A frequency band intelligent control method and system for wireless microphone

Abstract

The present invention relates to the field of wireless communication technology, and in particular to a method and system for intelligently controlling the frequency band of a wireless microphone. The method comprises the following steps: obtaining wireless microphone audio signal data and environmental sensor data, and performing preliminary calibration of the audio signal to obtain a preliminary calibration environmental audio data set; identifying environmental interference sources on the preliminary calibration environmental audio data set to obtain a spectrum interference identification report; obtaining real-time wireless spectrum resource allocation data; dynamically adjusting the frequency band of the real-time wireless spectrum resource allocation data to obtain a dynamically optimized frequency band adjustment data set; constructing a frequency response compensation model based on the dynamically optimized frequency band adjustment data set; adaptively allocating wireless microphone communication frequency band resources through the frequency response compensation model, thereby obtaining wireless microphone communication frequency band resource data, and transmitting it to a wireless microphone frequency band control platform. The present invention can significantly improve the signal quality of wireless microphones and the effective utilization rate of frequency band resources.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communications, and in particular to a frequency band intelligent control method and system for a wireless microphone. Background Art

[0002] With the rapid development of wireless communication technology, wireless microphones, as an important wireless communication device, have been widely used in performances, conferences, broadcasting and other fields. Wireless microphones can transmit audio information through wireless signals, which greatly improves the flexibility and convenience of use. However, with the increase in the number of wireless communication devices and the diversification of usage scenarios, the selection and management of frequency bands have gradually been exposed, becoming a key factor affecting the performance of wireless microphones. Traditional wireless microphones operate within a certain frequency band range, and the user usually manually selects the operating frequency or relies on the built-in frequency hopping mechanism of the device. However, due to limited spectrum resources, especially in high-density environments such as large conferences or performance venues, interference between frequency bands is very serious. When different wireless devices work in the same or adjacent frequency bands, the signals may interfere with each other, resulting in a decrease in signal quality, or even audio interruption or loss, which greatly affects the user experience. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for intelligently controlling the frequency band of a wireless microphone to solve at least one of the above technical problems.

[0004] To achieve the above object, a frequency band intelligent control method for a wireless microphone comprises the following steps:

[0005] Step S1: obtaining wireless microphone audio signal data and environmental sensor data, and performing preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set;

[0006] Step S2: performing spectrum decomposition on the preliminary calibration environment audio data set to obtain an environment audio decomposition spectrum, and identifying the environment interference source according to the environment audio decomposition spectrum to obtain a spectrum interference identification report;

[0007] Step S3: acquiring real-time wireless spectrum resource allocation data; performing frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjusting the wireless microphone working frequency band of the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set;

[0008] Step S4: performing audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and constructing a frequency response compensation model according to the audio signal frequency response compensation data;

[0009] Step S5: Optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate wireless microphone communication frequency band resources based on the real-time optimized signal data set to obtain wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0010] The present invention can eliminate the influence caused by signal interference or environmental changes in different environments by integrating and calibrating the wireless microphone audio signal data and environmental sensor data, and ensure the accuracy and stability of audio data. Spectral decomposition and identification of environmental interference sources can accurately locate and analyze the frequency band interference problem in the wireless microphone use environment. This precise interference source identification helps to identify the interference source in the frequency band in a targeted manner, avoid the signal quality degradation or audio interruption phenomenon during frequency band selection, and lay the foundation for subsequent frequency band adjustment and resource optimization. In the process of real-time wireless spectrum resource allocation, combined with the identification and analysis of interference patterns, the working frequency band of the wireless microphone can be dynamically adjusted, which not only avoids interference between frequency bands, but also enables the wireless microphone to intelligently select the frequency band according to the actual situation in a high-density environment, effectively reducing communication interruption or signal attenuation caused by frequency band congestion. This dynamic optimization process ensures that the wireless microphone can always operate within the optimal frequency band range in different scenarios, and maximizes the quality and stability of wireless communication. The frequency response compensation of the audio signal based on the frequency band adjustment data set effectively corrects the frequency distortion problem caused by spectrum interference, and further improves the clarity and quality of the audio signal. By constructing a frequency response compensation model, the frequency of the audio signal can be accurately optimized, so that the transmission performance of the wireless microphone in different environments and frequency bands is guaranteed. After frequency optimization, the quality of the audio signal is significantly improved, providing users with clearer and more stable audio output, ensuring the performance of the wireless microphone in various complex scenarios. By optimizing the continuous adjustment of the signal data set in real time, combined with the intelligent frequency band resource adaptive allocation mechanism, the wireless microphone can automatically identify and respond to changes in the surrounding environment, and flexibly adjust the frequency band under different signal conditions, thereby avoiding excessive occupation or interference of the frequency band. The optimized frequency band resource data is transmitted to the frequency band control platform to ensure the efficiency and accuracy of frequency band resource allocation. This process not only enhances the adaptability of the wireless microphone, but also ensures the stable operation of the entire system, especially in high-interference or high-density environments, effectively reducing the risk of frequency band conflicts and signal loss. Overall, the implementation of the above technical steps can improve the management efficiency of spectrum resources while ensuring the audio quality of the wireless microphone, and minimize the impact of frequency band interference on communication quality, so that the wireless microphone can always provide stable and clear audio transmission in complex environments, further enhancing the user experience and the applicability of the equipment.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: obtaining wireless microphone audio signal data and environmental sensor data, and performing audio signal demodulation on the audio signal data to be analyzed, thereby obtaining an original audio signal data set;

[0013] Step S12: synchronizing the data timestamps of the original audio signal data set and the environmental sensor data, thereby obtaining synchronized audio signal data and synchronized environmental sensor data;

[0014] Step S13: Analyze the environmental influencing factors on the synchronous audio signal data and the synchronous environmental sensor data, so as to obtain an audio signal influencing factor set;

[0015] Step S14: performing corresponding calibration factor modeling based on the audio signal factor set, thereby obtaining an environmental factor calibration factor set;

[0016] Step S15: performing signal offset calibration on the synchronous audio signal data according to the environmental factor calibration factor set, thereby obtaining a preliminary calibration environmental audio data set.

[0017] The present invention can ensure that the original audio signal data can be captured by acquiring wireless microphone audio signal data and environmental sensor data and demodulating the audio signal. This process lays a solid foundation for subsequent analysis and calibration, so that the audio signal of the wireless microphone can be accurately restored and processed. By synchronizing the timestamps of the audio signal data and the environmental sensor data, the errors caused by time delay or data asynchrony can be eliminated, and the consistency of the audio signal and the environmental data in time can be ensured, which is crucial for accurately analyzing signal interference and environmental changes. When the synchronized data is analyzed for environmental influencing factors, the potential influencing factors on the audio signal in the environment, such as temperature, humidity, electromagnetic interference, etc., can be identified and quantified. This analysis helps to extract the influencing factor set of the audio signal, and then provide data support for subsequent optimization and calibration. Based on the influencing factor set of the audio signal, a corresponding calibration factor model can be established, which helps to accurately compensate and adjust the audio signal of the wireless microphone for changes in a specific environment, thereby effectively solving problems such as frequency band interference and signal distortion. By calibrating the synchronous audio signal data for signal offset according to the environmental factor calibration factor set, the interference of environmental factors on the audio signal can be further eliminated, the clarity and stability of the signal can be improved, and the frequency band interference or signal loss can be avoided. These calibrated data provide a solid foundation for building a high-quality audio signal set, enabling wireless microphones to achieve optimal performance in various complex environments, thereby significantly improving the adaptability of the device and user experience.

[0018] Optionally, step S13 is specifically:

[0019] Step S131: performing data preprocessing on the synchronous audio signal data and the synchronous environmental sensor data respectively, so as to obtain the audio signal data to be analyzed and the environmental sensor data to be analyzed;

[0020] Step S132: extracting audio signal features from the audio signal data to be analyzed, thereby obtaining audio signal feature data; extracting environmental features from the environmental sensor data to be analyzed, thereby obtaining environmental feature data;

[0021] Step S133: Calculate the Pearson correlation coefficient based on the audio signal feature data and the environment feature data to obtain environment-audio signal correlation data, and perform relationship model regression modeling based on the environment-audio signal correlation data to obtain an environment-audio signal association model;

[0022] Step S134: performing principal component identification of audio signal influencing factors on the synchronous environment sensing data according to the environment-audio signal association model, thereby obtaining a principal component audio signal influencing factor set;

[0023] Step S135: performing an environmental condition time series analysis on the main component audio signal influencing factor set, thereby obtaining dynamic relationship data of the audio signal influencing factors;

[0024] Step S136: quantifying the impact factors according to the audio signal impact factor dynamic relationship data, thereby obtaining an audio signal impact factor set.

[0025] The data preprocessing of the present invention provides a clean data set for subsequent signal analysis and feature extraction, ensures the quality of audio signal data and environmental sensor data, and eliminates the influence of noise or abnormal data. By performing feature extraction on audio signal data and environmental sensor data respectively, the spectral features of the audio signal and the change features captured by the environmental sensor can be extracted, thereby providing accurate input for analysis and modeling. The Pearson correlation coefficient is calculated based on the audio signal feature data and the environmental feature data, and the correlation between environmental factors and audio signals can be quantified, providing reliable data support for subsequent modeling. The environment-audio signal association model constructed by regression modeling can reveal the specific impact of environmental changes on audio signals, and help accurately identify and predict audio signal changes caused by environmental changes. The establishment of this model provides a scientific basis for subsequent optimization, so that wireless microphones can adapt to environmental changes more intelligently. Based on the environment-audio signal association model, the principal component identification of audio signal influencing factors can be performed, and the most representative factors can be extracted from a large number of environmental influencing factors. This not only improves the calculation efficiency, but also helps to focus more on the environmental factors that have the greatest impact on audio signals, thereby effectively reducing complexity. The analysis of principal components lays the foundation for the acquisition of dynamic relationship data, and can conduct in-depth analysis of the changing laws and influencing mechanisms of audio signals, ensuring that the influencing factors can be processed in a targeted manner during the optimization and recovery of the signal. By performing time series analysis on the influencing factors, the dynamic change trend of the influencing factors can be captured, which is crucial for real-time adjustment of the frequency, gain or other signal processing strategies of wireless microphones, especially in complex environments, to dynamically respond to environmental changes and maintain signal stability. The process of quantifying the set of influencing factors of audio signals helps to accurately understand the degree of each influencing factor and its specific effect on the signal, thereby providing a strong basis for the calibration, optimization and interference avoidance of audio signals.

[0026] Optionally, step S2 specifically includes:

[0027] Step S21: performing short-time Fourier transform on the preliminary calibration environment audio data set to obtain an audio signal spectrum;

[0028] Step S22: performing bandwidth division according to the audio signal spectrum to obtain an ambient audio decomposition spectrum, and performing frequency band power spectrum density calculation on the ambient audio decomposition spectrum to obtain frequency band power spectrum density data;

[0029] Step S23: extracting spectrum features from the decomposed spectrum of the environmental audio, thereby obtaining spectrum feature data of the audio signal, and identifying the environmental interference source according to the frequency band power spectrum density data and the spectrum feature data of the audio signal, thereby obtaining interference source identification data;

[0030] Step S24: performing frequency band positioning and classification on the interference source identification data, thereby obtaining a frequency band interference report;

[0031] Step S25: Integrate the environmental interference source characteristics based on the interference source identification data and the frequency band interference report to obtain a spectrum interference identification report.

[0032] The present invention performs spectrum analysis on audio signals through short-time Fourier transform, which can effectively convert signals from time domain to frequency domain and obtain detailed spectrum information. This process not only helps to identify signal characteristics of different frequency bands, but also provides basic data for subsequent signal processing and optimization. After obtaining the spectrum of the audio signal, the spectrum is decomposed into multiple frequency bands through bandwidth division, and the refinement processing is effectively performed, which makes the identification of interference sources more accurate. Based on the calculation of frequency band power spectrum density, the power distribution of each frequency band can be accurately analyzed, and the contribution or interference degree of different frequency bands to signal quality can be further quantified. By extracting spectrum features from the decomposed spectrum, not only important frequency features can be extracted from the frequency domain, but also interference sources in the environment can be identified according to power spectrum density and spectrum feature data, thereby effectively distinguishing useful signals from interference signals. This process is the key to optimizing wireless microphone signals in dynamic environments, especially in scenarios where signal quality is greatly affected by the external environment, and potential interference can be identified and dealt with in advance. By performing frequency band positioning and classification on interference source identification data, the frequency band of the interference source can be accurately located, providing clear guidance for subsequent interference source management. The generation of frequency band interference reports provides a basis for optimizing spectrum resource allocation and adjusting the operating frequency band of wireless microphones, effectively avoiding interference between different wireless devices. By integrating interference source identification data and frequency band interference reports, it is possible to comprehensively analyze the interference characteristics of each frequency band and generate spectrum interference identification reports, providing comprehensive support for dynamic frequency band adjustment, frequency optimization and interference avoidance strategies of wireless microphones.

[0033] Optionally, step S23 is specifically:

[0034] Perform frequency band intensity distribution statistics according to the frequency band power spectrum density data, thereby obtaining frequency band intensity distribution data, and perform intensity slope calculation on the frequency band intensity distribution data, thereby obtaining frequency band intensity slope data;

[0035] According to the frequency band intensity slope data, high-slope frequency bands are identified to obtain abnormal intensity slope frequency band data;

[0036] Performing spectral feature discrete change frequency band identification on the spectral feature data of the audio signal, thereby obtaining spectral feature discrete change frequency band data;

[0037] Perform frequency band intersection operation on the frequency band data of abnormal intensity slope and the frequency band data of discrete changes in spectrum characteristics, so as to obtain the frequency band data of environmental interference sources;

[0038] Interference source pattern matching is performed on the frequency band data of environmental interference sources to obtain interference source identification data.

[0039] The frequency band intensity distribution statistics of the frequency band power spectral density data in the present invention can provide the power distribution of each frequency band, which provides important basic data for the subsequent interference source analysis. The intensity slope calculation further explores the changing trend of the signal intensity in the frequency band, and helps to identify the frequency bands with large changes. The calculation of these intensity slopes can accurately capture the fluctuations of signal intensity, especially in a complex electromagnetic environment, and can identify abnormal changes in the signal, which helps to locate the interference source. After identifying the frequency bands with abnormal intensity slopes, it is possible to further analyze whether there are significant changes in frequency characteristics in these frequency bands through the frequency band identification of discrete changes in spectral characteristics, so that the characteristics of the interference source can be more comprehensively understood. This discrete change in spectral characteristics not only helps to find the interference source, but also provides support for the accurate positioning of the interference source, thereby better preventing or reducing mutual interference within the frequency band. The frequency band intersection operation can combine the data of the frequency band with abnormal intensity slope and the frequency band with discrete changes in spectral characteristics, cross-validate from multiple angles, and further improve the accuracy of interference source identification. This process can effectively reduce the risk of misidentification and accurately lock the frequency band where the interference source is located, avoiding misjudgment caused by uneven distribution of interference sources. Interference source pattern matching based on environmental interference source frequency band data can quickly identify potential interference sources and their impact patterns by comparing historical interference patterns and current frequency band characteristics, thereby providing accurate data support for dynamic adjustment of frequency bands and adaptive adjustment of wireless microphones.

[0040] Optionally, step S24 is specifically:

[0041] Step S241: locating the interference frequency band range of the interference source identification data, thereby obtaining interference frequency band range data;

[0042] Step S242: performing frequency band topology analysis according to the interference frequency band range data, thereby obtaining frequency band interference positioning data;

[0043] Step S243: performing interference source spectrum feature recognition on the interference source recognition data to obtain interference source spectrum feature data, and classifying the interference source type according to the interference source spectrum feature data to obtain interference source classification data;

[0044] Step S244: performing spatial and temporal distribution statistics of interference sources based on the frequency band interference positioning data and the interference source classification data, thereby obtaining spatial and temporal distribution data of interference sources;

[0045] Step S245: performing interference source intensity assessment according to the interference source spectrum characteristic data to obtain interference source intensity data, and performing interference source impact intensity assessment based on the interference source spatiotemporal distribution data and the interference source impact intensity data to obtain interference source impact intensity data;

[0046] Step S246: integrating the frequency band characteristics of the interference source with respect to the frequency band interference positioning data, the interference source classification data, and the interference source impact strength data, thereby obtaining a frequency band interference report.

[0047] The interference frequency band range positioning in the present invention can clearly identify the frequency band range affected by the interference source, and provide basic data for the subsequent frequency band topology analysis. The frequency band topology analysis further reveals the position distribution of the interference source in the spectrum, which helps to understand the degree of influence of the interference source on each frequency band, thereby providing an effective basis for the reasonable allocation of frequency band resources. Interference source spectrum feature identification and interference source classification can help accurately distinguish different types of interference sources. By analyzing the spectrum characteristics of the interference source, the type and characteristics of the interference source can be identified, so as to formulate corresponding countermeasures. For example, for electromagnetic interference sources and other wireless signal sources, different frequency band management strategies can be adopted to minimize the impact of interference on wireless microphone communication. In addition, interference source classification can also help determine the nature and potential harmfulness of the interference source, and further enhance the interference warning capability. The spatiotemporal distribution statistics of the interference source can effectively depict the changing laws of the interference source in different time and space dimensions, thereby providing reference data for dynamic frequency band resource management. This analysis helps to predict the changing trend of the interference source, warn of potential frequency band resource bottlenecks in advance, and ensure the efficiency and stability of frequency band allocation. The statistics of the temporal and spatial distribution of interference sources can effectively depict the changing patterns of interference sources in different time and space dimensions, thus providing reference data for dynamic frequency band resource management. This analysis helps predict the changing trend of interference sources, warn of potential frequency band resource bottlenecks in advance, and ensure the efficiency and stability of frequency band allocation. Through the evaluation of interference source strength, the actual impact intensity of interference sources can be measured to provide a quantitative basis for frequency band management. Combining the temporal and spatial distribution data of interference sources and the impact intensity data, the global impact of interference sources can be more accurately evaluated, and timely countermeasures can be taken when interference occurs to adjust frequency band allocation and avoid interference from damaging wireless microphone communications. All identified data are integrated to generate a detailed frequency band interference report to provide decision support for frequency band resource optimization. Through the coordinated effect of these steps, the working frequency band of the wireless microphone can be adjusted more intelligently and dynamically, thereby improving communication quality, reducing the impact of interference, and enhancing user experience. In a high-density environment, interference conflicts between frequency bands can be effectively avoided to ensure the efficient and stable operation of the wireless microphone system.

[0048] Optionally, step S3 specifically includes:

[0049] Step S31: acquiring real-time wireless spectrum resource allocation data, and performing data preprocessing on the real-time wireless spectrum resource allocation data, thereby obtaining wireless spectrum resource allocation data to be analyzed;

[0050] Step S32: performing interference source influence pattern identification based on the spectrum interference identification report, thereby obtaining interference source influence pattern data;

[0051] Step S33: performing interference frequency band correlation analysis on the interference source impact pattern data and the environmental interference source frequency band data, thereby obtaining interference frequency band correlation pattern data;

[0052] Step S34: classifying the interference frequency band association pattern data into frequency band interference patterns, thereby obtaining frequency band interference pattern data;

[0053] Step S35: filtering the real-time wireless spectrum resource allocation data for severely interfered frequency bands according to the frequency band interference pattern data, thereby obtaining filtered spectrum resource allocation data, and identifying idle frequency bands for the filtered spectrum resource allocation data, thereby obtaining the working frequency band data of the wireless microphone to be selected;

[0054] Step S36: evaluating the idle frequency band communication signal quality of the working frequency band data of the wireless microphone to be selected according to the filtered spectrum resource allocation data, thereby obtaining the signal quality data of the working frequency band of the wireless microphone to be selected;

[0055] Step S37: Formulate a frequency band dynamic adjustment strategy based on the working frequency band data of the wireless microphone to be selected and the signal quality data of the working frequency band of the wireless microphone to be selected, so as to obtain a dynamically optimized frequency band adjustment data set, and transmit it to the wireless microphone frequency band control platform to execute the frequency band adjustment task.

[0056] The present invention obtains and preprocesses real-time wireless spectrum resource allocation data, and provides the latest spectrum usage. This data preprocessing process can eliminate noise and redundant information, and ensure the accuracy and reliability of the analysis results. Based on the spectrum interference identification report, interference source impact pattern recognition can help accurately understand the impact pattern of different interference sources on spectrum resources, thereby providing key information for subsequent frequency band adjustment. By identifying the impact pattern of the interference source, the temporal and spatial changes of interference can be predicted, thereby avoiding waste and conflict of frequency band resources. Interference frequency band correlation analysis combines the interference source impact pattern with the environmental interference source frequency band data, and can identify the correlation of the interference source in the spectrum, and further reveal the interference relationship between different frequency bands. This can more accurately identify which frequency bands will be affected by specific interference sources, and provide a basis for the optimal allocation of frequency band resources. Frequency band interference pattern classification further refines the impact of interference sources on frequency bands, identifies the interference characteristics of different frequency bands, and can formulate more accurate interference avoidance strategies for each frequency band. By filtering the severe interference frequency bands of real-time wireless spectrum resource allocation data, the severe interference frequency bands can be excluded, and the impact of interference sources on wireless microphone signals can be reduced. At the same time, after the filtered spectrum resource allocation data is identified through idle frequency bands, the currently idle frequency bands can be effectively identified, providing more possibilities and flexibility for the selection of the working frequency bands of wireless microphones. This process not only ensures the efficient use of idle frequency bands, but also improves the utilization rate of frequency band resources. The idle frequency band communication signal quality assessment ensures that the selected frequency band can provide sufficient communication quality by analyzing the signal quality of the idle frequency band. This assessment helps to make intelligent selections based on the actual signal quality of the frequency band, ensuring that the wireless microphone communication is carried out on a high-quality frequency band, thereby minimizing the communication quality problems caused by interference or signal attenuation. Based on the working frequency band data of the wireless microphone to be selected and its signal quality, a dynamic frequency band adjustment strategy can be formulated. This strategy makes the frequency band adjustment more flexible and real-time, and optimizes and adjusts according to the actual signal quality, improving the communication stability and anti-interference ability of the wireless microphone.

[0057] Optionally, step S4 is specifically:

[0058] Step S41: extracting frequency band features from the dynamically optimized frequency band adjustment data set, thereby obtaining dynamic frequency band signal quality data;

[0059] Step S42: performing audio signal frequency response analysis based on the dynamically adjusted frequency band signal quality data, thereby obtaining audio signal frequency response data before adjustment;

[0060] Step S43: acquiring real-time audio signal data, and performing audio frequency band signal quality evaluation on the real-time audio signal data, thereby obtaining real-time frequency band signal quality data;

[0061] Step S44: performing an audio signal frequency response analysis based on the real-time frequency band signal quality data to obtain adjusted audio signal frequency response data, and performing a frequency response error calculation on the audio signal frequency response data before adjustment and the audio signal frequency response data after adjustment to obtain audio signal frequency response error data;

[0062] Step S45: designing a frequency band performance compensation function according to the audio signal frequency response error data and the real-time frequency band signal quality data, thereby obtaining audio signal frequency response compensation data;

[0063] Step S46: constructing a frequency response compensation model according to the audio signal frequency response compensation data.

[0064] The frequency band feature extraction of the dynamically optimized frequency band adjustment data set in the present invention can help accurately evaluate the signal quality of different frequency bands, thereby providing a strong basis for subsequent frequency band adjustment. By obtaining the dynamically adjusted frequency band signal quality data, the performance of each frequency band under different working conditions can be deeply understood, laying the foundation for accurate frequency band adjustment. Next, the audio signal frequency response analysis can reveal the performance of the audio signal before the frequency band adjustment, thereby providing necessary benchmark data for frequency band optimization. By analyzing the audio signal frequency response data, the frequency band that needs to be optimized can be identified to avoid attenuation or distortion of the signal after the frequency band adjustment. Acquiring real-time audio signal data and evaluating the frequency band signal quality provides real-time data in actual operation, so that the frequency band selection not only depends on theoretical analysis, but also can adjust the strategy according to real-time feedback. The acquisition of real-time frequency band signal quality data can quickly reflect the changes in the frequency band in the environment, ensuring that the selection of the frequency band is consistent with the actual situation of the dynamic environment. Based on this data, the audio signal frequency response analysis can obtain the adjusted frequency response data, and the difference in signal quality before and after the frequency band adjustment can be quantified by calculating the frequency response error. This error calculation provides quantitative guidance for the optimization strategy, helping to understand the effect of the adjustment and where improvements need to be made. The frequency response error data of the audio signal is combined with the real-time frequency band signal quality data to design the frequency band performance compensation function. A compensation function can be developed to adjust the signal quality differences in different frequency bands to compensate for the audio distortion caused by environmental interference or improper frequency band selection. Through this compensation process, the wireless microphone can significantly improve the transmission quality of the audio signal, making it more adaptable to complex and changing environmental conditions and ensuring the clarity and stability of the audio signal. By constructing a frequency response compensation model, an adjustable model can be established to optimize the frequency response based on real-time data, so that the wireless microphone can provide the best audio transmission quality under any working conditions. This dynamic adjustment and optimization capability is the key to coping with the changing environment in the use of wireless microphones, and can ensure that the system still operates stably in high-interference and high-density scenarios, improving the user experience.

[0065] Optionally, step S5 specifically includes:

[0066] Step S51: performing abnormal signal quality frequency band identification on the adjusted audio signal frequency response data, thereby obtaining abnormal signal quality frequency band data;

[0067] Step S52: optimizing the frequency band gain balance of the abnormal signal quality frequency band data through the frequency response compensation model, thereby obtaining a real-time optimized signal data set;

[0068] Step S53: performing real-time frequency band allocation simulation according to the real-time optimized signal data set and the spectrum interference identification report, thereby obtaining real-time frequency band transmission simulation data;

[0069] Step S54: performing frequency band load balancing based on the real-time frequency band transmission simulation data, thereby obtaining balanced load frequency band communication transmission data;

[0070] Step S55: Adaptively optimize the balanced load frequency band communication transmission data for interference avoidance according to the interference source impact mode data, thereby obtaining the wireless microphone communication frequency band resource data, and transmitting it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0071] The present invention identifies the frequency band of abnormal signal quality for the adjusted audio signal frequency response data, and can effectively screen out those frequency bands with quality problems from a large number of frequency bands, providing key data for subsequent signal optimization and frequency band adjustment. By identifying the frequency band of abnormal signal quality, potential interference or quality degradation problems can be discovered in advance, thereby avoiding inappropriate interference sources or frequency distortion when selecting the frequency band. By optimizing the frequency band gain balance of the abnormal signal quality frequency band data through the frequency response compensation model, the gain of the frequency band signal can be dynamically adjusted to ensure that the transmission quality of the audio signal in the interference frequency band is improved, thereby obtaining a real-time optimized signal data set. The optimization process can reduce the impact of frequency band interference, improve the stability and quality of signal transmission, and provide optimized frequency band signal data for subsequent wireless microphone frequency band allocation. Based on the real-time optimized signal data set, the frequency band allocation simulation can simulate the performance of different frequency bands in actual applications, and analyze and predict the transmission effect after the frequency band allocation in advance. This simulation process not only helps to identify potential problems in frequency band allocation, but also optimizes the allocation strategy according to the real-time performance of the frequency band to ensure the continuous stability of communication quality. The real-time frequency band transmission simulation data provides a basis for the subsequent frequency band load balancing, which can effectively balance the load of different frequency bands, avoid overcrowding of some frequency bands or idleness of some frequency bands, and ensure the rational use of spectrum resources. This process further improves the transmission efficiency and stability of the wireless microphone system, while avoiding interference caused by excessive use of certain frequency bands. Adaptive interference avoidance optimization adjusts the frequency band communication transmission according to the interference source impact mode data, effectively avoiding the negative impact of interference sources on communication transmission. Through flexible interference avoidance strategies, the frequency band resource allocation of wireless microphones can be adjusted in real time to avoid the risk of communication interruption or quality degradation, and ensure the stable transmission of audio signals. The optimized wireless microphone frequency band resource data is transmitted to the wireless microphone frequency band control platform to perform the frequency band resource allocation task, thereby realizing the intelligent and automated management of the entire wireless microphone system. This can not only dynamically adapt to the changes in frequency band resources in different environments, but also automatically adjust the frequency band resources according to real-time data, ensuring the stable operation of wireless microphones in various complex scenarios, and improving the overall performance and user experience.

[0072] Optionally, the present specification further provides a frequency band intelligent control system for a wireless microphone, which is used to execute the frequency band intelligent control method for a wireless microphone as described above, and the frequency band intelligent control system for a wireless microphone includes:

[0073] An audio signal calibration module, used to obtain wireless microphone audio signal data and environmental sensor data, and perform preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set;

[0074] An environmental interference source identification module is used to perform spectrum decomposition on the preliminary calibration environmental audio data set to obtain an environmental audio decomposition spectrum, and identify environmental interference sources based on the environmental audio decomposition spectrum to obtain a spectrum interference identification report;

[0075] The frequency band dynamic adjustment module is used to obtain real-time wireless spectrum resource allocation data; perform frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjust the wireless microphone working frequency band based on the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set;

[0076] A compensation model building module, used to perform audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and building a frequency response compensation model according to the audio signal frequency response compensation data;

[0077] The frequency band resource allocation module is used to optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate the wireless microphone communication frequency band resources according to the real-time optimized signal data set to obtain the wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0078] The frequency band intelligent control system of the wireless microphone of the present invention can implement any one of the frequency band intelligent control methods of the wireless microphone of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the frequency band intelligent control method of the wireless microphone. The internal modules of the system cooperate with each other, thereby avoiding the influence of frequency band interference on communication quality, so that the wireless microphone can always provide stable and clear audio transmission in complex environments, further enhancing the user experience and the applicability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0080] Figure 1 It is a schematic diagram of the steps of the frequency band intelligent control method of the wireless microphone of the present invention;

[0081] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0082] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0083] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0084] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0085] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0086] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0087] To achieve this, please refer to Figures 1 to 3 The present invention provides a frequency band intelligent control method for a wireless microphone, the method comprising the following steps:

[0088] Step S1: obtaining wireless microphone audio signal data and environmental sensor data, and performing preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set;

[0089] In this embodiment, the wireless microphone audio signal data is obtained through the built-in receiver of the wireless microphone, and the environmental data provided by the environmental sensor (such as temperature and humidity sensor, noise sensor, etc.) is collected simultaneously. The audio signal enters the signal processing unit through the receiving module of the wireless microphone, and the environmental sensor data is transmitted to the data processing platform through the interface. By combining the environmental sensor data, the audio signal is preliminarily calibrated using a machine learning-based algorithm to eliminate signal distortion caused by factors such as environmental noise, temperature and humidity changes. This calibration process uses a dynamic adaptive algorithm to adjust the gain, noise suppression and other parameters of the audio signal in real time, thereby obtaining a preliminarily calibrated audio data set to ensure the quality and accuracy of the audio signal. The process can also dynamically adjust the calibration method according to different scenarios to ensure adaptation to various environmental changes.

[0090] Step S2: performing spectrum decomposition on the preliminary calibration environment audio data set to obtain an environment audio decomposition spectrum, and identifying the environment interference source according to the environment audio decomposition spectrum to obtain a spectrum interference identification report;

[0091] In this embodiment, the preliminary calibrated environmental audio data set is subjected to spectral decomposition by short-time Fourier transform (STFT) to obtain audio signal data of different frequency bands. Using spectrum analysis technology, the decomposed audio signal is subjected to power spectrum calculation of each frequency band, and the characteristic data of the environmental interference source is further extracted. By applying signal processing algorithms to these spectrum data, possible interference sources are identified, and their characteristics are identified in combination with environmental sensor data to form a spectrum interference identification report. The report not only lists the frequency range of the interference source, but also identifies its type (such as mechanical noise, electromagnetic interference, etc.), and classifies possible interference sources, providing accurate interference source positioning and feature labeling. This identification process is optimized using artificial intelligence technology, which can identify multiple interference sources in complex environments and provide them to subsequent processing modules in the form of reports.

[0092] Step S3: acquiring real-time wireless spectrum resource allocation data; performing frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjusting the wireless microphone working frequency band of the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set;

[0093] In this embodiment, the acquired wireless spectrum resource allocation data includes the current spectrum usage, congestion of each frequency band, signal strength, etc. By analyzing the frequency band interference pattern data in the spectrum interference identification report, the interference patterns of different frequency bands and their impact on the working frequency band of the wireless microphone are identified. Based on these interference patterns, the spectrum management algorithm is used for real-time optimization, and the working frequency band of the wireless microphone is adjusted according to the interference pattern to avoid the frequency band with severe interference. In this way, the dynamically optimized frequency band adjustment data set can make accurate frequency band selection in a real-time environment, so that the wireless microphone can avoid frequency band congestion and ensure transmission quality. During the frequency band adjustment process, the frequency band usage will be automatically predicted based on historical data and real-time analysis results to further improve the accuracy of the adjustment.

[0094] Step S4: performing audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and constructing a frequency response compensation model according to the audio signal frequency response compensation data;

[0095] In this embodiment, the frequency response of the audio signal is compensated by dynamically optimizing the frequency band adjustment data set. According to the frequency band adjustment result, the corresponding compensation function is calculated and applied to adjust the frequency response of the audio signal to correct the frequency offset caused by environmental interference, signal transmission attenuation and other problems. Using adaptive filtering technology, the frequency response compensation model can dynamically update the compensation parameters according to environmental changes to ensure that the frequency response of the audio signal is still in the best state after each frequency band adjustment. The compensation process not only takes into account the optimization of a single frequency band, but also integrates the information of multiple frequency bands to obtain the best overall frequency response. This compensation model can adjust its weight according to real-time data to optimize the transmission effect of the audio signal.

[0096] Step S5: Optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate wireless microphone communication frequency band resources based on the real-time optimized signal data set to obtain wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0097] In this embodiment, after frequency response compensation, the frequency of the audio signal is further optimized through the frequency response compensation model to ensure that the quality of the audio signal reaches the optimal level after adjusting the frequency band. This process combines the real-time optimization of the signal data set, automatically adjusts the frequency band selection through an adaptive algorithm, and adaptively allocates resources to the wireless microphone working frequency band based on factors such as the signal's frequency response, bandwidth, and interference. According to the signal quality of different frequency bands, the communication frequency band of the wireless microphone is dynamically allocated to ensure that it works in the frequency band with the least interference, while avoiding excessive congestion of the frequency band. The optimized frequency band resource data will be transmitted to the wireless microphone frequency band control platform in real time. The platform performs the frequency band resource allocation task based on these data to ensure that the audio signal transmission of the wireless microphone is stable and the interference is minimal, and provide data support for subsequent equipment optimization.

[0098] Optionally, step S1 specifically includes:

[0099] Step S11: obtaining wireless microphone audio signal data and environmental sensor data, and performing audio signal demodulation on the audio signal data to be analyzed, thereby obtaining an original audio signal data set;

[0100] In this embodiment, the wireless microphone captures audio signals through a built-in microphone, and environmental sensors (such as temperature and humidity sensors, air pressure sensors, etc.) also collect data on changes in the surrounding environment in real time. The audio signal is transmitted to the signal demodulation unit in the wireless microphone frequency band control platform through the wireless transmission module for demodulation processing. The demodulation unit uses frequency modulation (FM) or amplitude modulation (AM) demodulation technology to restore the received modulated audio signal to the original audio signal data set. These original audio signal data will be stored and processed, and the environmental sensing data (such as temperature, humidity, etc.) will be collected through the built-in sensors of the microphone to form an environmental sensing data set. In order to ensure high-quality demodulation of the signal, the signal demodulation process is accelerated by embedded hardware, and high-precision demodulation algorithms, such as fast Fourier transform (FFT), are used to accurately restore the frequency components of the audio signal and obtain the original audio signal data set.

[0101] Step S12: synchronizing the data timestamps of the original audio signal data set and the environmental sensor data, thereby obtaining synchronized audio signal data and synchronized environmental sensor data;

[0102] In this embodiment, the audio signal data set and the environmental sensor data set must be accurately time-stamped. This is because the audio signal and the environmental data are collected independently by different devices, so their time stamps are not necessarily consistent. In order to integrate these data together, an accurate time stamp is marked for each data point through GPS time synchronization or a synchronization mechanism based on an internal clock. The specific synchronization method can use a time alignment algorithm, such as linear interpolation based on an interpolation method, to ensure that the time axes of the two are completely aligned. A timing controller is used to synchronize the timestamp of the audio signal with the timestamp of the environmental sensor data to ensure that each audio signal data point has corresponding environmental information, and the timing error between different data sets is compressed to within the millisecond level. The synchronized audio signal data and environmental sensor data form a complete and time-consistent data set for subsequent analysis.

[0103] Step S13: Analyze the environmental influencing factors on the synchronous audio signal data and the synchronous environmental sensor data, so as to obtain an audio signal influencing factor set;

[0104] In this embodiment, the synchronized audio signal data and environmental sensor data are analyzed for environmental influencing factors. Specifically, the relationship between the frequency characteristics of the audio signal and the environmental sensor data (such as temperature and humidity, air pressure, noise, etc.) is subjected to multivariate regression analysis or machine learning modeling. Statistical models are used to analyze how environmental variables (such as temperature changes, humidity changes, air quality, etc.) affect the quality of the audio signal. For example, in a high humidity environment, the audio signal will be attenuated, and temperature changes will cause the frequency of the audio signal to drift. By using algorithms such as linear regression or support vector machines (SVM), the specific impact of environmental factors on the audio signal can be quantified to form a set of influencing factors. For example, an influencing factor set is generated, which includes the impact values ​​of each factor such as temperature, humidity, and air pressure on the audio signal gain, frequency response, etc. These factors will be used for subsequent signal calibration work.

[0105] Step S14: performing corresponding calibration factor modeling based on the audio signal factor set, thereby obtaining an environmental factor calibration factor set;

[0106] In this embodiment, a corresponding calibration factor model is established based on the set of audio signal influencing factors obtained from the above analysis. In specific implementation, a multivariable optimization algorithm (such as least squares method, Bayesian optimization, etc.) is used to fit the relationship between the influencing factors and the audio signal deviation. First, the influence mode of each environmental factor (such as temperature, humidity, etc.) on the audio signal is identified, and the model parameters are adjusted according to historical data or real-time measurement results to obtain accurate calibration factors. For example, a humidity calibration factor is generated based on the effect of humidity changes on the audio frequency response; a temperature calibration factor is generated based on the effect of temperature changes on the gain. These calibration factors will serve as the core part of the calibration model to compensate for the audio signal offset caused by environmental changes, ensure that the calibration factors can adapt to different environmental conditions, and improve the robustness and accuracy of the system.

[0107] Step S15: performing signal offset calibration on the synchronous audio signal data according to the environmental factor calibration factor set, thereby obtaining a preliminary calibration environmental audio data set.

[0108] In this embodiment, the synchronous audio signal data is calibrated for signal offset according to the obtained environmental factor calibration factor set. Specifically, the influencing factor is applied to the audio signal data to adjust its frequency, gain or other related parameters. For example, if it is detected that the temperature change causes the audio signal frequency offset, the frequency compensation is performed according to the environmental factor calibration factor; if the humidity increases and causes the audio signal to attenuate, the gain is adjusted according to the humidity factor. Through digital signal processing (DSP) technology, the system uses an adaptive filter or numerical integration method to compensate and adjust the audio signal in real time to ensure that the output audio signal can maintain high-quality performance under various environmental conditions. This process can eliminate the interference caused by environmental factors and ensure that the audio signal transmitted by the wireless microphone is stable and clear. After this process, the final preliminary calibration environment audio data set will provide high-quality input data for subsequent audio signal processing and optimization.

[0109] Optionally, step S13 is specifically:

[0110] Step S131: performing data preprocessing on the synchronous audio signal data and the synchronous environmental sensor data respectively, so as to obtain the audio signal data to be analyzed and the environmental sensor data to be analyzed;

[0111] In this embodiment, the audio signal data is filtered to remove noise and interference. Common filtering methods include low-pass filters, high-pass filters, and band-pass filters. According to the characteristics of the audio signal, a suitable filter is selected for signal preprocessing. For example, for the suppression of low-frequency noise, a band-pass filter can be used to retain the voice band (such as 200Hz to 3kHz range) signal. The environmental sensor data is also preprocessed, and methods such as denoising and missing value filling are used to ensure data quality. For the preprocessing of environmental sensor data, an interpolation algorithm (such as linear interpolation or spline interpolation) is used to fill in the missing data, and outliers are removed to ensure the continuity and integrity of each data set. After processing, the audio signal data to be analyzed and the environmental sensor data to be analyzed are generated for subsequent analysis.

[0112] Step S132: extracting audio signal features from the audio signal data to be analyzed, thereby obtaining audio signal feature data; extracting environmental features from the environmental sensor data to be analyzed, thereby obtaining environmental feature data;

[0113] In this embodiment, feature extraction is performed on the audio signal data to be analyzed. Audio signal feature extraction may include time domain features (such as signal amplitude, duration, etc.) and frequency domain features (such as spectrum, Mel-frequency cepstral coefficients MFCC, short-time Fourier transform STFT, etc.). For example, Fourier transform is used to perform frequency domain analysis on the audio signal to extract the main frequency components and spectrum amplitude of the signal. These spectrum features can reflect the voice information, tone changes, etc. in the audio signal. Environmental feature extraction includes time series analysis of environmental sensor data (such as temperature, humidity, air pressure, etc.) to extract data trends, periodicity and other features, such as using a sliding average method to smooth environmental data, eliminate short-term fluctuations, and obtain more stable environmental change features. Finally, the audio signal data and environmental data are converted into feature data sets that are easy to analyze through feature extraction.

[0114] Step S133: Calculate the Pearson correlation coefficient based on the audio signal feature data and the environment feature data to obtain environment-audio signal correlation data, and perform relationship model regression modeling based on the environment-audio signal correlation data to obtain an environment-audio signal association model;

[0115] In this embodiment, the Pearson correlation coefficient is used to calculate the correlation based on the extracted audio signal feature data and environmental feature data. The Pearson correlation coefficient is a standard method to measure the degree of linear correlation between two variables. The calculation formula is the ratio of covariance to standard deviation, and the value range is -1 to 1. The correlation between the audio signal and the environmental characteristics (such as temperature, humidity, air pressure, etc.) is calculated to obtain the environment-audio signal correlation data. The higher the correlation, the more significant the impact of environmental changes on the audio signal. Subsequently, based on the correlation data, a regression analysis (such as linear regression or multiple regression) is used to construct an environment-audio signal association model. For example, a regression algorithm is used to fit the mathematical relationship between environmental factors (temperature, humidity) and audio signal deviations to obtain an environment-audio signal association model. This model can help predict the changing trend of audio signals under different environmental conditions.

[0116] Step S134: performing principal component identification of audio signal influencing factors on the synchronous environment sensing data according to the environment-audio signal association model, thereby obtaining a principal component audio signal influencing factor set;

[0117] In this embodiment, the principal component identification of audio signal influencing factors is performed on the synchronous environmental sensor data according to the aforementioned environment-audio signal association model. The most representative principal component factors are extracted from the multi-dimensional environmental data through dimensionality reduction technology. For example, multiple environmental factors such as temperature, humidity, and air pressure are integrated into a principal component through PCA, and this principal component best represents the changes in environmental factors that affect the audio signal. These principal component factor sets can reduce the redundant information of environmental factors, retain key influencing factors, and provide clear and concise data input for subsequent analysis.

[0118] Step S135: performing an environmental condition time series analysis on the main component audio signal influencing factor set, thereby obtaining dynamic relationship data of the audio signal influencing factors;

[0119] In this embodiment, the environmental condition time series analysis is performed on the set of factors affecting the main component audio signal. Specifically, the main component factors are modeled in time series using time series analysis methods (such as autoregressive moving average model ARMA, long short-term memory network LSTM, etc.), so as to capture the dynamic characteristics of environmental factors changing over time. Through time series analysis, the time-varying effects of environmental factors (such as temperature and humidity) on audio signals can be identified. For example, temperature changes have a greater impact on audio signals in certain time periods, but less impact in other time periods. By modeling time series data, dynamic relationship data of audio signal influencing factors are obtained, which can reflect the impact patterns of environmental changes on different time scales.

[0120] Step S136: quantifying the impact factors according to the audio signal impact factor dynamic relationship data, thereby obtaining an audio signal impact factor set.

[0121] In this embodiment, quantification is performed based on the dynamic relationship data of the audio signal influencing factors obtained. Specifically, numerical methods (such as regression analysis, neural networks, etc.) are used to quantitatively analyze the audio signal influencing factors, so as to obtain the actual impact of each factor on the audio signal. Through quantification, a weight value can be assigned to each environmental factor to indicate the degree of its impact on the audio signal. For example, it is found that temperature has a greater impact on the frequency response of the audio signal, while humidity changes have a smaller impact on the gain of the signal. The quantified set of influencing factors will provide accurate data support for subsequent signal calibration and optimization, ensuring that the performance of the audio signal in a complex environment is more stable and reliable.

[0122] Optionally, step S2 specifically includes:

[0123] Step S21: performing short-time Fourier transform on the preliminary calibration environment audio data set to obtain an audio signal spectrum;

[0124] In this embodiment, a short-time Fourier transform (STFT) is performed on the preliminary calibrated environmental audio data set. The STFT method decomposes the audio signal into frequency domain signals in multiple short time windows. In specific implementation, the audio signal is divided into overlapping time domain windows, and the duration of each window can be set to 20ms to 50ms. The window function usually selects a Hanning window or a Hamming window to reduce the edge effect of the window function. The frequency spectrum information of the audio signal at different time points can be obtained through STFT. The specific process is to process the audio signal by framing, perform Fourier transform on each frame signal, and obtain the frequency spectrum data of the frame. In this way, a matrix representing the frequency distribution of the signal at each time point can be obtained, and the frequency components of the audio signal and their changing trends can be further analyzed.

[0125] Step S22: performing bandwidth division according to the audio signal spectrum to obtain an ambient audio decomposition spectrum, and performing frequency band power spectrum density calculation on the ambient audio decomposition spectrum to obtain frequency band power spectrum density data;

[0126] In this embodiment, bandwidth division is performed based on the spectrum data of the audio signal to extract frequency components of different frequency bands. This process usually divides the bandwidth according to the characteristics of the audio signal. For example, for voice signals, it can be divided into low frequency (0-500 Hz), medium frequency (500 Hz-2 kHz) and high frequency (above 2 kHz) bands. On this basis, the power spectral density (PSD) of each frequency band is calculated, which can be done by calculating the energy of each frequency component in each frequency band. For example, the spectrum of each frequency band is summed using the segmented averaging method or the frequency band integration method to obtain the power spectral density data of the frequency band. These data can reflect the energy distribution of the signal in different frequency bands and provide a basis for subsequent interference source identification.

[0127] Step S23: extracting spectrum features from the decomposed spectrum of the environmental audio, thereby obtaining spectrum feature data of the audio signal, and identifying the environmental interference source according to the frequency band power spectrum density data and the spectrum feature data of the audio signal, thereby obtaining interference source identification data;

[0128] In this embodiment, environmental interference sources are identified based on the calculated frequency band power spectrum density data and the frequency spectrum feature data of the audio signal. Audio signal spectrum feature extraction includes extracting common spectrum features, such as Mel-frequency cepstral coefficients (MFCC), spectrum centroid, spectrum kurtosis, etc. These features help to describe the frequency distribution of audio signals and their changing trends, and can especially reflect the characteristics of interference signals. By comparing the audio signal features and the spectrum of environmental noise, it is possible to identify which frequency bands are interfered with, and the interference sources include electrical equipment, traffic noise or other external noise sources. Using machine learning algorithms, such as K-means clustering or support vector machines (SVM), the interference components in the spectrum can be automatically separated from the normal audio signal, thereby generating interference source identification data, which provides a basis for subsequent frequency band positioning and classification.

[0129] Step S24: performing frequency band positioning and classification on the interference source identification data, thereby obtaining a frequency band interference report;

[0130] In this embodiment, the interference source identification data is frequency-band located and classified. Specifically, based on the interference source identification data, the audio signals in which frequency bands are interfered with are identified and classified. For example, for low-frequency interference sources, the interference components in the low frequency band (such as 50 Hz-500 Hz) can be identified; for high-frequency interference, the high frequency band (such as above 2 kHz) will be located. The location of the interference source can use the frequency band power spectrum density data to identify the frequency band that exceeds the normal range by setting a threshold. The interference source classification is divided into different categories such as electromagnetic interference and mechanical noise according to its characteristics. The key technology of this process is to accurately divide the interfered frequency bands and their types based on the power spectrum density and frequency characteristics of the signal, thereby providing strong support for subsequent frequency band adjustment and interference avoidance.

[0131] Step S25: Integrate the environmental interference source characteristics based on the interference source identification data and the frequency band interference report to obtain a spectrum interference identification report.

[0132] In this embodiment, the characteristics of the environmental interference sources are integrated based on the interference source identification data and the frequency band interference report. This process identifies and quantifies the nature and strength of the interference source by integrating information from different data sources. For example, the interference sources of each frequency band in the spectrum interference identification report are integrated with the time and frequency characteristics of their impact to form a complete environmental interference source characteristic model. The specific approach includes generating a spatiotemporal distribution map of the interference source based on the frequency band interference report, and further analyzing the possible source and strength of the interference source in combination with environmental conditions such as meteorological data and geographical location. Through this integration, a comprehensive spectrum interference identification report can be generated to provide a basis for frequency band optimization and accurate positioning of interference sources.

[0133] Optionally, step S23 is specifically:

[0134] Perform frequency band intensity distribution statistics according to the frequency band power spectrum density data, thereby obtaining frequency band intensity distribution data, and perform intensity slope calculation on the frequency band intensity distribution data, thereby obtaining frequency band intensity slope data;

[0135] In this embodiment, frequency band intensity distribution statistics are performed based on frequency band power spectrum density data. Specifically, the frequency spectrum of the audio signal is divided into multiple frequency bands, and the power spectrum density (PSD) of each frequency band is calculated. For example, for a wide-band audio signal, the frequency band can be divided at intervals of 10Hz or 100Hz. Then, the power value in each frequency band is counted to obtain the intensity distribution of the frequency band. For example, a histogram can be used to represent the power distribution of each frequency band, thereby obtaining frequency band intensity distribution data. These data help analyze which frequency bands have higher energy concentration, thereby providing a basis for subsequent interference source identification. Next, the intensity slope calculation of the frequency band intensity distribution data is performed. Specifically, the difference between adjacent power spectrum density values ​​of the frequency band is calculated to obtain the slope of the frequency band. For example, if the power value of the frequency band changes rapidly within a smaller frequency range, the slope value of the frequency band is larger. By calculating the intensity slope of the frequency band, the trend of the frequency band in intensity change can be identified, and the frequency band intensity slope data can be further obtained.

[0136] According to the frequency band intensity slope data, high-slope frequency bands are identified to obtain abnormal intensity slope frequency band data;

[0137] In this embodiment, high-slope frequency bands are identified based on the frequency band intensity slope data. This process identifies abnormal intensity changes in the frequency band by setting a slope threshold. For example, when the frequency band slope is greater than a certain threshold (such as 0.1 dB / ms), the frequency band is considered to be an interference frequency band. By analyzing the slope data of the frequency band, frequency bands with abnormally drastic intensity changes, that is, abnormal intensity slope frequency band data, can be identified. These frequency bands are usually affected by external interference, and there is communication interference or other types of noise. At this time, the abnormal frequency band is marked as a target frequency band that needs further processing.

[0138] Performing spectral feature discrete change frequency band identification on the spectral feature data of the audio signal, thereby obtaining spectral feature discrete change frequency band data;

[0139] In this embodiment, the frequency bands with discrete changes in the frequency spectrum characteristics are identified for the frequency spectrum characteristic data of the audio signal. The frequency spectrum characteristics of the audio signal include the spectrum centroid, spectrum flatness, spectrum width, etc. These characteristics help to describe the frequency distribution and changes of the signal. Specifically, the characteristic change rate of each frequency band in the audio signal spectrum can be calculated. When the spectrum characteristics change significantly in a short period of time, it is considered that these frequency bands have large discrete changes. For example, when the rate of change of the spectrum centroid exceeds a certain threshold, the frequency band will be identified as a frequency band with discrete changes. Finally, the frequency band data of discrete changes in the spectrum characteristics are obtained, which reflects the noise or interference that may appear in the audio signal.

[0140] Perform frequency band intersection operation on the frequency band data of abnormal intensity slope and the frequency band data of discrete changes in spectrum characteristics, so as to obtain the frequency band data of environmental interference sources;

[0141] In this embodiment, a frequency band intersection operation is performed on the abnormal intensity slope frequency band data and the frequency band data of discrete changes in spectral characteristics. Specifically, by calculating the intersection of the two sets of data, the overlapping parts in the two data sets are found. These intersection frequency bands have both abnormal intensity changes and discrete changes in spectral characteristics, and are usually frequency bands affected by external interference sources. For example, if a frequency band is marked as an abnormal frequency band in the intensity slope calculation and shows significant discrete changes in the spectral feature calculation, then the frequency band will be considered as a possible environmental interference source frequency band. Through the frequency band intersection operation, the frequency bands that are more affected by interference can be further screened out, thereby improving the accuracy of interference source identification.

[0142] Interference source pattern matching is performed on the frequency band data of environmental interference sources to obtain interference source identification data.

[0143] In this embodiment, interference source pattern matching is performed on the frequency band data of the environmental interference source. Specifically, by comparing the frequency band data of the environmental interference source with the known interference source pattern. For example, a predefined interference source library can be used, which includes common electromagnetic interference, broadcast signal interference, and other types of external noise source patterns. Through the matching process, the type of interference source in the frequency band and its characteristics can be determined, and interference source identification data can be generated. This data can assist in subsequent frequency band optimization and interference source management. By using a matching algorithm, such as a model-based matching algorithm (such as a Gaussian mixture model) or a data-based matching method, the interference source can be accurately identified and its impact on communication quality can be predicted.

[0144] Optionally, step S24 is specifically:

[0145] Step S241: locating the interference frequency band range of the interference source identification data, thereby obtaining interference frequency band range data;

[0146] In this embodiment, the interference source identification data is processed to locate the interference frequency band range. In specific implementation, the identified interference frequency band data is used in combination with the strength, change and other information of the spectrum data to locate the specific frequency band range of the interference. To this end, the starting and ending frequencies of the interference can be determined by calculating the distribution of the interference signal on the frequency band. For example, if the interference signal appears in the frequency band range of 10MHz to 15MHz, the frequency band range is determined by the strength and characteristics of the signal, thereby obtaining the interference frequency band range data. This data can provide a basis for subsequent frequency band optimization and interference source management.

[0147] Step S242: performing frequency band topology analysis according to the interference frequency band range data, thereby obtaining frequency band interference positioning data;

[0148] In this embodiment, frequency band topology analysis is performed based on the interference frequency band range data. The key to this process is to evaluate the propagation mode of interference by analyzing the relationship between the structure of the interference frequency band and the network environment. Spectrum analysis tools, such as Fourier transform, can be used to analyze the topology of the interference frequency band and compare it with the topology of the wireless communication network. By calculating the interaction between the interference signal and other frequency bands, the frequency band interference positioning data is obtained, and the frequency bands and areas where the interference source has the most serious impact are clearly marked, thereby helping further spectrum resource allocation and management.

[0149] Step S243: performing interference source spectrum feature recognition on the interference source recognition data to obtain interference source spectrum feature data, and classifying the interference source type according to the interference source spectrum feature data to obtain interference source classification data;

[0150] In this embodiment, the interference source spectrum feature identification is performed through the interference source identification data. Specifically, the spectrum features of the interference signal, including frequency distribution, spectrum width, spectrum peak and other features, are analyzed to identify the type of interference source. Machine learning or deep learning algorithms can be used to classify interference sources based on a known interference source spectrum library. For example, if the interference source of a certain frequency band shows spectrum features similar to those of a radio broadcast signal obtained based on expert experience or pre-defined, it can be classified as a broadcast interference source. Through this process, the interference source spectrum feature data is obtained, and the interference source type classification is further performed based on these data to obtain the interference source classification data. This step helps to quickly identify the type of interference source and take corresponding treatment measures.

[0151] Step S244: performing spatial and temporal distribution statistics of interference sources based on the frequency band interference positioning data and the interference source classification data, thereby obtaining spatial and temporal distribution data of interference sources;

[0152] In this embodiment, the temporal and spatial distribution statistics of the interference source are performed based on the frequency band interference positioning data and the interference source classification data. In the specific implementation, the temporal and spatial distribution characteristics of the interference source are analyzed by combining the frequency band position, timestamp, intensity and other data of the interference source. By using statistical models, such as time series analysis and spatial distribution analysis, the temporal and spatial regularities of the interference source can be identified. For example, if it is found that the interference signal of a certain frequency band is stronger at night and at certain specific time points, the temporal and spatial distribution data of the interference source can be generated to predict the trend of interference occurrence and help with interference management.

[0153] Step S245: performing interference source intensity assessment according to the interference source spectrum characteristic data to obtain interference source intensity data, and performing interference source impact intensity assessment based on the interference source spatiotemporal distribution data and the interference source impact intensity data to obtain interference source impact intensity data;

[0154] In this embodiment, the interference source strength is evaluated based on the interference source spectrum characteristic data. Specifically, the interference source's impact strength is evaluated by measuring the interference source's spectrum strength. This can be done through methods such as power spectrum density and signal strength comparison. Taking Wi-Fi interference as an example, the degree of its impact on surrounding wireless devices can be evaluated by measuring the power density of the interference frequency band. In addition, based on the interference source's spatiotemporal distribution data and the interference source's impact strength data, the interference source's impact strength is evaluated, and a comprehensive interference strength index is obtained by comprehensively considering factors such as the distribution density and time variation of the interference source. This evaluation result helps to quantify the frequency band interference and guide the optimal configuration of frequency band resources.

[0155] Step S246: integrating the frequency band characteristics of the interference source with respect to the frequency band interference positioning data, the interference source classification data, and the interference source impact strength data, thereby obtaining a frequency band interference report.

[0156] In this embodiment, the frequency band interference location data, interference source classification data and interference source impact intensity data are integrated. In the specific implementation, the data obtained from different analysis modules are combined and comprehensively processed through data fusion technology. For example, the specific location of the frequency band interference is combined with information such as the type and intensity of the interference source to obtain a complete frequency band interference report. The report includes not only the type and impact of the interference source, but also the spatial and temporal distribution and frequency band location of the interference source, which can provide detailed information for interference source suppression and frequency band optimization strategies. This report can help network administrators adjust spectrum resources in real time and improve communication quality.

[0157] Optionally, step S3 specifically includes:

[0158] Step S31: acquiring real-time wireless spectrum resource allocation data, and performing data preprocessing on the real-time wireless spectrum resource allocation data, thereby obtaining wireless spectrum resource allocation data to be analyzed;

[0159] In this embodiment, real-time wireless spectrum resource allocation data is obtained through the wireless microphone frequency band control platform, and these data are preprocessed. In specific implementation, the frequency band allocation information is obtained from the wireless microphone frequency band control platform, including the occupancy, idleness and historical interference data of each frequency band. In order to ensure the consistency and accuracy of the data, the preprocessing process includes data cleaning (such as removing outliers and processing missing data) and normalization. After preprocessing, the wireless spectrum resource allocation data to be analyzed will be obtained. For example, in the spectrum range from 10MHz to 1GHz, the real-time usage of each frequency band is obtained for subsequent analysis.

[0160] Step S32: performing interference source influence pattern identification based on the spectrum interference identification report, thereby obtaining interference source influence pattern data;

[0161] In this embodiment, interference source impact pattern recognition is performed based on the spectrum interference identification report. During implementation, the identified interference source characteristics and frequency band usage are analyzed to identify the interference source's impact pattern on wireless spectrum resources. For example, spectrum fluctuations in a particular frequency band may be caused by a fixed interference source. A machine learning model (such as a support vector machine or a neural network) is used to identify the interference pattern and classify the impact of the interference source on the frequency band into fixed, periodic, or random patterns. In this way, the interference source's impact pattern data can be obtained, providing a basis for subsequent frequency band optimization.

[0162] Step S33: performing interference frequency band correlation analysis on the interference source impact pattern data and the environmental interference source frequency band data, thereby obtaining interference frequency band correlation pattern data;

[0163] In this embodiment, interference frequency band correlation analysis is performed on the interference source impact pattern data and the environmental interference source frequency band data. Specifically, statistical methods and correlation analysis tools (such as Pearson correlation coefficient or cross-correlation analysis) are used to calculate the correlation between the interference source impact pattern and each frequency band in the environment. For example, strong interference in a certain frequency band is highly correlated with specific environmental interference sources (such as electronic equipment, building structures, etc.). After analysis, interference frequency band correlation pattern data can be obtained to determine which frequency bands have a strong correlation with specific interference sources, and provide data support for subsequent frequency band classification.

[0164] Step S34: classifying the interference frequency band association pattern data into frequency band interference patterns, thereby obtaining frequency band interference pattern data;

[0165] In this embodiment, frequency band interference pattern classification is performed based on interference frequency band association pattern data. In specific implementation, a classification algorithm (such as decision tree, K-means clustering, etc.) is used to classify the interference frequency band. For example, the frequency band is classified into high interference, low interference or no interference. By analyzing the intensity, change law and impact of the interference source pattern on different frequency bands, the interference degree of the frequency band is divided to provide a more detailed interference management solution for wireless communication optimization. Frequency band interference pattern data will be generated, including the interference category and level of each frequency band.

[0166] Step S35: filtering the real-time wireless spectrum resource allocation data for severely interfered frequency bands according to the frequency band interference pattern data, thereby obtaining filtered spectrum resource allocation data, and identifying idle frequency bands for the filtered spectrum resource allocation data, thereby obtaining the working frequency band data of the wireless microphone to be selected;

[0167] In this embodiment, the real-time wireless spectrum resource allocation data is filtered for severely interfered frequency bands based on the frequency band interference pattern data. The frequency bands that are in a state of severe interference are automatically identified through an algorithm and excluded from the available frequency bands. For example, if the interference frequency band pattern of a certain frequency band indicates that the frequency band is subject to greater interference in multiple environments, the frequency band will be marked as a "severely interfered frequency band" and eliminated. Next, the filtered spectrum resource allocation data is subjected to idle frequency band identification to determine which frequency bands are idle and have lower interference potential. Through this process, the wireless microphone working frequency band data to be selected is finally obtained. For example, in the frequency band range of 200MHz to 1GHz, an idle and non-severely interfered frequency band is selected as the working frequency band.

[0168] Step S36: evaluating the idle frequency band communication signal quality of the working frequency band data of the wireless microphone to be selected according to the filtered spectrum resource allocation data, thereby obtaining the signal quality data of the working frequency band of the wireless microphone to be selected;

[0169] In this embodiment, the idle frequency band communication signal quality evaluation is performed on the working frequency band data of the wireless microphone to be selected based on the filtered spectrum resource allocation data. In specific implementation, the signal quality evaluation is performed on each candidate idle frequency band, and its signal strength, signal-to-noise ratio, bit error rate and other parameters are measured. For example, if the signal quality of a certain frequency band is poor, resulting in a decrease in the communication quality of the wireless microphone, the frequency band will be excluded. By evaluating the performance indicators of the frequency band, the signal quality data of the working frequency band of the wireless microphone to be selected is generated to guide subsequent frequency band optimization decisions.

[0170] Step S37: Formulate a frequency band dynamic adjustment strategy based on the working frequency band data of the wireless microphone to be selected and the signal quality data of the working frequency band of the wireless microphone to be selected, so as to obtain a dynamically optimized frequency band adjustment data set, and transmit it to the wireless microphone frequency band control platform to execute the frequency band adjustment task.

[0171] In this embodiment, a dynamic frequency band adjustment strategy is formulated based on the working frequency band data of the wireless microphone to be selected and the signal quality data of the working frequency band of the wireless microphone to be selected. During the implementation process, a dynamic adjustment strategy is formulated through an optimization algorithm (such as a genetic algorithm or a particle swarm algorithm) in combination with factors such as the idle state of the frequency band, the interference level, and the signal quality. For example, in certain circumstances, the working frequency band of the wireless microphone is dynamically adjusted according to the quality of the idle frequency band to achieve the best communication quality. Finally, a dynamically optimized frequency band adjustment data set is generated and transmitted to the wireless microphone frequency band control platform to execute the frequency band adjustment task to ensure that the communication equipment is always in the best frequency band environment.

[0172] Optionally, step S4 is specifically:

[0173] Step S41: extracting frequency band features from the dynamically optimized frequency band adjustment data set, thereby obtaining dynamic frequency band signal quality data;

[0174] In this embodiment, the frequency band feature extraction is performed on the dynamically optimized frequency band adjustment data set, with the purpose of obtaining the signal quality data of the dynamically adjusted frequency band. Specifically, the spectrum information, interference situation, signal strength and other characteristics of each frequency band are first extracted, and then the signal quality of each frequency band is evaluated through these characteristics. For example, for each adjusted frequency band, its signal-to-noise ratio, distortion, frequency response characteristics and other data are extracted to determine the signal quality index of each frequency band after optimization. Through these characteristic data, the impact of frequency band adjustment on the quality of the audio signal can be analyzed, and finally the signal quality data of the dynamically adjusted frequency band can be obtained.

[0175] Step S42: performing audio signal frequency response analysis based on the dynamically adjusted frequency band signal quality data, thereby obtaining audio signal frequency response data before adjustment;

[0176] In this embodiment, the audio signal frequency response analysis is performed based on the dynamically adjusted frequency band signal quality data. During implementation, the frequency response analysis method (e.g., Fourier transform) is used to evaluate the frequency band signal quality before and after the adjustment. In this step, based on the frequency band signal quality before the adjustment, the response changes of the audio signal at different frequencies are analyzed to obtain the frequency response data of the audio signal before the adjustment. The gain and phase changes at different frequency points in the frequency band from low frequency to high frequency are analyzed to obtain the frequency response characteristics of the audio signal, and provide data support for the subsequent frequency response error calculation.

[0177] Step S43: acquiring real-time audio signal data, and performing audio frequency band signal quality evaluation on the real-time audio signal data, thereby obtaining real-time frequency band signal quality data;

[0178] In this embodiment, real-time audio signal data is obtained through a built-in microphone, and the audio frequency band signal quality evaluation is performed on the real-time audio signal data. Real-time audio signals of wireless microphones in actual environments are collected, and these audio signals are analyzed to evaluate the signal quality of their frequency bands. Algorithms such as FFT (Fast Fourier Transform) are used to perform spectrum analysis on audio signals to extract characteristics such as frequency band strength, noise level, and signal-to-noise ratio of the signal. Through these analyses, real-time frequency band signal quality data is obtained to determine the quality of the audio signal in the current frequency band.

[0179] Step S44: performing an audio signal frequency response analysis based on the real-time frequency band signal quality data to obtain adjusted audio signal frequency response data, and performing a frequency response error calculation on the audio signal frequency response data before adjustment and the audio signal frequency response data after adjustment to obtain audio signal frequency response error data;

[0180] In this embodiment, the audio signal frequency response analysis is performed based on the real-time frequency band signal quality data. First, the signal quality of the adjusted frequency band is analyzed, and the adjusted audio signal is evaluated in detail through frequency response analysis. For example, the frequency response analysis of the adjusted frequency band signal is performed using Fourier transform, and its frequency response data (including gain, phase and other information) is extracted. Then, the frequency response data before and after the adjustment are compared and analyzed, the frequency response error data is calculated, the gain difference of the signal at different frequency points is analyzed, and the performance change of the audio signal after the frequency band adjustment is detected. Through these calculations, the system can clearly understand the signal quality changes before and after the adjustment.

[0181] Step S45: designing a frequency band performance compensation function according to the audio signal frequency response error data and the real-time frequency band signal quality data, thereby obtaining audio signal frequency response compensation data;

[0182] In this embodiment, a frequency band performance compensation function is designed based on the audio signal frequency response error data and the real-time frequency band signal quality data. By comparing the frequency response error and the real-time signal quality data, the key factors affecting the quality of the audio signal (such as distortion and attenuation of specific frequencies in the frequency band) are analyzed. Based on these data, an algorithm (such as the least squares method) is used to design a frequency band performance compensation function to compensate for the frequency response error introduced after the frequency band adjustment. For example, a function is designed to adjust the gain of the low-frequency or high-frequency band to balance the frequency response characteristics of the entire frequency band to ensure the stability and clarity of the audio signal. The audio signal frequency response compensation data is generated by the compensation function for subsequent compensation operations.

[0183] Step S46: constructing a frequency response compensation model according to the audio signal frequency response compensation data.

[0184] In this embodiment, a frequency response compensation model is constructed based on the audio signal frequency response compensation data. During implementation, an optimization algorithm (such as a genetic algorithm, a neural network, etc.) is used to train and adjust the compensation model based on the designed frequency band performance compensation function. This model can perform real-time frequency response compensation on the audio signal under different frequency bands and environmental conditions. By continuously adjusting the parameters of the model to adapt to different interference sources, frequency band usage and environmental changes, a model that can automatically perform frequency response compensation is finally generated. This compensation model can adjust the audio signal of the wireless microphone in real time to ensure the best quality of audio transmission.

[0185] Optionally, step S5 specifically includes:

[0186] Step S51: performing abnormal signal quality frequency band identification on the adjusted audio signal frequency response data, thereby obtaining abnormal signal quality frequency band data;

[0187] In this embodiment, the frequency response data of the adjusted audio signal is used to identify the frequency bands with abnormal signal quality. In the specific implementation, the adjusted frequency response data is first analyzed to detect whether there is obvious signal quality abnormality in the frequency band. Using a spectrum analysis algorithm, signal loss, distortion or extreme attenuation areas in the frequency band are identified, which are manifested as abnormally high noise levels, severe attenuation or distortion. During the analysis process, statistical methods (such as standard deviation, skewness, etc.) or machine learning algorithms can be applied to mark the frequency bands with abnormal signal quality. For example, if the gain of a certain frequency band is significantly lower than the preset standard or the phase distortion exceeds the set threshold, the frequency band is marked as an abnormal signal quality band, and abnormal signal quality frequency band data is generated.

[0188] Step S52: optimizing the frequency band gain balance of the abnormal signal quality frequency band data through the frequency response compensation model, thereby obtaining a real-time optimized signal data set;

[0189] In this embodiment, the frequency response compensation model is used to optimize the frequency band gain balance of the abnormal signal quality frequency band data. Specifically, gain compensation will be performed on the frequency band that has been identified as abnormal according to the constructed frequency response compensation model. This process involves the dynamic adjustment of the frequency band gain. By analyzing the frequency response error and the target signal quality requirements, the compensation model will automatically calculate the gain adjustment parameters of each frequency band. For example, by adjusting the gain of the low-frequency part of a certain frequency band, the gain attenuation or distortion within the frequency band can be compensated. These optimized gain data will form a real-time optimized signal data set for subsequent transmission simulation and load balancing processing.

[0190] Step S53: performing real-time frequency band allocation simulation according to the real-time optimized signal data set and the spectrum interference identification report, thereby obtaining real-time frequency band transmission simulation data;

[0191] In this embodiment, a real-time frequency band allocation simulation is performed based on the real-time optimized signal data set and the spectrum interference identification report. The real-time optimized signal data set is used to evaluate the signal quality and load conditions of different frequency bands, and the transmission status of each frequency band is simulated in combination with the spectrum interference identification report. During this simulation process, the communication performance and carrying capacity of different frequency bands are estimated based on the signal quality, interference source and idle frequency band conditions of each frequency band. The performance of different frequency bands is iteratively analyzed multiple times using simulation algorithms (such as Monte Carlo simulation) to predict their communication quality in the actual environment, thereby generating real-time frequency band transmission simulation data. For example, if the simulation shows that some frequency bands have poor transmission performance in a high-interference environment, or that some frequency bands have low spectrum utilization, frequency band optimization will be performed based on this data.

[0192] Step S54: performing frequency band load balancing based on the real-time frequency band transmission simulation data, thereby obtaining balanced load frequency band communication transmission data;

[0193] In this embodiment, frequency band load balancing is performed based on real-time frequency band transmission simulation data. The transmission load of each frequency band is evaluated, and the load status of each frequency band is analyzed based on the real-time frequency band transmission simulation data. Through the load balancing algorithm (such as an algorithm based on minimum load priority, maximum throughput or load balancing constraints), the load distribution of each frequency band will be dynamically adjusted to ensure that the communication frequency band maintains optimal performance under load balancing. For example, the frequency band with heavier load will be adjusted to the frequency band with less interference or better signal quality, or the frequency band with lighter load will be allocated to more wireless microphones. This process ensures that all wireless microphone devices can stably obtain sufficient spectrum resources, avoid frequency band overload or resource waste, and finally generate balanced load frequency band communication transmission data.

[0194] Step S55: Adaptively optimize the balanced load frequency band communication transmission data for interference avoidance according to the interference source impact mode data, thereby obtaining the wireless microphone communication frequency band resource data, and transmitting it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0195] In this embodiment, adaptive interference avoidance optimization is performed on the communication transmission data of the balanced load frequency band according to the interference source impact pattern data. The interference source impact pattern data is analyzed to identify the type and location of the interference source that affects the signal quality. Then, based on this information, an adaptive algorithm (such as adaptive filtering, frequency band hopping, power control, etc.) is used to optimize the communication transmission of the balanced load frequency band to avoid the influence of the interference source. For example, if a frequency band encounters strong interference in a specific area, the frequency band of the wireless microphone will be adjusted, or anti-interference technology (such as spectrum hopping or power adjustment) will be used to ensure the quality of wireless communication. This optimization process will generate the final wireless microphone communication frequency band resource data, and transmit this data to the wireless microphone frequency band control platform to perform the frequency band resource allocation task, thereby achieving the optimal resource configuration and interference avoidance of the wireless microphone frequency band.

[0196] Optionally, the present specification further provides a frequency band intelligent control system for a wireless microphone, which is used to execute the frequency band intelligent control method for a wireless microphone as described above, and the frequency band intelligent control system for a wireless microphone includes:

[0197] An audio signal calibration module, used to obtain wireless microphone audio signal data and environmental sensor data, and perform preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set;

[0198] An environmental interference source identification module is used to perform spectrum decomposition on the preliminary calibration environmental audio data set to obtain an environmental audio decomposition spectrum, and identify environmental interference sources based on the environmental audio decomposition spectrum to obtain a spectrum interference identification report;

[0199] The frequency band dynamic adjustment module is used to obtain real-time wireless spectrum resource allocation data; perform frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjust the wireless microphone working frequency band based on the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set;

[0200] A compensation model building module, used to perform audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and building a frequency response compensation model according to the audio signal frequency response compensation data;

[0201] The frequency band resource allocation module is used to optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate the wireless microphone communication frequency band resources according to the real-time optimized signal data set to obtain the wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

[0202] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0203] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A frequency band intelligent control method for a wireless microphone, characterized in that: The following steps are involved: Step S1: obtaining wireless microphone audio signal data and environmental sensor data, and performing preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set; Step S2: performing spectrum decomposition on the preliminary calibration environment audio data set to obtain an environment audio decomposition spectrum, and identifying the environment interference source according to the environment audio decomposition spectrum to obtain a spectrum interference identification report; Step S3: acquiring real-time wireless spectrum resource allocation data; performing frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjusting the wireless microphone working frequency band of the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set; Step S4: performing audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and constructing a frequency response compensation model according to the audio signal frequency response compensation data; Step S5: Optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate wireless microphone communication frequency band resources according to the real-time optimized signal data set to obtain wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to perform the frequency band resource allocation task; Step S5 is specifically: Step S51: performing abnormal signal quality frequency band identification on the adjusted audio signal frequency response data, thereby obtaining abnormal signal quality frequency band data; Step S52: optimizing the frequency band gain balance of the abnormal signal quality frequency band data through the frequency response compensation model, thereby obtaining a real-time optimized signal data set; Step S53: performing real-time frequency band allocation simulation according to the real-time optimized signal data set and the spectrum interference identification report, thereby obtaining real-time frequency band transmission simulation data; Step S54: performing frequency band load balancing based on the real-time frequency band transmission simulation data, thereby obtaining balanced load frequency band communication transmission data; Step S55: Adaptively optimize the balanced load frequency band communication transmission data for interference avoidance according to the interference source impact mode data, thereby obtaining the wireless microphone communication frequency band resource data, and transmitting it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

2. The frequency band intelligent control method of a wireless microphone according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: obtaining wireless microphone audio signal data and environmental sensor data, and performing audio signal demodulation on the audio signal data to be analyzed, thereby obtaining an original audio signal data set; Step S12: synchronizing the data timestamps of the original audio signal data set and the environmental sensor data, thereby obtaining synchronized audio signal data and synchronized environmental sensor data; Step S13: Analyze the environmental influencing factors on the synchronous audio signal data and the synchronous environmental sensor data, so as to obtain an audio signal influencing factor set; Step S14: performing corresponding calibration factor modeling based on the audio signal factor set, thereby obtaining an environmental factor calibration factor set; Step S15: performing signal offset calibration on the synchronous audio signal data according to the environmental factor calibration factor set, thereby obtaining a preliminary calibration environmental audio data set.

3. The frequency band intelligent control method of a wireless microphone according to claim 2, characterized in that: Step S13 is specifically as follows: Step S131: performing data preprocessing on the synchronous audio signal data and the synchronous environmental sensor data respectively, so as to obtain the audio signal data to be analyzed and the environmental sensor data to be analyzed; Step S132: extracting audio signal features from the audio signal data to be analyzed, thereby obtaining audio signal feature data; Extract environmental features from the environmental sensor data to be analyzed, thereby obtaining environmental feature data; Step S133: Calculate the Pearson correlation coefficient based on the audio signal feature data and the environment feature data to obtain environment-audio signal correlation data, and perform relationship model regression modeling based on the environment-audio signal correlation data to obtain an environment-audio signal association model; Step S134: performing principal component identification of audio signal influencing factors on the synchronous environment sensing data according to the environment-audio signal association model, thereby obtaining a principal component audio signal influencing factor set; Step S135: performing an environmental condition time series analysis on the main component audio signal influencing factor set, thereby obtaining dynamic relationship data of the audio signal influencing factors; Step S136: quantifying the impact factors according to the audio signal impact factor dynamic relationship data, thereby obtaining an audio signal impact factor set.

4. The frequency band intelligent control method of a wireless microphone according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: performing short-time Fourier transform on the preliminary calibration environment audio data set to obtain an audio signal spectrum; Step S22: performing bandwidth division according to the audio signal spectrum to obtain an ambient audio decomposition spectrum, and performing frequency band power spectrum density calculation on the ambient audio decomposition spectrum to obtain frequency band power spectrum density data; Step S23: extracting spectrum features from the decomposed spectrum of the environmental audio, thereby obtaining spectrum feature data of the audio signal, and identifying the environmental interference source according to the frequency band power spectrum density data and the spectrum feature data of the audio signal, thereby obtaining interference source identification data; Step S24: performing frequency band positioning and classification on the interference source identification data, thereby obtaining a frequency band interference report; Step S25: Integrate the environmental interference source characteristics based on the interference source identification data and the frequency band interference report to obtain a spectrum interference identification report.

5. The frequency band intelligent control method of a wireless microphone according to claim 4, characterized in that: Step S23 is specifically as follows: Perform frequency band intensity distribution statistics according to the frequency band power spectrum density data, thereby obtaining frequency band intensity distribution data, and perform intensity slope calculation on the frequency band intensity distribution data, thereby obtaining frequency band intensity slope data; According to the frequency band intensity slope data, high-slope frequency bands are identified to obtain abnormal intensity slope frequency band data; Performing spectral feature discrete change frequency band identification on the spectral feature data of the audio signal, thereby obtaining spectral feature discrete change frequency band data; Perform frequency band intersection operation on the frequency band data of abnormal intensity slope and the frequency band data of discrete changes in spectrum characteristics, so as to obtain the frequency band data of environmental interference sources; Interference source pattern matching is performed on the frequency band data of environmental interference sources to obtain interference source identification data.

6. The frequency band intelligent control method of a wireless microphone according to claim 4, characterized in that: Step S24 is specifically as follows: Step S241: locating the interference frequency band range of the interference source identification data, thereby obtaining interference frequency band range data; Step S242: performing frequency band topology analysis according to the interference frequency band range data, thereby obtaining frequency band interference positioning data; Step S243: performing interference source spectrum feature recognition on the interference source recognition data to obtain interference source spectrum feature data, and classifying the interference source type according to the interference source spectrum feature data to obtain interference source classification data; Step S244: performing spatial and temporal distribution statistics of interference sources based on the frequency band interference positioning data and the interference source classification data, thereby obtaining spatial and temporal distribution data of interference sources; Step S245: performing interference source intensity assessment according to the interference source spectrum characteristic data to obtain interference source intensity data, and performing interference source impact intensity assessment based on the interference source spatiotemporal distribution data and the interference source impact intensity data to obtain interference source impact intensity data; Step S246: integrating the frequency band characteristics of the interference source with respect to the frequency band interference positioning data, the interference source classification data, and the interference source impact strength data, thereby obtaining a frequency band interference report.

7. The frequency band intelligent control method of a wireless microphone according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: acquiring real-time wireless spectrum resource allocation data, and performing data preprocessing on the real-time wireless spectrum resource allocation data, thereby obtaining wireless spectrum resource allocation data to be analyzed; Step S32: performing interference source influence pattern identification based on the spectrum interference identification report, thereby obtaining interference source influence pattern data; Step S33: performing interference frequency band correlation analysis on the interference source impact pattern data and the environmental interference source frequency band data, thereby obtaining interference frequency band correlation pattern data; Step S34: classifying the interference frequency band association pattern data into frequency band interference patterns, thereby obtaining frequency band interference pattern data; Step S35: filtering the real-time wireless spectrum resource allocation data for severely interfered frequency bands according to the frequency band interference pattern data, thereby obtaining filtered spectrum resource allocation data, and identifying idle frequency bands for the filtered spectrum resource allocation data, thereby obtaining the working frequency band data of the wireless microphone to be selected; Step S36: evaluating the idle frequency band communication signal quality of the working frequency band data of the wireless microphone to be selected according to the filtered spectrum resource allocation data, thereby obtaining the signal quality data of the working frequency band of the wireless microphone to be selected; Step S37: Formulate a frequency band dynamic adjustment strategy based on the working frequency band data of the wireless microphone to be selected and the signal quality data of the working frequency band of the wireless microphone to be selected, so as to obtain a dynamically optimized frequency band adjustment data set, and transmit it to the wireless microphone frequency band control platform to execute the frequency band adjustment task.

8. The frequency band intelligent control method of a wireless microphone according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: extracting frequency band features from the dynamically optimized frequency band adjustment data set, thereby obtaining dynamic frequency band signal quality data; Step S42: performing audio signal frequency response analysis based on the dynamically adjusted frequency band signal quality data, thereby obtaining audio signal frequency response data before adjustment; Step S43: acquiring real-time audio signal data, and performing audio frequency band signal quality evaluation on the real-time audio signal data, thereby obtaining real-time frequency band signal quality data; Step S44: performing an audio signal frequency response analysis based on the real-time frequency band signal quality data to obtain adjusted audio signal frequency response data, and performing a frequency response error calculation on the audio signal frequency response data before adjustment and the audio signal frequency response data after adjustment to obtain audio signal frequency response error data; Step S45: designing a frequency band performance compensation function according to the audio signal frequency response error data and the real-time frequency band signal quality data, thereby obtaining audio signal frequency response compensation data; Step S46: constructing a frequency response compensation model according to the audio signal frequency response compensation data.

9. A frequency band intelligent control system for a wireless microphone, characterized in that: Used to execute the frequency band intelligent control method of the wireless microphone as claimed in claim 1, the frequency band intelligent control system of the wireless microphone comprises: An audio signal calibration module, used to obtain wireless microphone audio signal data and environmental sensor data, and perform preliminary audio signal calibration on the wireless microphone audio signal data according to the environmental sensor data, thereby obtaining a preliminary calibration environmental audio data set; An environmental interference source identification module is used to perform spectrum decomposition on the preliminary calibration environmental audio data set to obtain an environmental audio decomposition spectrum, and identify environmental interference sources based on the environmental audio decomposition spectrum to obtain a spectrum interference identification report; The frequency band dynamic adjustment module is used to obtain real-time wireless spectrum resource allocation data; perform frequency band interference pattern recognition on the spectrum interference identification report to obtain frequency band interference pattern data, and dynamically adjust the wireless microphone working frequency band based on the real-time wireless spectrum resource allocation data based on the frequency band interference pattern data to obtain a dynamically optimized frequency band adjustment data set; A compensation model building module, used to perform audio signal frequency response compensation based on the dynamically optimized frequency band adjustment data set, thereby obtaining audio signal frequency response compensation data, and building a frequency response compensation model according to the audio signal frequency response compensation data; The frequency band resource allocation module is used to optimize the audio signal frequency through the frequency response compensation model to obtain a real-time optimized signal data set; adaptively allocate the wireless microphone communication frequency band resources according to the real-time optimized signal data set to obtain the wireless microphone communication frequency band resource data, and transmit it to the wireless microphone frequency band control platform to execute the frequency band resource allocation task.

Images