In-vehicle noise determination method and device, storage medium and program product

Abstract

One or more embodiments of the invention provide an in-vehicle noise determination method and device, a storage medium and a program product. The method comprises the following steps: acquiring a background noise signal associated with a target seat in a vehicle; under the condition that a target seat of the vehicle is provided with active noise reduction equipment, noise reduction effect distribution data corresponding to the target seat are obtained, and the noise reduction effect distribution data represent the noise reduction effects of the active noise reduction equipment on the background noise signals in multiple seat areas of the target seat; according to the background noise signal and the noise reduction effect distribution data, an estimated noise signal used for estimating noise sensed by a passenger of the target seat is determined, and then the real noise level sensed by the ears of the passenger in the actual working state of the active noise reduction system can be accurately estimated. The defect of noise estimation misalignment caused by spatial noise reduction difference due to neglecting of an active noise reduction system in the prior art is effectively overcome.

Description

Technical Field

[0001] This specification relates to one or more embodiments in the field of noise reduction technology, and more particularly to a method, apparatus, storage medium, and program product for determining in-vehicle noise. Background Technology

[0002] In-vehicle noise primarily originates from various sources, including powertrain noise from the engine, wind noise, and structural noise generated by tires and road surface. These noises mix and enter the cabin during vehicle operation, affecting passenger comfort. To improve the driving experience, the industry needs to accurately understand the actual state of cabin noise, especially acquiring noise information that reflects the occupants' true hearing, in order to support subsequent acoustic optimization and intelligent audio control.

[0003] In related technologies, noise signals are typically collected by placing microphones at fixed locations within the vehicle to estimate the cabin noise level. However, this method does not consider the impact of active noise cancellation systems equipped in some seats on the actual hearing experience of occupants. Because active noise cancellation systems generate a canceling sound field near the occupant's ears, the noise level at that location is lower than in other parts of the vehicle. Existing noise estimation methods relying solely on a single microphone cannot accurately reflect the true noise level perceived by the occupant, thus limiting the accuracy and adaptability of subsequent noise-related control measures. Summary of the Invention

[0004] In view of the above, one or more embodiments of this specification provide the following technical solutions: According to a first aspect of one or more embodiments of this specification, a method for determining in-vehicle noise is provided, the method comprising: Acquire the background noise signal associated with the target seat inside the vehicle; When the target seat of the vehicle is equipped with an active noise cancellation device, noise cancellation effect distribution data corresponding to the target seat is obtained. The noise cancellation effect distribution data characterizes the noise cancellation effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat. Based on the background noise signal and the noise reduction effect distribution data, a predicted noise signal is determined for estimating the noise perceived by the occupant of the target seat.

[0005] According to a second aspect of one or more embodiments of this specification, a vehicle interior noise determination device is provided, the device comprising: Background noise signal acquisition unit, used to acquire background noise signal associated with target seat inside vehicle; The distribution data acquisition unit is used to acquire noise reduction effect distribution data corresponding to the target seat when the target seat of the vehicle is equipped with an active noise cancellation device. The noise reduction effect distribution data characterizes the noise reduction effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat. The noise signal determination unit is used to determine a predicted noise signal for estimating the noise perceived by the occupant of the target seat based on the background noise signal and the noise reduction effect distribution data.

[0006] According to a third aspect of this specification, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0007] According to a fourth aspect of this specification, a computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the method described in the first aspect.

[0008] As can be seen from the above embodiments, this specification introduces noise reduction effect distribution data that quantifies the noise reduction effect of the active noise cancellation device in different areas of the target seat, and combines it with the collected background noise signal. This enables accurate prediction of the actual noise level perceived by the occupant's ears under the actual working state of the active noise cancellation system, effectively overcoming the defect of inaccurate noise estimation caused by ignoring the spatial noise reduction differences brought about by the active noise cancellation system in the prior art. Attached Figure Description

[0009] Figure 1 This is a system architecture diagram of a vehicle interior noise determination system shown in the embodiments disclosed in this specification; Figure 2 This is a schematic flowchart illustrating a method for determining in-vehicle noise according to an embodiment disclosed in this specification; Figure 3 This is a schematic flowchart illustrating another method for determining in-vehicle noise as disclosed in the embodiments of this specification; Figure 4 This is a schematic structural diagram of an electronic device shown in the embodiments of this specification; Figure 5 This is a block diagram illustrating an in-vehicle noise determination device according to an embodiment of this specification. Detailed Implementation

[0010] 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 specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification.

[0011] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0012] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0013] 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 manual are all information and data authorized by the user or fully authorized by all parties. The collection, use and processing of related data shall comply with the relevant laws, regulations and standards of the relevant regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0014] Figure 1 This is a schematic diagram of the architecture of a system for determining in-vehicle noise, provided as an exemplary embodiment. Figure 1 As shown, the system may include at least an active noise cancellation device 12 and an error microphone 14.

[0015] The target seat 12 refers to a specific seat inside the vehicle for which noise determination is required. It can be, for example, the driver's seat, the front passenger seat, or any of the rear seats. In this specification, the target seat 12 is the direct object of the noise determination method and is typically associated with at least one microphone for acquiring raw sound signals. This microphone can be located, for example, in the headrest or inside the seat, to acquire background noise signals related to the occupant of that seat. Furthermore, the seat may also be equipped with an active noise cancellation device 14, and the spatial location from which its noise cancellation effect on the occupant's hearing perception is evaluated.

[0016] Active noise cancellation device 14 is an optional system configured on target seat 12 to reduce noise perceived by the occupant. It typically includes a controller, one or more speakers, such as headrest speakers, and an error microphone that may be used to collect residual noise. The active noise cancellation device 14 achieves noise reduction by generating canceling sound waves that are out of phase with the background noise. In this specification, its core function lies in the spatial distribution of its noise reduction effect; that is, the amount of noise reduction varies in different seating areas of the target seat 12, such as the headrest area and the shoulder / back area. Corresponding noise reduction effect distribution data can be used to quantify the specific noise reduction effect of the device on the background noise signal in each seating area of ​​the corresponding target seat 12.

[0017] Those skilled in the art will understand that the deployment of the above-mentioned in-vehicle noise determination system is flexible. Its relevant functional modules can be integrated into the controller of the target seat or the active noise cancellation device itself, or they can be set in a preset independent electronic control unit (ECU) in the vehicle. This specification does not limit the specific deployment location and hardware form of the system.

[0018] Figure 2 This is a schematic flowchart illustrating an exemplary embodiment of a method for determining in-vehicle noise, as shown in this specification. Figure 2 As shown, the method may include the following steps: Step S202: Acquire the background noise signal associated with the target seat inside the vehicle.

[0019] First, the background noise signal associated with the target seat inside the vehicle can be acquired, specifically through real-time acquisition using a dedicated microphone positioned near the seat. This background noise signal reflects the basic noise conditions entering the target seat area and can be considered as the raw input for subsequent noise prediction.

[0020] Specifically, a standardized signal acquisition and processing procedure can be introduced to obtain the background noise signal associated with the target seat.

[0021] In one embodiment, the vehicle noise determination system can query a preset configuration mapping relationship based on the seat information of the target seat, such as the seat's physical location identifier or unique ID, to determine at least one microphone specifically used for collecting noise in the seat area. The placement of this microphone is flexible: it can be directly integrated into the seat itself, such as inside the seat headrest, seat back, or seat side; or it can be placed in the vehicle interior space adjacent to the seat, such as above the occupant's head or in the A-pillar, etc., and this specification does not limit this.

[0022] It is worth noting that the microphones identified here can be divided into two categories based on the configuration of the target seat: First, if the target seat is equipped with an active noise cancellation device, the microphone is usually the error microphone that comes with the active noise cancellation device, and the signal it collects is naturally related to the noise cancellation system of the seat; Second, if the target seat is not equipped with an active noise cancellation device, the microphone is a microphone placed close to the seat for regular noise collection.

[0023] Next, the system can acquire an initial background noise signal in real time based on the determined microphone. This signal is raw audio data containing ambient noise and possibly mixed with sound from the vehicle's audio system. Subsequently, the initial background noise signal can undergo preprocessing, including echo cancellation and / or noise reduction. Echo cancellation filters out echo interference generated at the microphone by the content played by the vehicle's speakers, while noise reduction suppresses non-steady-state interference or circuit noise in the signal. The signal obtained after this processing is a purer background noise signal that can be used for subsequent calculations.

[0024] Step S204: When the target seat of the vehicle is equipped with an active noise cancellation device, acquire noise cancellation effect distribution data corresponding to the target seat. The noise cancellation effect distribution data characterizes the noise cancellation effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat.

[0025] If the target seat is equipped with active noise cancellation, its corresponding noise reduction effect distribution data can be further obtained. This data can be obtained in advance through experimental measurement, simulation modeling, or preset parameters of the equipment, and can be stored and maintained in a structured form within the vehicle system. Taking experimental measurement as an example, this process is usually completed during the vehicle development or calibration phase: that is, under the normal operating condition of the active noise cancellation system, acoustic measurements are performed at different spatial points of each target seat in the actual vehicle for different noise types and noise scenarios. The noise types mentioned above can include, for example, engine noise, road noise, and wind noise, and the noise scenarios can include high-speed cruising, urban congestion, and bumpy road conditions. Specifically, with the headrest area as the center, measuring microphones or sound level meters can be arranged at fixed intervals of, for example, 5 cm in the horizontal and vertical directions, or a microphone array with the same spacing can be used directly to synchronously collect the sound pressure signals at each point. By calculating the loudness difference between the signal at the measurement point and the signal from the reference microphone in the vehicle, a noise reduction distribution map characterizing the noise reduction effect of the active noise cancellation device at each point in the seat space under that noise environment can be obtained. This is a specific form of the aforementioned noise reduction effect distribution data.

[0026] Within the vehicle system, a mapping relationship between different noise environment information and noise reduction effect distribution data can be pre-maintained locally or in designated network devices. When acquiring this distribution data, the vehicle's current noise environment information can be obtained in real-time or near real-time. Then, based on the aforementioned mapping relationship and the current noise environment information, the corresponding noise reduction effect distribution data can be queried or calculated. This data characterizes the actual noise reduction effect of the active noise cancellation device on the aforementioned background noise signal in different seat areas, such as the headrest area, shoulder and back area, and seat cushion area. It reflects the variation characteristics of the noise reduction effect with the spatial position of the seat, providing key spatial acoustic characteristics for accurately estimating the occupant's actual hearing experience.

[0027] Specifically, the aforementioned current noise environment information can be obtained based on the noise type and noise scenario of the background noise signal.

[0028] In one embodiment, firstly, based on the vehicle's environmental sensors such as cameras, radar, GPS / BeiDou modules, and road surface recognition sensors, environmental perception information surrounding the vehicle can be acquired, such as vehicle speed, road type, traffic flow, weather conditions, and window status. Simultaneously, the time-frequency characteristics of the acquired background noise signal can be combined to analyze the noise components. Next, based on independent analysis of the environmental perception information or the background noise signal, or a combined analysis of both, the main noise type of the background noise signal and its overall noise scene are determined. Finally, the system can use the identified noise type and noise scene as current noise environment information for subsequent querying of mapping relationships. This process allows the acquisition of noise reduction effect distribution data to dynamically adapt to the actual operating environment of the vehicle, improving the accuracy and scene adaptability of noise prediction.

[0029] In addition, the above system can add a conditional judgment before performing the steps of obtaining noise reduction effect distribution data and subsequent calculations, so as to improve the processing efficiency and practicality of the above method.

[0030] Specifically, before acquiring the noise reduction effect distribution data corresponding to the target seat, the system can first detect whether there is an occupant on the target seat. This detection can be achieved through seat pressure sensors, in-vehicle visual sensors such as cameras, seat belt buckle sensors, or a combination thereof.

[0031] If the detection result indicates that there is an occupant in the seat, it means that noise estimation for that seat is meaningful, and the system will continue with the subsequent steps of acquiring noise reduction effect distribution data and determining the estimated noise signal. Conversely, if the detection result indicates that there is no occupant in the seat, it means that noise assessment for that location is unnecessary. The system can stop executing subsequent processes for that seat in this method, thereby saving computational resources and avoiding the output of meaningless noise estimation results.

[0032] This optimization enables the noise determination method to intelligently adapt to changes in the distribution of occupants inside the vehicle, initiating signal processing and analysis only when necessary, demonstrating the rationality and efficiency of the system design. Following this judgment, if further execution is required, the system will, as described above, obtain the current noise environment information and query the corresponding noise reduction effect distribution data.

[0033] Step S206: Determine a predicted noise signal for estimating the noise perceived by the occupant of the target seat based on the background noise signal and the noise reduction effect distribution data.

[0034] Based on the acquired background noise signal and noise reduction effect distribution data, a predicted noise signal can be calculated to estimate the noise perceived by the target seat occupant. This signal not only contains the original information of the background noise, but also incorporates the noise reduction effect of the active noise cancellation device at the occupant's location, thus more realistically reflecting the occupant's actual auditory experience in an active noise cancellation environment.

[0035] The calculation of the predicted noise signal based on the background noise signal and noise reduction effect distribution data typically requires a specific processing procedure. This procedure first extracts one or more noise reduction parameters corresponding to the current background noise signal acquisition location from the noise reduction effect distribution data; these parameters are collectively referred to as the target noise reduction amount. Subsequently, the system calculates a gain coefficient based on these target noise reduction amounts. Finally, this gain coefficient is used to adjust and correct the original background noise signal, thereby obtaining a predicted noise signal that reflects the occupants' actual hearing experience. This specification will further explain the above process below.

[0036] First, the specific method for obtaining the target noise reduction amount depends on the deployment location of the microphones collecting the background noise signal. The system must first determine the source of the signal and then use different association rules to extract the corresponding noise reduction amount from the noise reduction effect distribution data. These are summarized into two cases below: In the first scenario, if the background noise signal originates from a first microphone located at the target seat headrest, such as an error microphone in an active noise cancellation device, the system can obtain two key parameters from the noise reduction effect distribution data: one is the first noise reduction amount of the headrest area itself, and the other is the second noise reduction amount at the actual location of the occupant's head. Here, the first noise reduction amount can be understood as a reference value for the noise reduction effect at the location of the error microphone at the headrest, while the second noise reduction amount reflects the actual value of the noise reduction effect as it changes spatially with position. The system uses this set of noise reduction amounts together as the target noise reduction amount required for subsequent calculations.

[0037] In the second scenario, if the background noise signal originates from a second microphone located elsewhere besides the headrest, such as the A-pillar or roof, then since this microphone's position deviates from the area with the optimal noise reduction effect, the system obtains a representative third noise reduction amount preset for the head area of ​​the target seat from the noise reduction effect distribution data. This third noise reduction amount could be the average noise reduction amount for that area or the noise reduction amount at a specific listening point. In this case, this third noise reduction amount will be used alone as the target noise reduction amount for correction.

[0038] In this way, the system can flexibly and accurately associate and obtain noise reduction information that matches the current signal acquisition conditions based on the actual hardware configuration, thus laying the foundation for subsequent accurate correction.

[0039] After determining the target noise reduction amount, the next step is to determine the gain coefficient used for signal correction.

[0040] Taking the first scenario as an example, the system can calculate a first gain coefficient based on the first noise reduction amount and the second noise reduction amount according to a first preset relationship. The "actual position of the occupant's head" associated with the second noise reduction amount can be determined in real-time using image recognition technology based on occupant images captured by in-vehicle image sensors, such as cameras. The first preset relationship is a predefined mathematical relationship, such as an exponential relationship, a linear relationship, or a combination thereof. Its input is the two noise reduction amounts mentioned above, and its output is the first gain coefficient. The magnitude of the first gain coefficient is positively correlated with the spatial distance between the headrest area and the actual position of the occupant's head. The underlying principle is that the second noise reduction amount characterizes the noise reduction effect at the occupant's actual position. The greater the difference between the second noise reduction amount and the first noise reduction amount at the headrest, the farther the occupant's head deviates from the headrest, which is the optimal noise reduction area (hereinafter referred to as the headrest reference point). In this case, the original background noise signal from the headrest microphone is less representative of the actual listening experience. Therefore, a larger correction coefficient, namely the first gain coefficient, is needed to compensate for the perceptual error caused by this spatial deviation.

[0041] After calculating the first gain coefficient, the signal correction stage begins. Its purpose is to generate the final estimated noise signal. The core of this correction process is a threshold-based judgment logic. The system compares the first gain coefficient with a preset gain threshold, which is a calibrated or optimized threshold value used to determine whether the spatial difference in noise reduction effect is significant enough to require signal scaling.

[0042] If the comparison result shows that the first gain coefficient is less than or equal to the gain threshold, it indicates that the difference in noise reduction effect between the occupant's head position and the headrest reference point is within an acceptable preset range, and the background noise signal collected by the headrest microphone can already represent the occupant's hearing perception quite well. Therefore, the system directly outputs the aforementioned background noise signal as the aforementioned estimated noise signal without performing additional scaling calculations.

[0043] Conversely, if the first gain coefficient is greater than the gain threshold, it indicates a significant difference in spatial noise reduction, necessitating signal calibration. In this case, the system multiplies the first gain coefficient by the background noise signal to obtain a new signal corrected for spatial noise effects, which is then used as the predicted noise signal. This multiplication operation is equivalent to simulating the change in noise reduction effect caused by occupant position deviation at the signal level, making the final prediction result more closely match the occupant's actual auditory experience at their actual location.

[0044] To illustrate the implementation of the above description in more detail, the following is an example of calculation and correction: First, a specific mathematical expression for the aforementioned first presupposed relationship can be: in, This represents the calculated first gain coefficient. The first noise reduction amount mentioned above refers to the maximum noise reduction amount of the active noise cancellation system at the reference point of the headrest area, expressed in decibels (dB). This represents the second noise reduction amount mentioned above, namely the noise reduction amount of the active noise cancellation system at the actual position of the occupant's head, also expressed in dB. In the formula... The difference directly reflects how the noise reduction effect changes with spatial position. The farther the occupant's head is from the headrest, the larger this difference is typically. The larger it is, the more consistent it is with the positive correlation characteristic mentioned earlier.

[0045] Subsequently, the collected and processed background noise signal can be set as follows: The final output predicted noise signal is The correction logic is as follows: in, This represents the preset gain threshold, which is a constant. A typical default value for this threshold can be set to... , which corresponds to The boundary point of noise reduction difference. When At that time, the original signal is used directly. That is, the background noise signal is used as the output. That is, the aforementioned estimated noise signal. When When, then the signal Multiply by the gain factor The corrected output is obtained. .

[0046] Next, taking the second scenario as an example, the target noise reduction amount is the third noise reduction amount, obtained from the noise reduction effect distribution data, which characterizes the noise reduction effect in the target seat head area. Since the second microphone that collects the background noise signal is itself far from the headrest area where noise reduction is optimal, the signal it collects cannot directly represent the occupant's hearing perception. Therefore, the processing logic is relatively simpler than that of the first scenario.

[0047] In this case, the system directly calculates a second gain coefficient based on the aforementioned third noise reduction amount and the second preset relationship. The aforementioned second preset relationship is another predefined mathematical relationship, whose input is the third noise reduction amount, and whose output is the second gain coefficient used for correction.

[0048] In the signal correction stage, the system can directly multiply the calculated second gain coefficient by the background noise signal from the second microphone to obtain the corrected predicted noise signal. This process is equivalent to uniformly calibrating the signals collected by microphones located outside the headrest to the noise level that the occupant's head area should perceive under the active noise cancellation system, thereby ensuring the consistency of the noise prediction method logic and the comparability of results under different microphone deployment schemes.

[0049] To illustrate the implementation of the above description in more detail, an example of calculation and correction is provided below: First, assume that a specific mathematical expression for the aforementioned second presupposed relationship is: in, This represents the calculated second gain coefficient. The third noise reduction measure mentioned above refers to the amount of noise reduction provided by the active noise cancellation system for the target head area of ​​the seat, such as a defined listening point or average area, and is measured in decibels.

[0050] Next, the background noise signal from the second microphone, after processing, can be... The final output predicted noise signal is... The corrected logic is direct multiplication: This operation will remove background noise signals. According to the second gain coefficient Scaling is performed to obtain the corrected predicted noise signal. .

[0051] Those skilled in the art will understand that when the target seat in the aforementioned vehicle is not equipped with active noise cancellation, the signal processing flow is simplified. In this case, since there is no spatial modulation effect from the active noise cancellation system on the occupant's actual hearing, the background noise signal collected and processed from the microphone associated with the seat can directly and accurately reflect the noise level entering the seat area. In other words, the system can directly output this background noise signal as the estimated noise signal without needing to perform steps such as acquiring noise reduction effect distribution data, calculating gain coefficients, and performing signal correction. This processing method not only logically conforms to the physical fact that the occupant's perceived noise equals the ambient background noise, but also significantly reduces the system's computational complexity and resource overhead, demonstrating the flexibility and efficiency of this method in adaptive processing based on different hardware configurations.

[0052] In practical applications, the aforementioned vehicles typically contain multiple passenger seats. The method described above can be further extended to the simultaneous processing and fusion of multiple target seats, thereby obtaining a comprehensive assessment that reflects the overall noise level within the vehicle cabin.

[0053] Specifically, the system can execute the aforementioned noise determination method in parallel or sequentially for multiple target seats in the vehicle, thereby obtaining a corresponding estimated noise signal for each target seat. Since each seat may have different hardware configurations, such as whether it is equipped with active noise cancellation devices or the deployment location of error microphones, the accuracy and representativeness of their corresponding estimated noise signals may differ. Therefore, the system assigns a weight to the estimated noise signal for each target seat based on the deployment status of its active noise cancellation devices and error microphones. This weight reflects the reliability of the noise estimation results under different configurations or the proportion of their contribution to the overall noise level.

[0054] For example, active noise-canceling seats equipped with headrest error microphones typically provide a more accurate reflection of occupant hearing in their predicted noise signals, thus deserving a higher weight. Seats without active noise cancellation may have their signals assigned a relatively lower weight. Finally, based on the assigned weights, the system performs a weighted average of the predicted noise signals from all target seats to calculate a comprehensive predicted noise signal for the vehicle's interior. This signal integrates noise information from multiple key locations within the cabin, providing a more comprehensive and robust characterization of the vehicle's overall noise level under current driving conditions. This provides a unified basis for subsequent vehicle acoustic management and comfort control decisions.

[0055] To illustrate further, we can assume that the target seats in the car are divided into three categories based on their hardware configuration, and each category is assigned a calculation coefficient, i.e., a weight: Type 1: Seats equipped with active noise cancellation systems and error microphones in the headrests.

[0056] Type 2: Seats equipped with active noise cancellation systems but without error microphones in the headrests, where the microphones are located in other positions such as the A-pillar.

[0057] Type 3: Seats without active noise cancellation systems.

[0058] Among them, can , , These are the weighting coefficients for the three types of seats mentioned above when calculating the overall average, and they satisfy... If no type of seat exists, its corresponding coefficient is 0.

[0059] The aforementioned comprehensive estimated noise signal can be calculated using the following formula: in: This represents the calculated overall estimated noise signal of the current data frame or its characteristic noise level, such as the noise peak. , , These represent the estimated noise level values, such as noise peak values, of the type 1, 2, and 3 seats in the current data frame. , , These represent the number of seats of type 1, 2, and 3, respectively. This is a summation index. For example, if both front seats of a vehicle belong to type 1, that is... Their noise peak values ​​are respectively and And there are no other types of seats. The comprehensive noise estimate is then... By adjusting the coefficients This allows for flexible reflection of the varying importance of different hardware configurations to the overall noise assessment.

[0060] Of course, in addition to generating a comprehensive predicted noise signal that reflects the overall noise level of the vehicle, the above method also supports independent assessment of the noise conditions of specific areas or groups of seats. In other words, the system can select a subset of all target seats according to actual application needs, such as focusing on the driver's area, the rear passenger area, or a specific type of seat, and calculate a local predicted noise signal based on the predicted noise signals corresponding to these seats. This local signal can be obtained through weighted averaging or other aggregation methods similar to but with limited range as the comprehensive signal, which can more accurately characterize the acoustic environment of specific areas in the vehicle, thereby providing more focused data for zonal noise control, personalized comfort settings, or acoustic optimization for specific occupants.

[0061] Based on the predicted noise signal obtained by the aforementioned method, which can accurately reflect the actual hearing of the occupants, the method provided in this specification can be further extended to the closed-loop control of the active noise cancellation system, thereby realizing a complete technical link from noise perception to noise suppression.

[0062] Specifically, after obtaining the estimated noise signal of the target seat, the system can determine the gain control value of the active noise cancellation device for the target seat based on the signal loudness, such as its sound pressure level, loudness level, or other perceived loudness indicators, and a preset loudness gain mapping relationship. The loudness gain mapping relationship defines the amount of gain adjustment required from the active noise cancellation device to achieve specific acoustic goals at different noise loudness levels, such as maintaining a constant subjective loudness at the occupant's location, optimizing noise reduction effects, and balancing sound quality. This adjustment can take the form of a lookup table, a function, or a set of rules.

[0063] Subsequently, the system can adjust the drive signals of one or more speakers in the active noise cancellation device based on the calculated gain control value. This adjustment is typically achieved by changing the amplification factor of the drive signal, i.e., the gain effect, thereby directly controlling the intensity of the canceled sound waves generated by the active noise cancellation system. Through this closed-loop process, the system can dynamically optimize the output of the active noise cancellation device based on a real-time and accurate estimate of the actual perceived noise at the occupant's location. This allows the device to not only operate based on a fixed noise reduction curve but also to adaptively respond to changes in the current noise environment and the occupant's position, ultimately achieving more precise and personalized cabin noise management and improving overall ride comfort.

[0064] The following is based on Figure 3 For example, this section introduces the specific process for determining in-vehicle noise. Figure 3 As shown, this method can be executed by a noise determination system in the vehicle, such as a processor integrated into a domain controller or a standalone ECU, and specifically includes the following steps: Step S302: Collect the original audio signal through the in-vehicle microphone and preprocess the signal to obtain the background noise signal.

[0065] In one embodiment, the noise determination system controls one or more microphones, such as headrest microphones and A-pillar microphones, positioned near the target seat to collect raw audio signals. The system then preprocesses the raw audio signals, specifically including echo cancellation and / or noise reduction. Echo cancellation removes audio streams such as music playing from the in-vehicle speakers and navigation prompts, while noise reduction suppresses non-steady-state interference. The signal obtained after this processing is the clean background noise signal, which mainly includes vehicle noise such as engine noise, road noise, and wind noise.

[0066] Step S304: Based on environmental sensor information and image information, determine the current noise scene and noise type.

[0067] In one embodiment, to achieve this step, the system needs to execute two information acquisition and processing sub-processes in parallel. First, the in-vehicle camera acquires images of the internal and external environment, obtaining visual information including road conditions, traffic density, and weather phenomena. Simultaneously, the system acquires data from other environmental sensors such as vehicle speed sensors, GPS, and radar. Next, the system can classify noise types based on time-frequency characteristics of the background noise signal, such as its spectrum and energy distribution, initially identifying it as road noise, engine noise, or wind noise. Finally, the system combines the image information and environmental sensor data to verify and refine the preliminary classification results, comprehensively determining the precise noise scene and noise type, which serves as the basis for subsequent queries of noise reduction effect data.

[0068] Step S306: Determine whether there is an occupant in the target seat.

[0069] In one embodiment, the noise determination system determines whether there is an occupant at the target seat location based on data from a seat pressure sensor, an in-vehicle camera, or a seatbelt buckle sensor. If no occupant is detected, the process jumps directly to step S320 without further noise estimation for that seat. If an occupant is detected, the process continues.

[0070] Step S308: Determine whether the target seat is equipped with an active noise cancellation system.

[0071] In one embodiment, the system queries vehicle configuration information to determine whether the target seat with occupants is equipped with active noise cancellation equipment. If not, the process proceeds to step S316. If it is, the process continues.

[0072] Step S310: Determine whether the error microphone of the active noise cancellation system is located on the seat headrest.

[0073] In one embodiment, the system can further determine, based on device configuration information, whether the error microphone of the active noise cancellation system is deployed on the seat headrest. This determination will decide which technical path to use for noise estimation. If yes, step S312 is executed; otherwise, step S314 is executed.

[0074] Step S312: For the case where the error microphone is on the headrest, determine the relative position of the occupant based on the image information, obtain the noise reduction amount, and calculate the noise estimation result.

[0075] In one embodiment, if the error microphone is located on the headrest, the system first determines the relative position of the passenger's head and the headrest area using image recognition technology based on the occupant image captured by the in-vehicle camera. Next, based on the noise scene and type determined in step S304, the system queries pre-stored noise reduction effect distribution data to obtain the first noise reduction amount G0 at the headrest and the second noise reduction amount G at the actual positions of the occupant's ears. Subsequently, the system uses the formula... Calculate the first gain coefficient and compare it with the gain threshold s. If If the signal collected and processed by the headrest error microphone is used directly as the noise estimation result of the seat; if Then multiply the signal by The corrected noise estimation results are obtained.

[0076] Step S314: If the error microphone is not on the headrest, obtain the noise reduction amount of the target area and correct the noise estimation signal.

[0077] In one embodiment, if the error microphone is not on the headrest, the system can directly query the noise reduction effect distribution data based on the noise scene and type to obtain the preset third noise reduction amount G1 for the target area of ​​the seat's head. Then, the system uses the formula... Calculate the second gain coefficient. Finally, the system multiplies the background noise signal from the error microphone by... The corrected noise estimation results are obtained.

[0078] Step S316: For seats without active noise cancellation systems, the in-vehicle microphone signal is used directly as the noise estimation result.

[0079] In one embodiment, for occupant seats that are determined by step S308 to not have an active noise cancellation system deployed, the system directly uses the background noise signal collected and processed from a conventional microphone near the seat as the noise estimation result for the seat.

[0080] Step S318: Fuse the results from multiple seats and calculate the estimated result of the average noise inside the vehicle.

[0081] In one embodiment, the noise determination system aggregates noise estimation results from different seats. Based on the hardware configuration of each seat, corresponding to the three scenarios in steps S312, S314, and S316, the system assigns weights, such as coefficients a, b, and c, to the noise estimation results for each seat. Finally, the system performs a weighted average of all weighted noise estimation results, calculated using a formula such as: Thus, the average noise estimation result inside the vehicle is obtained. .

[0082] Step S320: For seats detected as unoccupied, skip noise estimation.

[0083] In one embodiment, for a seat that is determined to be unoccupied in step S306, the system may choose not to perform the noise estimation process for that seat, and its weight in the weighted average in step S318 is zero.

[0084] Step S322: Determine and apply speaker gain based on the noise-gain mapping relationship.

[0085] In one embodiment, the noise determination system, or the audio domain controller in communication therewith, can estimate the final in-vehicle average noise level based on the obtained result. The system queries a preset noise gain mapping relationship based on the noise level or loudness. This mapping relationship defines the amount of gain adjustment required to maintain listening comfort. Based on this, the system determines the gain control value for one or more speakers in the vehicle, which may include active noise-canceling speakers and media playback speakers. Simultaneously, it applies this gain control value and adjusts the drive signal of the corresponding speaker, completing closed-loop control from noise perception to acoustic output.

[0086] Figure 4 This is a schematic structural diagram of an electronic device according to an exemplary embodiment. Please refer to... Figure 4 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile storage, and may also include other necessary hardware. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it, forming a determination device based on in-vehicle noise at the logical level. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0087] Figure 5 This specification illustrates a block diagram of a device for determining in-vehicle noise in an embodiment. Please refer to... Figure 5 The device includes: Background noise signal acquisition unit 502 is used to acquire background noise signals associated with target seats inside the vehicle; The distribution data acquisition unit 504 is used to acquire noise reduction effect distribution data corresponding to the target seat when the target seat of the vehicle is equipped with an active noise cancellation device. The noise reduction effect distribution data characterizes the noise reduction effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat. The noise signal determination unit 506 is used to determine a predicted noise signal for estimating the noise perceived by the occupant of the target seat based on the background noise signal and the noise reduction effect distribution data.

[0088] Optionally, the background noise signal acquisition unit 502 is specifically used for: Based on the seat information of the target seat, at least one microphone associated with the seat is determined; An initial background noise signal is acquired based on at least one determined microphone; The initial background noise signal is subjected to echo cancellation and / or noise reduction processing to obtain the background noise signal.

[0089] Optionally, the vehicle pre-maintains a mapping relationship between different noise environment information and noise reduction effect distribution data; the distribution data acquisition unit 504 is specifically used for: Obtain the current noise environment information of the vehicle; Based on the mapping relationship and the current noise environment information, the corresponding noise reduction effect distribution data is determined.

[0090] Optionally, the distributed data acquisition unit 504 is specifically used for: The vehicle's environmental sensors are used to acquire environmental perception information about the vehicle's surroundings. Based on the environmental perception information and the background noise signal, the noise type and noise scene of the background noise signal are determined as the current noise environment information.

[0091] Optionally, the estimated noise signal determination unit 506 is specifically used for: Based on the noise reduction effect distribution data, the target noise reduction amount associated with the acquisition location of the background noise signal is obtained; The gain coefficient is determined based on the target noise reduction amount; The background noise signal is corrected based on the gain coefficient to obtain the estimated noise signal.

[0092] Optionally, the estimated noise signal determination unit 506 is specifically used for: When the background noise signal comes from a first microphone located at the headrest of the target seat, a first noise reduction amount for the headrest area and a second noise reduction amount for the actual position of the occupant's head are obtained from the noise reduction effect distribution data; the first noise reduction amount and the second noise reduction amount are used as the target noise reduction amount. When the background noise signal comes from a second microphone located at a position other than the headrest, a third noise reduction amount corresponding to the head area of ​​the target seat is obtained from the noise reduction effect distribution data, and the third noise reduction amount is used as the target noise reduction amount.

[0093] Optionally, the background noise signal comes from the first microphone; the estimated noise signal determination unit 506 is specifically used for: The step of determining the gain coefficient based on the target noise reduction amount includes: calculating a first gain coefficient according to a first preset relationship based on the first noise reduction amount and the second noise reduction amount, wherein the magnitude of the first gain coefficient is positively correlated with the spatial distance between the headrest area and the actual position of the occupant's head; The step of correcting the background noise signal based on the gain coefficient to obtain the estimated noise signal includes: comparing the first gain coefficient with a gain threshold; if the first gain coefficient is less than or equal to the gain threshold, using the background noise signal as the estimated noise signal; and if the first gain coefficient is greater than the gain threshold, multiplying the first gain coefficient by the background noise signal to obtain the estimated noise signal.

[0094] Optionally, the actual position of the occupant's head is obtained based on occupant images collected by the vehicle's in-vehicle image sensors.

[0095] Optionally, before acquiring the noise reduction effect distribution data, the device further includes: Occupant detection unit, used to detect whether there is an occupant in the target seat; If the detection result is yes, then proceed with the steps of obtaining the noise reduction effect distribution data and determining the estimated noise signal. If the test result is negative, then the method should be stopped.

[0096] Optionally, the vehicle includes multiple target seats, and the device further includes: The signal weight allocation unit is used to assign weights to the estimated noise signals corresponding to each target seat based on the deployment status of the active noise cancellation devices and error microphones configured for each target seat. Based on the assigned weights, the estimated noise signals corresponding to the multiple target seats are weighted and averaged to obtain the comprehensive estimated noise signal inside the vehicle.

[0097] Optionally, the device further includes: The device adjustment unit is used to determine the gain control value of the active noise cancellation device for the target seat based on the signal loudness of the estimated noise signal and the preset loudness gain mapping relationship. The drive signal of the speaker in the active noise cancellation device is adjusted according to the gain control value.

[0098] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0099] Based on the same concept as the methods described above, this specification also provides a computer-readable storage medium having computer instructions stored thereon that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0100] Based on the same concept as the methods described above, this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0101] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0102] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0103] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a GPS receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0104] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0105] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0106] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0107] Therefore, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0108] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A method for determining in-vehicle noise, characterized in that, include: Acquire the background noise signal associated with the target seat inside the vehicle; When the target seat of the vehicle is equipped with an active noise cancellation device, noise cancellation effect distribution data corresponding to the target seat is obtained. The noise cancellation effect distribution data characterizes the noise cancellation effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat. Based on the background noise signal and the noise reduction effect distribution data, a predicted noise signal is determined for estimating the noise perceived by the occupant of the target seat.

2. The method according to claim 1, characterized in that, The acquisition of the background noise signal associated with the target seat inside the vehicle includes: Based on the seat information of the target seat, at least one microphone associated with the seat is determined; An initial background noise signal is acquired based on at least one determined microphone; The initial background noise signal is subjected to echo cancellation and / or noise reduction processing to obtain the background noise signal.

3. The method according to claim 1, characterized in that, The vehicle has a pre-maintained mapping relationship between different noise environment information and noise reduction effect distribution data; obtaining the noise reduction effect distribution data corresponding to the target seat includes: Obtain the current noise environment information of the vehicle; Based on the mapping relationship and the current noise environment information, the corresponding noise reduction effect distribution data is determined.

4. The method according to claim 3, characterized in that, The step of obtaining the current noise environment information of the vehicle includes: The vehicle's environmental sensors are used to acquire environmental perception information about the vehicle's surroundings. Based on the environmental perception information and the background noise signal, the noise type and noise scene of the background noise signal are determined as the current noise environment information.

5. The method according to claim 1, characterized in that, The step of determining the estimated noise signal for estimating the noise perceived by the occupant of the target seat based on the background noise signal and the noise reduction effect distribution data includes: Based on the noise reduction effect distribution data, the target noise reduction amount associated with the acquisition location of the background noise signal is obtained; The gain coefficient is determined based on the target noise reduction amount; The background noise signal is corrected based on the gain coefficient to obtain the estimated noise signal.

6. The method according to claim 5, characterized in that, The step of obtaining the target noise reduction amount associated with the acquisition location of the background noise signal based on the noise reduction effect distribution data includes: When the background noise signal comes from a first microphone located at the headrest of the target seat, a first noise reduction amount for the headrest area and a second noise reduction amount for the actual position of the occupant's head are obtained from the noise reduction effect distribution data; the first noise reduction amount and the second noise reduction amount are used as the target noise reduction amount. When the background noise signal comes from a second microphone located at a position other than the headrest, a third noise reduction amount corresponding to the head area of ​​the target seat is obtained from the noise reduction effect distribution data, and the third noise reduction amount is used as the target noise reduction amount.

7. The method according to claim 6, characterized in that, The background noise signal originates from the first microphone; The step of determining the gain coefficient based on the target noise reduction amount includes: calculating a first gain coefficient according to a first preset relationship based on the first noise reduction amount and the second noise reduction amount, wherein the magnitude of the first gain coefficient is positively correlated with the spatial distance between the headrest area and the actual position of the occupant's head; The step of correcting the background noise signal based on the gain coefficient to obtain the estimated noise signal includes: comparing the first gain coefficient with a gain threshold; if the first gain coefficient is less than or equal to the gain threshold, using the background noise signal as the estimated noise signal; and if the first gain coefficient is greater than the gain threshold, multiplying the first gain coefficient by the background noise signal to obtain the estimated noise signal.

8. The method according to claim 6 or 7, characterized in that, The actual position of the occupant's head is obtained based on occupant images collected by the vehicle's in-vehicle image sensors.

9. The method according to claim 1, characterized in that, Before acquiring the noise reduction effect distribution data, the method further includes: Detect whether there is an occupant in the target seat; If the detection result is yes, then proceed with the steps of obtaining the noise reduction effect distribution data and determining the estimated noise signal. If the test result is negative, then the method should be stopped.

10. The method according to claim 1, characterized in that, The vehicle includes multiple target seats, and the method further includes: Based on the deployment status of the active noise cancellation devices and error microphones configured for each target seat, weights are assigned to the estimated noise signals corresponding to each target seat; Based on the assigned weights, the estimated noise signals corresponding to the multiple target seats are weighted and averaged to obtain the comprehensive estimated noise signal inside the vehicle.

11. The method according to claim 1, characterized in that, The method further includes: Based on the estimated loudness of the noise signal and the preset loudness gain mapping relationship, the gain control value of the active noise cancellation device for the target seat is determined; The drive signal of the speaker in the active noise cancellation device is adjusted according to the gain control value.

12. A device for determining in-vehicle noise, characterized in that, include: Background noise signal acquisition unit, used to acquire background noise signal associated with target seat inside vehicle; The distribution data acquisition unit is used to acquire noise reduction effect distribution data corresponding to the target seat when the target seat of the vehicle is equipped with an active noise cancellation device. The noise reduction effect distribution data characterizes the noise reduction effect of the active noise cancellation device on the background noise signal at multiple seat areas of the target seat. The noise signal determination unit is used to determine a predicted noise signal for estimating the noise perceived by the occupant of the target seat based on the background noise signal and the noise reduction effect distribution data.

13. A computer-readable storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 11.

14. A computer program product, characterized in that, Includes a computer program / instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 11.

Images