Self-adaptive noise elimination method, device and equipment

Abstract

The embodiment of the invention relates to the technical field of vehicle automatic noise reduction, and discloses a self-adaptive noise elimination method, device and equipment, and the method comprises the steps: collecting a noise signal of a current driving scene of a vehicle; identifying the collected noise signal to identify the type of the current noise signal; when the type of the noise signal is a low-frequency resonance noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to a processing result to offset low-frequency resonance noise; when the type of the noise signal is a special sound signal, the noise signal is subjected to filtering, amplification and sharpening processing after being identified; the current working state of the vehicle is displayed, and corresponding operation of a driver is received according to the current working state. According to the self-adaptive noise elimination method provided by the invention, intelligent and self-adaptive vehicle noise control and special sound processing are realized, and the problems that a traditional vehicle noise reduction method is poor in low-frequency noise processing effect and cannot give consideration to special sound recognition are solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of automatic noise reduction for vehicles, and in particular to an adaptive noise elimination method, device and equipment. Background Art

[0002] During the driving process, the noise problem is like a ghost that keeps haunting the driver. Among them, the low-frequency noise problem caused by low-frequency resonance is particularly prominent. It is like a hidden sharp blade that not only ruthlessly reduces the driving comfort, but also when the driver is exposed to this harsh noise environment for a long time, it is very likely to cause damage to his health, like a chronic poison corroding the body.

[0003] At present, most vehicle noise reduction methods focus on passive sound insulation. However, low-frequency noise, such as low-frequency vibration of the engine and low-frequency noise generated by the contact between the tire and the road, has huge energy and long wavelength. This method is powerless to deal with low-frequency noise and it is difficult to effectively block it. This is because traditional sound insulation materials have relatively weak blocking ability against low-frequency noise, and low-frequency sound waves are like sharp needles that easily penetrate the "cloth" of sound insulation materials. In this way, people in the car can still clearly feel the low-frequency vibration and noise, which seriously affects the driving comfort and makes the originally pleasant driving journey noisy and unbearable.

[0004] Although some sound insulation materials have good heat insulation performance, this advantage may become a "stumbling block" for vehicle heat dissipation. For example, if too much sound insulation material is used in key parts such as the engine compartment, it is like putting on an overly thick "cotton coat" for the engine, which may seriously hinder the heat dissipation of the engine. Once the engine heat dissipation is not smooth, the temperature will rise sharply, which is like burying a "time bomb" for the health of the engine, greatly affecting the performance and life of the engine, and then affecting the normal operation and service life of the entire vehicle.

[0005] If passive noise reduction technology is to achieve a good noise reduction effect, it must be closely integrated with the vehicle's structural design. However, the complexity of the vehicle structure is beyond imagination. The vibration and noise transmission characteristics of different parts vary greatly, just like each part has its own unique "personality". This requires extremely precise structural design and optimization, which is undoubtedly a daunting challenge for automakers.

[0006] At the same time, active noise reduction technology has emerged in the field of headphones and other fields, showing excellent noise reduction capabilities, like a bright pearl shining in the field of noise reduction. Unfortunately, this technology is like a forgotten treasure in the field of vehicles and has not yet been fully explored and applied.

[0007] In addition, while working to reduce the noise inside the car, there is another key issue that cannot be ignored, that is, to ensure that the passengers in the car can clearly hear various important sounds, such as the voices of people talking, the sound of horns, the emergency sounds of ambulances, and other normal warning sounds that must be paid attention to during driving. This is like walking on a tightrope of noise reduction, and you must carefully maintain your balance, because only in this way can you ensure driving safety and avoid danger caused by not being able to hear warning sounds. Summary of the invention

[0008] In order to solve the problems that the passive noise reduction technology in the prior art has poor noise reduction effect, affects the driving comfort, affects the performance and life of the engine, and further affects the normal operation and service life of the entire vehicle, the embodiments of the present invention provide an adaptive noise elimination method, device and equipment.

[0009] According to an object of an embodiment of the present invention, there is provided an adaptive noise elimination method, comprising the following steps:

[0010] The noise signal of the vehicle's current driving scene is collected through the noise collection module;

[0011] Identify the collected noise signal to identify the type of the current noise signal;

[0012] When the noise signal is a low-frequency resonance noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonance noise; when the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified;

[0013] Display the current working status of the vehicle and receive corresponding operations from the driver according to the current working status.

[0014] In some optional implementations, the method further includes:

[0015] When the type of the noise signal is a low-frequency resonant noise signal, the intensity and frequency of the reverse sound wave signal are adjusted according to the current driving state of the vehicle monitored in real time;

[0016] When the type of the noise signal is a special sound signal, the function system corresponding to the special sound signal is communicated.

[0017] In some optional implementations, the current working status displayed includes the current noise reduction intensity and whether a special sound is detected;

[0018] Receiving a corresponding operation of the driver according to the current working state specifically includes:

[0019] Adjust the noise reduction intensity through the display and user interaction module;

[0020] and / or, setting a special sound reminder effect through a display and user interaction module;

[0021] And / or, intelligently reminding the driver through a display and user interaction module based on the detected special sound.

[0022] In some optional implementations, before the noise signal of the current driving scene of the vehicle is collected by the noise collection module, it is necessary to automatically adjust the collection parameters of the noise collection module according to the current driving scene of the vehicle.

[0023] In some optional implementations, the collection parameters of the noise collection module are automatically adjusted according to the current driving scene of the vehicle, specifically including:

[0024] The noise collection module collects the sound signal of the vehicle's current driving scene in real time, and processes the sound signal to obtain a real-time sound feature vector;

[0025] Identifying the sound feature vector by using a sound classification model, and determining the road scene to which the sound feature vector belongs according to the identification result;

[0026] The collection parameters of the noise collection module are automatically adjusted according to the road scene.

[0027] In some optional implementations, the method further includes:

[0028] Evaluate and analyze the recognition results of the sound classification model;

[0029] Compute evaluation metrics for sound classification models;

[0030] Optimize and improve the sound classification model based on the evaluation indicators.

[0031] In some optional implementations, the training of the sound classification model specifically includes:

[0032] The sound signals of different road scenes are collected through the noise collection module;

[0033] Analyze and process the collected sound signals to obtain the sound characteristics under different road scenes;

[0034] Process the extracted sound features to obtain a data set;

[0035] The selected sound classification model is trained and optimized using the data set to obtain a sound classification model that can accurately identify the differences in sound features under different road scenarios.

[0036] In some optional implementations, the current driving scene of the vehicle includes the vehicle's driving speed, road conditions, and weather conditions.

[0037] According to another object of an embodiment of the present invention, there is provided an adaptive noise elimination device, comprising: a data acquisition module, an audio processing module, a control module, and a display and user interaction module;

[0038] The data acquisition module is used to collect the noise signal of the current driving scene of the vehicle and send it to the audio processing module, and at the same time identify the current road scene according to the noise signal of the current driving scene, so as to automatically adjust the acquisition parameters of the noise acquisition module according to the road scene;

[0039] The audio processing module is used to identify the noise signal to identify whether the type of the current noise signal is a low-frequency resonance noise signal and / or a special sound signal; when the type of the noise signal is a low-frequency resonance noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonance noise; when the type of the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified;

[0040] The control module is used to adjust the intensity and frequency of the reverse sound wave signal according to the current driving state of the vehicle monitored in real time and the processing result of the noise signal, and at the same time realize the communication of the functional system corresponding to the special sound signal;

[0041] The display and user interaction module is used to display the current working state of the vehicle and receive corresponding operations from the driver according to the current working state.

[0042] According to another object of an embodiment of the present invention, there is provided an adaptive noise cancellation device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0043] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of any one of the above-mentioned adaptive noise elimination methods.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] The adaptive noise elimination method provided by the present invention eliminates the low-frequency noise generated by low-frequency resonance by generating a reverse sound wave signal based on the low-frequency resonance noise signal, thereby improving driving comfort and reducing the potential impact of noise on the driver's health; at the same time, special filtering and clarification processing are performed on the normal warning sounds that need to be paid attention to during vehicle driving, ensuring that the driver can clearly hear the normal warning sounds inside and outside the vehicle to ensure driving safety. In addition, the driver can also understand the current working status of the vehicle in real time and perform corresponding operations, which enhances the user experience. Therefore, the adaptive noise elimination method realizes an intelligent and adaptive vehicle noise control and special sound processing system, which overcomes the problem that traditional vehicle noise reduction methods have poor low-frequency noise processing effects and cannot take into account special sound recognition.

[0046] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0048] Figure 1 A schematic flow chart of an adaptive noise elimination method provided by an embodiment of the present invention is shown;

[0049] Figure 2 A schematic diagram of a process flow of adaptively adjusting acquisition parameters of a noise acquisition module in an adaptive noise elimination method provided by an embodiment of the present invention is shown;

[0050] Figure 3 A schematic diagram of a training process of a sound classification model in an adaptive noise elimination method provided by an embodiment of the present invention is shown;

[0051] Figure 4 A schematic structural diagram of an adaptive noise elimination device provided by an embodiment of the present invention is shown;

[0052] Figure 5 A schematic structural diagram of an adaptive noise elimination device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0053] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0054] In order to solve the problems that the passive noise reduction technology in the prior art has poor noise reduction effect, affects the driving comfort, affects the performance and life of the engine, and further affects the normal operation and service life of the entire vehicle, this embodiment provides an adaptive noise elimination method.

[0055] Figure 1 A schematic flow chart of an adaptive noise elimination method provided by an embodiment of the present invention is shown.

[0056] This embodiment provides an adaptive noise elimination method, such as Figure 1 As shown, the following steps are included:

[0057] S10. Collect the noise signal of the current driving scene of the vehicle through the noise collection module.

[0058] In this step, noise collection modules are set at multiple locations inside and outside the vehicle to collect various noise signals during the driving process of the vehicle, including various types of noise factors generated by the vehicle itself and various types of noise outside the driving scene.

[0059] In this step, the noise collection module continuously collects noise signals during normal driving of the vehicle.

[0060] S20. Identify the collected noise signal to identify the type of the current noise signal.

[0061] In this step, after the noise signal is collected by the noise collection module, the noise signal parameters are analyzed by the audio processing module using digital signal processing algorithms such as Fast Fourier Transform (FFT) to identify the type of the noise signal.

[0062] In this embodiment, the types of noise signals mainly include low-frequency resonant noise signals and special sound signals generated when the vehicle encounters bumpy roads, and the special sound signals include various alarm or reminder sound signals generated by the vehicle itself and various special alarm sound signals near the vehicle.

[0063] The various special alarm sound signals near the vehicle include ambulance sirens, fire truck sirens, police car sirens, sprinkler truck warning sounds, etc.

[0064] S30. When the type of the noise signal is a low-frequency resonant noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonant noise; when the type of the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified.

[0065] In this step, the corresponding processing of the identified noise signal is mainly realized.

[0066] For example, when the type of noise signal is a low-frequency resonant noise signal, the noise signal is processed and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonant noise, thereby improving driving comfort and reducing the potential impact of noise on the driver's health.

[0067] When the type of noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified to ensure that the driver can clearly hear the normal warning sounds inside and outside the vehicle to ensure driving safety.

[0068] S40. Display the current working state of the vehicle, and receive corresponding operations from the driver according to the current working state.

[0069] In this step, the current working state of the vehicle is displayed through the display and user interaction module, so that the driver can interact with the display and user interaction module, thereby receiving the corresponding operation of the driver according to the current working state.

[0070] For example, the current working status displayed includes the current noise reduction intensity, whether special sounds are detected, etc.

[0071] Then, the corresponding operation of the driver is received according to the current working state, including:

[0072] The driver adjusts the noise reduction intensity through the display and user interaction module, so that the display and user interaction module receives the driver's operation of adjusting the noise reduction intensity.

[0073] And / or, the driver sets a reminder effect of a special sound through the display and user interaction module, so that the display and user interaction module receives the driver's operation on the special sound setting.

[0074] And / or, the driver is intelligently reminded through the display and user interaction module according to the detected special sound.

[0075] Specifically, the display and user interaction module displays the current noise reduction intensity, whether special sounds are detected, etc.

[0076] The driver can adjust the noise reduction intensity, turn on or off specific functions, including turning on or off the reminder function of special sounds, or adjusting the volume of special sounds through the display and user interaction module or the steering wheel multi-function button operating system.

[0077] In addition, when special sound types that occur frequently are identified, the display and user interaction module will prompt the driver of possible changes in road conditions, and can be linked with the vehicle's navigation system to provide the driver with more comprehensive driving assistance information.

[0078] For example, if the system detects frequent ambulance sirens, it will remind the driver that there may be a hospital nearby and that the driver should be careful of pedestrians.

[0079] The adaptive noise elimination method provided in this embodiment eliminates the low-frequency noise generated by low-frequency resonance by generating a reverse sound wave signal based on the low-frequency resonance noise signal, thereby improving driving comfort and reducing the potential impact of noise on the driver's health; at the same time, special filtering and clarification processing are performed on the normal warning sounds that need to be paid attention to during vehicle driving, ensuring that the driver can clearly hear the normal warning sounds inside and outside the vehicle to ensure driving safety. In addition, the driver can also understand the current working status of the vehicle in real time and perform corresponding operations, which enhances the user experience. Therefore, the adaptive noise elimination method realizes an intelligent and adaptive vehicle noise control and special sound processing system, which overcomes the problem that the traditional vehicle noise reduction method has poor low-frequency noise processing effect and cannot take into account the special sound recognition.

[0080] In this embodiment, which is a preferred embodiment, the noise collection module adopts a high-sensitivity microphone and is provided with an amplifier connected to the microphone to ensure that it can accurately collect low-frequency resonance noise and other noise signals in complex environments.

[0081] Microphones are installed under the seats, inside the doors, on the chassis and other places prone to low-frequency resonance, as well as near the front and rear bumpers on the outside of the vehicle, to collect various noises generated by the vehicle itself and various external warning sounds in the vehicle driving scene.

[0082] In this embodiment, after the noise collection module collects the noise signal of the current driving scene of the vehicle, it sends it to the audio processing module for recognition processing.

[0083] When the vehicle encounters a bumpy road and generates low-frequency resonance noise, the noise collection module collects the low-frequency resonance noise signal, amplifies it through a preamplifier, and transmits it to the audio processing module.

[0084] After receiving the noise signal collected by the noise collection module, the audio processing module performs a digital signal processing algorithm such as a fast Fourier transform (FFT) to analyze the noise signal parameters to identify the type of the noise signal.

[0085] When the type of noise signal is a low-frequency resonance noise signal, the noise signal is subjected to digital signal processing such as fast Fourier transform (FFT) to determine parameters such as frequency, amplitude and phase of the low-frequency resonance noise signal, and then an amplifier is used to generate a reverse sound wave signal with corresponding parameters such as frequency, amplitude and phase to offset the low-frequency resonance noise.

[0086] When the type of noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified so that the driver can clearly hear the normal warning sounds inside and outside the vehicle to ensure driving safety.

[0087] In addition, in this embodiment, when the type of the noise signal is a low-frequency resonance noise signal, the intensity and frequency of the reverse sound wave signal are adjusted according to the current driving state of the vehicle monitored in real time.

[0088] For example, when the current driving state of the vehicle is that the engine and road noise increase when the vehicle accelerates, the intensity and frequency of the reverse sound wave signal are adjusted through the control module.

[0089] When the type of noise signal is a special sound signal, the control module communicates with the functional system corresponding to the special sound signal to ensure that the system works in coordination with functions such as navigation voice prompts and vehicle fault alarms without conflict.

[0090] Finally, the current working state of the vehicle is displayed through the set display and user interaction module, so that the driver can interact with the display and user interaction module and perform corresponding operations according to the current working state.

[0091] This embodiment is a preferred embodiment. Before the noise collection module collects the noise signal of the current driving scene of the vehicle, it is necessary to automatically adjust the collection parameters of the noise collection module according to the current driving scene of the vehicle so that the collection parameters of the noise collection module are adapted to the current driving scene of the vehicle.

[0092] Preferably, the collection parameters of the noise collection module are automatically adjusted according to the current driving scene of the vehicle, such as Figure 2 As shown, specifically including:

[0093] S101. The noise collection module collects the sound signal of the current driving scene of the vehicle in real time, and processes the sound signal to obtain a real-time sound feature vector.

[0094] This step specifically includes: collecting the sound signal of the vehicle's current driving scene in real time through the noise collection module;

[0095] The collected sound signals are preprocessed and feature extracted to obtain real-time sound feature vectors.

[0096] S102. Identify the sound feature vector using a sound classification model, and determine the road scene to which the sound feature vector belongs based on the identification result.

[0097] This step is specifically as follows: the identified sound feature vector is input into the trained sound classification model, and the sound classification model will output the corresponding scene category prediction result. It can also be understood that the sound classification model will output the road scene to which the current sound signal belongs.

[0098] Among them, road scenes include urban roads, highways or country roads, etc., and urban roads, highways or country roads will also be combined with weather conditions during the identification process, such as rain, snow, fog and other environments that affect sound propagation, to determine the current driving scene of the vehicle.

[0099] S103. Automatically adjust the collection parameters of the noise collection module according to the road scene.

[0100] This step specifically includes: automatically adjusting the collection sensitivity and collection frequency of the noise collection module according to the road scene to which the current sound signal identified in the above step belongs, combined with the vehicle's driving speed and the current weather conditions.

[0101] That is, it can be understood that the current driving scene of the vehicle includes the vehicle's driving speed, road conditions and weather conditions.

[0102] For example, when driving at high speeds, the focus is on improving the sensitivity of collecting special alarm sounds from long distances, and enhancing the ability to distinguish sounds in bad weather.

[0103] This embodiment is a preferred embodiment. After completing the sound signal recognition of the current driving scene of the vehicle, the recognition result of the sound classification model is evaluated and analyzed. Then the evaluation index of the sound classification model is calculated, including the calculation accuracy, recall rate, F1 value, etc. of the sound classification model, to measure the performance of the sound classification model; the sound classification model is optimized and improved according to the evaluation index to improve the accuracy and reliability of vehicle driving scene recognition. At the same time, the recognition results can also be fed back and processed accordingly according to the needs of actual applications, such as issuing an alarm, recording data, etc.

[0104] This embodiment is a preferred embodiment, the training of the sound classification model, such as Figure 3 As shown, specifically including:

[0105] S1021. Collect sound signals of different road scenes through the noise collection module.

[0106] This step includes: firstly selecting a professional audio acquisition device as a noise acquisition module, for example, using the high-sensitivity microphone mentioned above to ensure that the sound signals of various environments can be accurately captured.

[0107] During this process, attention should be paid to parameters such as the frequency response range and sensitivity of the noise collection module to meet the needs of sound collection in different road scenarios.

[0108] In addition, determine the audio collection locations and select representative locations for sound collection in different types of road scenes, such as urban roads, highways, and country roads.

[0109] For example, collection points can be set up at intersections of urban roads, service areas of highways, near farmland on rural roads, and other locations.

[0110] Set the collection time, consider the sound characteristics of different time periods, such as weekdays and holidays, daytime and nighttime, etc., and collect data separately to obtain comprehensive sound data.

[0111] Set the collection duration. The duration of each collection can be determined based on actual conditions. It is generally recommended to be no less than 10 minutes to ensure that various sound events in the scene can be covered.

[0112] S1022. Analyze and process the collected sound signals to obtain sound characteristics under different road scenes.

[0113] This step includes:

[0114] Perform a fast Fourier transform (FFT) on the collected sound signal to convert the time domain signal into a frequency domain signal to obtain the sound spectrum. By analyzing the frequency distribution, peak position, amplitude and other information in the spectrum, the spectrum characteristics of the sound in different scenarios can be extracted.

[0115] For example, the sound spectrum of a city road may have more mid- and low-frequency components, while the sound spectrum of a country road may be dominated by mid- and high-frequency components.

[0116] Mel-frequency cepstral coefficients (MFCC) are used to perform nonlinear transformation on the spectral characteristics of the sound signal to obtain the feature vector of the sound.

[0117] Calculate the energy distribution of sound signals in different frequency bands or time windows to obtain the energy characteristics of the sound.

[0118] The sound energy distribution in different scenarios will be different. For example, the sound energy of vehicles driving on highways is usually larger and more concentrated, while the sound energy of country roads is relatively small and more evenly distributed.

[0119] S1023. Process the extracted sound features to obtain a data set.

[0120] This step includes:

[0121] The extracted sound features are normalized or standardized to have the same scale and distribution range to avoid affecting the training effect of the sound classification model due to large differences in feature values.

[0122] During the training process of the sound classification model, the dataset is divided into a training set, a validation set, and a test set, usually in a ratio of 7:2:1 or 8:1:1.

[0123] S1024. Use the data set to train and optimize the selected sound classification model to obtain a sound classification model that can accurately identify the differences in sound features under different road scenarios.

[0124] This step is as follows: First, select a sound classification model. Common sound classification models include support vector machine (SVM), decision tree, random forest, neural network, etc. Select a suitable sound classification model based on specific application requirements and data characteristics. For example, for small-scale data sets, decision trees or random forests may perform better; while for large-scale and complex sound data, neural networks may have more advantages.

[0125] The selected sound classification model is trained using the training set. By adjusting the parameters and hyperparameters of the sound classification model, such as the number of neural network layers, the number of neurons, the learning rate, etc., the sound classification model can accurately learn the differences in sound features in different scenarios.

[0126] During the training process, the validation set is used to evaluate and monitor the performance of the sound classification model to prevent overfitting.

[0127] According to the evaluation results of the validation set, the sound classification model is continuously optimized and adjusted through the test set until satisfactory performance is achieved, thereby obtaining a sound classification model that can accurately identify the differences in sound features in different road scenarios.

[0128] The sound classification model is then used in an adaptive noise elimination method to identify the specific vehicle's current driving scene based on the sound signals of the vehicle's current driving scene collected in real time by the noise collection module, and to automatically adjust the collection parameters of the noise collection module based on the vehicle's current driving scene.

[0129] In some optional embodiments, the present invention also discloses an adaptive noise elimination device.

[0130] like Figure 4 As shown, the adaptive noise elimination device includes: a data acquisition module 100 , an audio processing module 200 , a control module 300 and a display and user interaction module 400 .

[0131] Among them, the data acquisition module 100 is used to collect the noise signal of the current driving scene of the vehicle and send it to the audio processing module 200, and at the same time identify the current road scene according to the noise signal of the current driving scene to automatically adjust the acquisition parameters of the noise acquisition module according to the road scene.

[0132] The audio processing module 200 is used to identify the noise signal to identify whether the type of the current noise signal is a low-frequency resonance noise signal and / or a special sound signal; when the type of the noise signal is a low-frequency resonance noise signal, the noise signal is processed and a corresponding reverse sound wave signal is generated based on the processing result to offset the low-frequency resonance noise; when the type of the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified.

[0133] The control module 300 is used to adjust the intensity and frequency of the reverse sound wave signal according to the current driving state of the vehicle monitored in real time and the processing result of the noise signal, and at the same time realize the functional system communication corresponding to the special sound signal.

[0134] The display and user interaction module 400 is used to display the current working state of the vehicle and receive corresponding operations from the driver according to the current working state.

[0135] In this embodiment, the selection type, setting position and implementation process of the data acquisition module 100 refer to the implementation process of the above-mentioned adaptive noise elimination method, and this embodiment will not repeat them.

[0136] The specific processing process of the audio processing module 200 on the noise signal of the current driving scene of the vehicle collected by the data collection module 100 refers to the implementation process in the above-mentioned adaptive noise elimination method, which will not be repeated in this embodiment.

[0137] The control module 300 coordinates the work of each module on the noise signal processed by the audio processing module 200 according to the vehicle driving scene. For details, please refer to the implementation process in the above-mentioned adaptive noise elimination method, which will not be repeated in this embodiment.

[0138] The display and user interaction module 400 displays the current working status of the vehicle, so that the display and user interaction module 400 receives the corresponding operation of the driver according to the current working status. The display and user interaction module 400 receives the corresponding operation process of the driver according to the current working status. Please refer to the implementation process in the above-mentioned adaptive noise elimination method for details, which will not be repeated in this embodiment.

[0139] In some optional embodiments, the present invention also discloses an adaptive noise cancellation device.

[0140] Figure 5 A schematic structural diagram of an adaptive noise elimination device provided by an embodiment of the present invention is shown.

[0141] like Figure 5As shown, the adaptive noise cancellation device includes: a processor 510 , a memory 520 , a communication interface 530 and a communication bus 540 . The processor 510 , the memory 520 and the communication interface 530 communicate with each other through the communication bus 540 .

[0142] In this embodiment, the memory 520 is used to store at least one executable instruction, and the executable instruction enables the processor 520 to perform the operation of the adaptive noise elimination method as described in any of the above embodiments; the communication interface 530 is used to communicate with other devices such as a client or other server network elements. The processor 510 is used to execute the program 550, which can specifically execute the relevant steps in the above adaptive noise elimination method embodiment.

[0143] Specifically, the program 550 may include program code including computer-executable instructions.

[0144] The processor 510 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the real vehicle driving assistance lateral control device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0145] The memory 520 is used to store the program 550. The memory 520 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0146] The program 550 may be specifically called by the processor 510 to enable the adaptive noise cancellation device to perform the operations of the adaptive noise cancellation method described in any of the above embodiments.

[0147] In some optional embodiments, the embodiments of the present invention further disclose a computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium. When the executable instruction is executed on an adaptive noise cancellation device / apparatus, the adaptive noise cancellation device / apparatus executes the steps of the adaptive noise cancellation method in any of the above method embodiments.

[0148] The specific implementation process of the adaptive noise elimination method described in this embodiment can be found in any of the above method embodiments, which will not be repeated in this embodiment.

[0149] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0150] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0151] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. An adaptive noise cancellation method, characterized in that: The following steps are involved: The noise signal of the vehicle's current driving scene is collected through the noise collection module; Identify the collected noise signal to identify the type of the current noise signal; When the noise signal is a low-frequency resonance noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonance noise; when the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified; Display the current working status of the vehicle and receive corresponding operations from the driver according to the current working status.

2. The adaptive noise cancellation method according to claim 1, characterized in that: Also includes: When the type of the noise signal is a low-frequency resonant noise signal, the intensity and frequency of the reverse sound wave signal are adjusted according to the current driving state of the vehicle monitored in real time; When the type of the noise signal is a special sound signal, the function system corresponding to the special sound signal is communicated.

3. The adaptive noise cancellation method according to claim 1, characterized in that: The current working status displayed includes the current noise reduction strength and whether special sounds are detected; Receiving a corresponding operation of the driver according to the current working state specifically includes: Adjust the noise reduction intensity through the display and user interaction module; and / or, setting a special sound reminder effect through a display and user interaction module; And / or, intelligently reminding the driver through a display and user interaction module based on the detected special sound.

4. The adaptive noise cancellation method according to claim 1, characterized in that: Before the noise signal of the current driving scene of the vehicle is collected by the noise collection module, it is necessary to automatically adjust the collection parameters of the noise collection module according to the current driving scene of the vehicle.

5. The adaptive noise cancellation method according to claim 4, characterized in that: Automatically adjust the collection parameters of the noise collection module according to the current driving scene of the vehicle, including: The noise collection module collects the sound signal of the vehicle's current driving scene in real time, and processes the sound signal to obtain a real-time sound feature vector; Identifying the sound feature vector by using a sound classification model, and determining the road scene to which the sound feature vector belongs according to the identification result; The collection parameters of the noise collection module are automatically adjusted according to the road scene.

6. The adaptive noise cancellation method according to claim 5, characterized in that: Also includes: Evaluate and analyze the recognition results of the sound classification model; Compute evaluation metrics for sound classification models; Optimize and improve the sound classification model based on the evaluation indicators.

7. The adaptive noise cancellation method according to claim 5, characterized in that: The training of the sound classification model specifically includes: The sound signals of different road scenes are collected through the noise collection module; Analyze and process the collected sound signals to obtain the sound characteristics under different road scenes; Process the extracted sound features to obtain a data set; The selected sound classification model is trained and optimized using the data set to obtain a sound classification model that can accurately identify the differences in sound features under different road scenarios.

8. The adaptive noise cancellation method according to claim 1, characterized in that: The current driving scene of the vehicle includes the vehicle's driving speed, road conditions and weather conditions.

9. An adaptive noise cancellation device, characterized in that: include: Data acquisition module, audio processing module, control module and display and user interaction module; The data acquisition module is used to collect the noise signal of the current driving scene of the vehicle and send it to the audio processing module, and at the same time identify the current road scene according to the noise signal of the current driving scene, so as to automatically adjust the acquisition parameters of the noise acquisition module according to the road scene; The audio processing module is used to identify the noise signal to identify whether the type of the current noise signal is a low-frequency resonance noise signal and / or a special sound signal; when the type of the noise signal is a low-frequency resonance noise signal, the noise signal is processed, and a corresponding reverse sound wave signal is generated according to the processing result to offset the low-frequency resonance noise; when the type of the noise signal is a special sound signal, the noise signal is identified and filtered, amplified and clarified; The control module is used to adjust the intensity and frequency of the reverse sound wave signal according to the current driving state of the vehicle monitored in real time and the processing result of the noise signal, and at the same time realize the communication of the functional system corresponding to the special sound signal; The display and user interaction module is used to display the current working state of the vehicle and receive corresponding operations from the driver according to the current working state.

10. An adaptive noise cancellation device, characterized in that include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the adaptive noise elimination method as described in any one of claims 1-8.

Images