Dynamic sound field adjustment system and method based on passenger position perception

Abstract

The present invention discloses a dynamic sound field adjustment system and method based on passenger position perception, and relates to the technical field of vehicle-mounted audio systems. The system includes a data acquisition module for real-time acquisition of passenger position data, vehicle status data, acoustic environment data, and user personalized demand data, and preprocessing; a data processing module extracts and fuses features of the preprocessed data to generate a multi-dimensional sound field feature vector, constructs an objective function, and solves the objective function using a genetic algorithm to output optimal sound field adjustment parameters; a strategy decision module selects an applicable adjustment strategy from a sound field adjustment strategy library according to the optimal sound field adjustment parameters; a parameter execution module dynamically adjusts the sound field center point position, frequency equalization parameters, and noise reduction compensation parameters according to the adjustment strategy to achieve closed-loop optimization of the sound field. The present invention can improve the sound quality balance and noise reduction effect of the vehicle-mounted audio system, and meet the personalized needs of multiple scenarios and multiple passengers.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted audio systems, and in particular to a dynamic sound field adjustment system and method based on passenger position perception. Background Art

[0002] As an important part of automotive intelligence, the in-vehicle audio system has been widely used to improve driving comfort and user experience. Current in-vehicle audio technology usually achieves sound optimization through fixed sound field parameters, combined with simple equalizer adjustments or preset sound modes to meet basic needs in different scenarios. At the same time, active noise reduction technology is gradually applied to the in-vehicle environment to reduce environmental noise interference by generating reverse sound waves. However, the existing system mainly adjusts the overall in-vehicle environment uniformly, lacks accurate perception and optimization of individual passenger positions, resulting in limitations in sound field effects and noise reduction performance.

[0003] The existing in-car audio technology has the following main problems: the sound field adjustment lacks dynamic adaptability and is difficult to adjust in real time according to the vehicle's driving status, passenger position and changes in ambient noise; the noise reduction technology fails to fully consider the actual needs of each passenger in the car and cannot achieve accurate noise reduction based on the passenger's position; in multi-passenger scenarios, the system usually prioritizes the driver's position and ignores the sound effects requirements of other passenger positions, resulting in insufficient sound field balance and poor overall sound quality experience. These problems are particularly evident in complex driving scenarios and multi-person commuting.

[0004] Therefore, there is an urgent need for a dynamic sound field adjustment system and method based on passenger position perception to achieve personalized optimization of the sound field and precise noise reduction, especially to improve the overall sound balance in multi-passenger scenarios and meet the personalized needs of different passengers. Summary of the invention

[0005] The present invention provides a dynamic sound field adjustment system and method based on passenger position perception, which realizes personalized optimization of the sound field and accurate generation of noise reduction signals by dynamically collecting passenger position and vehicle status data.

[0006] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0007] Dynamic sound field adjustment system based on passenger position perception, including:

[0008] Data collection module, used to collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing;

[0009] The data processing module is used to extract features from the preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, solve the objective function using a genetic algorithm, and output the optimal sound field adjustment parameters;

[0010] A strategy decision module, used for selecting an adjustment strategy from a sound field adjustment strategy library according to the optimal sound field adjustment parameters;

[0011] The parameter execution module is used to dynamically adjust the sound field center point position, frequency equalization parameters and noise reduction compensation parameters according to the adjustment strategy to achieve closed-loop optimization of the sound field.

[0012] As a preferred solution of the present invention, the data processing module includes:

[0013] A feature extraction unit is used to extract data features, including location features, state parameters, noise characteristics, and user preferences;

[0014] A feature fusion unit is used to fuse the extracted features to generate a multi-dimensional sound field feature vector;

[0015] An objective function construction unit, used to generate an optimization objective function according to the received multi-dimensional sound field feature vector;

[0016] The algorithm optimization unit is used to solve the optimization objective function based on the genetic algorithm and output the optimal sound field adjustment parameters.

[0017] Preferably, the objective function construction unit is implemented by the following steps:

[0018] Multidimensional sound field feature vector It is expressed as:

[0019] ;

[0020] in, Indicates The standardized value of the feature;

[0021] Defining optimization objective function based on multi-dimensional sound field feature vector for:

[0022] ;

[0023] in, Indicates The sound quality rating of each passenger at the center of the sound field, is the passenger weight, is the noise suppression weight, is the environmental noise interference function; Indicates the number of passengers in the current car; is the number of multi-dimensional sound field feature vectors; j Indicates j The index of the noise source; A variable representing a multi-dimensional sound field feature vector.

[0024] As a preferred solution of the present invention, the data acquisition module includes:

[0025] A passenger position data acquisition unit, which is used to collect the passenger's sitting posture distribution and position change data through a seat pressure sensor, collect the passenger's dynamic position characteristics through an in-vehicle camera, and generate the passenger's three-dimensional position coordinates using an image processing algorithm;

[0026] The vehicle status data acquisition unit is used to obtain the vehicle's speed, acceleration, braking status and driving mode through the vehicle system interface;

[0027] An acoustic environment data acquisition unit, used to collect the spectrum and sound pressure level of the noise signal inside the vehicle through a noise sensor;

[0028] The user personalized demand data collection unit is used to collect the user's volume, sound field positioning and noise reduction demand settings through the vehicle-machine interaction interface or mobile application.

[0029] Preferably, the algorithm optimization unit is implemented by the following steps:

[0030] receiving an optimization objective function generated by an objective function building unit;

[0031] Based on the parameter space defined by the optimization objective function, an initial optimization scheme set is generated, each set of optimization schemes consists of a sound field center point position, a frequency equalization parameter, and a noise reduction compensation parameter;

[0032] Calculate the fitness value of each group of optimization solutions for:

[0033] ;

[0034] in, Indicates The degree of violation of a constraint, is the penalty factor;

[0035] According to the fitness value, the roulette algorithm is used to select the solution with the highest fitness among the optimization solutions to enter the next round of optimization;

[0036] Perform crossover operation on the selected optimization scheme with crossover probability to generate a new optimization scheme:

[0037] ;

[0038] in, For the new optimization solution, and There are two existing optimization solutions: is the cross-proportional coefficient;

[0039] Adjust the parameters of the optimization scheme based on the mutation probability:

[0040] ;

[0041] in, To optimize the solution after mutation, To optimize the solution before mutation, is the random variation value;

[0042] Determine whether the following conditions are met: the maximum change rate of the fitness value of the optimization scheme is lower than the threshold or the number of iterations reaches the preset upper limit. If not, recalculate the fitness value of each group of optimization schemes;

[0043] When the convergence conditions are met, the optimization scheme with the highest fitness value is output as the optimal sound field adjustment parameters, including the sound field center point position, frequency equalization parameters and noise reduction compensation parameters.

[0044] As a preferred solution of the present invention, the policy decision module includes:

[0045] The strategy selection unit is used to select an adjustment strategy that matches the optimal sound field adjustment parameters from a sound field adjustment strategy library, wherein the sound field adjustment strategy library includes preset strategies for different scenarios such as high-speed driving, city driving and parking.

[0046] As a preferred solution of the present invention, the parameter execution module includes:

[0047] The sound field positioning unit is used to dynamically position the center point of the sound field by adjusting the output power and direction of the speaker;

[0048] Frequency equalization unit, used to optimize the gain parameters of the audio low frequency 20Hz to 250Hz, mid-frequency 250Hz to 4kHz and high frequency 4kHz to 20kHz bands;

[0049] The noise reduction control unit is used to reduce the interference of ambient noise on the sound field by generating reverse sound waves using active noise reduction technology.

[0050] Preferably, the noise reduction control unit reduces noise interference by using active noise reduction technology through the following steps:

[0051] The vehicle-mounted noise sensor is used to obtain the in-vehicle environmental noise signal in real time and analyze the frequency, phase and amplitude characteristics of the noise signal;

[0052] Combine the environmental dynamic parameters and passenger position data in the car to extract the noise characteristics that interfere with the center of the sound field and generate noise parameters for noise reduction calculation;

[0053] Based on the noise parameters, a reverse acoustic wave signal with a phase opposite to the target noise and matching amplitude is dynamically calculated;

[0054] The reverse sound wave signal is output through the vehicle speaker and superimposed with the target noise signal to reduce the interference of the target noise on the center of the sound field.

[0055] Preferably, the noise reduction control unit further comprises:

[0056] Based on the passenger position data and the speed, acceleration and braking status of the vehicle, the three-dimensional spatial position of the noise source is dynamically calculated to generate the noise source position information;

[0057] Combine the noise source location information and the three-dimensional position coordinates of the passenger to calculate the spatial relationship between the passenger and the noise source, and dynamically adjust the range of the noise reduction signal;

[0058] Based on passenger weight priorities, noise reduction compensation parameters are dynamically optimized to improve the noise reduction effect in multi-passenger scenarios.

[0059] The method for adjusting a dynamic sound field adjustment system based on passenger position perception comprises the following steps:

[0060] S1. Collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing;

[0061] S2. Extract features from the preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, solve the objective function using a genetic algorithm, and generate optimal adjustment parameters;

[0062] S3 selects a sound field adjustment strategy from the sound field adjustment strategy library according to the optimal adjustment parameters;

[0063] S4. According to the instructions of the adjustment strategy, the center point position of the sound field, frequency equalization parameters and noise reduction compensation parameters are adjusted to complete the closed-loop optimization of the sound field.

[0064] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention collects passenger position data, vehicle status data, acoustic environment data and user personalized demand data in real time, and dynamically adjusts the sound field center position, frequency equalization parameters and noise reduction compensation parameters based on these data. The system can provide each passenger with accurate personalized sound field optimization, significantly improving the comfort and user experience of the in-car sound effect. Combining multi-dimensional sound field feature vectors and active noise reduction technology, the system significantly reduces the interference of environmental noise by generating reverse sound waves. In particular, in multi-passenger scenarios, the system can dynamically optimize the noise reduction signal according to the passenger position and weight priority to ensure that each passenger enjoys a clear sound field effect. The system uses a genetic algorithm to solve the optimization objective function generated by the multi-dimensional sound field feature vector, quickly responds to the dynamic changes of the vehicle driving state, passenger position and environmental noise, realizes the closed-loop optimization of the sound field parameters, and ensures that stable and high-quality sound effects are provided under different driving modes. The system significantly improves the optimization accuracy of the sound field adjustment parameters by integrating multi-dimensional features such as position, state, noise and user preferences, avoiding the limitations of the traditional vehicle audio system in uniformly adjusting the overall environment. The system has a built-in library of various preset sound field adjustment strategies, covering different scenarios such as high-speed driving, urban driving and parking, and can flexibly adapt to a variety of complex driving scenarios. In addition, the system can be seamlessly integrated with existing vehicle interfaces, sensors and mobile applications, improving the adaptability and versatility of the overall solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0066] Figure 1 It is a schematic diagram of the modular structure of the system of the present invention;

[0067] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0069] Traditional in-vehicle audio systems have problems such as lack of dynamic adaptability of sound field adjustment, low noise reduction accuracy, and unbalanced sound field in multi-passenger scenarios. It is difficult to optimize the sound field according to real-time changes in vehicle status, passenger position, etc. The noise reduction scheme is usually based on a global noise model, ignoring the actual noise interference to passengers, and it is difficult to achieve personalized sound field adjustment in multi-passenger scenarios. The present invention introduces dynamic data acquisition and intelligent processing technology, proposes a dynamic sound field adjustment system and method based on passenger position perception, realizes personalized optimization and precise noise reduction of the sound field, and dynamically balances the sound effect requirements of each position in multi-passenger scenarios.

[0070] like Figure 1 FIG. 1 is an embodiment of the present invention, which provides a dynamic sound field adjustment system based on passenger position perception, including:

[0071] (1) Data acquisition module

[0072] Used to collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing;

[0073] The data acquisition module includes:

[0074] A passenger position data acquisition unit, which is used to collect the passenger's sitting posture distribution and position change data through a seat pressure sensor, collect the passenger's dynamic position characteristics through an in-vehicle camera, and generate the passenger's three-dimensional position coordinates using an image processing algorithm;

[0075] The vehicle status data acquisition unit is used to obtain the vehicle's speed, acceleration, braking status and driving mode through the vehicle system interface to form a data stream describing the vehicle's dynamic behavior;

[0076] An acoustic environment data acquisition unit, used to collect the spectrum and sound pressure level of the noise signal inside the vehicle through a noise sensor;

[0077] The user personalized demand data collection unit is used to collect the user's volume, sound field positioning and noise reduction demand settings through the vehicle-machine interaction interface or mobile application.

[0078] The collected multi-source data is preprocessed, including data normalization, denoising and time synchronization, to ensure the consistency and accuracy of each data stream.

[0079] (2) Data processing module

[0080] It is used to extract features from preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, use an optimization algorithm to solve the objective function, and output the optimal sound field adjustment parameters;

[0081] The data processing module includes:

[0082] A feature extraction unit is used to extract data features, including location features, state parameters, noise characteristics, and user preferences;

[0083] A feature fusion unit is used to fuse the extracted features to generate a multi-dimensional sound field feature vector;

[0084] An objective function construction unit, used to generate an optimization objective function according to the received multi-dimensional sound field feature vector;

[0085] The algorithm optimization unit is used to solve the optimization objective function based on the genetic algorithm and output the optimal sound field adjustment parameters.

[0086] In one embodiment, the objective function construction unit is implemented by the following steps:

[0087] Multidimensional sound field feature vector It is expressed as:

[0088] ;

[0089] in, Indicates The standardized value of the feature;

[0090] Defining optimization objective function based on multi-dimensional sound field feature vector for:

[0091] ;

[0092] in, Indicates The sound quality rating of each passenger at the center of the sound field, is the passenger weight, is the noise suppression weight, is the environmental noise interference function; Indicates the number of passengers in the current car; is the number of multi-dimensional sound field feature vectors; j Indicates j The index of the noise source; A variable representing a multi-dimensional sound field feature vector.

[0093] The algorithm optimization unit is implemented through the following steps:

[0094] receiving an optimization objective function generated by an objective function building unit;

[0095] Based on the parameter space defined by the optimization objective function, an initial optimization scheme set is generated, each set of optimization schemes consists of a sound field center point position, a frequency equalization parameter, and a noise reduction compensation parameter;

[0096] Calculate the fitness value of each group of optimization solutions for:

[0097] ;

[0098] in, Indicates The degree of violation of a constraint, is the penalty factor;

[0099] According to the fitness value, the roulette algorithm is used to select the solution with the highest fitness among the optimization solutions to enter the next round of optimization;

[0100] Perform crossover operation on the selected optimization scheme with crossover probability to generate a new optimization scheme:

[0101] ;

[0102] in, For the new optimization solution, and There are two existing optimization solutions: is the cross-proportional coefficient;

[0103] Adjust the parameters of the optimization scheme based on the mutation probability:

[0104] ;

[0105] in, To optimize the solution after mutation, To optimize the solution before mutation, is the random variation value;

[0106] Determine whether the following conditions are met: the maximum change rate of the fitness value of the optimization scheme is lower than the threshold or the number of iterations reaches the preset upper limit. If not, recalculate the fitness value of each group of optimization schemes;

[0107] When the convergence conditions are met, the optimization scheme with the highest fitness value is output as the optimal sound field adjustment parameters, including the sound field center point position, frequency equalization parameters and noise reduction compensation parameters.

[0108] (3) Strategy decision module

[0109] for selecting an adjustment strategy from a sound field adjustment strategy library according to the optimal sound field adjustment parameters;

[0110] The policy decision module includes:

[0111] The strategy selection unit is used to select an adjustment strategy that matches the optimal sound field adjustment parameters from a sound field adjustment strategy library, wherein the sound field adjustment strategy library includes preset strategies for different scenarios such as high-speed driving, city driving and parking.

[0112] (4) Parameter execution module

[0113] It is used to dynamically adjust the center point position of the sound field, frequency equalization parameters and noise reduction compensation parameters according to the adjustment strategy to achieve closed-loop optimization of the sound field.

[0114] The parameter execution module includes:

[0115] The sound field positioning unit is used to dynamically position the center point of the sound field by adjusting the output power and direction of the speaker;

[0116] Frequency equalization unit, used to optimize the gain parameters of the audio low frequency 20Hz to 250Hz, mid-frequency 250Hz to 4kHz and high frequency 4kHz to 20kHz bands;

[0117] The noise reduction control unit is used to reduce the interference of ambient noise on the sound field by generating reverse sound waves using active noise reduction technology.

[0118] In one embodiment, the noise reduction control unit reduces noise interference by using active noise reduction technology through the following steps:

[0119] The vehicle-mounted noise sensor is used to obtain the in-vehicle environmental noise signal in real time and analyze the frequency, phase and amplitude characteristics of the noise signal;

[0120] Combine the environmental dynamic parameters and passenger position data in the car to extract the noise characteristics that interfere with the center of the sound field and generate noise parameters for noise reduction calculation;

[0121] Based on the noise parameters, a reverse acoustic wave signal with a phase opposite to the target noise and matching amplitude is dynamically calculated;

[0122] The reverse sound wave signal is output through the vehicle speaker and superimposed with the target noise signal to reduce the interference of the target noise on the center of the sound field.

[0123] The noise reduction control unit uses passenger position data and vehicle interior dynamics parameters in the following steps:

[0124] The noise reduction control unit further comprises:

[0125] Based on the passenger position data and the speed, acceleration and braking status of the vehicle, the three-dimensional spatial position of the noise source is dynamically calculated to generate the noise source position information;

[0126] Combine the noise source location information and the three-dimensional position coordinates of the passenger to calculate the spatial relationship between the passenger and the noise source, and dynamically adjust the range of the noise reduction signal;

[0127] Based on passenger weight priorities, noise reduction compensation parameters are dynamically optimized to improve the noise reduction effect in multi-passenger scenarios.

[0128] like Figure 2 FIG. 2 is another embodiment of the present invention, which provides a method for adjusting a dynamic sound field adjustment system based on passenger position perception, comprising the following steps:

[0129] S1. Collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing;

[0130] S2. Extract features from the preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, solve the objective function using a genetic algorithm, and generate optimal adjustment parameters;

[0131] S3 selects a sound field adjustment strategy from the sound field adjustment strategy library according to the optimal adjustment parameters;

[0132] S4. According to the instructions of the adjustment strategy, the center point position of the sound field, frequency equalization parameters and noise reduction compensation parameters are adjusted to complete the closed-loop optimization of the sound field.

[0133] In summary, the present invention solves the problems of the existing vehicle audio system in terms of lack of personalization in sound field adjustment, insufficient dynamic adaptability, and limited noise suppression effect through dynamic sound field adjustment technology based on passenger position perception. By real-time acquisition of multi-source data and optimization of sound field adjustment parameters using genetic algorithms, the present invention can not only dynamically adjust the sound field center point position, frequency equalization parameters, and noise reduction compensation parameters, but also combine multi-dimensional feature fusion technology to achieve precise optimization and closed-loop control of sound effects. With the help of a preset sound field adjustment strategy library, the present invention can adapt to the needs of different driving scenarios, provide each passenger with a personalized and comfortable audio experience, and significantly improve the sound quality balance and noise reduction effect of the vehicle environment. In addition, the system structure of the present invention is reasonably designed, with high scalability and compatibility, and can be widely used in different types of vehicle audio systems, with significant technical advantages and industrial prospects.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0135] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0136] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A dynamic sound field adjustment system based on passenger position perception, characterized in that: include: Data collection module, used to collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing; The data processing module is used to extract features from the preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, solve the objective function using a genetic algorithm, and output the optimal sound field adjustment parameters; A strategy decision module, used for selecting an adjustment strategy from a sound field adjustment strategy library according to the optimal sound field adjustment parameters; A parameter execution module, used to dynamically adjust the sound field center point position, frequency equalization parameters and noise reduction compensation parameters according to the adjustment strategy to achieve closed-loop optimization of the sound field; The data processing module comprises: A feature extraction unit is used to extract data features, including location features, state parameters, noise characteristics, and user preferences; A feature fusion unit is used to fuse the extracted features to generate a multi-dimensional sound field feature vector; An objective function construction unit, used to generate an optimization objective function according to the received multi-dimensional sound field feature vector; An algorithm optimization unit, used to solve the optimization objective function based on a genetic algorithm and output optimal sound field adjustment parameters; The objective function construction unit is implemented by the following steps: The multi-dimensional sound field feature vector V is expressed as: V={v1,v2,...,v n } Among them, v n Represents the standardized value of the nth feature; The optimization objective function f(x) is defined based on the multi-dimensional sound field feature vector as follows: Among them, q i (x) represents the sound quality score of the ith passenger at the center of the sound field, w i is the passenger weight, p j is the noise suppression weight, g j (x) is the environmental noise interference function; m represents the number of passengers in the current car; n is the number of multi-dimensional sound field feature vectors; j represents the index of the jth noise source; x represents the variable of the multi-dimensional sound field feature vector; The data acquisition module comprises: A passenger position data acquisition unit, which is used to collect the passenger's sitting posture distribution and position change data through a seat pressure sensor, collect the passenger's dynamic position characteristics through an in-vehicle camera, and generate the passenger's three-dimensional position coordinates using an image processing algorithm; The vehicle status data acquisition unit is used to obtain the vehicle's speed, acceleration, braking status and driving mode through the vehicle system interface; An acoustic environment data acquisition unit, used to collect the spectrum and sound pressure level of the noise signal inside the vehicle through a noise sensor; The user personalized demand data collection unit is used to collect the user's volume, sound field positioning and noise reduction demand settings through the vehicle computer interactive interface or mobile application; The algorithm optimization unit is implemented by the following steps: receiving an optimization objective function generated by an objective function building unit; Based on the parameter space defined by the optimization objective function, an initial optimization scheme set is generated, each set of optimization schemes consists of a sound field center point position, a frequency equalization parameter, and a noise reduction compensation parameter; The fitness value F(x) of each group of optimization solutions is calculated as: Among them, C k (x) represents the degree of violation of the kth constraint, λ k is the penalty factor; According to the fitness value, the roulette algorithm is used to select the solution with the highest fitness among the optimization solutions to enter the next round of optimization; Perform crossover operation on the selected optimization scheme with crossover probability to generate a new optimization scheme: P new =α×P set1 +(1-a)×P set2 Among them, P new is the new optimization solution, P set1 and P set2 are two existing optimization schemes, α is the cross-proportional coefficient; Adjust the parameters of the optimization scheme based on the mutation probability: P mutated =P original +D Among them, P mutated is the optimization solution after mutation, P original is the optimization solution before mutation, Δ is the random mutation value; Determine whether the following conditions are met: the maximum change rate of the fitness value of the optimization scheme is lower than the threshold or the number of iterations reaches the preset upper limit. If not, recalculate the fitness value of each group of optimization schemes; When the convergence conditions are met, the optimization scheme with the highest fitness value is output as the optimal sound field adjustment parameters, including the sound field center point position, frequency equalization parameters and noise reduction compensation parameters.

2. The dynamic sound field adjustment system based on passenger position perception according to claim 1, characterized in that: The strategy decision module includes: a strategy selection unit, which is used to select an adjustment strategy that matches the optimal sound field adjustment parameters from a sound field adjustment strategy library, wherein the sound field adjustment strategy library includes preset strategies for different scenarios such as high-speed driving, urban driving and parking.

3. The dynamic sound field adjustment system based on passenger position perception according to claim 1, characterized in that: The parameter execution module includes: a sound field positioning unit, which is used to realize dynamic positioning of the center point of the sound field by adjusting the output power and direction of the loudspeaker; Frequency equalization unit, used to optimize the gain parameters of the audio low frequency 20Hz to 250Hz, mid-frequency 250Hz to 4kHz and high frequency 4kHz to 20kHz bands; The noise reduction control unit is used to reduce the interference of ambient noise on the sound field by generating reverse sound waves using active noise reduction technology.

4. The dynamic sound field adjustment system based on passenger position perception according to claim 3 is characterized in that: The noise reduction control unit reduces noise interference by using active noise reduction technology through the following steps: The vehicle-mounted noise sensor is used to obtain the in-vehicle environmental noise signal in real time and analyze the frequency, phase and amplitude characteristics of the noise signal; Combine the environmental dynamic parameters and passenger position data in the car to extract the noise characteristics that interfere with the center of the sound field and generate noise parameters for noise reduction calculation; Based on the noise parameters, a reverse acoustic wave signal with a phase opposite to the target noise and matching amplitude is dynamically calculated; The reverse sound wave signal is output through the vehicle speaker and superimposed with the target noise signal to reduce the interference of the target noise on the center of the sound field.

5. The dynamic sound field adjustment system based on passenger position perception according to claim 4 is characterized in that: The noise reduction control unit further comprises: Based on the passenger position data and the speed, acceleration and braking status of the vehicle, the three-dimensional spatial position of the noise source is dynamically calculated to generate the noise source position information; Combine the noise source location information and the three-dimensional position coordinates of the passenger to calculate the spatial relationship between the passenger and the noise source, and dynamically adjust the range of the noise reduction signal; Dynamically optimize noise reduction compensation parameters based on passenger weight priorities.

6. The adjustment method of the dynamic sound field adjustment system based on passenger position perception according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Collect passenger location data, vehicle status data, acoustic environment data and user personalized demand data in real time, and perform data preprocessing; S2. Extract features from the preprocessed data, fuse the extracted features to generate a multi-dimensional sound field feature vector and construct an objective function, solve the objective function using a genetic algorithm, and generate optimal adjustment parameters; S3 selects a sound field adjustment strategy from the sound field adjustment strategy library according to the optimal adjustment parameters; S4. According to the instructions of the adjustment strategy, the center point position of the sound field, frequency equalization parameters and noise reduction compensation parameters are adjusted to complete the closed-loop optimization of the sound field.

Images