Vehicle-mounted noise reduction method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a vehicle-mounted noise reduction method and device, equipment, a storage medium and a program product, and relates to the field of automobile noise reduction. The method comprises the following steps: acquiring dynamic parameters, noise data and object reference parameters of a target vehicle; on the basis of the dynamic parameters and the noise data, pre-judgment noise is modeled, and pre-judgment noise features are obtained; generating a reverse sound wave signal based on the reference parameter and the pre-judged noise feature; and compensating the reverse sound wave to obtain a noise reduction parameter, and sending the noise reduction parameter to the noise reduction equipment. According to the method, response lag is avoided by combining the dynamic parameters and the noise data, adaptive noise reduction effects can be obtained by different passengers, and personalized adaptation is realized. Differential compensation is designed, and the noise reduction efficiency is improved. The prompt tone is not inhibited by the noise reduction system, and the noise reduction effect and the driving safety are balanced. The noise reduction precision, the response speed, personalized adaptation and safety prompt tone transmission are all improved, and the adaptability of the system to complex road conditions is enhanced.

Description

Technical Field

[0001] This application relates to the field of automotive noise reduction, and more particularly to an in-vehicle noise reduction method, device, equipment, storage medium, and program product. Background Technology

[0002] In the modern automotive environment, passengers' demands for noise reduction experience are becoming increasingly diverse. Especially during long-distance driving or in noisy road conditions, such as highways and congested urban roads, in-vehicle noise, including but not limited to engine noise, tire noise, wind noise, and road bumps, can significantly affect passengers' auditory comfort and drivers' concentration.

[0003] In existing technologies, automotive noise reduction often employs a solution where the in-vehicle audio system releases reverse sound waves across its entire range. However, in-vehicle noise reduction cannot cater to the auditory needs of different passengers, and may result in over- or under-reduction in some areas, potentially masking important safety warnings. Furthermore, sound waves reflecting within the vehicle can easily create new noise.

[0004] Therefore, the existing vehicle noise reduction system has a poor noise reduction effect and urgently needs to be addressed. Summary of the Invention

[0005] This application provides a vehicle-mounted noise reduction method, apparatus, device, storage medium, and program product to solve the technical problem of poor noise reduction effect in vehicle-mounted noise reduction.

[0006] Firstly, this application provides an in-vehicle noise reduction method, including:

[0007] Acquire the target vehicle's dynamic parameters, noise data, and baseline parameters;

[0008] Based on dynamic parameters and noise data, the predicted noise is modeled to obtain the predicted noise characteristics;

[0009] Based on the benchmark parameters and predicted noise characteristics, an inverse acoustic signal is generated.

[0010] The reverse sound wave is compensated to obtain noise reduction parameters, which are then sent to the noise reduction device.

[0011] Secondly, this application provides an in-vehicle noise reduction device, comprising:

[0012] The parameter acquisition module is used to acquire the dynamic parameters, noise data, and baseline parameters of the target vehicle.

[0013] The noise prediction module is used to model the predicted noise based on dynamic parameters and noise data to obtain the predicted noise characteristics;

[0014] The reverse acoustic wave generation module is used to generate reverse acoustic wave signals based on reference parameters and predicted noise characteristics.

[0015] The noise reduction generation module is used to compensate for the reverse sound wave, obtain noise reduction parameters, and send the noise reduction parameters to the noise reduction device.

[0016] Thirdly, this application provides an electronic device, including: a processor and a memory communicatively connected to the processor;

[0017] The memory stores instructions that the computer executes;

[0018] The processor executes computer-executable instructions stored in memory to implement any of the methods of the first aspect.

[0019] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method of any one of the first aspects.

[0020] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method of any one of the first aspects.

[0021] The vehicle-mounted noise reduction method, device, equipment, storage medium, and program products provided in this application predict noise changes in advance by combining vehicle dynamic parameters and noise data, avoiding response lag and thus achieving precise noise reduction. The predictive noise reduction design makes the transition during noise changes smoother and reduces the sense of noise reduction interruption. Through target baseline parameters, different passengers can obtain adapted noise reduction effects, achieving personalized adaptation. Differentiated compensation is designed for the characteristics of bone conduction sound transmission loss, significantly reducing the error of reverse sound wave transmission and improving bone conduction noise reduction efficiency. Through noise reduction parameter settings, it is ensured that the warning sound is not suppressed by the noise reduction system, balancing the noise reduction effect and driving safety. Improvements have been made in noise reduction accuracy, response speed, personalized adaptation, and safety warning sound transmission, while enhancing the system's adaptability to complex road conditions. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] Figure 1 This is a schematic diagram of existing vehicle noise reduction methods;

[0024] Figure 2 A flowchart illustrating an in-vehicle noise reduction method provided in an embodiment of this application;

[0025] Figure 3 A flowchart illustrating a personalized noise reduction method based on bone conduction and vehicle dynamic linkage provided in this application embodiment;

[0026] Figure 4 This is a schematic diagram of the structure of a vehicle-mounted noise reduction device provided in an embodiment of this application;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0029] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0030] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0031] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0032] It should be noted that the vehicle noise reduction method, device, equipment, storage medium and program products provided in this application can be used in the field of automotive noise reduction, or in any field other than automotive noise reduction. The application field of the vehicle noise reduction method, device, equipment, storage medium and program products in this application is not limited.

[0033] First, the terms used in this invention and application will be explained:

[0034] ANC: Active Noise Cancellation, abbreviated as ANC.

[0035] BES: Bone Conduction Earphone System, abbreviated as BES.

[0036] VENS: Vehicle Environment Noise Sensor, abbreviated as VENS.

[0037] ADAS: Advanced Driving Assistance System, abbreviated as ADAS.

[0038] LMS: Least Mean Square, abbreviated as LMS.

[0039] NLMS: Normalized Least Mean Square, abbreviated as NLMS.

[0040] LPC: Linear Predictive Coding, abbreviated as LPC.

[0041] This application is specifically applied in modern automotive environments, specifically in scenarios where passengers and drivers wear noise-canceling devices. In modern automotive environments, passengers' demands for noise cancellation experiences are increasingly diverse, especially during long drives or in noisy road conditions (such as highways and congested urban areas). In-vehicle noise (such as engine noise, tire noise, wind noise, and road bumps) significantly impacts passenger auditory comfort and driving concentration. Existing noise cancellation solutions struggle to simultaneously address the personalized needs of different passengers and ensure the delivery of driving safety alerts. For example, drivers need to be aware of vehicle status in real time (such as reversing radar alerts and collision warnings) to ensure safety, while rear-seat passengers may be more focused on the immersive experience of audio-visual entertainment. Furthermore, the acoustic characteristics of the in-vehicle space are complex, with diverse sound wave propagation paths. Traditional all-around noise cancellation technologies are prone to creating new noise due to reflections, while traditional in-ear noise-canceling headphones, due to their wearing method, cannot synchronize with the vehicle's dynamic status, resulting in a delayed noise cancellation response.

[0042] Figure 1 This is a schematic diagram of existing vehicle noise reduction methods, such as... Figure 1As shown, in existing technologies, vehicle noise reduction mainly relies on two solutions: 1. Vehicle-wide noise reduction system: This involves placing a speaker array inside the vehicle to collect noise data in real time and generate inverse sound waves to cancel it out. 2. Traditional in-ear noise-canceling headphones: These use microphones to collect noise inside the ear and generate inverse sound waves to cancel out the noise.

[0043] However, in-vehicle noise cancellation systems have several drawbacks: due to the complex structure of the vehicle interior and the diverse sound wave reflection paths, a single reverse sound wave cannot accurately match the noise characteristics of different seating areas, easily leading to over-cancellation (such as masking important notification sounds) or under-cancellation in some areas. Furthermore, the overall reverse sound wave is prone to forming standing waves or noise during propagation due to reflection, which can actually reduce the overall noise cancellation effect. Traditional in-ear noise-canceling headphones also have drawbacks: they can only process noise inside the ear and cannot eliminate ambient noise inside and outside the vehicle (such as wind noise and tire noise). They lack access to vehicle dynamic data (such as speed, acceleration, and steering status) and cannot predict noise increases caused by changes in vehicle status (such as rapid acceleration or cornering), resulting in a lag in noise cancellation parameter adjustments.

[0044] Therefore, existing in-vehicle noise reduction methods have the following technical problems: 1. Insufficient targeting of in-vehicle all-area noise reduction: Existing all-area noise reduction systems cannot accurately match the noise characteristics of different seating areas, resulting in uneven noise reduction effects and even masking important safety warning sounds. 2. Lack of linkage between traditional noise-canceling headphones and vehicle systems: Existing headphones cannot obtain real-time vehicle dynamic data (such as speed, acceleration, and steering angle), resulting in a delayed noise reduction response and an inability to predict noise increases caused by changes in vehicle status. 3. Insufficient personalized adaptation: Existing technologies do not consider individual differences among passengers (such as ear canal structure and hearing sensitivity), resulting in noise reduction effects that cannot meet the needs of different groups, leading to low noise reduction satisfaction for some passengers. 4. Risk of safety warning sound transmission: Traditional noise reduction solutions do not isolate the frequency bands of safety warning sounds (such as reversing radar and collision warning), posing a risk that the warning sounds may be suppressed by the noise reduction system, affecting driving safety.

[0045] The vehicle-mounted noise reduction method, device, equipment, storage medium, and program products provided in this application fuse vehicle dynamic parameters with environmental noise data to construct a predictive noise model. By combining personalized parameters with bone conduction characteristics, they achieve dynamic, real-time, and personalized noise reduction control while ensuring the priority transmission of safety warning sounds. This aims to solve the aforementioned technical problems of the prior art.

[0046] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0047] Figure 2 This is a flowchart illustrating an in-vehicle noise reduction method provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes:

[0048] S201. Obtain the dynamic parameters, noise data, and object baseline parameters of the target vehicle.

[0049] In one example, the dynamic parameters of the target vehicle may include speed v, acceleration a, and steering angle θ. Noise data may include noise data collected at the current moment by an array of ambient noise sensors, including frequency. ,strength Phase The target reference parameters may include the ear canal resonant frequency (α) and auditory sensitivity (β) of the target subject, acquired by biosensors after the target subject wears the noise-canceling device. The biosensors collect the ear canal resonant frequency (α) and the target subject's auditory sensitivity (β) for different frequency bands by contacting the target subject's temporal bone, generating a personalized target reference parameter matrix. ).

[0050] S202. Based on dynamic parameters and noise data, model the predicted noise to obtain the predicted noise characteristics.

[0051] In one example, the dynamic parameters and noise data of the target vehicle acquired by the ADAS system can be input into the prediction model through the central processing unit to calculate the predicted noise characteristics of the next moment corresponding to the current moment. , , In this application, the predicted noise characteristics for the next 0.5-1 seconds corresponding to the current moment are used. , , This section provides an explanation, without specifying a particular time interval. For example, when a vehicle accelerates rapidly, the acceleration 'a' increases, and the noise intensity is calculated using a predictive model. It exhibits a non-linear growth trend, so the noise reduction parameters are adjusted to cancel out the noise in advance.

[0052] S203. Based on the reference parameters and predicted noise characteristics, generate an inverse acoustic signal.

[0053] In one example, the central processing unit generates a reverse acoustic signal based on predicted noise characteristics and an object baseline parameter matrix using an improved LMS algorithm. For instance, when the passenger has a high sensitivity to high-frequency noise β, the algorithm adjusts the filter weights to enhance the cancellation effect of the high-frequency reverse acoustic wave.

[0054] S204. Compensate for the reverse sound wave to obtain noise reduction parameters, and send the noise reduction parameters to the noise reduction device.

[0055] In one example, the amplitude of the reverse sound wave is adjusted using a compensation formula based on the difference in low-frequency / high-frequency loss in bone conduction (low-frequency loss rate 5-8%, high-frequency loss rate 15-20%).

[0056] The sound priority controller identifies safety alert tones (such as 1000-1500Hz pulse sounds) through feature matching, disables noise reduction for the corresponding frequency band of the safety alert tone, and amplifies the amplitude of the safety alert tone. Specifically, the safety alert audio band ( The frequency band to which the safety warning tone should be prioritized is selected. For example, when the reversing radar warning tone sounds, the system disables noise reduction in the 1000-1500Hz frequency band and increases its amplitude by 10%.

[0057] Based on real-time noise data and the current reverse acoustic signal, the adaptive filter weights are adjusted using the NLMS algorithm at preset time windows to adapt to sudden noise changes (such as sudden road bumps), generating dynamically optimized noise reduction parameters, which are then sent to the noise reduction device worn by the target. In this application, a preset time window of 0.1 seconds is used for illustration, but no specific limitation is made to the preset time window. For example, when a vehicle enters a bumpy road section, the adaptive filter weights are adjusted every 0.1 seconds using the NLMS algorithm to enhance noise cancellation capabilities.

[0058] In one implementation scenario, in-vehicle noise reduction can be achieved through a personalized noise reduction system based on bone conduction and vehicle dynamic linkage. Through deep interconnection between headphones and vehicle systems, personalized and predictive noise reduction can be achieved while ensuring the effective transmission of driving safety warning sounds.

[0059] For example, a personalized noise cancellation system based on bone conduction and vehicle dynamic linkage may include: bone conduction noise-canceling headphones, a vehicle ambient noise sensor array, a central noise cancellation processor, an ADAS data interface, and a sound priority controller. The bone conduction noise-canceling headphones can be worn on the passenger's temporal bone and have a built-in bone conduction sound unit, microphone, and biosensor. The biosensor monitors the wearing status and ear canal characteristics and connects wirelessly to the central noise cancellation processor. The vehicle ambient noise sensor array is distributed in the engine compartment, chassis, and window edges to collect noise data from different parts of the target vehicle in real time and transmits it to the central noise cancellation processor via wired connection. The central noise cancellation processor receives the noise data of the target vehicle collected by the vehicle ambient noise sensor array and the dynamic parameters of the target vehicle collected by the ADAS system, calculates the noise reduction parameters, and sends them to the bone conduction noise-canceling headphones. The ADAS data interface enables data interaction between the central noise cancellation processor and the vehicle's ADAS system, and obtains information such as vehicle speed, steering, and road conditions. The sound priority controller is used to determine the frequency and characteristics of preset safety warning sounds (such as reversing radar, collision warning, etc.) to ensure that they are not processed by noise reduction and are preferentially transmitted to the target object through bone conduction noise-canceling headphones.

[0060] Figure 3 A flowchart illustrating a personalized noise reduction method based on bone conduction and vehicle dynamics, as provided in this application embodiment, is shown below. Figure 3 As shown, personalized noise reduction methods based on bone conduction and vehicle dynamics can include:

[0061] 1. Initial Matching: After the passenger puts on the bone conduction noise-canceling headphones, the biosensor automatically collects two core data points: ① The biosensor collects the ear canal resonance frequency α (unit: Hz, frequency band division can be...) by contacting the passenger's temporal bone. (This application does not restrict the frequency band division method); ② The auditory sensitivity β of the target object is collected by biosensors (unit: dB, used to characterize the target object's perception threshold for different frequency bands, such as children having a higher sensitivity β to low frequencies of 20-200Hz, recorded as the object's reference parameter matrix). The β value corresponding to the frequency band. Bone conduction noise-canceling headphones transmit sound waves through skull vibrations, avoiding ear canal pressure. The following formula characterizes the personalized object reference parameter matrix generated based on the collected data: .

[0062] The object baseline parameter matrix will serve as the basis for subsequent personalized noise reduction and will be stored in the local database of the central noise reduction processor. When the same target object wears bone conduction noise-canceling headphones again, the historical data of the target object can be directly retrieved from the local database without repeated collection.

[0063] 2. Predictive Noise Modeling: A central noise reduction processor receives two types of data in real time: ① Vehicle dynamic parameters from the ADAS system, including: speed v (km / h); acceleration a (m / s²); steering angle θ (°). ② Noise data collected by the VENS array at the current moment, including: frequency... ,strength Phase The following formula can be used to predict the next 0.5-1 seconds ( The system predicts noise characteristics to achieve "early noise reduction preparation." These predicted noise characteristics include predicted noise frequency, predicted noise amplitude, and predicted noise phase.

[0064] The predicted noise frequency is calculated using the formula: .

[0065] In the formula, Predicted noise frequencies corresponding to future moments; This is the acceleration frequency correction factor, with a value ranging from 0.8 to 1.2; The speed frequency correction coefficient has a value of 0.2-0.5 and is obtained through training with historical driving data. In this application, the specific value of the correction coefficient is not limited.

[0066] The predicted noise amplitude is calculated using the formula. .

[0067] In the formula, The predicted noise amplitude for future moments; This is the acceleration intensity correction factor, with a value ranging from 0.5 to 0.8; The speed intensity correction coefficient, with a value of 0.1-0.3, is used to correct the nonlinear increase in noise intensity of the target vehicle during rapid acceleration and high-speed driving. In this application, the specific value of the correction coefficient is not limited.

[0068] The predicted noise phase is calculated using the formula:

[0069] .

[0070] In the formula, The predicted noise phase corresponding to future moments; The value of the steering phase correction coefficient is 0.1-0.2, which is used to solve the noise phase shift caused by vehicle vibration during the steering of the target strategy. The specific value of the correction coefficient is not limited in this application.

[0071] 3. Personalized reverse acoustic wave generation: Combining the predicted noise characteristics in step 2 with the personalized object reference parameters in step 1, reverse acoustic wave parameters are generated through an improved LMS algorithm to ensure that the noise reduction effect is adapted to different target objects.

[0072] Calculate the error signal at the current moment. The error signal is used to characterize the difference between the actual noise reduction at the current moment and the preset target noise reduction. In the formula, This represents the error signal at the current moment; The target noise reduction amount is preset according to the needs of the target object; This represents the current actual noise reduction amount.

[0073] Introducing auditory sensitivity into personalized object benchmark parameters The adaptive filter weights are updated to achieve personalized adjustments to the reverse acoustic signal for different target objects. In the formula, The adaptive filter weights for the next time step; is the adaptive filter weight at the current time; μ is the convergence factor, with a value of 0.01-0.05, used to control the convergence speed of the improved LMS algorithm; x(n) is the predicted noise signal at the current time.

[0074] Output reverse acoustic signal: , It is a reverse acoustic wave signal.

[0075] 4. Bone Conduction Compensation: Because bone conduction transmits sound through skull vibrations, it exhibits the characteristic of "low loss at low frequencies and high loss at high frequencies." For example, the loss rate for low frequencies (20-500Hz) is 5-8%, while the loss rate for high frequencies above 5000Hz is 15-20%. The following formula is used to compensate for the reverse sound wave in the corresponding frequency band to ensure effective cancellation:

[0076] .

[0077] In the formula, To compensate for the amplitude of the reverse acoustic wave; The uncompensated original reverse acoustic wave amplitude is, i.e. The magnitude of the absolute value; This is the frequency band loss compensation coefficient, low frequency band. High frequency band This application does not impose any restrictions on the specific value of the frequency band loss compensation coefficient.

[0078] 5. Priority Control and Execution: The sound priority controller identifies noise data through feature matching, recognizing safety warning sounds, such as the reversing radar warning sound, which is a 1000-1500Hz pulse sound. Using the following formula, noise reduction is applied to the noise data corresponding to the frequency band of non-safety warning sounds, while noise reduction is disabled and transmission is amplified for the noise data corresponding to the frequency band of safety warning sounds.

[0079] The set of frequency bands for non-safety alert sounds to be noise-reduced is determined using the following formula: In the formula, This is a frequency band for non-safety warning tones; It covers the entire frequency band from 20Hz to 20kHz; The frequency band to which the safety warning sound belongs, such as 1000-1500Hz, is not limited in this application.

[0080] The intensity of the safety warning sound is amplified using a formula: In the formula, To enhance the amplitude of the safety warning sound; The amplitude of the original safety warning sound is increased by 10% to ensure that the driver / passenger can clearly perceive the safety warning sound. In this application, the increase in the safety warning sound is not limited, and 10% is just one implementation method.

[0081] Different processing methods are adopted for different target objects. For example, when the target object is a driver, the data weight of the dynamic parameters of the target vehicle obtained from ADAS is increased during the calculation of noise reduction parameters, while retaining some road-sense-related noise data. At the same time, the priority of safety warning sounds is ensured, and the noise reduction intensity corresponding to the noise reduction parameters is slightly lower than that in passenger mode when the target object is a passenger.

[0082] When the target audience is passengers, the intensity of low-frequency noise reduction corresponding to the noise reduction parameters is increased, while unnecessary safety warning sounds are weakened. At the same time, the in-vehicle entertainment system of the target vehicle can be linked to achieve synergy between audio-visual effects and noise reduction.

[0083] 6. Dynamic Adjustment: Repeat steps 2-5 every 0.1 seconds to adjust the adaptive filter weights using the NLMS algorithm, in order to avoid noise reduction failure caused by sudden noise changes (such as sudden road bumps).

[0084]

[0085] In the formula, The energy of the input noise signal; It is the minimum value, and takes the value of This is to avoid the pathological problem of a denominator of 0.

[0086] By employing a predictive noise modeling algorithm, ADAS vehicle dynamic parameters (speed, acceleration, steering angle) are integrated into the noise prediction formula, achieving noise reduction 0.5-1 second in advance. This solves the lag problem of traditional noise reduction's "noise first, then processing" approach, improving response speed by over 30%. Furthermore, a personalized LMS algorithm incorporates auditory sensitivity parameters into the classic LMS algorithm. This allows the reverse sound waves to adapt to the different ear canal structures and hearing characteristics of passengers, avoiding the problem of poor performance for some people due to a "one-size-fits-all" approach to noise reduction. This improves the consistency of noise reduction satisfaction among different passengers by 50%. Furthermore, a differentiated compensation coefficient is designed based on the bone conduction frequency band compensation formula, taking into account the characteristics of sound transmission loss in bone conduction. This reduces the reverse acoustic wave transmission error from ±8dB in traditional solutions to within ±2dB, improving bone conduction noise reduction efficiency by 30%. Through safe frequency band isolation logic, and The formula clearly defines the boundary between noise cancellation and safety alerts, ensuring 100% recognition rate and transmission strength for safety alerts, thus balancing noise cancellation effectiveness with driving safety. Compared to existing technologies, noise cancellation response speed is improved by more than 30%, passenger subjective noise cancellation satisfaction is increased by 40%, and there is no risk of safety alerts being masked. Furthermore, bone conduction avoids the pressure on the ear canal experienced by traditional in-ear headphones.

[0087] In another implementation scenario, the bone conduction unit can be replaced with an air conduction open-back headphone, achieving noise reduction through directional sound wave transmission. Air conduction open-back headphones offer greater wearing comfort; however, their isolation from external ambient noise is slightly worse, and their noise reduction accuracy is significantly affected by sound waves within the vehicle's interior.

[0088] The vehicle-mounted noise reduction method provided in this embodiment combines vehicle dynamic parameters and noise data to predict noise changes in advance, avoiding response lag and achieving precise noise reduction. The predictive noise reduction design makes the transition during noise changes smoother and reduces the sense of noise reduction interruption. By using target baseline parameters, different passengers can obtain suitable noise reduction effects, achieving personalized adaptation. Differential compensation is designed for the characteristics of bone conduction sound loss, significantly reducing reverse sound wave transmission errors and improving bone conduction noise reduction efficiency. Through noise reduction parameter settings, it is ensured that the warning sound is not suppressed by the noise reduction system, balancing noise reduction effect and driving safety. Improvements are made in noise reduction accuracy, response speed, personalized adaptation, and safety warning sound transmission, while also enhancing the system's adaptability to complex road conditions.

[0089] Optionally, the dynamic parameters include the target vehicle's speed, acceleration, and steering angle. Based on the dynamic parameters and noise data, the predicted noise is modeled to obtain the predicted noise features, including: obtaining the predicted noise frequency based on the target vehicle's speed and acceleration and the current noise frequency; obtaining the predicted noise amplitude based on the target vehicle's speed and acceleration and the current noise amplitude; and obtaining the predicted noise phase based on the target vehicle's steering angle and the current noise frequency. The predicted noise frequency, predicted noise amplitude, and predicted noise phase are combined to obtain the predicted noise features.

[0090] In one example, dynamic parameters include: velocity v (km / h); acceleration a (m / s²); and steering angle θ (°). Noise data includes: frequency. ,strength Phase The predicted noise characteristics for the next 0.5-1 seconds (Δt=0.5-1s) are predicted using the following formula. These predicted noise characteristics include the predicted noise frequency, predicted noise amplitude, and predicted noise phase.

[0091] Calculate the predicted noise frequency: In the formula, Predicted noise frequencies corresponding to future moments; This is the acceleration frequency correction factor, with a value ranging from 0.8 to 1.2; The speed frequency correction coefficient has a value of 0.2-0.5 and is obtained through training with historical driving data. In this application, the specific value of the correction coefficient is not limited.

[0092] Calculate and predict noise amplitude In the formula, The predicted noise amplitude for future moments; This is the acceleration intensity correction factor, with a value ranging from 0.5 to 0.8; The speed intensity correction coefficient, with a value of 0.1-0.3, is used to correct the nonlinear increase in noise intensity of the target vehicle during rapid acceleration and high-speed driving. In this application, the specific value of the correction coefficient is not limited.

[0093] The predicted noise phase is calculated as follows:

[0094] .

[0095] In the formula, The predicted noise phase corresponding to future moments; The value of the steering phase correction coefficient is 0.1-0.2, which is used to solve the noise phase shift caused by vehicle vibration during the steering of the target strategy. The specific value of the correction coefficient is not limited in this application.

[0096] In another example, a Long Short-Term Memory (LSTM) network can be used in the predictive noise modeling stage. LSTM networks construct more complex nonlinear prediction models by capturing the temporal correlation between vehicle dynamic parameters (such as acceleration and speed) and historical noise data. For example, when a vehicle frequently accelerates rapidly, the LSTM network can learn the nonlinear growth pattern of noise intensity and acceleration and dynamically adjust the prediction weights.

[0097] By incorporating the dynamic parameters of the target vehicle into the noise prediction formula, the predictive model can more accurately capture the complex patterns of noise changes, such as nonlinear noise increments during sudden bumps and sharp turns. This improves the accuracy of early generation of noise reduction parameters and reduces noise reduction lag caused by prediction bias. Furthermore, the model can adapt to the dynamic characteristics of different driving scenarios, enhancing the system's adaptability to complex road conditions.

[0098] Optionally, based on the reference parameters and predicted noise characteristics, a reverse acoustic wave signal is generated, including: obtaining the error signal between the current noise reduction amount and the reference parameters based on the reference parameters; updating the current adaptive filter weights based on the error signal, the reference parameters, and the predicted noise characteristics; and generating the reverse acoustic wave signal based on the current adaptive filter weights and the predicted noise characteristics.

[0099] In one example, the inverse acoustic wave parameters are generated using an improved LMS algorithm: the error signal at the current moment is calculated, which characterizes the difference between the actual noise reduction at the current moment and the preset target noise reduction. In the formula, This represents the error signal at the current moment; The target noise reduction amount is preset according to the needs of the target object; This represents the current actual noise reduction amount.

[0100] By introducing the auditory sensitivity β(n) from the personalized object baseline parameters, the weights of the adaptive filter are updated to achieve personalized adjustment of the inverse acoustic signal for different target objects: In the formula, The adaptive filter weights for the next time step; is the adaptive filter weight at the current time; μ is the convergence factor, with a value of 0.01-0.05, used to control the convergence speed of the improved LMS algorithm; x(n) is the predicted noise signal at the current time.

[0101] Output reverse acoustic signal: y(n+1) is the reverse acoustic signal.

[0102] In another example, biosensors can be introduced to monitor the physiological state of the target object in real time (such as heart rate, brain waves, etc.) and combine it with a personalized baseline parameter matrix (M_base). When the target object is detected to be in a fatigued state, the system automatically increases the noise reduction intensity of low-frequency noise (such as engine roar) to reduce auditory fatigue; when the target object is detected to be focused, the noise reduction intensity is reduced to retain some ambient sound and enhance driving alertness.

[0103] By introducing an auditory sensitivity parameter into the classic LMS algorithm, the obtained reverse sound wave can better adapt to the ear canal structure and hearing characteristics of different passengers, solving the problem of "one-size-fits-all" adaptation in traditional noise reduction systems. By dynamically adjusting the noise reduction parameters according to the individual differences of passengers, the noise reduction satisfaction of different passengers can be greatly improved.

[0104] Optionally, the reverse acoustic wave is compensated to obtain noise reduction parameters, and the noise reduction parameters are sent to the noise reduction device. This includes: supplementing the reverse acoustic wave signal based on the absolute value of the reverse acoustic wave signal and the corresponding frequency band of the reverse acoustic wave signal to obtain the compensated reverse acoustic wave amplitude; returning a step of modeling the predicted noise based on dynamic parameters and noise data according to a preset time window to obtain the predicted noise characteristics; updating the current adaptive filter weights in combination with the object type of the noise reduction device; compensating the current reverse acoustic wave amplitude based on the updated adaptive filter weights to obtain the noise reduction parameters, and sending the noise reduction parameters to the noise reduction device.

[0105] In one example, the frequency band compensation formula addresses the difference in sound loss at different frequency bands in bone conduction by adjusting the frequency band characteristics of noise reduction parameters (such as the amplitude of the reverse acoustic wave). For instance, in the high-frequency band (above 5000Hz), the system significantly enhances the amplitude of the reverse acoustic wave by using γ(f) = 0.15-0.20 to offset the high-frequency loss of bone conduction; while in the low-frequency band (20-500Hz), γ(f) = 0.05-0.08 is used to slightly compensate for low-frequency loss. The specific frequency band compensation formula is as follows: ,in, The frequency band loss compensation factor specifically includes at least one of the following: low frequency band (20-500Hz) The value range is 0.05-0.08; high frequency band (above 5000Hz) The value range is 0.15-0.20.

[0106] In another example, the vibration feedback signal of the passenger's skull can be monitored in real time by a vibration sensor built into the noise reduction device and compared with a preset theoretical loss model. When a deviation between the actual vibration intensity and the theoretical value is detected, the compensation coefficient γ(f) is dynamically adjusted, for example, by increasing the value of γ in the high-frequency range (above 5000Hz) to compensate for the actual loss.

[0107] By employing a frequency band compensation formula, the problem of noise reduction deviation caused by uneven bone conduction sound transmission loss is resolved. Through differentiated adjustment of γ(f), the amplitude of the reverse sound wave in the high-frequency band is increased by 15-20%, thereby significantly enhancing the cancellation capability of high-frequency noise while maintaining noise reduction stability in the low-frequency band.

[0108] Optionally, the current adaptive filter weights are updated based on the object type of the noise reduction device, including: when the object of the noise reduction device is a first type of object, determining whether the noise data is a safety warning tone; when the noise data is a safety warning tone, updating the adaptive filter weights corresponding to the safety warning tone based on a first preset magnification, to obtain the updated adaptive filter weights.

[0109] In one example, noise data is identified through feature matching to recognize safety warning sounds, such as the 1000-1500Hz pulse sound of a reversing radar. Noise reduction is then applied to the noise data corresponding to the frequency bands of non-safety warning sounds using the following formula, while noise reduction is disabled and transmission is enhanced for the noise data corresponding to the frequency bands of safety warning sounds.

[0110] The set of frequency bands for non-safety alert sounds to be noise-reduced is determined using the following formula: In the formula, This is a frequency band for non-safety warning tones; It covers the entire frequency band from 20Hz to 20kHz; The frequency band to which the safety warning sound belongs, such as 1000-1500Hz, is not limited in this application.

[0111] The intensity of the safety warning sound is amplified using a formula: In the formula, To enhance the amplitude of the safety warning sound; The amplitude of the original safety warning sound is increased by 10% to ensure that the driver / passenger can clearly perceive the safety warning sound. In this application, the increase in the safety warning sound is not limited, and 10% is just one implementation method.

[0112] Different processing methods are adopted for different target objects. For example, when the target object is a driver, the data weight of the dynamic parameters of the target vehicle obtained from ADAS is increased during the calculation of noise reduction parameters, while retaining some road-sense-related noise data. At the same time, the priority of safety warning sounds is ensured, and the noise reduction intensity corresponding to the noise reduction parameters is slightly lower than that in passenger mode when the target object is a passenger.

[0113] In another example, during the safe frequency band isolation phase, safety alert sounds are identified by combining audio signal characteristics (such as spectral energy distribution) with ADAS event data (such as reversing and collision warning trigger status). For instance, when the ADAS system triggers a reversing warning, the system simultaneously analyzes the pulse characteristics in the audio signal (such as short-term energy surges in the 1000-1500Hz frequency band) to confirm the authenticity of the alert sound.

[0114] In another example, an adaptive learning rate mechanism is introduced to dynamically adjust the learning rate (μ) of the NLMS algorithm based on the severity of noise abrupt changes. When drastic noise changes are detected (such as on bumpy roads), μ is increased to accelerate the filter weight update speed; when the noise tends to stabilize, μ is decreased to avoid overfitting. For example, when a vehicle enters a bumpy road, the system detects drastic fluctuations in high-frequency noise and automatically increases μ to accelerate the filter weight update speed and quickly adapt to the abrupt noise change; while on stable road sections, the system decreases μ to avoid noise reduction fluctuations caused by frequent adjustments.

[0115] By employing safe frequency band isolation logic, the formula clearly defines the boundary between noise reduction and safety alert sounds, ensuring 100% recognition rate and transmission intensity of safety alert sounds, thus balancing noise reduction effectiveness and driving safety. For scenarios targeting drivers, ADAS data weighting is enhanced to prioritize the transmission of warning sounds, with noise reduction intensity slightly lower than in passenger mode, while retaining some road-related noise.

[0116] Optionally, updating the current adaptive filter weights based on the object type of the noise reduction device further includes: when the object of the noise reduction device is a second type of object, when the frequency of the noise data is lower than a preset frequency threshold, updating the adaptive filter weights corresponding to the noise data based on a second preset multiplier to obtain the updated adaptive filter weights.

[0117] In one example, when the target is a passenger, the intensity of low-frequency noise reduction corresponding to the noise reduction parameters is increased, while unnecessary safety warning sounds are weakened. Simultaneously, the vehicle's in-vehicle entertainment system can be linked to achieve synergy between audio-visual effects and noise reduction.

[0118] When the target audience is passengers, the intensity of low-frequency noise reduction is increased according to the noise reduction parameters. Different passengers can obtain suitable noise reduction effects, achieving dynamic adaptation of personalized noise reduction parameters and further improving noise reduction satisfaction. By linking with the in-vehicle entertainment system to achieve synergy between audio-visual effects and noise reduction, passenger satisfaction is further enhanced.

[0119] Optional noise reduction devices include: bone conduction sound generators, microphones, and biosensors, which are wirelessly connected to a central noise reduction processor.

[0120] In one example, the bone conduction sound unit may include: headphones that transmit sound waves through skull vibrations, avoiding pressure on the ear canal. The target wears the headphones on the temporal bone, where the bone conduction sound unit cancels out ambient noise. The noise cancellation device can utilize a wireless communication module to enable data transmission between a central noise cancellation processor and the noise cancellation device.

[0121] By utilizing wireless communication between bone conduction headphones and a central processing unit, along with an improved LMS algorithm, dynamic adaptation of personalized noise cancellation parameters is achieved. Through integrated hardware structures (such as biosensors and wireless communication modules) and algorithmic collaborative processing, the problems of lag and insufficient individual adaptation in traditional noise cancellation systems are resolved.

[0122] Optionally, the object reference parameters are obtained, including: obtaining the ear canal resonant frequency of the target object through a biosensor; determining the auditory sensitivity matrix of the target object based on the ear canal resonant frequency; combining the ear canal resonant frequency and the auditory sensitivity matrix to obtain the object reference parameters of the target object; and storing the object reference parameters in the central noise reduction processor.

[0123] In one example, a biosensor is used to acquire the ear canal resonant frequency and auditory sensitivity. After a passenger wears a noise-canceling device, the biosensor acquires the ear canal resonant frequency α (in Hz, frequency band division can be...) by contacting the passenger's temporal bone. (This application does not impose restrictions on the frequency band division method.) The auditory sensitivity β (unit: dB, used to characterize the target object's perception threshold for different frequency bands; for example, children have a higher sensitivity β to low frequencies of 20-200Hz) is collected by biosensors and recorded as a target reference parameter matrix. The β value corresponding to the frequency band. The following formula characterizes the personalized object reference parameter matrix generated based on the collected data. .

[0124] In another example, the noise reduction device may also include a built-in vibration sensor to monitor the vibration feedback signal of the target object's skull in real time and compare it with a preset theoretical loss model. When a deviation between the actual vibration intensity and the theoretical value is detected, the compensation coefficient γ(f) is dynamically adjusted, for example, by increasing the value of γ in the high-frequency range (above 5000Hz) to compensate for the actual loss.

[0125] By using biosensors to collect real-time data on the ear canal resonant frequencies and auditory sensitivities at different frequency bands when passengers wear noise-canceling devices, a personalized baseline parameter matrix is ​​generated. This matrix serves as the basis for subsequent adjustments to noise-canceling parameters, solving the "one-size-fits-all" problem of traditional noise-canceling systems. The system can dynamically adjust noise-canceling parameters based on individual passenger differences, thereby improving noise-canceling satisfaction for different passengers.

[0126] Optionally, acquiring noise data of the target vehicle includes: setting up a vehicle environmental noise sensor array in the target vehicle, the vehicle environmental noise sensor array being distributed in the engine compartment, chassis, and window edges of the target vehicle; and collecting noise data of the target vehicle through the vehicle environmental noise sensor array.

[0127] In one example, a vehicle ambient noise sensor array is deployed in the engine compartment, chassis, and window edges of the target vehicle to collect real-time noise data. This noise data comprises noise characteristics acquired by the ambient noise sensor array, including but not limited to frequency, intensity, and phase. For example, when driving on a highway, tire noise has a frequency range of 100-500Hz, and its intensity increases with vehicle speed. The noise data (such as frequency, intensity, and phase) describes the physical characteristics of the current noise.

[0128] By leveraging real-time noise data from an array of environmental noise sensors and combining it with vehicle dynamic parameters (speed, acceleration, steering angle) obtained from the ADAS system, it becomes easier to construct predictive noise modeling formulas. These formulas include calculations for predicted frequency, intensity, and phase. This allows the system to predict noise characteristics 0.5-1 seconds in advance (such as non-linear increases in noise intensity due to rapid acceleration or phase shifts during cornering), facilitating the generation of noise reduction parameters in advance. By generating these parameters and sending them to the noise reduction equipment, the system can complete the cancellation preparation before the noise actually occurs, significantly shortening the noise reduction response time.

[0129] Optionally, the dynamic parameters of the target vehicle are obtained, including: obtaining the dynamic parameters of the target vehicle from the driver assistance system of the target vehicle through the driver assistance system data interface, and sending the dynamic parameters to the central noise reduction processor.

[0130] In one example, the vehicle's dynamic parameters (speed v, acceleration a, steering angle θ) are obtained from the target vehicle's ADAS system via a driver assistance system data interface. These dynamic parameters include parameters acquired in real-time from the ADAS system during the target vehicle's operation, including but not limited to speed, acceleration, and steering angle, used to characterize changes in the vehicle's state. For example, when the target vehicle accelerates rapidly, the acceleration parameter increases, used to predict the nonlinear increase in noise intensity.

[0131] By acquiring vehicle dynamic parameters (speed, acceleration, steering angle) through the ADAS system and combining them with real-time noise data from an array of environmental noise sensors, the predictive model can generate noise reduction parameters in advance, avoiding the feeling of noise reduction interruption due to lag.

[0132] Optionally, the noise reduction parameters are obtained by: receiving noise data collected by the vehicle's environmental noise sensor array and dynamic parameters collected by the driver assistance system data interface through the central noise reduction processor; obtaining the noise reduction parameters through the central noise reduction processor and sending the noise reduction parameters to the noise reduction device.

[0133] In one example, a central noise reduction processor is connected to a noise reduction device, a vehicle ambient noise sensor array, and an ADAS system. It receives vehicle dynamic parameters, real-time noise data, and a personalized reference parameter matrix to generate future noise characteristics and noise reduction parameters. The central noise reduction processor generates noise reduction parameters by combining the personalized reference parameter matrix with an improved LMS algorithm. The bone conduction headphones generate reverse sound waves based on the noise reduction parameters to perform noise reduction.

[0134] The central noise reduction processor combines real-time noise data from the vehicle's environmental noise sensor array with vehicle dynamic parameters from the ADAS system (such as speed, acceleration, and steering angle) to generate predicted noise characteristics. An improved LMS algorithm, based on a personalized baseline parameter matrix and future noise characteristics, generates noise reduction parameters tailored to passenger needs and transmits them to the noise reduction device via a wireless communication module. The noise reduction device generates inverse sound waves based on the noise reduction parameters, using skull vibration to cancel out environmental noise. This achieves a complete processing chain from data acquisition to noise reduction execution. The improved LMS algorithm in the central noise reduction processor, combined with personalized parameters, adapts the noise reduction parameters to passenger needs, while the noise reduction device receives the parameters and performs noise reduction via a wireless communication module.

[0135] Figure 4 This is a schematic diagram of the structure of a vehicle-mounted noise reduction device provided in an embodiment of this application, as shown below. Figure 4 As shown, the vehicle-mounted noise reduction device 40 provided in this embodiment includes:

[0136] The parameter acquisition module 401 is used to acquire the dynamic parameters, noise data and object reference parameters of the target vehicle;

[0137] The noise prediction module 402 is used to model the predicted noise based on dynamic parameters and noise data to obtain the predicted noise characteristics;

[0138] The reverse acoustic wave generation module 403 is used to generate a reverse acoustic wave signal based on reference parameters and predicted noise characteristics.

[0139] The noise reduction generation module 404 is used to compensate for the reverse sound wave, obtain noise reduction parameters, and send the noise reduction parameters to the noise reduction device.

[0140] In one possible implementation, the dynamic parameters include the target vehicle's speed, acceleration, and steering angle. The noise prediction module 402 is specifically used to: obtain a predicted noise frequency based on the target vehicle's speed and acceleration and the current noise frequency; obtain a predicted noise amplitude based on the target vehicle's speed and acceleration and the current noise amplitude; obtain a predicted noise phase based on the target vehicle's steering angle and the current noise frequency; and combine the predicted noise frequency, predicted noise amplitude, and predicted noise phase to obtain the predicted noise characteristics.

[0141] In one possible implementation, the reverse acoustic wave generation module 403 is specifically used to: obtain the error signal between the current noise reduction amount and the reference parameters based on the reference parameters; update the current adaptive filter weights based on the error signal, the reference parameters, and the predicted noise characteristics; and generate a reverse acoustic wave signal based on the current adaptive filter weights and the predicted noise characteristics.

[0142] In one possible implementation, the noise reduction generation module 404 is specifically used for: supplementing the reverse acoustic wave signal according to the absolute value of the reverse acoustic wave signal and the frequency band corresponding to the reverse acoustic wave signal to obtain the compensated reverse acoustic wave amplitude; returning the steps of modeling the predicted noise based on dynamic parameters and noise data according to a preset time window to obtain the predicted noise characteristics; updating the current adaptive filter weights in combination with the object type of the noise reduction device; compensating the current reverse acoustic wave amplitude based on the updated adaptive filter weights to obtain noise reduction parameters; and sending the noise reduction parameters to the noise reduction device.

[0143] In one possible implementation, the noise reduction generation module 404 is further specifically used to: when the object of the noise reduction device is a first type of object, determine whether the noise data is a safety prompt tone; when the noise data is a safety prompt tone, update the adaptive filter weights corresponding to the safety prompt tone based on a first preset magnification, and obtain the updated adaptive filter weights.

[0144] In one possible implementation, the noise reduction generation module 404 is further specifically used to: when the object of the noise reduction device is a second type of object, and when the frequency of the noise data is lower than a preset frequency threshold, update the adaptive filter weights corresponding to the noise data based on a second preset multiplier to obtain the updated adaptive filter weights.

[0145] In one possible implementation, the noise reduction device includes a bone conduction sound generator, a microphone, and a biosensor, and is wirelessly connected to a central noise reduction processor.

[0146] In one possible implementation, the parameter acquisition module 401 is specifically used to: acquire the ear canal resonance frequency of the target object through a biosensor; determine the auditory sensitivity matrix of the target object based on the ear canal resonance frequency; combine the ear canal resonance frequency and the auditory sensitivity matrix to obtain the object reference parameters of the target object; and store the object reference parameters in the central noise reduction processor.

[0147] In one possible implementation, the parameter acquisition module 401 is further specifically used to: set up a vehicle environmental noise sensor array in the target vehicle, the vehicle environmental noise sensor array being distributed in the engine compartment, chassis, and window edges of the target vehicle; and collect noise data of the target vehicle through the vehicle environmental noise sensor array.

[0148] In one possible implementation, the parameter acquisition module 401 is further specifically used to: acquire the dynamic parameters of the target vehicle from the target vehicle's driving assistance system through the driving assistance system data interface, and send the dynamic parameters to the central noise reduction processor.

[0149] In one possible implementation, the noise reduction generation module 404 is further specifically used to: receive noise data collected by the vehicle environmental noise sensor array and dynamic parameters collected by the driving assistance system data interface through the central noise reduction processor; obtain noise reduction parameters through the central noise reduction processor and send the noise reduction parameters to the noise reduction device.

[0150] The vehicle noise reduction device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0151] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 50 may include a memory 501 and a processor 502. Optionally, the electronic device may also include a transceiver 503, wherein the memory 501 and the processor 502 communicate with each other; for example, the memory 501, the processor 502 and the transceiver 503 may communicate via a communication bus 504, the memory 501 is used to store a computer program, and the processor 502 executes the computer program to implement the method of the above embodiments.

[0152] Optionally, the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps in the method embodiments disclosed in this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0153] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the methods in any of the above method embodiments.

[0154] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the methods in any of the above method embodiments.

[0155] All or part of the steps in the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0156] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0157] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0158] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0159] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

[0160] In this application, the term "comprising" and its variations can refer to non-limiting inclusion; the term "or" and its variations can refer to "and / or". The terms "first", "second", etc., in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0161] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0162] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0163] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0164] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0165] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0166] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0167] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0168] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0169] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A vehicle-mounted noise reduction method, characterized in that, The method includes: Acquire the target vehicle's dynamic parameters, noise data, and baseline parameters; Based on the dynamic parameters and the noise data, the predicted noise is modeled to obtain the predicted noise characteristics. Based on the reference parameters and the predicted noise characteristics, a reverse acoustic signal is generated; The reverse sound wave is compensated to obtain noise reduction parameters, and the noise reduction parameters are sent to the noise reduction device.

2. The method according to claim 1, characterized in that, The dynamic parameters include the target vehicle's speed, acceleration, and steering angle. Based on the dynamic parameters and the noise data, the predicted noise is modeled to obtain predicted noise characteristics, including: Based on the speed and acceleration of the target vehicle, the predicted noise frequency is obtained according to the current noise frequency; Based on the speed and acceleration of the target vehicle, the predicted noise amplitude is obtained according to the current noise amplitude; Based on the steering angle of the target vehicle, a predicted noise phase is obtained according to the current noise frequency and the predicted noise phase. The predicted noise frequency, the predicted noise amplitude, and the predicted noise phase are combined to obtain the predicted noise characteristics.

3. The method according to claim 2, characterized in that, The reference parameters and the predicted noise characteristics are used as a basis. Generating a reverse acoustic signal includes: Based on the reference parameters, obtain the error signal between the current noise reduction amount and the reference parameters; Based on the error signal, the reference parameters, and the predicted noise characteristics, the current adaptive filter weights are updated. The reverse acoustic signal is generated based on the current adaptive filter weights and the predicted noise characteristics.

4. The method according to claim 3, characterized in that, The step of compensating for the reverse acoustic wave to obtain noise reduction parameters and sending the noise reduction parameters to the noise reduction device includes: The reverse acoustic wave signal is supplemented based on the absolute value of the reverse acoustic wave signal and the frequency band corresponding to the reverse acoustic wave signal to obtain the compensated reverse acoustic wave amplitude. According to the preset time window, the steps of modeling the predicted noise based on the dynamic parameters and the noise data to obtain the predicted noise characteristics are returned, and the current adaptive filter weights are updated in combination with the object type of the noise reduction device; Based on the updated adaptive filter weights, the current reverse acoustic wave amplitude is compensated to obtain noise reduction parameters, which are then sent to the noise reduction device.

5. The method according to claim 4, characterized in that, The step of updating the current adaptive filter weights based on the object type of the noise reduction device includes: When the object of the noise reduction device is a first type of object, it is determined whether the noise data is a safety warning tone; When the noise data is a safety warning tone, the adaptive filter weights corresponding to the safety warning tone are updated based on a first preset magnification to obtain the updated adaptive filter weights.

6. The method according to claim 4, characterized in that, The step of updating the current adaptive filter weights based on the object type of the noise reduction device further includes: When the object of the noise reduction device is a second type of object, and when the frequency of the noise data is lower than a preset frequency threshold, the adaptive filter weights corresponding to the noise data are updated based on a second preset multiplier to obtain the updated adaptive filter weights.

7. The method according to claim 1, characterized in that, The noise reduction device includes a bone conduction sound generator, a microphone, and a biosensor. The noise reduction device is wirelessly connected to a central noise reduction processor.

8. The method according to claim 7, characterized in that, The acquisition of object baseline parameters includes: The target object's ear canal resonant frequency is obtained using the biosensor. Based on the ear canal resonant frequency, the auditory sensitivity matrix of the target object is determined. The ear canal resonant frequency and the auditory sensitivity matrix are combined to obtain the object reference parameters of the target object, and the object reference parameters are stored in the central noise reduction processor.

9. The method according to claim 8, characterized in that, The acquisition of noise data of the target vehicle includes: An array of vehicle ambient noise sensors is installed in the target vehicle, and the array of vehicle ambient noise sensors is distributed in the engine compartment, chassis, and window edges of the target vehicle. The noise data of the target vehicle is collected using the vehicle environmental noise sensor array.

10. The method according to claim 9, characterized in that, The acquisition of the target vehicle's dynamic parameters includes: The dynamic parameters of the target vehicle are obtained from the target vehicle's driver assistance system via the driver assistance system data interface, and the dynamic parameters are sent to the central noise reduction processor.

11. The method according to claim 10, characterized in that, The obtained noise reduction parameters include: The central noise reduction processor receives noise data collected by the vehicle environmental noise sensor array and dynamic parameters collected by the driving assistance system data interface. The noise reduction parameters are obtained through the central noise reduction processor, and then sent to the noise reduction device.

12. A vehicle-mounted noise reduction device, characterized in that, The device includes: The parameter acquisition module is used to acquire the dynamic parameters, noise data, and baseline parameters of the target vehicle. The noise prediction module is used to model the predicted noise based on the dynamic parameters and the noise data to obtain the predicted noise characteristics; The reverse acoustic wave generation module is used to generate a reverse acoustic wave signal based on the reference parameters and the predicted noise characteristics. The noise reduction generation module is used to compensate the reverse sound wave, obtain noise reduction parameters, and send the noise reduction parameters to the noise reduction device.

13. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 11.

15. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 11.

Images