjustment simulation, simulate the specific impact of volume changes on the sound field layout by adjusting the output power and frequency distribution of multiple audio equipment in the venue, and generate a simulated sound field distribution diagram to obtain volume parameter simulation data;

[0019] Adjustment strategy parameter generation submodule: Based on the volume parameter simulation data, adjustment strategy parameters are generated, and the output configuration and adjustment sequence of each device are determined by analyzing the coverage parameters and output status of the audio equipment in the area in the sound field distribution map to obtain the adjustment strategy parameters.

[0020] Preferably, the Kriging interpolation method is according to the formula:

[0021]

[0022] Where: Z ′ (s) is the sound field distribution value of the position s to be predicted, μ is the global average sound field value, λ i is the weight coefficient, which is calculated by the covariance matrix, Z(s i ) is the sampling point s i The sound field value of the prediction point s, n is the total number of sampling points, α is the adjustment coefficient related to the site layout, D(s,L) is the distance influence function from the prediction point s to the obstacle, L is the obstacle distribution set in the site, β is the adjustment coefficient related to the audience distribution density, H(s) is the audience distribution density value of the prediction point s, γ is the adjustment coefficient related to the sound source power, and P(s) is the sound source power value received by the prediction point s.

[0023] Preferably, the dynamic output adjustment module includes an output parameter adjustment submodule, a sound field effect monitoring submodule and a dynamic adjustment result generation submodule, wherein:

[0024] Output parameter adjustment submodule: Based on the adjustment strategy parameters, the particle swarm optimization algorithm is used to dynamically adjust the power allocation range of the audio equipment, adjust the spatial direction and coverage of the sound output and associate the sound field distribution, complete the output parameter coordination, and generate the audio equipment output adjustment parameters;

[0025] Sound field effect monitoring submodule: Based on the output adjustment parameters of the audio equipment, multiple monitoring points are set to record changes in sound pressure level and volume coverage, and sound wave distribution data in the sound field is recorded in real time to perform sound field coverage and balance verification, and obtain dynamic monitoring data of sound field effects;

[0026] Dynamic adjustment result generation submodule: based on the sound field effect dynamic monitoring data, gradually adjust the output parameters of the audio equipment, and correct the output configuration by analyzing the differences in the sound field coverage and the areas of uneven sound pressure distribution to obtain dynamic adjustment results.

[0027] Preferably, the particle swarm optimization algorithm is based on the formula:

[0028]

[0029] in: is the velocity value of particle j at the k+1th iteration, φ is the inertia weight, is the velocity value of particle j at the kth iteration, a1 is the learning factor, b1 is a random number, q j is the adaptation position reached by particle j in the historical iteration, is the position of particle j at the kth iteration, a2 is the learning factor, b2 is a random number, z is the global adaptation position in all particle histories, ρ is the sound field coverage weight factor, c j is the dynamic environment correction factor, The current position of the particle The deviation value from the target sound field coverage area, η is the sound directivity weight factor, d j Adjust the correction factor for the sound output, The current position of the particle The corresponding sound source directivity optimization value.

[0030] Preferably, the volume fine adjustment module includes a volume fine adjustment submodule, a sound field balance optimization submodule and a fine adjustment result generation submodule, wherein:

[0031] Volume fine-tuning submodule: Based on the dynamic adjustment result, the output volume intensity and frequency distribution value of the audio equipment are adjusted by region, the relative power ratio between the devices is set, and the sound field coverage of the local area is verified to generate volume fine-tuning optimization parameters;

[0032] Sound field balance optimization submodule: based on the volume fine-tuning optimization parameters, by measuring the difference in sound pressure levels in each area and optimizing the volume distribution in turn, the strength relationship of the sound field in the coverage area is compared and adjusted to obtain sound field balance optimization data;

[0033] Fine-tuning result generation submodule: Based on the sound field balance optimization data, the output frequency, power and coverage angle of the audio equipment are optimized by region, the balance of the global sound field distribution is verified and corrected, and a fine-tuning result is generated.

[0034] Preferably, the volume effect evaluation module includes a volume output monitoring submodule, a listener experience evaluation submodule and a sound field uniformity analysis submodule, wherein:

[0035] Volume output monitoring submodule: Based on the fine adjustment result, the volume data of different areas are collected at fixed points through a sound level meter, and the sound pressure level and volume fluctuation range of each area are recorded at the same time. The collected sound pressure data are sorted and the time axis is marked to generate volume output monitoring data;

[0036] Audience experience evaluation submodule: Based on the volume output monitoring data, feedback data from audiences in different regions are collected and combined with sound pressure level changes to analyze auditory comfort, feedback data are classified and statistically analyzed by region, auditory perception distribution of each region is obtained, and audience experience evaluation data is obtained;

[0037] Sound field uniformity analysis submodule: Based on the audience experience evaluation data, the sound pressure levels in each area are compared to calculate the uniformity of the sound field distribution, and the areas with large differences in sound pressure levels are recorded. By summarizing the specific values ​​and distribution characteristics of the sound pressure differences between areas, the adjustment effect evaluation is obtained.

[0038] Preferably, the feedback data of listeners in different areas are collected and the auditory comfort is analyzed in combination with the sound pressure level changes. Based on the sound pressure level changes in different areas and the listener feedback data, fixed points are set in the areas to collect feedback, and the listener feedback data is recorded in three dimensions: scoring data, perceptual description, and regional distribution data. At the same time, combined with the data trend of the sound pressure level changes, interval matching and classification statistics are performed between the fluctuation range of the sound pressure level and the listener's comfort score, the influence of the sound pressure level change on the auditory comfort is analyzed, and the auditory perception distribution is summarized.

[0039] A method for controlling a stage intelligent voice-controlled speaker, the method for controlling a stage intelligent voice-controlled speaker being executed based on the control system of the stage intelligent voice-controlled speaker, comprising the following steps:

[0040] Step 1: Based on the real-time volume data obtained by the environmental noise sensor, the volume change curve of each time period is segmented, the volume fluctuation amplitude is calculated and the peak and trough points of the fluctuation are extracted, the fluctuation frequency and amplitude changes are analyzed, the change trend is compared with the established standard threshold, and the environmental volume prediction model is generated through multi-segment interval calculation;

[0041] Step 2: Based on the environmental volume prediction model, the venue layout information and audience distribution data are called, the audience distribution density and spatial parameters of the distance from the audio equipment in each sound field area are extracted, the sound pressure coverage range in the area is calculated, the sound pressure coverage value of each area is compared with the venue sound field requirements, the insufficient coverage parameters are extracted and the adjustment range is derived, and the regional sound pressure matching value is adjusted in combination with the venue sound field reflection characteristics and the target volume distribution parameters, and the Kriging interpolation algorithm is used to perform parameter fitting and supplementation on the multi-region sound field data to generate volume adjustment strategy parameters;

[0042] Step 3: Based on the volume adjustment strategy parameters, dynamically adjust the output settings of the audio equipment, calculate the corresponding values ​​of the output power and frequency band range of each device, and adjust the output power of devices in different partitions by matching the device power with the partition sound pressure coverage requirements one by one. The volume output parameters are gradually allocated to each device, and the device output configuration is optimized and allocated using the particle swarm optimization algorithm to complete the dynamic output adjustment and generate the dynamic output configuration parameters of the audio equipment;

[0043] Step 4: Based on the dynamic output configuration parameters of the audio equipment, the sound pressure distribution value is adjusted in a small range in each partition, the sound pressure mean value in the partition is compared with the target sound field distribution value one by one, and the fine-tuning parameter range is calculated. By optimizing the power output and crossover frequency band settings of each device, the sound pressure value compensation and device output optimization are finally completed, and the volume fine optimization result is generated;

[0044] Step 5: Based on the volume fine optimization result, the real-time volume value output by the audio equipment is monitored by a sound level meter, the sound pressure distribution and uniformity parameters in each partition sound field are extracted, the sound pressure distribution data is compared with the optimization result parameters, the distribution of the sound field uniformity deviation and the audience's perceived volume change is calculated, the overall volume adjustment effect is evaluated, and finally the sound field adjustment evaluation data is generated.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] 1. In the present invention, by collecting environmental noise data in real time and combining it with a dynamic data analysis method, the time distribution and amplitude characteristics of volume fluctuations can be accurately captured, and future volume trends can be predicted based on historical data. This logic based on dynamic prediction enhances the responsiveness to sound changes in volume control;

[0047] 2. In the present invention, the Kriging interpolation method is used to accurately analyze the sound field requirements, and the sound field parameters are adjusted to match the requirements of different regions, thereby improving the uniformity of the sound field and the accuracy of coverage, and at the same time improving the intelligence and automation level of the sound system;

[0048] 3. In the present invention, the output power and frequency distribution of the audio equipment are dynamically adjusted through the particle swarm optimization algorithm, so that the output volume can be continuously optimized according to the real-time environment and sound field requirements, reducing the phenomenon of uneven sound field distribution, and through the combination of continuous sound pressure level monitoring and audience feedback data, the adaptability of the audio system to complex scenes is improved, meeting the personalized needs of different stage performances. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a system flow chart of the present invention;

[0050] Figure 2It is a schematic diagram of the system framework of the present invention;

[0051] Figure 3 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] See also Figure 1 The present invention provides a technical solution: a control system for stage intelligent voice-controlled audio includes:

[0054] Real-time volume monitoring module: collects volume fluctuation data through environmental noise sensors, monitors volume data in real time and predicts future volume trends through dynamic data analysis, collects environmental volume changes and performs volume fluctuation analysis to obtain environmental volume predictions;

[0055] Volume adjustment strategy module: Based on the prediction of ambient volume, the Kriging interpolation method is used to analyze the sound field requirements in combination with the venue layout information and the audience distribution data. The volume parameter adjustment is used to simulate the impact of different sound field layouts, adjust the volume output parameters to match the ideal sound field distribution, and generate adjustment strategy parameters.

[0056] Dynamic output adjustment module: By adjusting the strategy parameters, the particle swarm optimization algorithm is used to adjust the output settings of each audio device, the sound field effect is adjusted to match the sound field distribution of the venue through continuous monitoring, and the output of the audio device is adjusted in real time to obtain dynamic adjustment results;

[0057] Volume fine-tuning module: Based on the dynamic adjustment results, the volume matching is optimized by adjusting the volume in a small range, and the volume output is precisely adjusted to balance the sound field, generating fine-tuning results;

[0058] Volume effect evaluation module: Based on the fine-tuning results, the volume output and sound field effect are continuously monitored through a sound level meter. At the same time, the impact of volume adjustment on the audience experience is evaluated and the uniformity of the sound field is analyzed to obtain an adjustment effect evaluation.

[0059] See also Figure 2 The real-time volume monitoring module includes a volume data acquisition submodule, a dynamic data analysis submodule and a volume trend prediction submodule, wherein:

[0060] Volume data collection submodule: collects volume fluctuation data based on the environmental noise sensor, records the volume fluctuation amplitude and frequency changes through time-sharing sampling, and marks and segments the volume fluctuation data on the time axis to generate volume fluctuation collection data;

[0061] Dynamic data analysis submodule: Based on the volume fluctuation data, the volume change points and statistical data distribution within the continuous time interval are extracted, and the volume fluctuation frequency and amplitude characteristics are analyzed to obtain the volume fluctuation law analysis results;

[0062] Volume trend prediction submodule: Based on the volume fluctuation law analysis results, analyze the volume historical fluctuation data and calculate the volume trend curve, predict the volume change range in the future time interval, and obtain the environmental volume prediction;

[0063] Volume data collection submodule: Based on the volume fluctuation data collected by the environmental noise sensor, the fixed time interval sampling method is used to record the sampled data in time, the sampling interval is set to 500 milliseconds and the sampled volume value is recorded. The volume value of each sampling point is attached with a timestamp label by the timestamp labeling method, and the sampled data is divided into independent data segments according to the time interval through segmentation processing. The time interval division rule is 60 seconds per segment and each segment data is stored as an array structure of the volume fluctuation value within the segment to generate volume fluctuation collection data;

[0064] Dynamic data analysis submodule: Based on the volume fluctuation data, the linear regression algorithm is used to count the volume change points in the continuous time interval, the timestamp and volume value of the sampling point are input and the timestamp is used as the independent variable and the volume value as the dependent variable, the volume fluctuation trend in the time interval is calculated and the extreme points and mean points of the fluctuation are extracted, the frequency distribution of the volume value sequence is calculated using discrete Fourier transform and the frequency distribution sequence and amplitude distribution characteristics are extracted, the frequency range and amplitude distribution law of the volume fluctuation are analyzed, and the volume fluctuation law analysis results are generated;

[0065] Volume trend prediction submodule: Based on the results of volume fluctuation law analysis, the ARIMA model is used to perform trend fitting analysis on the historical volume fluctuation data. The volume fluctuation data of the past 120 seconds is input into the model and the model autoregression order is set to 2, the difference order is set to 1, and the moving average order is set to 2. The model training results are used to generate time series prediction data and normalize them. The volume change amplitude in the future time interval is calculated through the multi-time step prediction method. The prediction time interval is set to the next 10 minutes and the step size is set to 30 seconds to generate the environmental volume prediction.

[0066] See also Figure 2 The volume adjustment strategy module includes a sound field demand analysis submodule, a volume parameter adjustment simulation submodule and an adjustment strategy parameter generation submodule, wherein:

[0067] Sound field demand analysis submodule: Based on the prediction of ambient volume, the Kriging interpolation method is used, combining the venue layout information and the audience distribution data, and by calculating the sound field distribution data at different locations in the venue, the sound field adjustment demand data of a specific area is extracted to obtain the sound field demand parameters;

[0068] Volume parameter adjustment simulation submodule: Based on the sound field demand parameters, the volume parameter adjustment simulation is performed. By adjusting the output power and frequency distribution of multiple audio equipment in the venue, the specific impact of volume changes on the sound field layout is simulated, and a simulated sound field distribution diagram is generated to obtain volume parameter simulation data;

[0069] Adjustment strategy parameter generation submodule: Based on the volume parameter simulation data, the adjustment strategy parameters are generated. By analyzing the coverage parameters and output status of the audio equipment in the area in the sound field distribution map, the output configuration and adjustment sequence of each device are determined, and the adjustment strategy parameters are obtained;

[0070] Sound field demand analysis submodule: Based on the prediction of the ambient volume, the Kriging interpolation method is used to calculate the venue layout information and the audience distribution data. First, the spatial coordinate points in the venue layout information are sampled, the sampling interval is set to 1 meter, and the venue coordinate points are constructed as a three-dimensional space dot matrix. The number of listeners and the distribution density value in each area are extracted based on the audience distribution data. The coordinate points are associated with the density data and then input into the Kriging model. The interpolation kernel function is determined by calculating the covariance matrix between the spatial points. The sound field distribution data of each position in the sound field is interpolated using the covariance matrix and the interpolation kernel function, and the difference between the interpolation result and the original distribution data is calculated. The sound field adjustment demand data of a specific area in the venue is extracted to generate the sound field demand parameters.

[0071] Volume parameter adjustment simulation submodule: Based on the sound field demand parameters, the output power and frequency distribution of multiple audio equipment in the venue are adjusted and simulated. The audio equipment parameter list is called to extract the output power value, frequency range and coverage area information of each device. The output power value of the device is adjusted step by step using the power adjustment algorithm. The increment of each adjustment is set to 20% of the current power value and the power change curve is recorded. The crossover settings of each device are adjusted in combination with the frequency range. The low-frequency and high-frequency cutoff points of the crossover are moved to both sides by 10 Hz respectively to change the frequency distribution range. At the same time, the adjusted power and frequency parameters are called to generate a simulated sound field distribution diagram, and the sound field coverage range and sound pressure changes are recorded one by one to generate volume parameter simulation data;

[0072] Adjustment strategy parameter generation submodule: Based on the volume parameter simulation data, by analyzing the sound pressure coverage status of each area in the simulated sound field distribution diagram and the output configuration of the audio equipment, the output power and coverage range of each device are extracted, and the sorting algorithm is used to calculate the adjustment order from near to far according to the distance of the device. The output power of the device is gradually allocated and the power increment is set according to the adjustment strategy parameters. The device configuration list in the adjustment strategy is generated, and the adjustment strategy parameters are obtained by integrating the output power and frequency range of the device.

[0073] See also Figure 2, Kriging interpolation method, according to the formula:

[0074]

[0075] Where: Z ′ (s) is the sound field distribution value of the position s to be predicted, μ is the global average sound field value, λ i is the weight coefficient, which is calculated by the covariance matrix, Z(s i ) is the sampling point s i The sound field value of the prediction point s, n is the total number of sampling points, α is the adjustment coefficient related to the site layout, D(s,L) is the distance influence function from the prediction point s to the obstacle, L is the obstacle distribution set in the site, β is the adjustment coefficient related to the audience distribution density, H(s) is the audience distribution density value of the prediction point s, γ is the adjustment coefficient related to the sound source power, and P(s) is the sound source power value received by the prediction point s.

[0076] Execution process: First, calculate the global average sound field value μ, and then use the sound field value Z(s i ) Establish the covariance matrix and determine the weight coefficient λ according to the spatial correlation i , calculate the preliminary predicted sound field value, then use the newly added parameters to optimize the sound field distribution, analyze the venue layout information to obtain the obstacle distribution set L, calculate the distance D(s,L) from the predicted point s to the nearest obstacle through geometric acoustic simulation, and set the adjustment coefficient α in combination with the material characteristics of the obstacle. Then, combine the audience distribution data to statistically predict the audience density value H(s) of the prediction point s, and determine the adjustment coefficient β according to the attenuation effect of the density change on the sound field. Finally, analyze the sound source power distribution, measure the sound source power value P(s) received by the prediction point s, and optimize the adjustment coefficient γ according to the influence of power on the sound field. Substitute all parameters into the formula to achieve accurate prediction of the stage sound field and provide a basis for the sound field distribution for the intelligent control of the sound system.

[0077] See also Figure 2 The dynamic output adjustment module includes an output parameter adjustment submodule, a sound field effect monitoring submodule and a dynamic adjustment result generation submodule, wherein:

[0078] Output parameter adjustment submodule: Based on the adjustment strategy parameters, the particle swarm optimization algorithm is used to dynamically adjust the power allocation range of the audio equipment, adjust the spatial direction and coverage of the sound output and associate it with the sound field distribution, complete the output parameter coordination, and generate the output adjustment parameters of the audio equipment;

[0079] Sound field effect monitoring submodule: Based on the output adjustment parameters of the audio equipment, multiple monitoring points are set to record the changes in the sound pressure level and volume coverage, and the sound wave distribution data in the sound field is recorded in real time to perform sound field coverage and balance verification, and obtain dynamic monitoring data of the sound field effect;

[0080] Dynamic adjustment result generation submodule: Based on the dynamic monitoring data of the sound field effect, the output parameters of the audio equipment are gradually adjusted. By analyzing the differences in the sound field coverage and the areas of uneven sound pressure distribution, the output configuration is corrected to obtain the dynamic adjustment results.

[0081] Output parameter adjustment submodule: Based on the adjustment strategy parameters, the particle swarm optimization algorithm is used to dynamically adjust the power distribution range of the audio equipment. The output power value, sound wave direction angle and coverage range of the audio equipment are set as the particle position. The initial speed of each particle is set to 5% of the power adjustment range. The global fitness function is used to evaluate the sound field coverage and power distribution of each device. The fitness function generates a fitness value by calculating the coverage uniformity and sound pressure distribution range of the target sound field area. The particle position is adjusted to the optimal solution of the power value and sound wave direction angle through the update formula, and it is iterated until convergence. The output power distribution and direction angle adjustment of the audio equipment are completed, and the output adjustment parameters of the audio equipment are generated;

[0082] Sound field effect monitoring submodule: Based on the output adjustment parameters of the audio equipment, the sound pressure level and volume coverage in the sound field are monitored in real time. The sound field monitoring module is called to set the monitoring point coordinates and sampling frequency. The monitoring point coordinates are evenly distributed at intervals of 5 meters and cover all audience areas of the venue. The sampling frequency is set to collect once every 1 second. The sound pressure level data and coverage range value of each monitoring point are recorded. The collected data is marked with a timestamp in real time and stored as a dynamic distribution data table. The coverage uniformity value is calculated by comparing the sound pressure differences between the monitoring points, and it is verified whether the sound pressure level in each area meets the distribution requirements to generate dynamic monitoring data of the sound field effect.

[0083] Dynamic adjustment result generation submodule: Based on the dynamic monitoring data of the sound field effect, the output parameters of the audio equipment are gradually adjusted. By analyzing the difference in sound pressure level and coverage in each area, the regional data of uneven sound pressure distribution is extracted, and the regional data is associated with the output parameters of the current audio equipment. The output power and direction angle of the equipment in the uneven area are gradually adjusted. The step size of the power adjustment is 10% of the current value and the adjusted coverage is recorded. The equipment configuration is corrected and the dynamic adjustment results are generated;

[0084] See also Figure 2 , particle swarm optimization algorithm, according to the formula:

[0085]

[0086] in: is the velocity value of particle j at the k+1th iteration, φ is the inertia weight, is the velocity value of particle j at the kth iteration, a1 is the learning factor, b1 is a random number, qj is the adaptation position reached by particle j in the historical iteration, is the position of particle j at the kth iteration, a2 is the learning factor, b2 is a random number, z is the global adaptation position in all particle histories, ρ is the sound field coverage weight factor, c j is the dynamic environment correction factor, The current position of the particle The deviation value from the target sound field coverage area, η is the sound directivity weight factor, d j Adjust the correction factor for the sound output, The current position of the particle The corresponding sound source directivity optimization value.

[0087] Execution process: First, initialize the speed and position of the particle group and calculate the current speed of the particle and location The inertia weight υ is used to balance the global and local search capabilities of the particle swarm, and the particles are guided to their individual historical optimal positions q based on the learning factors a1 and a2 combined with the random numbers b1 and b2 j The particle velocity is updated based on the historical optimal position z of the group. Then, new parameters are introduced to meet the specific needs of sound control. First, the sound field distribution and coverage requirements of the venue are analyzed to calculate the sound field coverage weight factor ρ. Combined with the current position of the particle The geometric deviation from the target coverage area to obtain the coverage deviation value Dynamically adjust the coverage range, and then calculate the dynamic environment correction coefficient c based on real-time environment detection data j , correct the particle position and velocity, analyze the directivity requirements of the audio equipment, and calculate the audio directivity weight factor η and the directivity optimization value combined with the coverage angle optimization strategy of the sound source The sound field is evenly distributed by optimizing the sound field coverage direction, and finally the adjustment correction coefficient d is calculated based on the output power adjustment strategy of the audio equipment. j , comprehensively consider the power distribution range and directional optimization, substitute all parameters into the formula, complete the speed and position update of the particles, generate the output adjustment parameters of the audio equipment through multiple iterations, and realize the intelligent coordination of power distribution, directional coverage and sound field distribution.

[0088] See also Figure 2 The volume fine adjustment module includes a volume fine adjustment submodule, a sound field balance optimization submodule and a fine adjustment result generation submodule, wherein:

[0089] Volume fine-tuning submodule: Based on the dynamic adjustment results, the output volume intensity and frequency distribution value of the audio equipment are adjusted by region, the relative power ratio between the devices is set, and the sound field coverage of the local area is verified to generate volume fine-tuning optimization parameters;

[0090] Sound field balance optimization submodule: Based on volume fine-tuning optimization parameters, by measuring the sound pressure level differences in each area and optimizing the volume distribution in turn, the sound field strength relationship in the coverage area is compared and adjusted to obtain sound field balance optimization data;

[0091] Fine-tuning result generation submodule: Based on the sound field balance optimization data, the output frequency, power and coverage angle of the audio equipment are optimized by region, the balance of the global sound field distribution is verified and corrected, and the fine-tuning result is generated;

[0092] Volume fine-tuning submodule: Based on the dynamic adjustment results, the output volume intensity and frequency distribution value of the audio equipment are adjusted by region, the device parameter management module is called to extract the current power output value and frequency range of each audio equipment, the difference between the sound pressure level data of each area and the target volume value is calculated, the difference is used as the volume adjustment step, the volume intensity adjustment step is set to 10% of the difference and gradually increased, the ratio control method is used to calculate the relative power ratio between the devices, the regional sound field coverage model is used to check the sound field coverage of the local area point by point, the sound pressure value of each check point is compared with the sound pressure value of the adjacent point, and the power configuration parameters of the abnormal coverage point are recorded to generate the volume fine-tuning optimization parameters;

[0093] Sound field balance optimization submodule: Based on the volume fine-tuning optimization parameters, the sound pressure level data of each area is measured, and the hierarchical optimization method is used to gradually optimize the sound pressure level difference. The sound pressure level data in the area is divided into five levels according to the relationship between strength and weakness. The output volume of the audio equipment in each level is dynamically adjusted, and the regional sound field data model is called to calculate the difference in the strength relationship of the sound field in the coverage area. The difference in strength is controlled within the set threshold range and the uneven area is locally adjusted. The corrected parameters are compared twice by updating the equipment frequency output range and power coverage value to obtain the sound field balance optimization data;

[0094] Fine-tuning result generation submodule: Based on the sound field balance optimization data, the output frequency, power and coverage angle of the audio equipment in each area are optimized in different areas. The global sound field balance model is called to calculate the sound field coverage status in the current area. The upper and lower limits of the frequency output value are gradually adjusted according to the coverage range requirements. The amplitude of each adjustment is set to 1% of the current frequency band and the adjusted sound field coverage value is recorded. The sound pressure distribution is corrected by adjusting the coverage angle area by area. The angle adjustment step is set to 1 degree and the corresponding sound pressure level change value after the angle change is dynamically recorded. The global sound field balance is checked point by point and the parameter configuration is corrected to generate fine-tuning results.

[0095] See also Figure 2The volume effect evaluation module includes a volume output monitoring submodule, a listener experience evaluation submodule and a sound field uniformity analysis submodule, wherein:

[0096] Volume output monitoring submodule: Based on the fine-tuning results, the volume data of different areas are collected at fixed points through a sound level meter, and the sound pressure level and volume fluctuation range of each area are recorded. The collected sound pressure data is sorted and the time axis is marked to generate volume output monitoring data;

[0097] Audience experience evaluation submodule: Based on the volume output monitoring data, feedback data from listeners in different regions is collected and combined with the sound pressure level changes to analyze auditory comfort. The feedback data is classified and statistically analyzed by region to obtain the auditory perception distribution of each region and the audience experience evaluation data.

[0098] Sound field uniformity analysis submodule: Based on the audience experience evaluation data, the sound pressure level of each area is compared to calculate the uniformity of the sound field distribution, and the areas with large differences in sound pressure levels are recorded. By summarizing the specific values ​​and distribution characteristics of the sound pressure differences between areas, the adjustment effect evaluation is obtained;

[0099] Volume output monitoring submodule: Based on the fine-tuning results, the volume data of each area is collected at a fixed point through a sound level meter. The spatial distribution interval of the monitoring points is set to 5 meters and the coordinates are marked by area. The sound pressure level data recorded at each monitoring point is bound to the timestamp, and the collected sound pressure data is sorted into a time series data set. The collected time series is sorted into 10-second segments by calling the data segmentation algorithm, and the volume fluctuation range and sound pressure level change trend in each segment are marked to generate volume output monitoring data.

[0100] Audience experience evaluation submodule: Based on the volume output monitoring data, the subjective feedback data of the audience in each area is collected through the regional feedback collection device, and the feedback data is divided into three categories: volume comfort score, volume uniformity perception and auditory fatigue degree. The feedback data is classified by region and a regional feedback data table is established. The subjective feedback score and the sound pressure level change are linearly correlated with the sound pressure level change sequence in the monitoring data. The feedback mean and distribution characteristics within the sound pressure change range of each region are extracted. The feedback data is classified and summarized through regional statistical methods to obtain audience experience evaluation data;

[0101] Sound field uniformity analysis submodule: Based on the audience experience evaluation data, the sound pressure level of each area is compared and analyzed point by point, and the regional sound pressure level data is mapped to the venue sound field model according to the spatial distribution of the monitoring points. The unevenness of the sound field distribution is obtained by calculating the mean square error of the sound pressure level between the areas, and the areas with large sound pressure level differences and their corresponding specific values ​​are recorded. The distribution characteristics of the sound pressure level difference areas are analyzed and the frequency of regional differences is counted. The sound pressure distribution characteristic table of the difference areas is generated to obtain the adjustment effect evaluation;

[0102] Feedback data from listeners in different areas were collected and analyzed in combination with changes in sound pressure levels for auditory comfort. Based on the changes in sound pressure levels and listener feedback data in different areas, fixed points were set up in the area to collect feedback and record the listeners' subjective evaluation of volume comfort, auditory fatigue, and sound clarity. The listener feedback data were organized into three dimensions: scoring data, perceptual description, and regional distribution data. At the same time, combined with the data trend of sound pressure level changes, interval matching and classification statistics were performed between the fluctuation range of sound pressure levels and the listeners' comfort scores, the impact of sound pressure level changes on auditory comfort was analyzed, and the auditory perception distribution was summarized.

[0103] See also Figure 3 A control method for stage intelligent voice-controlled audio is provided. The control method for stage intelligent voice-controlled audio is performed based on the control system of the stage intelligent voice-controlled audio, and comprises the following steps:

[0104] Step 1: Based on the real-time volume data obtained by the environmental noise sensor, the volume change curve of each time period is segmented, the volume fluctuation amplitude is calculated and the peak and trough points of the fluctuation are extracted, the fluctuation frequency and amplitude changes are analyzed, the change trend is compared with the established standard threshold, and the environmental volume prediction model is generated through multi-segment interval calculation;

[0105] Step 2: Based on the environmental volume prediction model, the venue layout information and audience distribution data are called to extract the audience distribution density and spatial parameters of the distance from the audio equipment in each sound field area, calculate the sound pressure coverage range in the area, compare the sound pressure coverage value of each area with the venue sound field requirements, extract the insufficient coverage parameters and derive the adjustment range, combine the venue sound field reflection characteristics and target volume distribution parameters, adjust the regional sound pressure matching value, use the Kriging interpolation algorithm to perform parameter fitting and supplementation on the multi-region sound field data, and generate volume adjustment strategy parameters;

[0106] Step 3: Based on the volume adjustment strategy parameters, dynamically adjust the output settings of the audio equipment, calculate the corresponding values ​​of the output power and frequency band range of each device, and adjust the output power of devices in different partitions by matching the device power with the partition sound pressure coverage requirements one by one. The volume output parameters are gradually allocated to each device, and the particle swarm optimization algorithm is used to optimize the device output configuration, complete the dynamic output adjustment, and generate the dynamic output configuration parameters of the audio equipment;

[0107] Step 4: Based on the dynamic output configuration parameters of the audio equipment, make small adjustments to the sound pressure distribution value in each partition, compare the average sound pressure value in the partition with the target sound field distribution value one by one, calculate the fine-tuning parameter range, and optimize the power output and crossover frequency band settings of each device to finally complete the sound pressure value compensation and device output optimization, and generate a fine volume optimization result;

[0108] Step 5: Based on the volume fine-tuning results, monitor the real-time volume value output by the audio equipment through a sound level meter, extract the sound pressure distribution and uniformity parameters in each partition sound field, compare the sound pressure distribution data with the optimization result parameters, calculate the distribution of the sound field uniformity deviation and the audience's perceived volume change, evaluate the overall volume adjustment effect, and finally generate the sound field adjustment evaluation data.

[0109] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A control system for stage intelligent voice-controlled audio, characterized in that: The system comprises: Real-time volume monitoring module: collects volume fluctuation data through environmental noise sensors, monitors volume data in real time and predicts future volume trends through dynamic data analysis, collects environmental volume changes and performs volume fluctuation analysis to obtain environmental volume predictions; Volume adjustment strategy module: based on the environmental volume prediction, the Kriging interpolation method is used to analyze the sound field requirements in combination with the venue layout information and the audience distribution data, the volume parameter adjustment is used to simulate the influence of different sound field arrangements, the volume output parameters are adjusted to match the ideal sound field distribution, and the adjustment strategy parameters are generated; Dynamic output adjustment module: through the adjustment strategy parameters, the particle swarm optimization algorithm is used to adjust the output settings of each audio device, the sound field effect is adjusted to match the sound field distribution of the venue through continuous monitoring, and the output of the audio device is adjusted in real time to obtain dynamic adjustment results; Volume fine adjustment module: based on the dynamic adjustment result, the volume matching is optimized by adjusting the volume in a small range, the volume output is accurately adjusted to balance the sound field, and a fine adjustment result is generated; Volume effect evaluation module: Based on the fine adjustment results, the volume output and sound field effect are continuously monitored through a sound level meter, while the impact of volume adjustment on the audience experience is evaluated and the sound field uniformity is analyzed to obtain an adjustment effect evaluation.

2. The control system of the stage intelligent voice-controlled audio system according to claim 1 is characterized in that: The real-time volume monitoring module includes a volume data acquisition submodule, a dynamic data analysis submodule and a volume trend prediction submodule, wherein: Volume data collection submodule: collects volume fluctuation data based on the environmental noise sensor, records the volume fluctuation amplitude and frequency changes through time-sharing sampling, and marks and segments the volume fluctuation data on the time axis to generate volume fluctuation collection data; Dynamic data analysis submodule: based on the volume fluctuation collection data, extract the volume change points and statistical data distribution within the continuous time interval, and analyze the volume fluctuation frequency and amplitude characteristics to obtain the volume fluctuation law analysis results; Volume trend prediction submodule: Based on the volume fluctuation law analysis results, analyze the volume historical fluctuation data and calculate the volume trend curve, predict the volume change amplitude in the future time interval, and obtain the environmental volume prediction.

3. The control system of the stage intelligent voice-controlled audio system according to claim 1 is characterized in that: The volume adjustment strategy module includes a sound field demand analysis submodule, a volume parameter adjustment simulation submodule and an adjustment strategy parameter generation submodule, wherein: Sound field demand analysis submodule: Based on the environmental volume prediction, the Kriging interpolation method is used, the venue layout information and the audience distribution data are combined, and the sound field distribution data at different positions in the venue are calculated to extract the sound field adjustment demand data of a specific area and obtain the sound field demand parameters; Volume parameter adjustment simulation submodule: based on the sound field demand parameters, perform volume parameter adjustment simulation, simulate the specific impact of volume changes on the sound field layout by adjusting the output power and frequency distribution of multiple audio equipment in the venue, and generate a simulated sound field distribution diagram to obtain volume parameter simulation data; Adjustment strategy parameter generation submodule: Based on the volume parameter simulation data, adjustment strategy parameters are generated, and the output configuration and adjustment sequence of each device are determined by analyzing the coverage parameters and output status of the audio equipment in the area in the sound field distribution map to obtain the adjustment strategy parameters.

4. The control system of the stage intelligent voice-controlled audio system according to claim 3 is characterized in that: The Kriging interpolation method is as follows: Where: Z ′ (s) is the sound field distribution value of the position s to be predicted, μ is the global average sound field value, λ i is the weight coefficient, which is calculated by the covariance matrix, Z(s i ) is the sampling point s i The sound field value of the prediction point s, n is the total number of sampling points, α is the adjustment coefficient related to the site layout, D(s,L) is the distance influence function from the prediction point s to the obstacle, L is the obstacle distribution set in the site, β is the adjustment coefficient related to the audience distribution density, H(s) is the audience distribution density value of the prediction point s, γ is the adjustment coefficient related to the sound source power, and P(s) is the sound source power value received by the prediction point s.

5. The control system of the stage intelligent voice-controlled audio system according to claim 1 is characterized in that: The dynamic output adjustment module includes an output parameter adjustment submodule, a sound field effect monitoring submodule and a dynamic adjustment result generation submodule, wherein: Output parameter adjustment submodule: Based on the adjustment strategy parameters, the particle swarm optimization algorithm is used to dynamically adjust the power allocation range of the audio equipment, adjust the spatial direction and coverage of the sound output and associate the sound field distribution, complete the output parameter coordination, and generate the audio equipment output adjustment parameters; Sound field effect monitoring submodule: Based on the output adjustment parameters of the audio equipment, multiple monitoring points are set to record changes in sound pressure level and volume coverage, and sound wave distribution data in the sound field is recorded in real time to perform sound field coverage and balance verification, and obtain dynamic monitoring data of sound field effects; Dynamic adjustment result generation submodule: based on the sound field effect dynamic monitoring data, gradually adjust the output parameters of the audio equipment, and correct the output configuration by analyzing the differences in the sound field coverage and the areas of uneven sound pressure distribution to obtain dynamic adjustment results.

6. The control system of the stage intelligent voice-controlled audio system according to claim 1 is characterized in that: The particle swarm optimization algorithm is based on the formula: in: is the velocity value of particle j at the k+1th iteration, φ is the inertia weight, is the velocity value of particle j at the kth iteration, a1 is the learning factor, b1 is a random number, q j is the adaptation position reached by particle j in the historical iteration, is the position of particle j at the kth iteration, a2 is the learning factor, b2 is a random number, z is the global adaptation position in all particle histories, ρ is the sound field coverage weight factor, c j is the dynamic environment correction factor, The current position of the particle The deviation value from the target sound field coverage area, η is the sound directivity weight factor, d j Adjust the correction factor for the sound output, The current position of the particle The corresponding sound source directivity optimization value.

7. The control system of the stage intelligent voice-controlled audio system according to claim 6, characterized in that: The volume fine adjustment module includes a volume fine adjustment submodule, a sound field balance optimization submodule and a fine adjustment result generation submodule, wherein: Volume fine-tuning submodule: Based on the dynamic adjustment result, the output volume intensity and frequency distribution value of the audio equipment are adjusted by region, the relative power ratio between the devices is set, and the sound field coverage of the local area is verified to generate volume fine-tuning optimization parameters; Sound field balance optimization submodule: based on the volume fine-tuning optimization parameters, by measuring the sound pressure level differences in each area and optimizing the volume distribution in turn, the strength relationship of the sound field in the coverage area is compared and adjusted to obtain sound field balance optimization data; Fine-tuning result generation submodule: Based on the sound field balance optimization data, the output frequency, power and coverage angle of the audio equipment are optimized by region, the balance of the global sound field distribution is verified and corrected, and a fine-tuning result is generated.

8. The control system of the stage intelligent voice-controlled audio system according to claim 1 is characterized in that: The volume effect evaluation module includes a volume output monitoring submodule, a listener experience evaluation submodule and a sound field uniformity analysis submodule, wherein: Volume output monitoring submodule: Based on the fine adjustment result, the volume data of different areas are collected at fixed points through a sound level meter, and the sound pressure level and volume fluctuation range of each area are recorded at the same time. The collected sound pressure data are sorted and the time axis is marked to generate volume output monitoring data; Audience experience evaluation submodule: Based on the volume output monitoring data, feedback data from audiences in different regions are collected and combined with sound pressure level changes to analyze auditory comfort, feedback data are classified and statistically analyzed by region, auditory perception distribution of each region is obtained, and audience experience evaluation data is obtained; Sound field uniformity analysis submodule: Based on the audience experience evaluation data, the sound pressure levels in each area are compared to calculate the uniformity of the sound field distribution, and the areas with large differences in sound pressure levels are recorded. By summarizing the specific values ​​and distribution characteristics of the sound pressure differences between areas, the adjustment effect evaluation is obtained.

9. The control system of the stage intelligent voice-controlled audio system according to claim 8, characterized in that: The method collects feedback data from listeners in different areas and analyzes auditory comfort in combination with sound pressure level changes. Based on the sound pressure level changes in different areas and the listener feedback data, a fixed-point feedback collection method is set in the area to record the listeners' subjective evaluation of volume comfort, auditory fatigue and sound clarity. The listener feedback data is organized into three dimensions: scoring data, perceptual description and regional distribution data. At the same time, combined with the data trend of sound pressure level changes, interval matching and classification statistics are performed between the fluctuation range of the sound pressure level and the listener's comfort score, the influence of the sound pressure level change on auditory comfort is analyzed, and the auditory perception distribution is summarized.

10. A method for controlling stage intelligent voice-controlled audio, characterized in that: The control system of the stage intelligent voice-controlled audio system according to any one of claims 1 to 9 comprises the following steps: Step 1: Based on the real-time volume data obtained by the environmental noise sensor, the volume change curve of each time period is segmented, the volume fluctuation amplitude is calculated and the peak and trough points of the fluctuation are extracted, the fluctuation frequency and amplitude changes are analyzed, the change trend is compared with the established standard threshold, and the environmental volume prediction model is generated through multi-segment interval calculation; Step 2: Based on the environmental volume prediction model, the venue layout information and audience distribution data are called, the audience distribution density and spatial parameters of the distance from the audio equipment in each sound field area are extracted, the sound pressure coverage range in the area is calculated, the sound pressure coverage value of each area is compared with the venue sound field requirements, the insufficient coverage parameters are extracted and the adjustment range is derived, and the regional sound pressure matching value is adjusted in combination with the venue sound field reflection characteristics and the target volume distribution parameters, and the Kriging interpolation algorithm is used to perform parameter fitting and supplementation on the multi-region sound field data to generate volume adjustment strategy parameters; Step 3: Based on the volume adjustment strategy parameters, dynamically adjust the output settings of the audio equipment, calculate the corresponding values ​​of the output power and frequency band range of each device, and adjust the output power of devices in different partitions by matching the device power with the partition sound pressure coverage requirements one by one. The volume output parameters are gradually allocated to each device, and the device output configuration is optimized and allocated using the particle swarm optimization algorithm to complete the dynamic output adjustment and generate the dynamic output configuration parameters of the audio equipment; Step 4: Based on the dynamic output configuration parameters of the audio equipment, the sound pressure distribution value is adjusted in a small range in each partition, the sound pressure mean value in the partition is compared with the target sound field distribution value one by one, and the fine-tuning parameter range is calculated. By optimizing the power output and crossover frequency band settings of each device, the sound pressure value compensation and device output optimization are finally completed, and the volume fine optimization result is generated; Step 5: Based on the volume fine optimization result, the real-time volume value output by the audio equipment is monitored by a sound level meter, the sound pressure distribution and uniformity parameters in each partition sound field are extracted, the sound pressure distribution data is compared with the optimization result parameters, the distribution of the sound field uniformity deviation and the audience's perceived volume change is calculated, the overall volume adjustment effect is evaluated, and finally the sound field adjustment evaluation data is generated.

Images