A vehicle noise reduction control method, device, equipment, vehicle and medium

Abstract

The application discloses a vehicle noise reduction control method, device, equipment, vehicle and medium. The method comprises the following steps: acquiring real-time positioning information and real-time speed information of a special vehicle, and current positioning information and external sound information of a current vehicle; determining a relative distance between the special vehicle and the current vehicle and an estimated time for the special vehicle to approach the current vehicle according to the real-time positioning information, the real-time speed information and the current positioning information; performing voiceprint recognition on the external sound information to determine voiceprint information, a voiceprint source direction and a voiceprint confidence; comparing the voiceprint source direction according to the voiceprint information, the voiceprint confidence, the voiceprint source direction and the real-time positioning information to determine a source direction comparison result; and controlling noise reduction of the current vehicle in response to the relative distance, the estimated time and the source direction comparison result all meeting preset conditions. The technical scheme improves the flexibility and accuracy of noise reduction and improves the safety of driving.

Description

Technical Field

[0001] This application relates to the field of vehicle manufacturing technology, and in particular to a vehicle noise reduction control method, device, equipment, vehicle, and medium. Background Technology

[0002] Current active noise cancellation technology in vehicles primarily works by generating inverse sound waves to cancel out external noise, thereby creating a quieter driving environment and improving driving comfort. However, current noise cancellation strategies typically rely on fixed algorithms to uniformly process continuous or broadband noise, lacking the ability to flexibly adjust based on sound type.

[0003] Furthermore, the limitations of noise detection and identification technologies exacerbate these problems. When collecting external sounds, the system struggles to accurately distinguish between regular background noise and warning sounds with specific meanings. This can lead to the inadvertently including critical warning sounds from special vehicles (such as police cars, fire trucks, and ambulances) as noise during noise reduction, preventing drivers from promptly noticing emergencies and posing potential risks to driving safety. Therefore, ensuring the accurate identification and transmission of critical sound signals while effectively reducing noise remains a pressing technological challenge. Summary of the Invention

[0004] This application provides a vehicle noise reduction control method, apparatus, device, vehicle, and medium to improve the flexibility and accuracy of vehicle noise reduction.

[0005] According to one aspect of this application, a vehicle noise reduction control method is provided, comprising: Acquire real-time location and speed information of special vehicles, as well as the current location information and external sound information of the current vehicle; Based on real-time location information, real-time speed information, and current location information, determine the relative distance between the feature vehicle and the current vehicle, as well as the estimated time for the special vehicle to approach the current vehicle. Voiceprint recognition is performed on external sound information to determine voiceprint information, voiceprint source direction, and voiceprint confidence level; Based on voiceprint information, voiceprint confidence, voiceprint source direction and real-time location information, the voiceprint source direction is compared to determine the source direction comparison result; The noise reduction of the current vehicle is controlled in response to the fact that the relative distance, estimated time, and source direction comparison results all meet the preset conditions.

[0006] According to another aspect of this application, a vehicle noise reduction control device is provided, comprising: The vehicle information acquisition module is used to acquire real-time location information and real-time speed information of special vehicles, as well as the current location information and external sound information of the current vehicle. The distance-time determination module is used to determine the relative distance between the feature vehicle and the current vehicle, as well as the estimated time for the special vehicle to approach the current vehicle, based on real-time positioning information, real-time speed information, and current positioning information. The external voiceprint recognition module is used to perform voiceprint recognition on external sound information to determine the voiceprint information, the direction of the voiceprint source, and the voiceprint confidence level. The source direction comparison module is used to compare the source direction of the voiceprint based on the voiceprint information, voiceprint confidence, voiceprint source direction and real-time positioning information, and determine the source direction comparison result; The vehicle noise reduction control module is used to control the noise reduction of the current vehicle in response to the fact that the comparison results of relative distance, estimated time and source direction all meet the preset conditions.

[0007] According to another aspect of this application, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle noise reduction control method according to any embodiment of this application.

[0008] According to another aspect of this application, a vehicle is provided, the vehicle being equipped with an electronic device provided in the embodiments of this application, for implementing the vehicle noise reduction control method described in any embodiment of this application.

[0009] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle noise reduction control method according to any embodiment of this application.

[0010] In the technical solution of this application embodiment, real-time positioning information and real-time speed information of the special vehicle, as well as the current positioning information and external sound information of the current vehicle are obtained; based on the real-time positioning information, real-time speed information, and current positioning information, the relative distance between the special vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle are determined. The determination of the relative distance and estimated time can provide a specific basis for judging the adjustment of noise reduction, and simplifies the calculation, thereby improving the efficiency of the judgment; voiceprint recognition is performed on the external sound information to determine the voiceprint information, voiceprint source direction, and voiceprint confidence. The recognition of external sound information can help determine the voiceprint information and source direction of the special vehicle, so as to judge whether the special vehicle is emitting sound; based on the voiceprint information... The system compares the voiceprint confidence level, voiceprint source direction, and real-time location information to determine the source direction comparison result. By comparing the source direction and real-time location information, it determines whether the voiceprint information is emitted by a special vehicle in the corresponding direction, so as to more accurately control the noise reduction adjustment in a specific direction. In response to the fact that the relative distance, estimated time, and source direction comparison results all meet the preset conditions, the noise reduction of the current vehicle is controlled. When the distance, time, and source direction comparison results that need to be judged all meet the conditions, it can be determined that the special vehicle is emitting special voiceprint information, and then targeted noise reduction adjustments can be made, which improves the flexibility and accuracy of noise reduction, ensures the driver's perception of special external sounds, and improves driving safety.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a vehicle noise reduction control method according to Embodiment 1 of this application; Figure 2A This is a flowchart of a vehicle noise reduction control method according to Embodiment 2 of this application; Figure 2B This is a schematic diagram of a noise reduction and sound insulation collaborative control provided in Embodiment 2 of this application; Figure 3 This is a schematic diagram of a vehicle noise reduction control device according to Embodiment 3 of this application; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the vehicle noise reduction control method of the embodiments of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This application provides a flowchart of a vehicle noise reduction control method according to Embodiment 1. This embodiment is applicable to situations where a vehicle adjusts its external noise levels. The method can be executed by a vehicle noise reduction control device, which can be implemented in hardware and / or software. This device can be configured in an electronic device, which can be installed in the vehicle. Figure 1 As shown, the method includes: S110: Obtain real-time location and speed information of special vehicles, as well as current location information and external sound information of the current vehicle.

[0017] Special vehicles can be vehicles performing special tasks, such as police cars, fire trucks, ambulances, and roadside assistance vehicles. Because of the special nature of their missions, these vehicles typically emit different sounds while driving on the road to alert surrounding vehicles and pedestrians to their presence. Real-time location information can be data on the real-time location of special vehicles, such as latitude and longitude coordinates. Real-time speed information can be data on the real-time speed of special vehicles. Both real-time location and speed information can be broadcast by special vehicles traveling on the road, making it available to other vehicles.

[0018] The vehicle in question can be one requiring noise reduction. Whether the driver is driving, on the road, or resting in the car, reducing external noise can improve the driver's experience and provide a quiet environment for rest. The current location information can be real-time data about the vehicle's location, such as its latitude and longitude, which can be obtained through satellite positioning. External sound information can be a collection of various sounds detected by the vehicle, including sounds from special vehicles and various ambient noises. For example, multiple high signal-to-noise ratio (SNR) microphones can be installed on the exterior of the vehicle to collect sound information. For instance, MEMS (Micro-Electro-Mechanical System) high SNR microphones can be placed on the front grille, side mirrors, and trunk to collect external sound information from all directions.

[0019] S120. Based on real-time positioning information, real-time speed information, and current positioning information, determine the relative distance between the feature vehicle and the current vehicle, as well as the estimated time for the special vehicle to approach the current vehicle.

[0020] The relative distance can be the distance between the feature vehicle and the current vehicle. Since this application focuses on noise reduction control, and sound mainly propagates through the air in roads, road conditions can be temporarily disregarded, and the distance can be simplified and included in the calculation as a straight-line distance. The estimated time can be the predicted meeting time between the current vehicle and the feature vehicle, i.e., how long after the feature vehicle and the current vehicle may meet. It can be calculated based on the relative distance and the speeds of the two vehicles. Of course, it should be noted that the purpose of calculating the estimated time in this application is not to predict whether the feature vehicle will meet the current vehicle, but to use this estimated time to determine whether the noise reduction strategy needs to be adjusted.

[0021] In one optional implementation, determining the relative distance between the feature vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle, based on real-time positioning information, real-time speed information, and current positioning information, may include: determining the relative distance based on real-time positioning information and current positioning information; and determining the estimated time based on the relative distance and real-time speed information.

[0022] The real-time positioning information of the special vehicle and the current positioning information of the current vehicle can be used to calculate the straight-line distance between the two vehicles, which can then be used as the relative distance. Accordingly, based on the relative distance, the estimated time can be calculated in real time according to the speeds of the two vehicles. It should be noted that the positional relationship between the special vehicle and the current vehicle in this application only assumes they are traveling towards each other, and that they might pass each other. The estimated time is calculated in real time under this assumption. Therefore, this estimated time can be used to assist in adjusting the noise reduction strategy. In reality, the special vehicle may be far away from the current vehicle. Since the estimated time is calculated in real time, a shorter estimated time can be interpreted as the two vehicles approaching each other, while a longer estimated time means they are moving away. This can thus assist in adjusting the noise reduction strategy.

[0023] In the above implementation, by assuming a proximity model between the special vehicle and the current vehicle, the relative distance and estimated time are calculated to assist in subsequent adjustments to the noise reduction strategy, which helps to improve the flexibility and accuracy of noise reduction.

[0024] S130. Perform voiceprint recognition on external sound information to determine voiceprint information, voiceprint source direction, and voiceprint confidence level.

[0025] The voiceprint information can be the voiceprint information of a special vehicle, that is, special voiceprint information that only special vehicles can emit, such as the siren of a police car, the siren of a fire truck, or the alarm of an ambulance. The direction of the voiceprint source can be the direction of the source of the voiceprint information relative to the current vehicle. The voiceprint confidence level can be the degree of credibility of the identified voiceprint information. For example, if the confidence level of a voiceprint being identified as a siren is 95%, it means that there is a 95% probability that the voiceprint is a siren, which is relatively credible. The voiceprint information, along with the corresponding voiceprint confidence level, can be identified by a pre-trained machine learning model, such as a CNN (Convolutional Neural Network) model. This model takes the collected external sound information as input and outputs the voiceprint recognition result (i.e., voiceprint information) and the corresponding voiceprint confidence level. This application embodiment does not limit the specific construction and training process of the model. The direction of the voiceprint source can be determined based on the sound signal received by a microphone deployed on the outside of the vehicle, and this application embodiment does not limit this.

[0026] S140. Based on the voiceprint information, voiceprint confidence level, voiceprint source direction and real-time positioning information, compare the voiceprint source direction to determine the source direction comparison result.

[0027] Understandably, voiceprint information and voiceprint confidence can determine whether a voiceprint is a warning sound emitted by a special vehicle. Based on this, the direction of the voiceprint's origin becomes credible, and a direction comparison is then performed to obtain the corresponding source direction comparison result. Understandably, if the comparison result shows that the source direction of the voiceprint matches the relative direction between the two vehicles, then it can be considered that noise reduction adjustment is indeed needed for that voiceprint; if the comparison result shows that the source direction of the voiceprint does not match the relative direction between the two vehicles, then it can be considered that the voiceprint may be spoofed, i.e., it is not a voiceprint emitted by a special vehicle, and noise reduction adjustment is not necessary.

[0028] S150 responds to the fact that the comparison results of relative distance, estimated time and source direction all meet the preset conditions, and controls the noise reduction of the current vehicle.

[0029] The preset conditions can be verification conditions used to validate the comparison results of relative distance, estimated time, and source direction. When the comparison results of relative distance, estimated time, and source direction all pass the verification, it can be determined that the noise reduction needs to be adjusted. For example, if the detected relative distance is less than 500 meters, the estimated time is less than 60 seconds, and the source direction comparison result shows that the directions are consistent, then the noise reduction equipment of the current vehicle is controlled to adjust the corresponding noise reduction strategy.

[0030] Specifically, the noise reduction control of the current vehicle includes: in response to the source direction comparison result being consistent with the direction, controlling the reduction of noise reduction intensity in the source direction of the soundprint.

[0031] Understandably, this application aims to address the problem of existing vehicle noise reduction methods being too simplistic. Using the same noise reduction techniques and intensities for all external sounds can easily prevent drivers from clearly hearing warning sounds from emergency vehicles outside the vehicle. Therefore, when the relative distance, estimated time, and source direction comparison results in the aforementioned steps all meet preset conditions, the noise reduction intensity in the direction of the sound signature is reduced, allowing the driver to clearly hear the sounds from emergency vehicles in that direction. This improves the flexibility and accuracy of noise reduction, ensuring that the sounds of emergency vehicles are accurately conveyed to the driver, thereby guaranteeing driving safety.

[0032] In the technical solution of this application embodiment, real-time positioning information and real-time speed information of the special vehicle, as well as the current positioning information and external sound information of the current vehicle are obtained; based on the real-time positioning information, real-time speed information, and current positioning information, the relative distance between the special vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle are determined. The determination of the relative distance and estimated time can provide a specific basis for judging the adjustment of noise reduction, and simplifies the calculation, thereby improving the efficiency of the judgment; voiceprint recognition is performed on the external sound information to determine the voiceprint information, voiceprint source direction, and voiceprint confidence. The recognition of external sound information can help determine the voiceprint information and source direction of the special vehicle, so as to judge whether the special vehicle is emitting sound; based on the voiceprint information... The system compares the voiceprint confidence level, voiceprint source direction, and real-time location information to determine the source direction comparison result. By comparing the source direction and real-time location information, it determines whether the voiceprint information is emitted by a special vehicle in the corresponding direction, so as to more accurately control the noise reduction adjustment in a specific direction. In response to the fact that the relative distance, estimated time, and source direction comparison results all meet the preset conditions, the noise reduction of the current vehicle is controlled. When the distance, time, and source direction comparison results that need to be judged all meet the conditions, it can be determined that the special vehicle is emitting special voiceprint information, and then targeted noise reduction adjustments can be made, which improves the flexibility and accuracy of noise reduction, ensures the driver's perception of special external sounds, and improves driving safety.

[0033] Example 2 Figure 2A This is a flowchart of a vehicle noise reduction control method provided in Embodiment 2 of this application. This embodiment further refines the determination operation of the source direction comparison result based on the foregoing embodiments and implementation methods. Figure 2A As shown, the method includes: S210. Obtain real-time location and speed information of special vehicles, as well as current location information and external sound information of the current vehicle.

[0034] S220. Based on real-time positioning information, real-time speed information, and current positioning information, determine the relative distance between the feature vehicle and the current vehicle, as well as the estimated time for the special vehicle to approach the current vehicle.

[0035] S230. Perform voiceprint recognition on external sound information to determine voiceprint information, voiceprint source direction, and voiceprint confidence level.

[0036] S240. Based on the voiceprint information, voiceprint confidence level, and preset confidence level threshold, determine whether the voiceprint information matches the special vehicle.

[0037] The confidence threshold can be a threshold set for the confidence of voiceprints, used to determine whether the voiceprint information is reliable. For example, if the confidence threshold is set to 95%, when the voiceprint information obtained by the algorithm model in the aforementioned embodiment is identified by the model as a police car with a confidence level greater than or equal to 95%, it can be considered that the voiceprint information matches a police car, that is, it can be confirmed that the voiceprint belongs to a police car, and that the voiceprint information belongs to a siren. Conversely, when the confidence level of the voiceprint information being identified as a police car is less than 95%, it is determined that the voiceprint does not belong to a police car.

[0038] S250: In response to the voiceprint information matching the special vehicle, the source direction comparison result is determined based on real-time positioning information and the direction of voiceprint source.

[0039] When the voiceprint information matches the corresponding characteristic vehicle, the real-time location information broadcast by the special vehicle is compared with the direction of the voiceprint source to determine whether the source directions are consistent.

[0040] S260 responds to the fact that the comparison results of relative distance, estimated time and source direction all meet the preset conditions, and controls the noise reduction of the current vehicle.

[0041] In the technical solution of this application embodiment, the consistency between voiceprint information and special vehicles is verified by voiceprint information, voiceprint confidence level and confidence level threshold, thereby ensuring the accuracy of voiceprint recognition.

[0042] In one alternative implementation, the method may further include: A1. Obtain the current vehicle body status information and raindrop density information from the rain sensor.

[0043] The vehicle body status information can be information about the vehicle itself, including but not limited to information about its driving status (such as vehicle speed, steering angle, etc.) and the status information of body components (such as window status, seat status, etc.). This vehicle body status information can be acquired by relevant vehicle control elements or sensors; this application embodiment does not limit this. The rain sensor can be a sensor installed outside the vehicle to detect ambient rainfall, and the rain sensor collects raindrop density information and provides it to the vehicle for reference.

[0044] A2. Adjust the confidence threshold based on vehicle body status information and raindrop density information.

[0045] It should be noted that the constant changes in the vehicle's condition can easily affect the tire noise, wind noise, and other noises generated during vehicle operation. Rainfall outside the vehicle also produces different rain sounds, all of which can affect the identification and comparison of the voiceprint information of special vehicles. Therefore, when noise increases due to the influence of vehicle condition information and raindrop density information, the confidence threshold can be lowered to make it easier to identify and confirm the voiceprint information of special vehicles. Conversely, if noise decreases or there is no other noise (e.g., no tire noise or wind noise when parked) due to the influence of vehicle condition information and raindrop density information, the confidence threshold can be increased (or restored to its original value) to ensure the accuracy of identification. Of course, a machine learning model can be trained using historical vehicle condition data, raindrop density, and the adjustment process of the confidence threshold, enabling the model to adjust the confidence threshold based on vehicle condition information and raindrop density information. This application does not limit this approach.

[0046] A3. Based on the adjusted confidence threshold and voiceprint information, determine whether the voiceprint information matches the special vehicle.

[0047] The confidence level of the voiceprint information is then determined based on the adjusted confidence threshold. For example, under the influence of wind noise, tire noise, and rain noise, the confidence level of a police car siren is only 93%, indicating that it is affected by these other noises. If judged according to the original confidence threshold of 95%, this voiceprint information cannot be identified as matching a police car. However, by lowering the confidence threshold to 90%, the voiceprint information with a 93% confidence threshold can be identified as matching a police car, thereby improving the flexibility, adaptability, and accuracy of voiceprint recognition.

[0048] In the above embodiments, by adjusting the confidence threshold based on vehicle body status information and raindrop density information, the confidence of voiceprint information corresponding to the voiceprint information decreases under the influence of other noises. This can effectively improve the flexibility and accuracy of voiceprint information recognition for special vehicles and help improve the flexibility and accuracy of noise reduction adjustment.

[0049] In a further optional embodiment, the vehicle body status information includes the current vehicle speed, real-time steering angle, and window opening degree; Accordingly, A2 describes adjusting the confidence threshold based on vehicle body status information and raindrop density information, including: determining the environmental interference coefficient based on current vehicle speed, real-time steering angle, window opening degree, and raindrop density information; and reducing the confidence threshold based on the environmental interference coefficient.

[0050] The environmental interference coefficient measures the degree of interference from various external noises on the voiceprint information of special vehicles. It's understood that higher vehicle speeds lead to greater wind and tire noise, resulting in more interference; larger steering angles may generate additional wind and tire noise; larger window openings allow more external sounds to enter the vehicle, increasing driver interference; and denser raindrops generate more noise. These factors negatively impact the recognition of voiceprint information for special vehicles. Therefore, an environmental interference coefficient is first determined based on this information, and then the confidence threshold is adjusted accordingly. For example, the current vehicle speed, real-time steering angle, window opening, and raindrop density can be quantified and normalized to map them to a unified dimension. A single environmental interference coefficient is then obtained through weighted summation. The CNN model mentioned in the preceding embodiments and implementations typically outputs a confidence score, which is compared with a preset confidence threshold during recognition. The base threshold is determined using a validation set under ideal conditions (low interference). When the environmental interference coefficient increases, the signal-to-noise ratio decreases, and the confidence level of the model output is generally low. Using a fixed threshold at this point can easily lead to missed detections. Therefore, the threshold needs to be appropriately lowered to include real voiceprints masked by noise. The higher the environmental interference coefficient, the lower the corresponding confidence threshold needs to be. The relationship between the changes in the environmental interference coefficient and the confidence threshold can be determined by those skilled in the art through extensive experiments; this application does not limit this.

[0051] In the above implementation, the environmental interference coefficient is determined based on various types of external factors, and the confidence threshold is further reduced based on the environmental interference coefficient, thereby encompassing the real voiceprint information of special vehicles affected by noise, improving the rationality, flexibility and accuracy of voiceprint recognition, and helping to improve the driver's driving safety and driving experience.

[0052] Figure 2B This is a schematic diagram of a noise reduction and sound insulation collaborative control method provided in Embodiment 2 of this application. Figure 2B As shown, this application provides a practical example based on the foregoing embodiments and implementation methods. This example uses a "sound-position" collaborative approach to adjust noise reduction, as detailed below: First, the data acquisition layer.

[0053] ①V2X data acquisition module: Hardware components: Pre-installed V2X chip, dual antennas, and signal amplifier. The dual antennas are used to receive signals from RSU (Roadside Unit) and OBU (Onboard Unit). The signal amplifier can enhance the reception sensitivity within 500m. Data types include: RSU-issued data, such as special vehicle types (police cars / ambulances / fire trucks, etc.), satellite positioning coordinates (accuracy ≤ 1m), driving speed (km / h), driving direction, and update frequency (e.g., 10Hz); OBU-directly connected data, such as emergency priority (e.g., "Level 1 priority" for ambulances), expected route, warning duration, and latency ≤ 100ms. The working principle is that the chip receives wireless signals (frequency band 5.9GHz), analyzes the data frames of the wireless signals, filters invalid data (such as distance > 500m), and transmits it to the judgment center, with a packet loss rate ≤ 0.1%.

[0054] ② Voiceprint acquisition module: Hardware components: Four high signal-to-noise ratio microphones, deployed in the vehicle's front grille (collecting frontal sound, 40cm above the ground), left and right rearview mirrors (collecting side sound, 1.2m above the ground), and trunk (collecting rear sound, 50cm above the ground). Specifications: Signal-to-noise ratio ≥60dB, sampling rate 48kHz, frequency response range 20-2000Hz, sensitivity -26dBFS.

[0055] The working principle is that the microphone collects ambient sound, reduces noise through a preamplifier, and then performs A / D (analogue-to-digital) conversion (16-bit precision), followed by filtering in the 20-2000Hz frequency band, and finally transmits it to the judgment center, with a sampling interval of 10ms.

[0056] ③ Vehicle status acquisition module: Hardware components: CAN (Controller Area Network) bus interface module, data parsing unit; The collected data includes: driving status: speed (km / h, accuracy ±1), steering angle (±45°); cabin status: window opening degree (0%=fully closed, 100%=fully open), and current working mode of ANC (Active Noise Cancellation).

[0057] The working principle is as follows: it receives broadcast data from the ECU (electronic control unit) via the CAN bus, parses the data frames, extracts key parameters, and transmits them to the judgment center, updating the frequency to 5Hz.

[0058] ④ Environmental perception module: Hardware components: rain sensor and vehicle speed sensor, with the vehicle speed sensor potentially integrated into ESP (Electronic Stability Program).

[0059] The perception data includes: rainfall level (0 = no rain, 5 = heavy rain) and environmental noise baseline (calculated based on vehicle speed: wind noise at 60km / h on highway, baseline is 65dB).

[0060] The working principle is as follows: the rain sensor detects the raindrop density, the vehicle speed sensor obtains the driving speed, calculates the environmental interference coefficient and transmits it to the judgment center, which is used to adjust the voiceprint recognition threshold.

[0061] Second, determine the central layer: ① CNN voiceprint recognition algorithm is used: Input: 20-2000Hz frequency spectrum (256×256 pixels) from the voiceprint acquisition module; Network structure: 3 convolutional layers (extracting frequency / temporal features) → 2 pooling layers (dimensionality reduction) → 1 fully connected layer (classification); Output: Recognition result (special vehicle type / non-special), confidence level (0-100%), recognition time ≤50ms; ②Location verification algorithm: The straight-line distance between the two points is calculated based on the satellite positioning coordinates (e.g., latitude and longitude coordinates) of the special vehicle and the current vehicle; the relative direction is calculated using the difference between latitude and longitude coordinates.

[0062] Estimated arrival time of special vehicles: Estimated time = relative distance / (speed of special vehicle / 3.6), where 3.6 is a unit conversion factor.

[0063] ③ Decision logic: Effective early warning is triggered if the following conditions are met simultaneously: voiceprint confidence ≥ 95%, relative distance ≤ 500m, estimated time ≤ 60s, and the direction of the voiceprint source is consistent with the direction of the special vehicle; if two or less of the above conditions are met, a suspected early warning can be triggered, data is recorded but noise reduction control is not triggered; if only ordinary ambient sound is identified, the regular ANC strategy is maintained.

[0064] Third, the execution control layer module ①ANC dynamic control module Hardware components: ANC controller (supports multi-channel adjustment), 4 independent channel speakers (corresponding to 4 microphone positions) and gain adjustment unit; Control logic: ① Direction-adaptive noise reduction: Target location (location of special vehicles): The loudspeaker stops outputting reverse sound waves, preserving the sound with a retention rate of ≥98%; Non-target location: Adjust noise reduction amount according to vehicle speed. Low speed (≤30km / h): 3-5dB (reduce ambient noise shielding); Medium speed (30 - 60 km / h): 5 - 8 dB (linear adjustment); High speed (≥60 km / h): 8 - 13 dB (enhanced wind noise cancellation); ② Sound gain control: Trigger condition: relative distance ≤ 100 m; Gain parameter: 2 - 5 dB (ensure sound intensity 85 - 120 dB, upper limit of auditory comfort), only gain special vehicle feature frequency bands (siren 300 - 600 Hz, ambulance 500 - 800 Hz); Response time: from receiving the determination instruction to completion of adjustment ≤ 300 ms, adjustment accuracy ±0.5 dB.

[0065] IV. Vehicle head unit display and warning module: Hardware components: central control screen (resolution 2560×1440), HUD (Head - Up Display) with a field of view angle of 12°, seat vibration module (4 directions, corresponding to the four sides of the vehicle), and vehicle head unit speakers.

[0066] Control logic: ① AR display Identification style: red dynamic icons (police car identification "警", ambulance identification "红十字", fire truck identification "火苗"), size changes with distance (occupying 5% of the screen at 50 m, 2% of the screen at 300 m); mark the relative distance (such as "300 m to the left rear"), estimated arrival time (such as "19.8 s"), and arrow - pointing direction; the priority should be top - displayed, covering other non - safety information (such as music lyrics); ② Multimodal warning: Trigger condition is relative distance ≤ 50 m; warning methods can include but are not limited to auditory, tactile, and visual. Among them, Auditory: the speaker plays a prompt tone ("Ambulance approaching from the left rear, please give way"), volume ≤ 60 dB; Tactile: seat vibration in the corresponding direction (frequency 2 - 3 Hz, intensity 5 - 8 N); Visual: red flashing of the screen border (frequency 1 Hz); Termination condition: relative distance > 500 m or estimated time > 60 s or driver manually turns off (steering wheel shortcut key / voice command).

[0067] Three different examples are introduced below.

[0068] Example 1. Ambulance warning on urban roads (current vehicle speed 40 km / h, sunny day) Trigger conditions include: The V2X module receives the following information from the RSU: Ambulance (Type=2), Satellite Positioning (X=120.001°, Y=30.002°), Speed=60km / h, Direction=270° (due west); Current vehicle satellite positioning (X=120.004°, Y=30.002°), all windows closed; The microphone in the left rearview mirror collects voiceprints: 500-800Hz periodic waves, confidence level = 98%.

[0069] The execution steps include: (1) Dual verification judgment: relative distance = 330m (≤500m), estimated time = 19.8s (≤60s), direction is left rear consistent with microphone position, judged as a valid warning; (2) ANC adjustment: noise reduction of the left rearview mirror speaker is paused, noise reduction of 8dB (medium speed) in other directions, and no gain at 330m; (3) Vehicle display: The HUD displays a red "cross" icon, marked "330m to the left rear, 19.8s", with the arrow pointing to the left rear; (4) Multimodal warning: When the distance drops to 50m, a prompt sound is played, the left side of the seat vibrates, and the screen frame flashes; (5) Termination: When the distance increases to 550m, normal ANC is restored and the icon disappears.

[0070] Example 2: Highway fire truck warning (current vehicle speed 100km / h, heavy rain) The triggering condition is: The V2X module directly receives data from the fire truck's OBU, type=3, satellite positioning (X=119.998°, Y=30.005°), speed=80km / h, direction=90° (due east). Current vehicle satellite positioning (X=120.002°, Y=30.005°), all windows closed, rainfall level = 4 (heavy rain); The microphone in the right rearview mirror collects voiceprints: 400-700Hz attenuated wave, confidence level = 99% (threshold increases to 98% during heavy rain).

[0071] The execution steps are as follows: (1) Dual verification judgment: if the relative distance = 440m (≤500m), the estimated time = 19.8s (≤60s), and the direction is consistent with the microphone position to the right front, then it is judged as a valid warning; (2) ANC adjustment: noise reduction of the right rearview mirror speaker is paused, noise reduction of 12dB in other directions (strong wind noise in heavy rain at high speed), no gain at 440m; (3) Vehicle display: The central control screen displays a red "flame" icon, marked "440m to the right front, 19.8s", with an arrow pointing to the right front; (4) Multimodal warning: When the distance drops to 50m, a warning sound is played (volume 60dB, which drowns out the sound of rain), the right side of the seat vibrates, and the screen flashes; (5) Termination: The fire truck changes lanes (direction changes to 180°), and resumes normal ANC when the estimated time is >60.

[0072] Example 3: Police car warning on urban roads in rainy weather (current vehicle speed 20km / h, light rain) The triggering condition is: The V2X module receives police car data from the RSU: Type=1, satellite positioning (X=120.003°, Y=30.001°), speed=50km / h, direction=180° (due south). The vehicle's current satellite positioning is (X=120.003°, Y=30.004°), and the window is half open (50% opening). The trunk microphone collects voiceprints: 300-600Hz pulse waves, confidence level = 97%.

[0073] The execution steps are as follows: (1) Double verification judgment: if the relative distance = 330m (≤500m), the estimated time = 23.8s (≤60s), and the direction behind is consistent with the microphone position, then it is judged as a valid warning; (2) ANC adjustment: The trunk speaker is paused for noise reduction, and the noise reduction in other directions is 4dB (low speed). Because the car window is half open, the gain is 4dB (to compensate for the sound loss when the window is open). (3) Vehicle display: The central control screen and HUD simultaneously display a red "warning" icon, marked "330m behind, 23.8s", with an arrow pointing backward; (4) Multimodal warning: When the distance drops to 50m, a prompt sound is played, the back of the seat vibrates, and the screen flashes; (5) Termination: When the distance between the police car and the overtaking vehicle is greater than 500m, normal ANC is resumed.

[0074] Example 3 Figure 3 This is a schematic diagram of a vehicle noise reduction control device provided in Embodiment 3 of this application. Figure 3 As shown, the device 300 includes: The vehicle information acquisition module 310 is used to acquire the real-time location information and real-time speed information of special vehicles, as well as the current location information and external sound information of the current vehicle. The distance-time determination module 320 is used to determine the relative distance between the feature vehicle and the current vehicle, as well as the estimated time for the special vehicle to approach the current vehicle, based on real-time positioning information, real-time speed information, and current positioning information. The external voiceprint recognition module 330 is used to perform voiceprint recognition on external sound information and determine the voiceprint information, the direction of the voiceprint source, and the voiceprint confidence level. The source direction comparison module 340 is used to compare the source direction of the voiceprint based on the voiceprint information, voiceprint confidence, voiceprint source direction and real-time positioning information, and determine the source direction comparison result; The vehicle noise reduction control module 350 is used to control the noise reduction of the current vehicle in response to the fact that the comparison results of relative distance, estimated time and source direction all meet the preset conditions.

[0075] In the technical solution of this application embodiment, real-time positioning information and real-time speed information of the special vehicle, as well as the current positioning information and external sound information of the current vehicle are obtained; based on the real-time positioning information, real-time speed information, and current positioning information, the relative distance between the special vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle are determined. The determination of the relative distance and estimated time can provide a specific basis for judging the adjustment of noise reduction, and simplifies the calculation, thereby improving the efficiency of the judgment; voiceprint recognition is performed on the external sound information to determine the voiceprint information, voiceprint source direction, and voiceprint confidence. The recognition of external sound information can help determine the voiceprint information and source direction of the special vehicle, so as to judge whether the special vehicle is emitting sound; based on the voiceprint information... The system compares the voiceprint confidence level, voiceprint source direction, and real-time location information to determine the source direction comparison result. By comparing the source direction and real-time location information, it determines whether the voiceprint information is emitted by a special vehicle in the corresponding direction, so as to more accurately control the noise reduction adjustment in a specific direction. In response to the fact that the relative distance, estimated time, and source direction comparison results all meet the preset conditions, the noise reduction of the current vehicle is controlled. When the distance, time, and source direction comparison results that need to be judged all meet the conditions, it can be determined that the special vehicle is emitting special voiceprint information, and then targeted noise reduction adjustments can be made, which improves the flexibility and accuracy of noise reduction, ensures the driver's perception of special external sounds, and improves driving safety.

[0076] In one optional implementation, the source direction comparison module 340 may include: The matching judgment unit is used to determine whether the voiceprint information matches the special vehicle based on the voiceprint information, voiceprint confidence level and preset confidence level threshold. The result determination unit is used to determine the source direction comparison result based on the real-time positioning information and the source direction of the voiceprint in response to the matching of voiceprint information with special vehicles.

[0077] In one alternative embodiment, the device 300 may further include: The status rainfall acquisition module is used to acquire the current vehicle body status information and raindrop density information from the rain sensor; The threshold adjustment module is used to adjust the confidence threshold based on vehicle body status information and raindrop density information; The adjusted judgment module is used to determine whether the voiceprint information matches the special vehicle based on the adjusted confidence threshold and voiceprint information.

[0078] In one optional implementation, the vehicle status information includes the current vehicle speed, real-time steering angle, and window opening degree; Accordingly, the threshold adjustment module may include: The interference coefficient determination unit is used to determine the environmental interference coefficient based on the current vehicle speed, real-time steering angle, window opening degree, and raindrop density information. The threshold reduction unit is used to reduce the confidence threshold based on the environmental interference coefficient.

[0079] In one optional implementation, the vehicle noise reduction control module 350 can be specifically used to: control the reduction of noise reduction intensity in the direction of soundprint source in response to the comparison result of the source direction being consistent.

[0080] In one optional embodiment, the vehicle information acquisition module 310 may include: The relative distance determination unit is used to determine the relative distance based on real-time positioning information and current positioning information; The estimated time determination unit is used to determine the estimated time based on relative distance and real-time speed information.

[0081] The vehicle noise reduction control device provided in this application embodiment can execute the vehicle noise reduction control method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each vehicle noise reduction control method.

[0082] Example 4 Figure 4A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0083] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0084] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0085] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle noise reduction control methods.

[0086] This application also provides a vehicle that may be equipped with the aforementioned electronic devices to implement a vehicle noise reduction control method described in the foregoing embodiments and implementation methods of this application.

[0087] In some embodiments, the vehicle noise reduction control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle noise reduction control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle noise reduction control method by any other suitable means (e.g., by means of firmware).

[0088] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0092] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0093] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0094] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the vehicle noise reduction control method provided in any embodiment of this application. This program product shares the same inventive concept as the vehicle noise reduction control methods disclosed in the embodiments of this application, and therefore will not be described in detail here.

[0095] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0096] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A vehicle noise reduction control method, characterized in that, include: Acquire real-time location and speed information of special vehicles, as well as the current location information and external sound information of the current vehicle; Based on the real-time positioning information, the real-time speed information, and the current positioning information, the relative distance between the feature vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle are determined. Voiceprint recognition is performed on the external sound information to determine the voiceprint information, the direction of voiceprint source, and the voiceprint confidence level; Based on the voiceprint information, the voiceprint confidence level, the voiceprint source direction, and the real-time positioning information, the voiceprint source direction is compared to determine the source direction comparison result. In response to the fact that the relative distance, the estimated time, and the comparison result of the source direction all meet the preset conditions, the noise reduction of the current vehicle is controlled.

2. The method according to claim 1, characterized in that, The step of comparing the voiceprint source direction based on the voiceprint information, the voiceprint confidence level, the voiceprint source direction, and the real-time positioning information to determine the source direction comparison result includes: Based on the voiceprint information, the voiceprint confidence level, and a preset confidence threshold, determine whether the voiceprint information matches the special vehicle. In response to the voiceprint information matching the special vehicle, the source direction comparison result is determined based on the real-time positioning information and the voiceprint source direction.

3. The method according to claim 2, characterized in that, The method further includes: Obtain the current vehicle body status information and raindrop density information from the rain sensor; The confidence threshold is adjusted based on the vehicle body status information and the raindrop density information. Based on the adjusted confidence threshold and the voiceprint information, it is determined whether the voiceprint information matches the special vehicle.

4. The method according to claim 3, characterized in that, The vehicle status information includes current vehicle speed, real-time steering angle, and window opening degree; The step of adjusting the confidence threshold based on the vehicle body state information and the raindrop density information includes: The environmental interference coefficient is determined based on the current vehicle speed, the real-time steering angle, the window opening degree, and the raindrop density information. Based on the environmental interference coefficient, the confidence threshold is reduced.

5. The method according to any one of claims 1-4, characterized in that, The noise reduction control of the current vehicle includes: In response to the fact that the comparison result of the source direction is consistent, the noise reduction intensity of the source direction of the voiceprint is controlled to be reduced.

6. The method according to any one of claims 1-4, characterized in that, The step of determining the relative distance between the feature vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle, based on the real-time positioning information, the real-time speed information, and the current positioning information, includes: The relative distance is determined based on the real-time location information and the current location information; The estimated time is determined based on the relative distance and the real-time speed information.

7. A vehicle noise reduction control device, characterized in that, include: The vehicle information acquisition module is used to acquire real-time location information and real-time speed information of special vehicles, as well as the current location information and external sound information of the current vehicle. The distance-time determination module is used to determine the relative distance between the feature vehicle and the current vehicle, and the estimated time for the special vehicle to approach the current vehicle, based on the real-time positioning information, the real-time speed information, and the current positioning information. An external voiceprint recognition module is used to perform voiceprint recognition on the external sound information to determine the voiceprint information, the direction of the voiceprint source, and the voiceprint confidence level. The source direction comparison module is used to compare the voiceprint source direction based on the voiceprint information, the voiceprint confidence, the voiceprint source direction and the real-time positioning information, and determine the source direction comparison result; The vehicle noise reduction control module is used to control the noise reduction of the current vehicle in response to the fact that the relative distance, the estimated time, and the comparison result of the source direction all meet preset conditions.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle noise reduction control method according to any one of claims 1-6.

9. A vehicle, characterized in that, The vehicle is equipped with the electronic equipment provided in claim 8, for implementing the vehicle noise reduction control method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle noise reduction control method according to any one of claims 1-6.

Images