Sound control method and system based on AI internet of things technology

Abstract

The application discloses a sound control method and system based on AI Internet of Things technology, and relates to the technical field of sound signal processing.The method comprises the following steps: S1, collecting acoustic characteristic data of a target space in real time through an Internet of Things sensor; S2, analyzing the acoustic characteristics of the space based on the collected data by using an artificial intelligence model; S3, generating a preliminary control instruction of sound equalizer parameters according to the analysis result; and S4, optimizing the preliminary control instruction by using a path planning model, generating an optimized control instruction, and sending the control instruction to a sound device to adjust the equalizer parameters in real time to solve the sound distortion problem.The sound control method and system based on AI Internet of Things technology can solve the sound distortion problem by adjusting the sound equalizer parameters in real time according to the acoustic characteristics of the space.

Description

Technical Field

[0001] This invention relates to the field of audio signal processing technology, specifically to an audio control method and system based on AI Internet of Things (IoT) technology. Background Technology

[0002] With the rapid development of artificial intelligence and the Internet of Things (IoT) technologies, smart speaker systems are gradually becoming popular in various application scenarios such as home entertainment, in-vehicle systems, and conference venues. Current speaker control methods mainly rely on users selecting fixed equalizer preset modes, such as "cinema mode" or "voice enhancement." These modes are based on general environmental tuning and do not take into account changes in the actual acoustic characteristics of the space.

[0003] In reality, room structure, furniture layout, sound-absorbing materials, and human activity all significantly impact the propagation path and reflection of sound. Because existing systems lack effective sensing and response mechanisms for these spatial acoustic parameters, sound distortion often occurs, such as frequency shifts, echo enhancement, or severe reverberation, thus affecting the user's listening experience. To address these issues, some high-end audio systems have introduced automatic environmental sensing and acoustic compensation functions, attempting to collect sound signals through built-in microphones and adaptively adjust parameters. However, these systems typically employ static models or rely on initial setup conditions, failing to continuously track and respond to dynamic changes in the spatial environment. For example, when furniture moves, curtains open and close, or people move around, the originally calibrated equalizer parameters become difficult to apply, leading to unbalanced audio output. More importantly, these methods generally lack AI-driven learning and optimization mechanisms, failing to optimize strategies based on accumulated historical environmental data. Summary of the Invention

[0004] The purpose of this invention is to provide a sound control method and system based on AI Internet of Things technology, which adjusts the parameters of the sound equalizer in real time according to the spatial acoustic characteristics to solve the problem of sound distortion.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a sound control method based on AI Internet of Things technology, the method comprising:

[0006] S1. Acoustic characteristic data of the target space are collected in real time through IoT sensors;

[0007] S2. Based on the collected data, the spatial acoustic characteristics are analyzed using an artificial intelligence model, including the real-time acquisition of the reverberation time value of the current point in the space by sensors, and the output of the optimal reverberation time value that should be achieved under the current environment by the artificial intelligence model, determining the reverberation time deviation value, and the artificial intelligence model performing attribution analysis on the reverberation time deviation value.

[0008] S3. Generate preliminary control instructions for the audio equalizer parameters based on the analysis results. This includes the artificial intelligence model outputting adjustment values ​​for each frequency band based on the analysis results, and assigning frequency band weights according to the importance of the evaluation to determine the preliminary control instructions.

[0009] S4. The initial control command is optimized through the path planning model to generate the optimized control command. The control command is sent to the audio equipment to adjust the equalizer parameters in real time to solve the sound distortion problem. The control command includes the actual gain value of each frequency band to realize intelligent priority control.

[0010] Preferably, the specific steps for determining the reverberation time deviation value in S2 include subtracting the optimal reverberation time value that should be achieved under the current environment from the reverberation time value at the current point to obtain the reverberation time deviation value.

[0011] Preferably, the specific method for determining the final control command in S3 includes multiplying the frequency band weight by the adjustment value of the frequency band to obtain the weighted adjustment value of each frequency band; integrating the weighted adjustment values ​​of all frequency bands to generate a preliminary control command, wherein the preliminary control command is a set of commands containing the weighted adjustment values ​​of each frequency band, used to guide the parameter adjustment of the audio equalizer.

[0012] Preferably, step S1 further includes using IoT sensors to monitor the acoustic characteristics data of the target space in real time, establishing a model for the propagation process of sound wave data in space, calculating the sound energy distribution of each region, predicting the propagation of sound energy over time, and quantifying the sound energy intensity at different spatial locations.

[0013] Preferably, the specific formula for calculating the acoustic energy distribution of each region is as follows:

[0014] A(t) = A0e -kt ;

[0015] Where A(t) represents the acoustic energy distribution in the region, t represents time, A0 represents the initial sound pressure intensity, e represents the base of the natural logarithm, and k represents the attenuation coefficient of the sound wave during its propagation in the target space.

[0016] Preferably, the specific method for real-time adjustment of equalizer parameters in S4 includes: optimizing the initial control command through a path planning model, calculating the cost of adjustment for each frequency band, and weighted summing of the adjustment costs for all frequency bands to generate a comprehensive cost function; solving the comprehensive cost function using an optimization algorithm to determine the optimal adjustment path; generating an optimized control command based on the optimal control path, the control command including the actual gain value of each frequency band; and sending the optimized control command to the audio equipment via a network, the audio equipment adjusting the equalizer parameters according to the control command to achieve precise sound effect control.

[0017] Preferably, in step S1, the IoT sensor acquires sound characteristic data of the target space in real time through multiple data acquisition methods, including audio sensors, environmental sensors, and temperature and humidity sensors. The audio sensor is used to collect acoustic parameters such as sound pressure, frequency, reverberation, and echo. The environmental sensor is used to collect environmental data such as ambient noise level and spatial layout changes. The temperature and humidity sensor is used to collect environmental parameters such as temperature and humidity. All collected data is transmitted in real time to an artificial intelligence model for comprehensive analysis to more accurately evaluate the acoustic characteristics of the target space.

[0018] Preferably, step S3 further includes automatically generating personalized equalizer parameters based on the preferences of users in different spaces. Specifically, this involves collecting users' sound effect preference data through mobile devices, including users' volume preferences, timbre preferences, and sound effect requirements for different frequency bands and specific scenarios; inputting the users' preference data into an artificial intelligence model, which then generates personalized equalizer parameters based on the users' preference data and the acoustic characteristics data of the target space.

[0019] Preferably, the IoT sensor collects and transmits data in real time through time synchronization technology to ensure high-precision synchronous analysis of sound characteristic data in dynamic environmental changes.

[0020] An audio control system based on AIoT technology is provided to implement the steps of the audio control method based on AIoT technology, the system comprising:

[0021] Internet of Things (IoT) sensors are used to collect acoustic characteristic data of the target space in real time.

[0022] An artificial intelligence analysis model is used to analyze spatial acoustic characteristics based on collected data and generate preliminary control commands for audio equalizer parameters based on the analysis results.

[0023] Path planning model: used to optimize the initial control command, calculate the cost of adjustment for each frequency band, perform a weighted summation of the adjustment costs for all frequency bands to generate a comprehensive cost function, solve the comprehensive cost function to determine the optimal adjustment path, and generate optimized control commands based on the optimal adjustment path;

[0024] Control command transmission module: Used to send optimized control commands to the audio equipment via the network. The audio equipment adjusts the equalizer parameters according to the control commands to achieve precise sound effect control and solve the sound distortion problem.

[0025] As can be seen from the above technical solution, the present invention has the following beneficial effects:

[0026] This audio control method and system based on AIoT technology collects real-time acoustic characteristic data of the target space through IoT sensors. Based on the collected data, it uses an artificial intelligence model to analyze the spatial acoustic characteristics and generates real-time adjustment commands for the equalizer parameters. These commands are then sent to the audio equipment to adjust the equalizer parameters in real time to solve sound distortion problems. The system can respond to environmental changes in real time, such as room structure adjustments, furniture layout changes, or human activity, ensuring optimal sound output in any environment. It intelligently optimizes the gain of each frequency band, eliminating problems such as frequency shift, echo enhancement, and severe reverberation, thereby effectively avoiding sound distortion and improving the user's listening experience. It can learn the user's sound preferences and the changing patterns of the spatial environment to provide personalized audio adjustment solutions. Compared with traditional audio systems that rely on static models, it has stronger adaptability and long-term optimization capabilities, achieving precise adjustment and optimization of sound effects. Users only need to enjoy the best sound quality without worrying about adjustment details, simplifying the operation process. It uses real-time adjustment of the equalizer parameters based on spatial acoustic characteristics to solve sound distortion problems. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the method flow of the present invention.

[0028] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Example 1:

[0031] like Figure 1 As shown, the present invention provides a technical solution: a speaker control method based on AI Internet of Things technology, the method comprising:

[0032] S1. Acoustic characteristic data of the target space are collected in real time through IoT sensors;

[0033] S2. Based on the collected data, the spatial acoustic characteristics are analyzed using an artificial intelligence model, including the real-time acquisition of the reverberation time value of the current point in the space by sensors, and the output of the optimal reverberation time value that should be achieved under the current environment by the artificial intelligence model, determining the reverberation time deviation value, and the artificial intelligence model performing attribution analysis on the reverberation time deviation value.

[0034] S3. Generate preliminary control instructions for the audio equalizer parameters based on the analysis results. This includes the artificial intelligence model outputting adjustment values ​​for each frequency band based on the analysis results, and assigning frequency band weights according to the importance of the evaluation to determine the preliminary control instructions.

[0035] S4. The initial control command is optimized through the path planning model to generate the optimized control command. The control command is sent to the audio equipment to adjust the equalizer parameters in real time to solve the sound distortion problem. The control command includes the actual gain value of each frequency band to realize intelligent priority control.

[0036] This audio control method based on AIoT technology collects real-time acoustic characteristic data of the target space using IoT sensors, particularly the reverberation time value at the current point within the space. These sensors can measure and transmit the sound spectrum, noise level, echo, and other acoustic features of the environment, ensuring complete acoustic information is captured within the target space. The sensors then feed this real-time data back to the AI ​​system for further processing and analysis.

[0037] After receiving this data, the artificial intelligence model first analyzes the spatial acoustic characteristics based on a predetermined algorithm, especially calculating the reverberation time in the current environment. Reverberation time is the rate at which sound decays in space, and it directly affects the clarity of sound and the acoustic effect of the space. The artificial intelligence model compares the real-time data in the environment to obtain the difference between the actual reverberation time and the optimal reverberation time in the current space, i.e., the reverberation time deviation value. The calculation of this deviation value not only takes into account the current environmental conditions, but also factors such as the size, shape, and material properties of the space.

[0038] By analyzing the attribution of reverberation time deviation, the AI ​​model further identifies the specific sources of sound distortion, such as sound quality problems caused by factors like sound wave reflection, insufficient sound-absorbing materials, or unreasonable spatial layout. Through this analysis, the system can specifically optimize and adjust the audio settings to improve sound quality.

[0039] Based on the above analysis, the AI ​​model generates real-time adjustment commands for the audio equalizer parameters. Specifically, the model outputs adjustment values ​​for each frequency band and assigns different weights based on the degree of influence of each band on the overall sound quality. The weight allocation is based on the importance of the frequency band's contribution to the final sound quality, ensuring reasonable optimization priorities. For example, low-frequency bands may be significantly affected by reflections, while high-frequency bands may experience sound distortion due to air absorption. Through this intelligent priority control, the system can flexibly adjust the gain of each frequency band to ensure that the audio output meets the optimal requirements of spatial acoustics.

[0040] These optimized control commands are sent to the audio equipment in real time via IoT protocols. The audio equipment automatically adjusts the equalizer parameters based on the received commands, optimizing the gain values ​​of each frequency band and effectively solving sound distortion problems. The audio equipment not only adjusts its audio output according to real-time changes in the spatial environment but also adaptively adjusts in dynamic acoustic environments to achieve optimal sound quality. The entire process is controlled by an artificial intelligence system, which automatically completes acoustic data acquisition, analysis, and adjustment, and provides real-time feedback on the optimization results, ensuring stable, high-quality sound effects in different spatial environments without human intervention.

[0041] This AI-based IoT-driven audio control method significantly improves the performance and adaptability of audio equipment through intelligent real-time acoustic data acquisition and analysis. First, the method automatically analyzes the acoustic characteristics of the target space and adjusts the equalizer parameters in real time according to the actual needs of the current environment, effectively solving the sound distortion problem caused by complex acoustic environments that traditional audio equipment struggles to handle. Second, through attribution analysis of reverberation time deviation using an AI model, it accurately identifies and optimizes sound problems within the space without manual intervention, reducing operational difficulty and labor costs. Furthermore, this method dynamically adjusts audio frequency bands through intelligent priority control, ensuring optimal sound quality output in different spatial environments and improving the stability and reliability of the audio system. Simultaneously, the system can flexibly adapt to different environmental changes, meeting the needs of various scenarios and enhancing the versatility of the equipment. Ultimately, this method not only improves sound quality but also increases user convenience by reducing the complexity of adjusting audio equipment, making the audio equipment more intelligent and efficient.

[0042] Example 2:

[0043] The specific steps for determining the reverberation time deviation value in S2 include subtracting the optimal reverberation time value that should be achieved under the current environment from the reverberation time value at the current point to obtain the reverberation time deviation value.

[0044] In this embodiment, firstly, acoustic characteristic data of the target space is collected in real time using IoT sensors to obtain the reverberation time value at the current point within the space. Next, an artificial intelligence model compares this reverberation time value at the current point with the optimal reverberation time value that should be achieved under the current environment, calculating the reverberation time deviation value. Specifically, the reverberation time deviation value is obtained by subtracting the optimal reverberation time value from the reverberation time value in the current environment. This deviation value reflects the degree of distortion in the sound output within the target space. The artificial intelligence model further analyzes this deviation value, attributing it to different factors in the acoustic environment, such as sound wave reflection, the distribution of sound-absorbing materials, and spatial layout, thereby identifying the root cause of sound quality distortion. This attribution analysis helps the artificial intelligence system intelligently adjust the audio equipment to reduce reverberation time deviation, improve sound quality, and optimize the sound effect.

[0045] Example 3:

[0046] The specific method for determining the final control command in S3 includes multiplying the frequency band weight by the adjustment value of the frequency band to obtain the weighted adjustment value of each frequency band; integrating the weighted adjustment values ​​of all frequency bands to generate a preliminary control command, which is a set of commands containing the weighted adjustment values ​​of each frequency band, used to guide the parameter adjustment of the audio equalizer.

[0047] In step S3, the AI ​​model determines the final control command by analyzing the acoustic data and reverberation time deviation values ​​from the preceding steps. Specifically, the AI ​​model first calculates the adjustment value (i.e., the adjustment amount of the audio gain for each frequency band) based on the adjustment value for each frequency band. Next, the model multiplies the adjustment value for each frequency band by its importance weight to obtain a weighted adjustment value for each band. The determination of the frequency band weights is based on the degree of influence of the frequency band on sound quality, typically considering the contributions of low and high frequencies, as well as their sensitivity in different spatial acoustic environments. Using the weighted adjustment values, the AI ​​model can calculate the final adjustment command for each frequency band. The final control command combines the adjustment values ​​and weights of each frequency band, allowing the audio equipment to precisely adjust the gain values ​​of each frequency band according to these comprehensive commands, optimizing sound quality performance and resolving sound distortion issues.

[0048] By multiplying the frequency band weights by the adjustment values ​​of each frequency band, the generated final control command can intelligently and dynamically adjust according to the importance of each frequency band, thereby achieving precise audio adjustment of the audio equipment in different spatial acoustic environments. This method makes the audio adjustment process more intelligent, avoiding simple gain adjustments in traditional methods by considering the contribution of each frequency band to sound quality, thus optimizing the performance of the entire audio system. Furthermore, the introduction of frequency band weights enhances the system's adaptability, enabling flexible adjustment of audio output based on changes in the actual environment, ensuring optimal sound quality in various usage scenarios. Users no longer need to manually adjust the audio equipment; the system's automated intelligent adjustment greatly simplifies the operation process and improves the user experience. Simultaneously, precise frequency band adjustment significantly reduces sound distortion, providing clearer and more realistic sound quality, greatly enhancing the performance and reliability of the audio equipment.

[0049] Example 4:

[0050] S1 includes using IoT sensors to monitor the acoustic characteristics of the target space in real time, establishing a model of the sound wave propagation process in space, calculating the sound energy distribution in each region, predicting the propagation of sound energy over time, and quantifying the sound energy intensity at different spatial locations.

[0051] In step S1, IoT sensors capture sound wave propagation information within the target space by monitoring its acoustic characteristics in real time. Specifically, the IoT sensors not only collect acoustic data but also model the sound wave propagation process. This model analyzes the propagation of sound waves from the sound source to different spatial locations, calculating the sound energy distribution in each area. Based on the propagation laws of sound waves, the system can predict the change of sound energy over time and quantify the sound energy intensity at different spatial locations. This process provides accurate spatial acoustic information for further analysis and optimization of audio equipment settings, making subsequent reverberation time analysis and equalizer adjustment command generation more scientific and precise.

[0052] By monitoring the propagation of sound waves in real time through IoT sensors and establishing a spatial acoustic energy distribution model, the system can gain a deep understanding of the propagation characteristics and acoustic energy distribution of sound waves within space. This method can accurately quantify the acoustic energy intensity at different spatial locations, providing a comprehensive understanding of the spatial acoustic environment and ensuring that audio equipment can be optimized and adjusted according to the specific acoustic characteristics of the target space. Through this modeling and prediction of sound wave propagation, the adaptability of audio equipment to complex environments can be improved, enabling more efficient acoustic adjustments and providing optimal sound quality. Furthermore, the ability to acquire and predict real-time acoustic data allows the system to continuously optimize in dynamic environments, further enhancing the intelligence and automation level of the audio system. This not only reduces the user's operational burden but also enhances the intelligent response capabilities and operational precision of the audio equipment, greatly improving the user experience.

[0053] The specific formula for calculating the acoustic energy distribution of each region in S1 is as follows:

[0054] A(t) = A0e -kt ;

[0055] Where A(t) represents the acoustic energy distribution in the region, t represents time, A0 represents the initial sound pressure intensity, e represents the base of the natural logarithm, and k represents the attenuation coefficient of the sound wave during its propagation in the target space.

[0056] The system monitors the acoustic characteristics of the target space using IoT sensors, calculating and analyzing the sound energy distribution in each area. To accurately quantify the change in sound energy over time, a sound wave attenuation model is employed to describe the sound energy propagation process. Specifically, the change in sound energy distribution is expressed by the following formula:

[0057] A(t) = A0e -kt ;

[0058] Where A(t) represents the acoustic energy distribution in the region, t represents time, A0 represents the initial sound pressure intensity, e represents the base of the natural logarithm, and k represents the attenuation coefficient of the sound wave during its propagation in the target space.

[0059] This formula accurately simulates the propagation and attenuation of sound waves in space, providing precise acoustic data support for adjusting audio equipment. Using this model, the corresponding sound energy intensity can be calculated for each area within a space, and the temporal evolution of sound energy can be predicted. This allows the audio system to monitor changes in the acoustic environment in real time and adjust the audio equipment based on the predicted sound energy distribution, ensuring optimal sound quality in different areas.

[0060] This method employs a sound wave attenuation model to calculate and predict sound energy distribution, enabling precise quantification of sound energy intensity in different areas of the target space and real-time tracking of sound energy changes over time. This model provides more accurate acoustic data support, helping audio equipment intelligently adjust its output parameters and optimize sound quality. By considering the attenuation effect of sound wave propagation, the system can more scientifically predict the acoustic environment of various areas within the space, ensuring that audio equipment provides ideal sound quality under different conditions. Furthermore, this method enhances the system's dynamic adaptability, automatically adjusting audio equipment settings when the spatial acoustic environment changes, thereby improving the intelligence level of the audio system and the user experience.

[0061] A(t) represents the sound energy distribution in the target area at time t, indicating the energy intensity of the sound wave at different locations in the target space, which attenuates over time. A0 is the initial sound pressure level, representing the sound wave intensity at the initial time t=0, usually determined by measuring the output of the audio equipment or the sound pressure level at the sound source. t is time, representing the time elapsed from the sound source to the current moment, usually calculated through the system's internal time synchronization mechanism. The attenuation coefficient k reflects the attenuation rate of the sound wave during its propagation in space, mainly affected by factors such as the size and shape of the space and the sound-absorbing materials, and is usually determined through experimental measurement or acoustic modeling. Experimental data can be collected by IoT sensors at different locations, and the value of k can be calculated based on the propagation characteristics of the sound wave through optimization algorithms or theoretical models. In summary, by reasonably determining these parameters, the system can accurately simulate the attenuation process of sound energy in space, thereby providing scientific data support for adjusting audio equipment, optimizing sound quality performance, and improving the intelligence level of the audio system.

[0062] Example 5:

[0063] The specific method for real-time adjustment of equalizer parameters in S4 includes: optimizing the initial control command through a path planning model, calculating the cost of adjustment for each frequency band, and weighted summing of the adjustment costs for all frequency bands to generate a comprehensive cost function; solving the comprehensive cost function using an optimization algorithm to determine the optimal adjustment path; generating an optimized control command based on the optimal control path, the control command including the actual gain value of each frequency band; and sending the optimized control command to the audio equipment via a network, whereby the audio equipment adjusts the equalizer parameters according to the control command to achieve precise sound effect control.

[0064] In step S4, the system uses a path planning model to calculate the adjustment amount and corresponding weight of each frequency band, thus obtaining the cost of adjusting each frequency band. Specifically, the frequency band adjustment cost measures the optimization cost required to adjust a certain frequency band, which is closely related to the sound effect impact and adjustment difficulty of that frequency band. For example, adjusting low-frequency bands may involve more complex spatial acoustic characteristics, thus incurring higher adjustment costs; while adjusting high-frequency bands may be more direct and less costly. The adjustment cost of each frequency band is obtained by multiplying the adjustment amount of that band by its weight. This process quantifies the optimization resources required to adjust different frequency bands.

[0065] Next, the system performs a weighted summation of the adjustment costs for all frequency bands. This weighted summation process not only integrates the adjustment costs of each frequency band but also considers the importance of each band in the overall sound quality, ensuring that the system prioritizes adjusting the frequency bands that have a greater impact on sound quality. This weighted summation method helps the system find the optimal adjustment path within limited resources or optimization time, thereby avoiding over-adjustment of certain frequency bands or neglect of adjustment of certain important frequency bands, thus achieving optimal global sound effects.

[0066] Ultimately, the optimized adjustment path is generated as the optimal control command and sent to the audio equipment via the network. Upon receiving the optimized adjustment command, the audio equipment adjusts the equalizer parameters in real time, precisely controlling the gain value of each frequency band. This adjustment adapts to the acoustic characteristics of the space, ensuring optimal sound quality performance in different environments and usage scenarios. Through this intelligent adjustment process, the audio system can automatically optimize sound output without manual intervention, ensuring clear and accurate sound while avoiding distortion or imbalanced sound quality issues.

[0067] By applying a path planning model, the system can intelligently find the optimal adjustment path across all frequency bands, thereby optimizing sound quality. The calculation of the adjustment cost of each frequency band multiplied by its weight allows the system to comprehensively consider the importance and adjustment difficulty of each band, achieving more precise sound control. Through weighted summation, the system can achieve a reasonable balance between different frequency bands, avoiding over-adjustment or imbalance in certain bands and ensuring the stability and balance of sound quality. Furthermore, this method can automatically adjust the equalizer parameters of the audio equipment based on the acoustic characteristics of the space, without manual intervention, greatly improving the intelligence and ease of operation of the audio equipment. Ultimately, users can enjoy more accurate and higher-quality sound effects while reducing the complexity of equipment maintenance and debugging.

[0068] Example 6:

[0069] In S1, the IoT sensor acquires sound characteristic data of the target space in real time through multiple data acquisition methods, including audio sensors, environmental sensors, and temperature and humidity sensors. The audio sensor is used to collect acoustic parameters such as sound pressure, frequency, reverberation, and echo. The environmental sensor is used to collect environmental data such as ambient noise level and changes in spatial layout. The temperature and humidity sensor is used to collect environmental parameters such as temperature and humidity. All collected data is transmitted in real time to an artificial intelligence model for comprehensive analysis to more accurately evaluate the acoustic characteristics of the target space.

[0070] In step S1, IoT sensors acquire real-time sound characteristic data of the target space through various data acquisition methods. These data acquisition methods include audio sensors, environmental sensors, and temperature and humidity sensors. The functions of each sensor are as follows: the audio sensor is mainly responsible for collecting acoustic characteristics such as sound pressure and frequency in the space, accurately capturing changes in audio signals; the environmental sensor is used to monitor echo and reverberation phenomena in the space, capturing reflected sound wave information, which is crucial for understanding the sound effects in the space; the temperature and humidity sensor can acquire real-time temperature and humidity data in the space, and these factors have a direct impact on sound wave propagation speed and sound quality.

[0071] All the sound characteristic data acquired by these sensors, including sound pressure level, frequency, reverberation, and echo, are transmitted to the artificial intelligence model in real time. The AI ​​model analyzes this data and automatically determines whether the acoustic characteristics of the space meet the optimal sound effect requirements by comparing the actual measured values ​​with the ideal target values. If it finds that some characteristics have not reached the ideal values, the model will generate corresponding adjustment instructions to guide the equalizer adjustment and sound effect optimization in subsequent steps.

[0072] By combining multiple sensors, this method can comprehensively and accurately collect sound characteristic data in the target space. The coordinated use of audio sensors, environmental sensors, and temperature and humidity sensors enables the system not only to monitor the sound wave characteristics within the space but also to perceive the real-time impact of environmental factors such as temperature and humidity on sound wave propagation and sound effects. This multi-dimensional data acquisition method significantly improves the system's adaptability and accuracy. Real-time analysis of this multi-source data by an artificial intelligence model allows audio equipment to intelligently adjust based on actual environmental conditions, optimizing sound quality and avoiding sound instability or distortion caused by environmental changes. Through this intelligent audio control, users can experience consistently high-quality sound without manual intervention, enhancing the intelligence level of audio equipment and the user experience.

[0073] Example 7:

[0074] S3 also includes automatically generating personalized equalizer parameters based on the preferences of users in different spaces. Specifically, it involves collecting users' sound effect preference data through mobile devices, including users' volume preferences, timbre preferences, and sound effect requirements in specific scenarios for different frequency bands; inputting the users' preference data into an artificial intelligence model, which then generates personalized equalizer parameters based on the users' preference data and the acoustic characteristics data of the target space.

[0075] In step S3, the system not only generates equalizer parameters based on the acoustic characteristics of the space, but also automatically generates personalized equalizer parameters considering the preferences of users in different spaces. Specifically, the system collects and analyzes users' sound effect preference data, such as their preferences for volume, bass, and treble frequencies of the audio system, and combines this with acoustic data within the space to automatically adjust the equalizer parameters to meet personalized sound effect needs. To achieve this goal, the artificial intelligence model learns and adjusts based on users' historical preferences and real-time feedback, making the equalizer parameter settings more in line with user expectations. For example, if a user prefers a strong bass effect, the system will prioritize adjusting the gain value of the low-frequency band; if a user prefers clear high frequencies, the system will adjust the gain value of the high-frequency band accordingly. Through this personalized setting, the audio system can provide the best sound effect experience to meet the needs of different users.

[0076] This method significantly enhances the flexibility of audio systems and the user experience by automatically generating personalized equalizer parameters based on the sound preferences of users in different spaces. Personalized sound adjustments precisely meet diverse user needs; whether a user prefers bass or seeks clear high frequencies, the system intelligently optimizes the sound. The artificial intelligence model learns from users' historical preferences and real-time feedback, ensuring each adjustment is more closely aligned with the user's needs, avoiding the complexity of manual operation. This feature not only improves the intelligence of the audio system but also reduces the user's workload through automated adjustments, allowing audio equipment to provide a more personalized and comfortable listening experience. Furthermore, the generation of personalized equalizer parameters ensures that users can always enjoy ideal sound performance in different spaces and usage scenarios.

[0077] Example 8:

[0078] IoT sensors collect and transmit data in real time through time synchronization technology, ensuring high-precision synchronous analysis of sound characteristic data in dynamic environmental changes.

[0079] In step S1, IoT sensors collect and transmit data in real time using time synchronization technology, ensuring high-precision synchronous analysis of sound characteristic data amidst dynamic environmental changes. Specifically, time synchronization technology ensures that when multiple sensors simultaneously collect data within the target space, the timestamps of each sensor remain consistent, avoiding data deviations caused by time asynchrony between sensors. Through this time synchronization, the system can accurately synchronize sound characteristic data collected by different sensors, such as sound pressure, frequency, reverberation, and echo, ensuring that this data reflects the overall acoustic environment of the space at the same moment. The real-time transmitted synchronized data, processed by an artificial intelligence model, provides accurate and reliable acoustic analysis data for subsequent sound optimization. Thus, when faced with dynamically changing environmental factors within the space (such as changes in temperature and humidity, changes in spatial layout, and external noise interference), the system can respond quickly, ensuring the efficiency and accuracy of sound adjustment and avoiding sound distortion or inaccurate adjustment due to data lag or inconsistency.

[0080] Through time-series synchronization technology, the system can achieve high-precision data synchronization among multiple sensors, ensuring the accuracy and timeliness of sound characteristic data. Especially under dynamic environmental changes (such as temperature and humidity variations or interference from other external noise sources), time-series synchronization technology ensures that data from each sensor reflects the acoustic characteristics of the space at the same point in time, avoiding data lag or misalignment, thereby improving the system's response speed and accuracy to environmental changes. This technology enables artificial intelligence models to perform more accurate acoustic analysis and sound effect optimization based on high-precision synchronized data, ensuring that audio equipment consistently provides high-quality sound effects in different environments and time periods. Through this precise data synchronization and real-time analysis, the audio system can quickly adjust equalizer parameters and optimize sound quality output, greatly enhancing the intelligence level of the audio equipment and the user experience.

[0081] like Figure 2 As shown, an audio control system based on AIoT technology is also provided to implement the steps of the audio control method based on AIoT technology. The system includes:

[0082] Internet of Things (IoT) sensors are used to collect acoustic characteristic data of the target space in real time.

[0083] An artificial intelligence analysis model is used to analyze spatial acoustic characteristics based on collected data and generate preliminary control commands for audio equalizer parameters based on the analysis results.

[0084] Path planning model: used to optimize the initial control command, calculate the cost of adjustment for each frequency band, perform a weighted summation of the adjustment costs for all frequency bands to generate a comprehensive cost function, solve the comprehensive cost function to determine the optimal adjustment path, and generate optimized control commands based on the optimal adjustment path;

[0085] Control command transmission module: Used to send optimized control commands to the audio equipment via the network. The audio equipment adjusts the equalizer parameters according to the control commands to achieve precise sound effect control and solve the sound distortion problem.

[0086] This AI-based audio control system comprises four main modules: IoT sensors, an AI analysis module, an equalizer control module, and a control command transmission module. The IoT sensors are responsible for real-time acquisition of acoustic characteristic data of the target space, including sound pressure level, frequency, reverberation, and echo, and ensure precise synchronization of data from multiple sensors through time-series synchronization technology. The acquired data is transmitted to the AI ​​analysis module, which utilizes machine learning and data analysis techniques to analyze the acoustic characteristics of the space in real time, identifying acoustic problems such as reverberation time deviation and frequency band imbalance. Subsequently, the equalizer control module generates control commands for the equalizer parameters based on the AI ​​analysis results, adjusting the frequency band gain of the audio equipment in real time to optimize sound quality and resolve sound distortion issues. Finally, the control command transmission module sends these optimized control commands to the audio equipment, ensuring that the equipment can adjust the equalizer parameters based on real-time analysis, thereby providing precise sound effect control in dynamic environmental changes and ensuring optimal sound performance.

[0087] This invention's audio control system effectively combines IoT sensors, an AI analysis module, an equalizer control module, and a control command transmission module to achieve precise control of audio equipment. The system can collect and analyze acoustic characteristic data within a space in real time, automatically generating personalized sound effect optimization schemes to ensure high-quality sound output from the audio equipment under various environmental conditions. By adjusting the equalizer parameters in real time, it solves the sound distortion problem and improves the performance and adaptability of the audio system. The system has a high level of intelligence, automatically adjusting according to environmental changes and user preferences, greatly improving the user experience and simplifying the operation process. Simultaneously, through high-precision data synchronization and rapid response, the system can consistently provide stable sound performance in dynamic environmental changes, enhancing the reliability and efficiency of the audio equipment.

[0088] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for controlling audio based on AI IoT technology, characterized in that, The method includes: S1. Acoustic characteristic data of the target space are collected in real time through IoT sensors; S2. Based on the collected data, the spatial acoustic characteristics are analyzed using an artificial intelligence model, including the real-time acquisition of the reverberation time value of the current point in the space by sensors, and the output of the optimal reverberation time value that should be achieved under the current environment by the artificial intelligence model, determining the reverberation time deviation value, and the artificial intelligence model performing attribution analysis on the reverberation time deviation value. S3. Generate preliminary control instructions for the audio equalizer parameters based on the analysis results. This includes the artificial intelligence model outputting adjustment values ​​for each frequency band based on the analysis results, and assigning frequency band weights according to the importance of the evaluation to determine the preliminary control instructions. S4. Optimize the initial control command through the path planning model to generate the optimized control command. Send the control command to the audio equipment to adjust the equalizer parameters in real time to solve the sound distortion problem. The control command includes the actual gain value of each frequency band to realize intelligent priority control. The specific steps for determining the reverberation time deviation value in S2 include subtracting the optimal reverberation time value that should be achieved under the current environment from the reverberation time value at the current point to obtain the reverberation time deviation value. The specific method for determining the final control command in S3 includes multiplying the frequency band weight by the adjustment value of the frequency band to obtain the weighted adjustment value of each frequency band; integrating the weighted adjustment values ​​of all frequency bands to generate a preliminary control command, which is a set of commands containing the weighted adjustment values ​​of each frequency band, used to guide the parameter adjustment of the audio equalizer; The S1 also includes using IoT sensors to monitor the acoustic characteristics data of the target space in real time, establishing a model for the propagation process of the sound wave data in space, calculating the sound energy distribution of each region, predicting the propagation of sound energy over time, and quantifying the sound energy intensity at different spatial locations. The specific formula for calculating the acoustic energy distribution of each region is as follows: ; in, Indicates the current sound energy distribution in the region. Indicates time, This represents the initial sound pressure level. The base of the natural logarithm. This represents the attenuation coefficient of sound waves during their propagation in the target space.

2. The audio control method based on AI IoT technology according to claim 1, characterized in that: The specific method for real-time adjustment of equalizer parameters in S4 includes: optimizing the initial control command through a path planning model, calculating the cost of adjustment for each frequency band, and weighted summing of the adjustment costs for all frequency bands to generate a comprehensive cost function; solving the comprehensive cost function using an optimization algorithm to determine the optimal adjustment path; and generating an optimized control command based on the optimal control path, wherein the control command includes the actual gain value for each frequency band. The optimized control command is sent to the audio equipment via the network. The audio equipment adjusts the equalizer parameters according to the control command to achieve precise sound effect control.

3. The audio control method based on AI IoT technology according to claim 1, characterized in that: In S1, the IoT sensor acquires sound characteristic data of the target space in real time through multiple data acquisition methods, including audio sensors, environmental sensors, and temperature and humidity sensors. The audio sensor is used to collect acoustic parameters such as sound pressure, frequency, reverberation, and echo. The environmental sensor is used to collect environmental data such as ambient noise level and changes in spatial layout. The temperature and humidity sensor is used to collect environmental parameters such as temperature and humidity. All collected data is transmitted in real time to an artificial intelligence model for comprehensive analysis to more accurately evaluate the acoustic characteristics of the target space.

4. The audio control method based on AI IoT technology according to claim 1, characterized in that: The S3 also includes automatically generating personalized equalizer parameters based on the preferences of users in different spaces. Specifically, this involves collecting users' sound effect preference data through mobile devices. The preference data includes users' volume preferences, timbre preferences, and sound effect requirements for different frequency bands and specific scenarios. The user's preference data is then input into an artificial intelligence model, which generates personalized equalizer parameters based on the user's preference data and the acoustic characteristics data of the target space.

5. The audio control method based on AI IoT technology according to claim 1, characterized in that: The IoT sensor uses time synchronization technology to collect and transmit data in real time, ensuring high-precision synchronous analysis of sound characteristic data in dynamic environmental changes.

6. A sound control system based on AI Internet of Things (AIIoT) technology, used to implement the steps of the sound control method based on AIIoT technology as described in any one of claims 1-5, characterized in that, The system includes: Internet of Things (IoT) sensors are used to collect acoustic characteristic data of the target space in real time. An artificial intelligence analysis model is used to analyze spatial acoustic characteristics based on collected data and generate preliminary control commands for audio equalizer parameters based on the analysis results. Path planning model: used to optimize the initial control command, calculate the cost of adjustment for each frequency band, perform a weighted summation of the adjustment costs for all frequency bands to generate a comprehensive cost function, solve the comprehensive cost function to determine the optimal adjustment path, and generate optimized control commands based on the optimal adjustment path; Control command transmission module: Used to send optimized control commands to the audio equipment via the network. The audio equipment adjusts the equalizer parameters according to the control commands to achieve precise sound effect control and solve the sound distortion problem.

Images