Intelligent indoor noise reduction and sound scene optimization system

Abstract

The invention relates to the technical field of indoor environment control, and discloses an intelligent indoor noise reduction and sound scene optimization system, which comprises the following modules: a noise monitoring module; a scene identification module; a user preference module; the sound scene optimization module is configured to dynamically match sound scene resources through a three-dimensional matrix based on the noise data, scene types and user preferences; the active noise reduction module is configured to generate reverse sound waves according to the noise spectrum characteristics, and target noise is counteracted through the loudspeaker array; a sound scene playing module; and an evaluation feedback module. According to the invention, the active noise reduction module is combined to suppress low-frequency and high-frequency noise in a partitioned manner, the noise reduction efficiency is improved, meanwhile, the sound scene optimization module based on the three-dimensional matrix dynamically matches scene requirements and user preferences, double targets of noise covering and sound scene immersion are realized, the user comfort is improved, and the user experience is improved. The loudspeaker is especially suitable for various living spaces, office spaces, commercial areas and special places with high requirements for sound environment.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor environment control, and particularly to an intelligent indoor noise reduction and soundscape optimization system. Background Art

[0002] Currently, with the acceleration of urbanization and the improvement of people's living standards, the problem of indoor noise pollution has become increasingly serious. External noise sources such as traffic noise, industrial noise, and construction noise, as well as internal noise sources such as household appliances, ventilation equipment, and human activities, jointly affect the quality of the indoor sound environment. Long-term exposure to a high-noise environment can cause many adverse effects on people's physical and mental health, such as hearing damage, increased psychological stress, sleep disorders, and reduced work efficiency. Existing indoor noise reduction technologies mainly include passive noise reduction methods such as using sound insulation materials, installing sound insulation doors and windows, and using sound absorption panels, as well as active noise reduction methods such as using active noise reduction headphones and active noise reduction devices. However, these methods have some limitations. Passive noise reduction methods often have limited effects and will occupy a certain amount of space; active noise reduction devices usually can only reduce noise at specific frequencies, and have high costs and difficult maintenance. In addition, existing noise reduction technologies often only focus on reducing the noise level, while ignoring the comfort and functionality of the sound environment. Summary of the Invention

[0003] To make up for the above deficiencies, the present invention provides an intelligent indoor noise reduction and soundscape optimization system, which solves the comprehensive problem that existing indoor noise reduction technologies cannot simultaneously and efficiently suppress noise, dynamically optimize the soundscape environment, and adapt to the personalized needs of multiple scenarios. By integrating active noise suppression, intelligent soundscape matching, and closed-loop feedback regulation, the coordinated improvement of noise reduction effects and sound environment comfort is achieved.

[0004] In the first aspect, the present invention provides the following technical solutions: An intelligent indoor noise reduction and soundscape optimization system, including the following modules: A noise monitoring module, configured to collect indoor environmental noise data in real time through a microphone array, analyze the spectrum, intensity, and persistence of the noise, and identify the noise type; A scene recognition module, configured to determine the current indoor functional scene based on sensor data or user activity information; A user preference module, configured to collect and dynamically update the user's soundscape preference data; A soundscape optimization module, configured to dynamically match soundscape resources through a three-dimensional matrix based on the noise data, scene type, and user preferences; An active noise reduction module, configured to generate a reverse sound wave according to the noise spectrum characteristics and cancel the target noise through a speaker array; A soundscape playback module, configured to call music library resources and play the adapted soundscape content through a speaker; The evaluation feedback module is configured to adjust system parameters based on physical metrics and user subjective ratings.

[0005] Preferably, the noise monitoring module includes: A spectrum analysis unit that uses FFT to analyze the spectral distribution of noise and distinguish low-frequency, medium-frequency, and high-frequency noise; A persistence recognition unit that determines whether the noise is continuous, intermittent, or pulsed through time series analysis; A noise database that stores historical noise data and noise reduction strategies.

[0006] Preferably, the scenario recognition module determines the functional scenario in the following manner: Time information; User activity data, including stationary or moving states; Room type, including bedroom, living room, or study.

[0007] Preferably, the dimensions of the three-dimensional matrix include a noise characteristic axis, a scenario context axis, and a user preference axis. The matrix weights are calculated by the formula W = αNx + βCy + γPz, where Nx is the noise characteristic fitness, Cy is the scenario fitness, Pz is the user preference fitness, and α, β, γ are weight factors; The construction of the three-dimensional matrix of the soundscape optimization module includes: The noise characteristic axis, classified by spectral range, intensity, and persistence; The scenario context axis, defining the soundscape goal according to functional requirements; The user preference axis, dynamically adjusting the adaptation weights according to music type, volume, and style.

[0008] Preferably, the active noise reduction module includes: A low-frequency noise suppression unit that generates a reverse sound wave and cancels the noise through a low-frequency speaker; A high-frequency noise suppression unit that generates an adaptive filtering signal and covers the noise source area through a high-frequency speaker; A real-time feedback unit that dynamically adjusts the phase and amplitude of the reverse sound wave.

[0009] Preferably, the arrangement of the speaker array includes: Installing embedded full-frequency speakers at the four corners of the ceiling in the bedroom and arranging low-frequency speakers near the bed; Adopting a surround sound system in the living room and arranging mid-high frequency speakers on both side walls; Installing a full-frequency speaker directly in front of the desktop in the study.

[0010] Preferably, the comprehensive score of the evaluation feedback module is calculated by the following formula: Total score = 0.6 Physical score 0.4 Subjective scoring, where the physical scoring is based on the background noise attenuation value, the reverberation time compliance rate, and the signal-to-noise ratio improvement value, and the subjective scoring is based on the comfort, clarity, and scene adaptability of the user terminal.

[0011] In a second aspect, the present invention provides the following technical solution. An intelligent indoor noise reduction and soundscape optimization method includes the following steps: Collect and analyze the spectrum, intensity, and persistence of indoor noise in real time; Identify the current functional scenario and obtain the user's soundscape preference; Dynamically match soundscape resources based on a three-dimensional matrix and calculate the adaptation weight; Generate a reverse sound wave to cancel the target noise and play the adapted soundscape through a speaker; Optimize the system parameters by combining physical indicators and user feedback.

[0012] Preferably, the noise analysis includes: Use FFT to analyze the spectrum distribution; analyze the noise persistence through time series; store the noise data in a database; The speaker arrangement method includes: A combined arrangement of an embedded full-frequency speaker and a low-frequency speaker in the bedroom; a mid-high frequency speaker arrangement of a surround sound system in the living room; a full-frequency speaker arrangement directly in front of the desktop in the study.

[0013] In a third aspect, the invention provides the following technical solution. A computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned intelligent indoor noise reduction and soundscape optimization method is implemented.

[0014] In a fourth aspect, the present invention provides the following technical solution. A readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent indoor noise reduction and soundscape optimization method is implemented.

[0015] The present invention has the following beneficial effects: 1. In the present invention, the noise monitoring module analyzes the noise spectrum, intensity, and persistence in real time, and combines with the active noise reduction module to suppress low-frequency and high-frequency noises in different zones, improving the noise reduction efficiency; at the same time, the soundscape optimization module based on the three-dimensional matrix dynamically matches the scene requirements and user preferences, achieving the dual goals of noise masking and soundscape immersion, improving the user's comfort, and is particularly suitable for various living spaces, office places, commercial areas, and special places with high requirements for the acoustic environment, such as recording studios, hospital wards, etc.

[0016] 2. In the present invention, the user preference module records and learns the user's soundscape selection habits, and combines with the collaborative filtering algorithm to recommend adapted resources, supporting dynamic adjustment of music types, volumes, and styles to meet the personalized needs of different users.

[0017] 3. In the present invention, the scene recognition module based on time, user activities, and room types ensures a high degree of matching between the soundscape strategy and the real-time environment; the evaluation and feedback module dynamically adjusts the noise reduction intensity and matrix weights through physical indicators and user ratings, forming a "monitoring - execution - feedback" closed loop to improve the long-term operation stability of the system.

[0018] 4. In the present invention, the modular design supports seamless linkage with the smart home system. The partition layout of the speaker array adapts to the acoustic characteristics of different rooms. Users can flexibly expand or adjust the hardware configuration, reducing the system deployment cost and significantly enhancing the maintenance convenience.

[0019] 5. In the present invention, the sound field distribution is optimized through the directional arrangement of speakers and digital signal processing technology, and the reverberation time control error is less than 0.1 second; the active noise reduction module adjusts the acoustic wave parameters in combination with real-time feedback, and the noise attenuation value fluctuation range is controlled within ±2dB, enhancing the stability of the noise reduction effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a framework diagram of the intelligent indoor noise reduction and soundscape optimization system proposed by the present invention; Figure 2 is a flowchart of the intelligent indoor noise reduction and soundscape optimization method proposed by the present invention; Figure 3 is a flowchart of an embodiment of the intelligent indoor noise reduction and soundscape optimization system proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The technical solutions in 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 a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment 1: Referring to Figures 1-3 , in the first embodiment of the present invention, the present invention provides an intelligent indoor noise reduction and soundscape optimization system, including the following modules: The noise monitoring module is configured to collect indoor environmental noise data in real time through a microphone array, analyze the spectrum, intensity, and persistence of the noise, and identify the noise type; The scene recognition module is configured to determine the current indoor functional scene based on sensor data or user activity information; A user preference module, configured to collect and dynamically update the user's soundscape preference data; A soundscape optimization module, configured to dynamically match soundscape resources through a three-dimensional matrix based on noise data, scene types, and user preferences; An active noise reduction module, configured to generate an inverse sound wave according to the noise spectrum characteristics and cancel the target noise through a speaker array; A soundscape playback module, configured to call music library resources and play the adapted soundscape content through speakers; An evaluation and feedback module, configured to adjust system parameters through physical indicators and user subjective ratings.

[0023] In this embodiment, the noise monitoring module is responsible for real-time collection and analysis of indoor noise data, providing key information such as noise type, spectrum characteristics, and persistence for the system, which is the data basis for noise reduction and soundscape optimization. By arranging an omnidirectional microphone and a directional microphone array, the noise monitoring requirements of different indoor areas are covered. The omnidirectional microphone is installed at the center position of the space (such as the bedroom ceiling) to capture the overall background noise; the directional microphones are deployed near windows, doors, and household appliances to accurately locate external traffic noise or internal equipment noise.

[0024] After the noise signal is converted by analog-to-digital conversion, the low-frequency, medium-frequency, and high-frequency components are distinguished through spectrum analysis, and combined with time series analysis to determine whether the noise is continuous, intermittent, or pulsed. The historical noise data is stored in the database for optimizing the noise reduction strategy. The extraction of multi-dimensional noise characteristics supports precise noise reduction, and the layout of directional microphones enhances the noise source localization ability.

[0025] In this embodiment, the scene recognition module determines the current indoor functional scene through multi-source data fusion to ensure that the soundscape optimization meets the actual usage requirements. In this embodiment, the scene determination is based on time information, user activity data, and room type. For example: Sleep scene: during the night period (such as 22:00 - 6:00) and the bedroom sensor detects that the user is in a stationary state; Work scene: keyboard input or screen usage signal is detected in the study area during the day; Entertainment scene: the living room infrared sensor detects multiple people's activities or the TV device is turned on.

[0026] The user can manually switch the scene mode through the mobile phone App, and the system automatically records the preferences to optimize subsequent recognition.

[0027] The advantages are: dynamic scene adaptation improves the matching degree between the sound environment and user behavior.

[0028] In this embodiment, the user preference module collects and dynamically updates the user's soundscape selection habits to support personalized sound environment regulation. When the user uses it for the first time, they select the preference type (such as natural sounds, light music), volume requirements, and style preferences through the interaction interface. The system continuously records the historical selection data and recommends similar soundscape resources through the collaborative filtering algorithm. For example, if the user repeatedly selects the combination of "rain sound + low frequency", the system will preferentially match similar resources. The personalized recommendation mechanism is used to enhance the user experience, and dynamic learning is carried out to improve the adaptation accuracy.

[0029] In this embodiment, the soundscape optimization module dynamically matches the optimal soundscape resources through a three-dimensional matrix, and realizes intelligent decision-making by combining noise, scene, and user preferences. The construction of the three-dimensional matrix includes the following dimensions: Noise characteristic axis: Classify noise according to spectrum, intensity, and persistence; Scene context axis: Define the soundscape goals of different scenes (for example, the sleep scene needs to mask noise, and the work scene needs clear speech); User preference axis: Dynamically adjust the weights according to music type, volume, and style.

[0030] The system calculates the soundscape adaptation weight based on noise data, scene type, and user preferences, and calls the resource with the highest priority from the pre-classified music library. For example, in a low-frequency traffic noise environment, the rain sound effect is preferentially matched to mask the noise.

[0031] In this embodiment, the active noise reduction module cancels the target noise by generating reverse sound waves, reducing the indoor noise level. Specifically, for low-frequency noise (such as traffic noise), reverse sound waves are generated by low-frequency speakers arranged near the noise source; for high-frequency noise (such as household appliance noise), high-frequency speakers are used to play masking sounds or adaptive filtering signals.

[0032] The noise reduction effect is real-time feedback through the microphone array, and the phase and amplitude of the sound waves are dynamically adjusted. For example, when it is detected that the residual noise after noise reduction exceeds the standard, the system automatically increases the intensity of the reverse sound waves. The advantages are: the zonal noise reduction strategy improves the noise suppression efficiency, and the real-time feedback mechanism ensures the noise reduction stability.

[0033] In this embodiment, the soundscape playback module calls the music library resources according to the optimization results, and creates a comfortable sound environment through the speaker array. The zonal speaker layout adapts to different scene requirements, and the sound field equalization technology improves the auditory comfort.

[0034] Specifically, the speakers are arranged according to functional zones: Bedroom: Full-frequency speakers are installed at the four corners of the ceiling to provide a uniform sound field, and low-frequency speakers near the bed enhance the noise reduction effect; Living room: A 5.1 surround sound system is adopted, and mid-high frequency speakers are arranged on both sides of the wall to optimize the audio-visual experience; Study: The full-frequency speakers directly in front of the desktop reduce reverberation and improve speech clarity.

[0035] The played content is adjusted for equalization through a digital signal processor (DSP) to ensure uniform sound field distribution.

[0036] In this embodiment, the evaluation and feedback module comprehensively evaluates the system effect through physical indicators and user ratings, and dynamically optimizes parameters. Specifically, the physical indicators include the background noise attenuation value, the reverberation time compliance rate, and the signal-to-noise ratio improvement value, which are measured in real time by sensors; the user's subjective ratings collect feedback on comfort, clarity, and scene adaptability through the App interface.

[0037] The system adjusts parameters such as the noise reduction intensity and the soundscape matching weight according to the comprehensive score (e.g., total score = 0.6×physical score + 0.4×subjective score). For example, when the user's rating is low, the weight of the user's preference (γ) is preferentially increased.

[0038] The above technical solutions of this embodiment have the following advantages: 1. Module collaboration: Data communication among modules forms a closed loop of "monitoring, recognition, optimization, execution, and feedback" to achieve dynamic regulation of the acoustic environment.

[0039] 2. Precise adaptation: The integration of noise feature analysis, scene recognition, and user preferences ensures real-time matching of the soundscape with the environment.

[0040] 3. Expandability: The modular design supports linkage with smart home systems (such as lighting and temperature control) to enhance the overall living experience.

[0041] In a specific implementation, the noise monitoring module includes: A spectrum analysis unit that uses FFT to analyze the spectral distribution of noise and distinguish low-frequency, medium-frequency, and high-frequency noise; A persistence recognition unit that determines whether the noise is continuous, intermittent, or pulsed through time series analysis; A noise database that stores historical noise data and noise reduction strategies.

[0042] In a specific implementation, the scene recognition module determines the functional scene in the following ways: Time information; User activity data, including stationary or moving states; Room type, including bedroom, living room, or study.

[0043] Specifically: Time information: The system obtains the current time through the built-in clock and associates the scene according to the preset rules. For example, at night (22:00 - 6:00), the bedroom is automatically determined as the sleep scene, and during the day (8:00 - 18:00), the study is determined as the working scene.

[0044] User activity data: Stationary state: Detect whether the user is stationary through infrared sensors or pressure mattresses (e.g. no mobile signal on the bed in the bedroom for more than 10 minutes); Movement status: The motion sensor is used to detect the user activity frequency in the living room (for example, if the number of movements per minute is ≥5 times, it is considered an entertainment scene).

[0045] Room Type: The user manually marks the room type (e.g., bedroom, living room) when the system is initialized; The system automatically recommends the default type based on the room layout (area, furniture configuration) and supports manual modification.

[0046] Specifically, the scene recognition module is connected to the time management system, human body sensor and room type recognition system of the intelligent prefabricated house. The time management system provides accurate time information, and the scene recognition module uses this as a basis for scene judgment. For example, the night time period is likely to correspond to the sleeping scene. The human body sensor monitors the user's activity data in real time. When it is detected that the user is in a static state for a long time, combined with the time and room type, if it is in the bedroom and the time is night, it can be judged as a sleeping scene; if the user is detected to be in a moving state and in the living room, combined with the time if it is daytime, it may be an entertainment or daily activity scene. The room type recognition system can determine the room type through specific equipment layout, decoration style and other information in the room. This enables the scene recognition module to accurately determine the current functional scene based on multi-dimensional information, provide accurate scene basis for subsequent soundscape optimization and noise reduction processing, and improve the adaptability and intelligence of the system.

[0047] In a specific embodiment, the dimensions of the three-dimensional matrix include a noise characteristic axis, a scene context axis, and a user preference axis, and the matrix weight is calculated by the formula W=αNx+βCy+γPz, where Nx is the noise characteristic adaptation, Cy is the scene adaptation, Pz is the user preference adaptation, and α, β, γ are weight factors.

[0048] The three-dimensional matrix construction of the soundscape optimization module includes: The noise characteristics axis is classified by spectral range, intensity and persistence; The scene situation axis defines the soundscape objectives according to functional requirements; User preference axis dynamically adjusts the adaptation weight according to music type, volume and style.

[0049] Specific: Noise characteristic axis: Spectrum range: low frequency (<250Hz) corresponds to traffic noise, medium frequency (250Hz-2kHz) corresponds to human voice, and high frequency (>2kHz) corresponds to household appliance noise; Intensity classification: Low (<40dB), Medium (40 - 60dB), High (>60dB); Persistence classification: Continuous (such as air conditioner sound), Intermittent (such as doorbell), Pulse (such as knocking sound).

[0050] Scene context axis: Sleep scene: The goal is to mask low - frequency noise and play a soothing soundscape (such as rain sound); Work scene: The goal is to improve speech clarity and play neutral music without lyrics (such as piano music); Entertainment scene: The goal is to enhance immersion and play a dynamic soundscape (such as electronic music).

[0051] User preference axis: Music type: Record preference tags through the user's historical selection (such as "natural sound", "classical music"); Volume requirement: Adjust the playback volume level according to the user's manual setting or system learning; Style preference: Dynamically optimize based on scoring data (such as increasing the weight if the user prefers a low - frequency soundscape).

[0052] Weight factor adjustment: α = 0.5, β = 0.3, γ = 0.2, and the system dynamically adjusts according to user feedback (such as increasing γ when the user's score is low).

[0053] Specifically, when the soundscape optimization module constructs a three - dimensional matrix, in terms of the noise characteristic axis, it is connected to the noise monitoring module to obtain noise data. The noise is divided into low - frequency, medium - frequency, and high - frequency according to the frequency spectrum range, into low, medium, and high according to intensity, and into continuous, intermittent, and pulse types according to persistence, so as to comprehensively describe the noise characteristics. The scene context axis defines the soundscape goals according to different room types and functional requirements. For example, the sleep scene in the bedroom requires a soothing, low - frequency background sound, while the entertainment scene requires a dynamic, high - energy soundscape. The user preference axis obtains data through the user preference module and dynamically adjusts and adapts the weights according to the user's preferences for music type, volume, and style. The formula for calculating the matrix weight W = αNx+βCy+γPz is based on a comprehensive consideration of noise characteristics, scene requirements, and user preferences. By adjusting the weight factors α, β, γ, the importance of different factors in matching soundscape resources can be flexibly controlled, enabling the soundscape optimization module to find the most suitable soundscape resources for different noise environments, scenes, and user preferences, and improving the accuracy and personalization of soundscape optimization.

[0054] In a specific implementation, the active noise reduction module includes: Low - frequency noise suppression unit, generating a reverse sound wave and canceling the noise through a low - frequency speaker; High - frequency noise suppression unit, generating an adaptive filtering signal and covering the noise source area through a high - frequency speaker; The real-time feedback unit dynamically adjusts the phase and amplitude of the reverse sound wave.

[0055] Specifically, the low-frequency noise suppression unit obtains low-frequency noise data by connecting with the noise monitoring module, and generates sound waves with the opposite phase to the low-frequency noise according to these data. The low-frequency speakers are arranged at specific positions indoors, such as near the bed in the bedroom, and the generated reverse sound waves are played out. Using the principle of sound wave interference, the reverse sound waves and the low-frequency noise cancel each other out, effectively reducing the impact of low-frequency noise on users. After the high-frequency noise suppression unit obtains the high-frequency noise data, it generates an adaptive filtering signal and emits the signal to the noise source area through the high-frequency speakers to cover the high-frequency noise. The real-time feedback unit continuously collects indoor noise data and dynamically adjusts the phase and amplitude of the reverse sound wave according to the actual noise reduction effect. For example, if it is found that the low-frequency noise has not been completely canceled, the real-time feedback unit will adjust the phase and amplitude of the reverse sound wave generated by the low-frequency noise suppression unit, so as to achieve a more accurate and efficient noise reduction effect and create a quieter indoor environment for users.

[0056] In a specific implementation manner, the arrangement method of the speaker array includes: Install embedded full-frequency speakers at the four corners of the ceiling in the bedroom, and arrange low-frequency speakers near the bed; Adopt a surround sound system in the living room, and arrange mid-high frequency speakers on both sides of the wall; Install a full-frequency speaker directly in front of the desktop in the study.

[0057] Specifically, in the bedroom, installing embedded full-frequency speakers at the four corners of the ceiling can achieve a relatively uniform sound field coverage, enabling the sound to spread relatively evenly at various positions in the bedroom. Arranging low-frequency speakers near the bed because people are more sensitive to low-frequency noise during sleep, and the low-frequency speakers can specifically enhance the noise reduction effect and at the same time play a soothing low-frequency soundscape for the sleep scenario. The living room adopts a surround sound system, and mid-high frequency speakers are arranged on both sides of the wall. This arrangement method can create a surround stereo effect, optimize the mid-frequency and high-frequency playback effects, and enhance the entertainment experience. For example, when watching movies or listening to music, users can feel richer and more immersive sounds. Installing a full-frequency speaker directly in front of the desktop in the study is to provide high-definition voice or background music playback when users are working or studying, reduce room echo interference, ensure that users can clearly hear the sound content, and improve concentration.

[0058] In a specific implementation manner, the comprehensive score of the evaluation feedback module is calculated by the following formula: Total score = 0.6 × Physical score + 0.4 × Subjective score, where the physical score is based on the background noise attenuation value, the reverberation time compliance rate, and the signal-to-noise ratio improvement value, and the subjective score is based on the comfort, clarity, and scene adaptability scores of the user terminal.

[0059] Specifically, the evaluation and feedback module is connected to the microphone array and the user terminal. The microphone array collects indoor sound data in real time. Based on this, the evaluation and feedback module calculates the background noise attenuation value, the reverberation time compliance rate, and the signal-to-noise ratio improvement value, and determines the physical score accordingly. These physical indicators can objectively reflect the noise reduction and soundscape optimization effects of the system. At the same time, the evaluation and feedback module obtains the user's scores for comfort, clarity, and scene adaptability from the user terminal as subjective scores. Through the formula total score = 0.6 * physical score + 0.4 * subjective score, the objective physical indicators and the user's subjective feelings are comprehensively considered, making the evaluation result more comprehensive and accurate. According to this comprehensive score, the evaluation and feedback module can judge the current operation effect of the system, and then adjust system parameters, such as adjusting the speaker volume, soundscape resource matching strategy, etc., to achieve the continuous optimization of the system and continuously improve the user experience.

[0060] Embodiment 2: Referring to Figures 2-3 , in the second embodiment of the present invention, the present invention provides the following technical solution, an intelligent indoor noise reduction and soundscape optimization method, including the following steps: Collect and analyze the spectrum, intensity, and persistence of indoor noise in real time; Identify the current functional scene and obtain the user's soundscape preference; Dynamically match soundscape resources based on a three-dimensional matrix and calculate the adaptation weight; Generate reverse sound waves to cancel the target noise and play the adapted soundscape through the speaker; Optimize system parameters by combining physical indicators and user feedback.

[0061] Preferably, the noise analysis includes: Use FFT to analyze the spectrum distribution; analyze the noise persistence through time series; store the noise data in the database; The speaker arrangement methods include: The combined arrangement of embedded full-frequency speakers and low-frequency speakers in the bedroom; the mid-high frequency speaker arrangement of the surround sound system in the living room; the full-frequency speaker arrangement directly in front of the desktop in the study.

[0062] Specifically, the method includes the following steps: Step S1: Indoor sound environment standard formulation.

[0063] Based on relevant international and domestic acoustic standards, combined with the usage functions of different places and people's psychological needs, formulate a scientific and reasonable indoor sound environment standard.

[0064] The first step, physical acoustics indicators: Background noise level (NoiseLevel, LAeq): Measure the average sound pressure level of indoor noise (unit: dB(A)). Bedroom (night): ≤30 dB; Living room (day): ≤40 dB; Kitchen: ≤50 dB.

[0065] Reverberation time (ReverberationTime, T30): The time it takes for sound to decay to 60 dB of the initial sound pressure level after reflection in the room. Study: 0.4 - 0.6 seconds (clear speech); Living room: 0.6 - 0.8 seconds (rich sound).

[0066] Signal-to-noise ratio (SignaltoNoiseRatio, SNR): The ratio of the signal sound (such as speech, music) to the background noise. Video calls, learning environment: ≥20 dB; Entertainment scene: ≥15 dB.

[0067] Frequency spectrum characteristics (FrequencySpectrum): Low-frequency noise control: <250 Hz (such as traffic noise); High-frequency noise control: >2 kHz (such as kitchen appliance noise).

[0068] Step 2, subjective evaluation indicators: Sound comfort: The psychological impact of noise on occupants.

[0069] Sound clarity: The recognizability of speech and music.

[0070] Soundscape functionality: Whether the sound environment meets the current scene requirements (such as relaxation, concentration).

[0071] Step S2: Indoor soundscape zoning.

[0072] According to the functional layout and usage requirements of the indoor space, divide the indoor space into different soundscape zones, such as the bedroom zone, living room zone, study zone, kitchen zone, bathroom zone, etc. Each soundscape zone has its specific background noise value range and sound environment requirements. Use a combination of acoustic simulation software and on-site measurement methods to determine the background noise value range of each soundscape zone, considering factors such as space size, shape, decoration materials, and surrounding environment. For example, the background noise value range of a room close to a traffic artery should be relatively high, while that of a room located in a quiet community can be relatively low.

[0073] Step S3: Construction of the soundscape music atlas and music library.

[0074] The core of the soundscape music atlas is to establish a set of mapping rules for dynamically matching the noise environment and music resources to achieve the best soundscape effect in different indoor scenes. This atlas comprehensively considers factors such as noise characteristics, indoor usage scenarios, and user subjective needs.

[0075] Step 1: Construct the three-dimensional matrix structure of the soundscape map: The three axes of the three-dimensional matrix are the noise characteristic axis, the scene context axis, and the user preference axis.

[0076] The noise characteristic axis represents the type and characteristics of the current environmental noise, including the following dimensions: Spectrum range: low frequency (<250 Hz), medium frequency (250 Hz - 2 kHz), high frequency (>2 kHz).

[0077] Noise intensity: low (<40 dB), medium (40 - 60 dB), high (>60 dB).

[0078] Noise persistence: continuous (such as air conditioner sound), intermittent (such as doorbell sound), pulsed (such as knocking sound).

[0079] The scene context axis represents the functional scene where the current user is located, including: Sleep scene: requires soothing, low-frequency background sound.

[0080] Work scene: requires neutral or non-lyrical background sound, with focus prioritized.

[0081] Entertainment scene: requires a dynamic, high-energy soundscape.

[0082] Relaxation scene: requires natural sound effects (such as rain sound, ocean wave sound).

[0083] The user preference axis represents the personalized needs and preferences of the user: Music type preference: such as natural sound, instrumental music, white noise.

[0084] Volume requirement: soft volume, standard volume, higher volume.

[0085] Style preference: such as liking low frequency, preferring a brisk rhythm.

[0086] The three-dimensional matrix is represented by M[x][y][z], corresponding to the noise characteristic axis (x), the scene context axis (y), and the user preference axis (z) respectively. The values in the matrix represent the adaptation weights, and the higher the weight, the more suitable the music resource.

[0087] Example of matrix value: M[low-frequency noise][sleep scene][rain sound preference] = 0.9, indicating that the adaptation degree of low-frequency noise + rain sound in the sleep scene is 90%.

[0088] Step S4: Matrix construction.

[0089] Step 1, Noise characteristic analysis: Collect environmental noise data in real time through a microphone array, use FFT (Fast Fourier Transform) to analyze the spectrum distribution, determine the noise intensity (dB) and spectrum type (low frequency, medium frequency, high frequency), and identify the noise persistence (continuous, intermittent, pulsed).

[0090] Step 2, Scene context recognition: Obtain the current context information from the sensors or the central control system of the intelligent prefabricated house, and identify the scene according to time, user activities (such as sleeping, working), room type (bedroom, living room), etc. For example, the bedroom is usually a sleeping scene at night, and the study may be a working scene during the day.

[0091] Step 3, User preference collection: Initial setting: Select the preferred music types and styles through a questionnaire or user manual selection.

[0092] Dynamic learning: The system updates the preference model according to the user's historical selection records.

[0093] Step S5: Matrix weight calculation.

[0094] Use the weight distribution model to calculate the fitness of music resources: W = αNx + βCy + γPz. Where, Nx is the noise characteristic fitness (matched according to the spectrum and intensity); Cy is the scene context fitness (according to the context and functional requirements); Pz is the user preference fitness; α, β, γ are weight factors, representing the importance ratios of noise characteristics, context, and preferences.

[0095] Step S6: Sound source analysis and monitoring.

[0096] Use advanced acoustic sensors and signal processing technologies to analyze and monitor the sound sources inside and outside the room.

[0097] Step 1, Identify the characteristics of the noise type, source, intensity, and frequency distribution, etc., to provide a basis for subsequent noise reduction processing.

[0098] Step 2, Install multiple acoustic sensors at different positions inside the room to achieve all-round monitoring of indoor noise. The sensors can collect noise data in real time and transmit it to the central control system through a wireless network for analysis and processing.

[0099] Step 3, Establish a noise database to record the characteristics of different types of noise.

[0100] Step S7: Speaker layout system and microphone array setting.

[0101] Step 1, Speaker layout: Bedroom speaker arrangement: Install embedded speakers at the four corners of the ceiling to achieve uniform sound field coverage. At the same time, arrange low-frequency speakers near the bed to enhance noise reduction and play soothing soundscapes.

[0102] Living room speaker arrangement: Adopt a stereo surround speaker arrangement method (such as a 5.1 or 7.1 system), with speakers arranged on both side walls and in the middle area to optimize the mid-frequency and high-frequency playback effects and enhance the entertainment experience.

[0103] Study room speaker arrangement: For the work area, arrange 12 full-range speakers directly in front of the desktop to provide high-definition voice or background music playback and reduce room echo interference. The design of the speaker positions follows the principle of acoustic symmetry, and by adjusting the speaker angles and power, the ratio of direct sound to reflected sound is optimized.

[0104] Second step, microphone array setting: Microphone type selection: Use omnidirectional microphones to capture 360-degree sound field data, combined with directional microphones to accurately locate the direction of the noise source.

[0105] Bedroom microphone arrangement: Install 1 omnidirectional microphone in the center of the ceiling for real-time monitoring of background noise; install directional microphones at the windows and doors to accurately collect the characteristics of external noise sources.

[0106] Living room microphone arrangement: Install omnidirectional microphones in the corners to monitor the overall sound field, and install directional microphones in the TV area to evaluate the clarity of audio-visual playback.

[0107] Kitchen microphone arrangement: Install directional microphones near the home appliance area to identify high-frequency noise.

[0108] All microphones are connected to the intelligent central control terminal wirelessly or by wire to achieve real-time data collection and processing, providing data support for noise reduction and soundscape optimization.

[0109] Step S8: Evaluation of noise reduction and soundscape effects.

[0110] First step, physical index evaluation: Background noise attenuation value: Evaluate the noise reduction effect by comparing the changes in ambient sound pressure levels before and after the speakers are turned on. The target is a noise reduction value ≥ 10 dB.

[0111] Reverberation time (T30): After noise reduction and soundscape playback, measure whether the indoor reverberation time meets the requirements of the functional area. The target values are: 0.3 - 0.5 seconds for the bedroom; 0.6 - 0.8 seconds for the living room.

[0112] Signal-to-noise ratio (SNR): The ratio of the optimized signal to the background noise should meet the requirements of different scenarios: For learning or working scenarios: SNR ≥ 20 dB; for entertainment scenarios: SNR ≥ 15 dB.

[0113] Step 2, User Subjective Evaluation: Comfort: The user's subjective perception of sound comfort, whether it reduces harsh or uncomfortable sounds.

[0114] Clarity: The user's evaluation of the recognition of voice or music playback effects.

[0115] Scene Adaptability: The user's evaluation of the matching degree of soundscape playback with the current situational needs (such as relaxation, concentration).

[0116] Step 3, Evaluation Process: Noise Data Collection: Through a microphone array, real-time collect sound field data, including noise level, spectral distribution, and reverberation time.

[0117] Noise Reduction Effect Measurement: Compare the noise spectral characteristics before and after the speaker operates, and calculate the noise attenuation value.

[0118] Soundscape Playback Test: Measure the change in signal-to-noise ratio after soundscape playback, and evaluate the masking effect of background noise.

[0119] User Experience Survey: Collect the user's subjective scores on noise reduction and soundscape effects through a smart terminal.

[0120] Comprehensive Evaluation: The physical indicators and subjective scores are weighted and calculated to obtain a comprehensive evaluation. The formula is: Total Score = 0.6 × Physical Score + 0.4 × Subjective Score.

[0121] Example 3: In the third embodiment of the present invention, based on the same inventive concept, a computer-readable storage medium is proposed. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent indoor noise reduction and soundscape optimization method of the above embodiment.

[0122] Example 4: In the fourth embodiment of the present invention, based on the same inventive concept, a computer device is proposed, including: a processor, a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory and implement the intelligent indoor noise reduction and soundscape optimization method of the above embodiment.

[0123] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0124] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent indoor noise reduction and soundscape optimization system, characterized in that: Includes the following modules: A noise monitoring module, configured to collect indoor environmental noise data in real time through a microphone array, analyze the spectrum, intensity and persistence of the noise, and identify the type of noise; A scene recognition module configured to determine a current indoor functional scene based on sensor data or user activity information; A user preference module configured to collect and dynamically update the user's soundscape preference data; A soundscape optimization module, configured to dynamically match soundscape resources through a three-dimensional matrix based on noise data, scene type, and user preferences; An active noise reduction module configured to generate reverse sound waves according to the noise spectrum characteristics to cancel the target noise through the speaker array; A soundscape playback module, configured to call music library resources and play adapted soundscape content through a speaker; The evaluation feedback module is configured to adjust system parameters through physical indicators and user subjective scores.

2. The system according to claim 1, characterized in that The noise monitoring module comprises: Spectrum analysis unit, which uses FFT to analyze the spectrum distribution of noise and distinguish low-frequency, medium-frequency and high-frequency noise; The persistence identification unit determines whether the noise is continuous, intermittent or pulsed through time series analysis; Noise database, storing historical noise data and noise reduction strategies.

3. The system according to claim 1, characterized in that The scene recognition module determines the functional scene in the following manner: Time information; User activity data, including stationary or mobile status; The type of room, including bedroom, living room, or study.

4. The system according to claim 1, characterized in that The dimensions of the three-dimensional matrix include a noise characteristic axis, a scene context axis, and a user preference axis. The matrix weight is calculated by the formula W=αNx+βCy+γPz, where Nx is the noise characteristic adaptation, Cy is the scene adaptation, Pz is the user preference adaptation, and α, β, γ are weight factors; The three-dimensional matrix construction of the soundscape optimization module includes: The noise characteristics axis is classified by spectral range, intensity and persistence; The scene situation axis defines the soundscape objectives according to functional requirements; User preference axis dynamically adjusts the adaptation weight according to music type, volume and style.

5. The system according to claim 1, characterized in that The active noise reduction module comprises: A low-frequency noise suppression unit that generates reverse sound waves and cancels out noise through the low-frequency speaker; A high-frequency noise suppression unit that generates an adaptive filtering signal and covers the noise source area through a high-frequency speaker; Real-time feedback unit dynamically adjusts the phase and amplitude of the reverse sound wave.

6. The system according to claim 1, characterized in that The arrangement of the speaker array includes: Embedded full-range speakers are installed at the four corners of the bedroom ceiling, and low-frequency speakers are arranged near the bed; A surround sound system is used in the living room, with mid- and high-frequency speakers arranged on the walls on both sides; A full-range speaker is installed directly in front of the desktop in the study.

7. The system according to claim 1, characterized in that The comprehensive score of the evaluation feedback module is calculated by the following formula: Total score = 0.6 Physical score 0.4 Subjective scoring: the physical scoring is based on the background noise attenuation value, the reverberation time compliance rate and the signal-to-noise ratio improvement value; the subjective scoring is based on the comfort, clarity and scene adaptability of the user terminal.

8. An intelligent indoor noise reduction and soundscape optimization method, characterized in that: The following steps are involved: Collect and analyze the spectrum, intensity and persistence of indoor noise in real time; Identify the current functional scenario and obtain the user's soundscape preferences; Dynamically match soundscape resources based on a three-dimensional matrix and calculate the adaptation weight; Generates reverse sound waves to cancel the target noise and plays the adapted soundscape through the speaker; Combine physical indicators with user feedback to optimize system parameters.

9. The intelligent indoor noise reduction and soundscape optimization method according to claim 8, characterized in that: The noise analysis includes: Use FFT to analyze spectrum distribution; analyze noise persistence through time series; store noise data in a database; The speaker arrangement includes: The combination of embedded full-range speakers and low-frequency speakers in the bedroom; the arrangement of mid- and high-frequency speakers of the surround sound system in the living room; and the arrangement of full-range speakers directly in front of the desktop in the study.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the intelligent indoor noise reduction and soundscape optimization method according to claim 8 or 9 is implemented.

Images