Sound wave generation method and device, vehicle and storage medium

Abstract

The invention relates to a sound wave generation method and device, a vehicle and a storage medium, and belongs to the technical field of sound processing and vehicles. The method comprises the steps that in response to a received sound wave playing instruction of a user, a sound wave signal corresponding to the user is played, and a first sound wave parameter of the sound wave signal corresponding to the user is associated with a first user group to which the user belongs. Therefore, according to the scheme, self-adaptive adjustment of the sound waves and personalized adaptation of sound wave styles are achieved, the universality of the sound waves to users with different driving habits is greatly improved, personalized sound wave experience which is more immersive and more conforms to the driving styles of the users is brought to the users, and the playing effect of the sound waves is improved.

Description

Technical Field

[0001] The present disclosure relates to the fields of sound processing and vehicle technology, and in particular to a sound wave generation method, device, vehicle, and storage medium. Background Art

[0002] In the new energy vehicle sector, Enhanced Sound Environment (ESE), an in-vehicle active sound audio technology, aims to create a unique driving atmosphere by simulating the roar of a traditional gasoline engine through electronic devices. This technology typically utilizes the in-vehicle sound system or external speakers, generating sound effects based on preset programs or vehicle driving data to enhance the immersive and engaging driving experience. Summary of the Invention

[0003] The present disclosure provides a sound wave generation method, device, vehicle, server, and computer-readable storage medium to improve the sound wave playback effect. The technical solutions of the present disclosure are as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a sound wave generation method is provided, comprising: in response to receiving a sound wave playing instruction from a user, playing a sound wave signal corresponding to the user, wherein a first sound wave parameter of the sound wave signal corresponding to the user is associated with a first user group to which the user belongs.

[0005] According to a second aspect of an embodiment of the present disclosure, a sound wave generating device is provided, including: a playback module, configured to play a sound wave signal corresponding to a user in response to receiving a sound wave playback instruction from the user, wherein a first sound wave parameter of the sound wave signal corresponding to the user is associated with a first user group to which the user belongs.

[0006] According to a third aspect of an embodiment of the present disclosure, a vehicle is provided, comprising a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the steps of the method described in the first aspect of the embodiment of the present disclosure.

[0007] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method described in the first aspect of the embodiment of the present disclosure are implemented.

[0008] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects: In response to receiving a sound wave playback instruction from a user, the corresponding sound wave signal of the user is played, and the first sound wave parameter of the corresponding sound wave signal of the user is associated with the first user group to which the user belongs. Thus, by determining the first user group to which the user belongs and generating a sound wave signal based on the first sound wave parameter of the first user group, the sound wave style preferences of different users are considered, the adaptive adjustment of the sound wave and the personalized adaptation of the sound wave style are realized, the universality of the sound wave for users with different driving habits is greatly improved, a more immersive and personalized sound wave experience that better suits the user's own driving style is brought to the user, and the playback effect of the sound wave is improved.

[0009] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure and do not constitute an improper limitation of the present disclosure.

[0011] Figure 1 is a flowchart of a sound wave generation method shown according to an exemplary embodiment.

[0012] Figure 2 is a flowchart of a sound wave generation method shown according to another exemplary embodiment.

[0013] Figure 3 is a flowchart of a sound wave generation method shown according to another exemplary embodiment.

[0014] Figure 4 is a flowchart of a sound wave generation method shown according to another exemplary embodiment.

[0015] Figure 5 is a flowchart of a sound wave generation method shown according to another exemplary embodiment.

[0016] Figure 6 is a flowchart of a sound wave generation method shown according to another exemplary embodiment.

[0017] Figure 7 is a structural diagram of generating a sound wave signal shown according to an exemplary embodiment.

[0018] Figure 8 is a flowchart of generating a sound wave signal shown according to an exemplary embodiment.

[0019] Figure 9 is a block diagram of a sound wave generation device shown according to an exemplary embodiment.

[0020] Figure 10 is a block diagram of a vehicle shown according to an exemplary embodiment. Detailed implementation manners

[0021] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described here can be implemented in an order different from those illustrated or described here. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0023] Figure 1 is a flowchart of a sound wave generation method shown according to an exemplary embodiment. As Figure 1 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0024] S101, in response to receiving a sound wave playback instruction from a user, play the sound wave signal corresponding to the user, and the first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs.

[0025] It should be noted that the execution subject of the sound wave generation method of the embodiments of the present disclosure is an electronic device, and the electronic device includes a vehicle control system, a vehicle sound wave generation system, etc. The sound wave generation method of the embodiments of the present disclosure can be executed by the sound wave generation device of the embodiments of the present disclosure, and the sound wave generation device of the embodiments of the present disclosure can be configured in any electronic device to execute the sound wave generation method of the embodiments of the present disclosure.

[0026] Optionally, the sound wave generation method provided by the embodiments of the present disclosure can be executed by a vehicle control system and a vehicle sound wave generation system. That is, the vehicle control system and the vehicle sound wave generation system receive a sound wave playback instruction from a user and play a sound wave signal according to the sound wave playback instruction.

[0027] It should be noted that the engine of a fuel vehicle generates different sounds under different operating states of the vehicle, and when the operating state is switched, the sound of the vehicle also changes. For example, the operating states include starting, accelerating, decelerating, turning, braking, etc.

[0028] Optionally, the operating state of the vehicle can be monitored, and in response to detecting any operating state, a sound wave playback instruction can be obtained. For example, in response to detecting that the vehicle is accelerating, a sound wave playback instruction can be obtained.

[0029] Optionally, a sound wave playback instruction can be generated based on an in-vehicle terminal. The user operates the in-vehicle terminal to generate a sound wave playback instruction. For example, when the user turns on the sound wave playback control switch on the in-vehicle terminal, a sound wave playback instruction is generated.

[0030] Optionally, the switching of the operating state of the vehicle can also be monitored, and in response to detecting that the vehicle switches from one operating state to another operating state, a sound wave playback instruction can be obtained. For example, in response to detecting that the vehicle switches from accelerating to decelerating, a sound wave playback instruction can be obtained.

[0031] Optionally, the first sound wave parameter of the sound wave signal corresponding to the user can be determined, and the sound wave signal can be generated and played according to the first sound wave parameter.

[0032] Optionally, the first sound wave parameter refers to the sound wave parameter used to generate the sound wave signal corresponding to the user, and the first sound wave parameter is associated with the first user group to which the user belongs. Among them, the first user group refers to the user group with similar driving habits to the user. The sound wave preferences of users in the same user group are also similar. That is to say, users in the same user group can use the same sound wave parameter to generate and play the sound wave signal.

[0033] For example, the driving habits of user A and user C are frequent hard accelerations. User A and user B can be regarded as user group 1. The driving habits of user C and user D do not have hard accelerations. User C and user D can be regarded as user group 2. If the driving habit of user E does not have hard accelerations, the first user group to which user E belongs is user group 2.

[0034] For another example, the sound wave parameter corresponding to user group 1 is parameter A, and the sound wave parameter corresponding to user group 1 is parameter B. If the first user group is user group 1, the first sound wave parameter is parameter A; if the first user group is user group 2, the first sound wave parameter is parameter B.

[0035] Optionally, by determining the first user group to which the user belongs, the first sound wave parameter is determined according to the first user group. Optionally, the users can be clustered to determine the first user group to which the user belongs.

[0036] For example, a clustering model can be used to cluster the users according to the driving data of the users to determine the first user group.

[0037] Optionally, the driving data of the user during the vehicle driving process can be collected in real time to obtain the driving data of the user.

[0038] Optionally, historical driving data of the user can also be obtained as the driving data of the user. The historical driving data can be stored in a cloud server, and the historical driving data of the user can be obtained from the cloud server.

[0039] Optionally, the sound wave signal corresponding to the user can be played. The first sound wave parameter can be determined according to the first user group, and the sound wave signal corresponding to the user can be generated according to the first sound wave parameter, and the sound wave signal corresponding to the user can be played.

[0040] Optionally, a mapping relationship between different user groups and different sound wave parameters can be established in advance. By determining the first user group to which the user belongs and querying this mapping relationship, the sound wave parameters corresponding to the user group can be determined as the first sound wave parameter.

[0041] Optionally, based on the first sound wave parameter, the generation of the sound wave signal can be performed, so as to play the sound wave signal. Optionally, the steps of sound source generation, sound source mixing, and sound source post-processing can be performed according to the first sound wave parameter to generate the sound wave signal corresponding to the user.

[0042] For example, the parameters related to sound source generation are determined from the sound wave parameters, and the parameters related to sound source generation are used to generate the sound source, and multiple sound source signals are obtained.

[0043] For example, the parameters related to sound source mixing are determined from the sound wave parameters, and the parameters related to sound source mixing are used to mix the sound sources, so as to mix multiple sound source signals to obtain a sound source mixed signal.

[0044] For example, the parameters related to sound source post-processing are determined from the sound wave parameters, and the parameters related to sound source post-processing are used to perform sound source post-processing, so as to perform post-processing on the sound source mixed signal to obtain a sound wave signal.

[0045] Optionally, after the sound wave signal is generated, based on the Controller Area Network (CAN) of the vehicle, the sound wave signal can be transmitted to the vehicle horn, and the sound wave signal can be played through the vehicle horn to provide the sound wave signal that meets the user's preference for the user.

[0046] It should be noted that before receiving the sound wave playback instruction of the user, the authorization information of the user can be received. The authorization information is used to indicate that when the sound wave playback instruction is received, the sound wave signal corresponding to the user is played. If the authorization information of the user is not received, multiple sound wave parameters stored in advance can be obtained from the vehicle memory, and at least one sound wave parameter can be selected from the multiple sound wave parameters to generate and play the sound wave signal.

[0047] It should be noted that the sound wave signal can be generated only based on sound wave parameters, or can be combined with real-time driving data. That is, the sound wave signals generated by the same user with the same sound wave parameters under different real-time driving states or different real-time driving data can also be different.

[0048] The sound wave generation method provided by the embodiments of the present disclosure plays the sound wave signal corresponding to the user in response to receiving the sound wave playing instruction of the user. The first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs. Thus, by determining the first user group to which the user belongs and generating the sound wave signal based on the first sound wave parameter of the first user group, the sound wave style preferences of different users are considered, the adaptive adjustment of the sound wave and the personalized adaptation of the sound wave style are realized, the universality of the sound wave for users with different driving habits is greatly improved, a more immersive and personalized sound wave experience that fits the user's own driving style is brought to the user, and the playing effect of the sound wave is improved.

[0049] Figure 2 is a flowchart of a sound wave generation method shown according to an exemplary embodiment, as Figure 2 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0050] S201, in response to receiving the sound wave playing instruction of the user, determine the first user group to which the user belongs according to the driving data of the user.

[0051] Optionally, in response to receiving the sound wave playing instruction, the driving data of the user during the vehicle driving process can be obtained. For example, by collecting the driving data of the user in real time, and through the vehicle CAN, collect the driving data of the user during the vehicle driving process.

[0052] Optionally, the driving data of the user includes: driving data and driving scenario data. Among them, the driving data includes: lane change frequency, gear shift frequency, vehicle speed, horn frequency, pedal opening change rate; the driving scenario data includes: road type, driving time period and other data.

[0053] Optionally, the driving data of the user can be collected based on various sensors of the vehicle itself, and based on the CAN interface, the driving data of the user is transmitted to the CAN. For example, the lane change frequency can be collected by using a steering angle sensor. For example, the gear shift frequency and vehicle speed can be collected by using a vehicle speed sensor. For example, the horn frequency can be collected by using a sound sensor. For example, the pedal opening change rate can be collected by using a pedal position sensor. For example, the environmental data can be collected based on an image acquisition device, and the road type can be analyzed according to the environmental data. For example, the driving time period can be obtained based on the clock system of the vehicle.

[0054] Optionally, in response to receiving a sound wave playback instruction, historical driving data of the user can be obtained as the driving data of the user.

[0055] Optionally, based on a set sampling period, it can be determined whether to collect the user's driving data in real time and whether to obtain the user's historical driving data.

[0056] For example, in response to receiving a sound wave playback instruction, if it is determined that the moment of receiving the sound wave playback instruction is within the sampling period, the user's driving data is collected in real time. In response to receiving a sound wave playback instruction, if it is determined that the moment of receiving the sound wave playback instruction is not within the sampling period, the user's historical driving data is obtained.

[0057] Optionally, it can also be determined whether the user of the currently driven vehicle is the same as the user of the vehicle driven last time. If they are the same, the historical driving data of the user can be obtained as the driving data of the user. If they are different, the user's driving data can be collected in real time.

[0058] It can be understood that after obtaining the user's driving data, a clustering model can be used to cluster the user based on the driving data to determine the first user group to which the user belongs. The clustering model can collect the user's driving data in real time and be trained based on the driving data until the training is completed to obtain a trained clustering model. After obtaining the trained clustering model, the user can be clustered based on the user's historical driving data.

[0059] That is to say, it can also be determined whether the clustering model meets the training end condition, and when the training end condition is met, the historical driving data of the user is obtained. If the training end condition is not met, the user's driving data can be collected in real time.

[0060] Optionally, before determining the first user group to which the user belongs based on the driving data, the collected driving data can be preprocessed to improve the data quality. Optionally, preprocessing operations such as data cleaning, data encoding, and data standardization can be performed on the driving data.

[0061] Optionally, based on the clustering model, the user can be clustered according to the driving data to determine the first user group to which the user belongs. For example, a Gaussian Mixture Model (GMM) can be used for clustering.

[0062] Optionally, the feature vector corresponding to the driving data can be obtained, and the GMM calculates the matching degree between different user groups and the user's driving data based on the feature vector, and takes the user group with the highest matching degree as the user group to which the user belongs.

[0063] Optionally, the process of training the GMM can be expressed as:

[0064]

[0065] Among them, N is the number of data points, K is the number of Gaussian distributions, and θ represents the model parameters, including the mean μ of each Gaussian distribution j , covariance ∑ j and mixing coefficient π j . Among them, π j represents the weight of the j-th Gaussian distribution in the GMM, and x i represents the feature vector corresponding to the user's driving data.

[0066] Optionally, the expectation maximization algorithm can be used to solve the above formula (1), so as to obtain the optimal parameters corresponding to the GMM, and the GMM can be configured with the optimal parameters, so as to obtain the trained GMM.

[0067] Optionally, the steps of using the expectation maximization algorithm to solve the above formula (1) may include initializing parameters, the expectation step, and the expectation maximization step.

[0068] Optionally, the parameters in the initialization parameters include: the mean μ of the Gaussian distribution j , covariance ∑ j and mixing coefficient π j . Among them, the mean μ j can be obtained from the feature dataset of the N-dimensional driving data by randomly sampling M groups of data and calculating based on the M groups of data. M is a natural number greater than 1 and less than N. The covariance is set as the identity matrix, and the mixing coefficient is set as 1 / K.

[0069] For example, for driving data containing multiple features such as acceleration, braking frequency, and steering angle, by randomly selecting a data point, the feature values such as acceleration, braking frequency, and steering angle constitute the initial mean vector of a certain Gaussian distribution.

[0070] Optionally, the expectation step and the expectation maximization step may include iteratively updating the parameters, and setting the iteration termination condition as the difference between the expectation of the current iteration and the expectation of the previous iteration is less than the iteration termination threshold, which can be expressed as |L(θ new ) - L(θ)| < δ, where δ can be set to 0.0001. When the iteration termination condition is triggered, determine the parameters corresponding to the current expectation as the optimal parameters of the model, and configure the GMM with the optimal parameters to obtain the trained GMM, so as to use the GMM to cluster the users according to the user's driving data, determine the first user group to which the user belongs, so that users with similar driving behavior patterns can be grouped into one category, and then each category of users may correspond to a specific sound wave parameter.

[0071] Optionally, whether the iteration termination condition is met can be used as whether the GMM meets the training end condition. That is, when the GMM meets the iteration termination condition, the historical driving data of the user can be obtained. When the iteration termination condition is not met, the driving data of the user is collected in real time.

[0072] Optionally, after determining the first user group to which the user belongs, the model data of the GMM can be updated based on the user and the first user group to which the user belongs, and the updated model data can be used to determine the first user group to which the next user belongs in the next clustering, so as to improve the accuracy of clustering.

[0073] S202. Play the sound wave signal corresponding to the user. The first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs.

[0074] For the relevant content of step S202, reference can be made to the above embodiments and will not be elaborated here.

[0075] The sound wave generation method provided by the embodiments of the present disclosure responds to receiving a sound wave playback instruction, determines the first user group to which the user belongs according to the driving data, so that the first sound wave parameter can be determined according to the first user group, and the sound wave signal can be generated and played according to the first sound wave parameter. Thus, the sound wave signal is generated according to the driving data of the user, taking into account the influence of the user's driving habits on the preference for the sound wave style, realizing the adaptive adjustment of the sound wave and the personalized adaptation of the sound wave style, greatly improving the universality of the sound wave for users with different driving habits, and bringing a more immersive and personalized sound wave experience that fits the user's own driving style to the user.

[0076] Figure 3 is a flowchart of a sound wave generation method shown according to an exemplary embodiment. As Figure 3 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0077] S301. In response to receiving the sound wave playback instruction of the user, according to the driving data, obtain the first feature vector corresponding to the driving data of the user.

[0078] Optionally, by performing feature extraction on the driving data, a feature vector can be obtained, and this feature vector can be used as the first feature vector corresponding to the driving data of the user. For example, a machine learning method can be used to perform feature extraction on the driving data. By encoding, pooling the driving data, and using a convolutional neural network to extract the first feature vector of the driving data from the pooled driving data as the first feature vector corresponding to the driving data of the user.

[0079] Optionally, the first feature vector can be a feature matrix. For example, a feature matrix is obtained by performing feature extraction on the driving data, and the feature matrix is used as the first feature vector.

[0080] S302. Obtain the similarity between the second feature vector and the first feature vector corresponding to at least one candidate user group respectively.

[0081] Optionally, the second feature vector corresponding to at least one candidate user group can be obtained, the Euclidean distance between the first feature vector and the second feature vector can be calculated, and the Euclidean distance can be used as the similarity between the second feature vector and the first feature vector corresponding to at least one candidate user group respectively. Among them, the smaller the Euclidean distance, the higher the similarity.

[0082] Optionally, the cosine similarity between the first feature vector and the second feature vector can be calculated as the similarity between the second feature vector and the first feature vector corresponding to at least one candidate user group respectively. Among them, the closer the cosine similarity is to 1, the higher the similarity.

[0083] Optionally, a pre-trained GMM can be used to calculate the similarity between the first feature vector and the second feature vector. Among them, the model data of the GMM contains the second feature vector corresponding to at least one candidate user group respectively, and then the similarity between the first feature vector and the second feature vector can be calculated according to the model data of the GMM. For the process of training the GMM, reference can be made to Figure 1 the embodiments, which will not be elaborated here.

[0084] S303. Determine the first user group to which the user belongs among at least one candidate user group according to the similarity.

[0085] Optionally, the maximum similarity can be obtained from the similarities between the second feature vector and the first feature vector corresponding to at least one candidate user group respectively, and according to the maximum similarity, the candidate user group corresponding to the maximum similarity can be determined from at least one candidate user group as the first user group to which the user belongs.

[0086] For example, if the similarity is the cosine similarity, the candidate user groups include group A, group B, and group C, the cosine similarity between the first feature vector and the second feature vector of group A is 0.6, the cosine similarity between the first feature vector and the second feature vector of group B is 0.3, and the cosine similarity between the first feature vector and the second feature vector of group C is 0.8, then 0.8 can be determined as the maximum similarity, and group C can be used as the first user group to which the user belongs.

[0087] S304. Play the sound wave signal corresponding to the user, and the first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs.

[0088] For the relevant content of step S304, reference can be made to the embodiments related to generating the sound wave signal, which will not be elaborated here.

[0089] The sound wave generation method provided by the embodiments of the present disclosure obtains the first feature vector of the user's driving data, determines the similarity between the second feature vector corresponding to at least one candidate user group and the first feature vector, and determines the first user group to which the user belongs according to the similarity. Thus, it is possible to group users based on their driving habits, so that the sound wave parameters can match different user groups, and then play a more personalized sound wave signal that meets the user's preferences.

[0090] Figure 4 is a flowchart of a sound wave generation method shown according to an exemplary embodiment. As Figure 4 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0091] S401, in response to receiving a sound wave playback instruction from the user, obtain the first sound wave parameter corresponding to the first user group according to the first user group to which the user belongs and the mapping relationship between the user group and the sound wave parameter pre-constructed.

[0092] Optionally, the mapping relationship between the user group and the sound wave parameter can be pre-constructed according to the group identifier of the user group and the parameter identifier of the sound wave parameter.

[0093] Optionally, by determining the first group identifier corresponding to the first user group, and by querying the mapping relationship between the user group and the sound wave parameter, determining the group identifier that is the same as the first group identifier, and the parameter identifier that has a mapping relationship with this group identifier, and then the parameter identifier can be determined as the first sound wave parameter corresponding to the first user group.

[0094] Optionally, before obtaining the first sound wave parameter corresponding to the first user group according to the first user group to which the user belongs and the mapping relationship between the user group and the sound wave parameter pre-constructed, different candidate user groups corresponding to different candidate sound wave parameters can also be determined, and then the mapping relationship between the user group and the sound wave parameter can be constructed.

[0095] Optionally, the candidate sound wave parameters can be scored by user samples, and the score can be used as the matching degree between the candidate sound wave parameter and the user, and the mapping relationship can be constructed based on the matching degree and the driving data corresponding to the user.

[0096] Optionally, by obtaining candidate sound wave parameters, generating candidate sound wave signals based on the candidate sound wave parameters, and playing the candidate sound wave signals. During the playback of the candidate sound wave signals, user samples can perform an operation of input matching degree on the in-vehicle terminal. By receiving the operation of input matching degree of the user sample, based on the operation, determine the matching degree corresponding to the candidate sound wave parameters, where the matching degree is used to jointly construct a mapping relationship with the historical driving data of the user sample.

[0097] For example, the operation of inputting the matching degree can be that the user sample can perform an operation of selecting the matching degree on the in-vehicle terminal, or the user sample can input text information on the in-vehicle terminal, and the text information includes the score of the matching degree, or the user sample can input the matching degree through voice.

[0098] For example, multiple candidate matching degrees can be displayed on the in-vehicle terminal, and the user sample can select the matching degree by clicking on any one of the candidate matching degrees. The user sample can also select any one of the candidate matching degrees through voice to achieve the selection of the matching degree.

[0099] Optionally, multiple sound wave parameters sent by the server can be received as candidate sound wave parameters. The sound wave parameters of the server can be pre-installed during vehicle production. The playback effects of different sound wave parameters are also different.

[0100] Optionally, for any candidate sound wave parameter, determine multiple matching degrees of the candidate sound wave signal generated by any candidate sound wave parameter, determine the matching degrees whose matching degrees are greater than the matching degree threshold from the multiple matching degrees, and determine the historical driving data corresponding to the matching degrees greater than the matching degree threshold, and generate a user group based on the user sample associated with the historical driving data. Further, a mapping relationship between the user group and the sound wave parameters can be constructed.

[0101] Optionally, the matching degree and the historical driving data of the sample user can be sent to the server, and the server establishes a mapping relationship between the user group and the sound wave parameters according to the matching degree and the historical driving data.

[0102] For example, if the user sample is 1000 people, 50 candidate sound wave parameters can be obtained and 50 corresponding candidate sound wave signals can be generated. Set scores for different matching degrees, such as "very matching" is recorded as 5 points, "relatively matching" is recorded as 4 points, "medium" is recorded as 3 points, "relatively not matching" is recorded as 2 points, and "very not matching" is recorded as 1 point. When in the driving scenario of any one of the candidate sound wave signals and the candidate sound wave signal obtains an evaluation of "relatively matching", it can be recorded as 4 points.

[0103] If the average score of the candidate sound wave signals corresponding to a certain type of driving data 1 (such as a high frequency of hard acceleration and a large proportion of driving time on highways) for 1000 user samples is 4 points on the semantic dimension of "very exciting - relatively exciting - medium - relatively soothing - very soothing", then the mapping relationship between the candidate sound wave parameters corresponding to "relatively exciting" and the user group can be established based on the driving data.

[0104] When it is detected that the user's driving data is the same as driving data 1, the candidate sound wave parameters can be obtained as the first sound wave parameters according to the mapping relationship, and a sound wave signal can be generated and played according to the first sound wave parameters.

[0105] Optionally, the mapping relationship between the user group and the sound wave parameters can be stored in the memory of the vehicle control system or the vehicle sound wave generation system, or stored in the cloud server. When the first user group is determined, by accessing the system memory or accessing the cloud server, the mapping relationship can be obtained, and the first sound wave parameters corresponding to the user can be determined by querying the mapping relationship.

[0106] S402, play the sound wave signal corresponding to the user according to the first sound wave parameters.

[0107] Optionally, steps such as sound source generation, sound source mixing, and sound source post-processing can be performed according to the first sound wave parameters to generate and play the sound wave signal corresponding to the user.

[0108] Optionally, the sound wave parameters related to sound source generation can be obtained from the first sound wave parameters, and the sound source generation can be performed using the sound wave parameters related to sound source generation, and multiple sound source signals with different audio tracks can be obtained. For example, the frequency and volume are obtained from the first sound wave parameters as the sound wave parameters related to sound source generation, and then multiple sound source signals with different audio tracks are generated using the sound wave parameters related to sound source generation.

[0109] Optionally, the sound wave parameters related to sound source mixing can be obtained from the first sound wave parameters, and the sound source mixing can be performed using the sound wave parameters related to sound source mixing to obtain a sound source mixed signal. Optionally, parameters such as the volume, balance, and phase of the sound source signal can be adjusted to ensure that each sound source signal can coexist harmoniously and form a unified and layered sound wave effect.

[0110] Optionally, sound source post - processing refers to optimizing and providing sound effects for the sound source mixed signal. Optionally, by obtaining the sound wave parameters related to sound source post - processing from the first sound wave parameters and using the sound wave parameters related to sound source post - processing to post - process the sound source mixed signal, a sound wave signal is obtained. Optionally, the sound source mixed signal can be filtered based on the sound wave parameters related to sound source post - processing to obtain a sound wave signal. For example, the sound wave parameters related to sound source post - processing can be the parameters of a filter, and the filter is configured using these parameters, and the sound source mixed signal is filtered using this filter to obtain a sound wave signal.

[0111] Optionally, after the sound wave signal is generated, based on the vehicle CAN, the sound wave signal can be transmitted to the vehicle horn, and the sound wave signal is played through the horn to provide the user with a sound wave signal that conforms to the user's driving preferences.

[0112] The sound wave generation method provided by the embodiments of the present disclosure determines the first sound wave parameters corresponding to the first user group according to the first user group to which the user belongs and the mapping relationship between the pre - constructed user groups and sound wave parameters, and plays the sound wave signal corresponding to the user according to the first sound wave parameters. Thus, according to the pre - constructed mapping relationship, the first sound wave parameters corresponding to the first user group can be determined, so that the sound wave parameters can match different user groups, thereby playing a more personalized sound wave signal that meets the user's preferences.

[0113] Figure 5 is a flowchart of a sound wave generation method shown according to an exemplary embodiment. As Figure 5 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0114] S501, in response to receiving a sound wave playback instruction from the user, generate sound source signals of multiple tracks according to the sound source generation parameters in the first sound wave parameters.

[0115] Optionally, the first sound wave parameters include but are not limited to: harmonic amplitude, frequency conversion rate, motor speed, harmonic order, sound source frequency shift speed, sound source loudness, sound effect parameters, etc.

[0116] Optionally, obtain the sound source generation parameters from the first sound wave parameters and generate sound source signals of multiple tracks according to the sound source generation parameters.

[0117] Optionally, the sound source generation parameters include at least one of the acoustic parameters corresponding to the order method and the acoustic parameters corresponding to the frequency conversion method. Among them, the acoustic parameters corresponding to the order method at least include harmonic amplitude, frequency conversion rate, motor speed, and harmonic order. The acoustic parameters corresponding to the frequency conversion method at least include sound source frequency shift speed and sound source loudness.

[0118] Based on the above embodiments, the embodiments of the present disclosure can explain the process of determining the sound source generation parameters. It should be noted that the process of calculating the first sound wave parameter is executed on the cloud server. The vehicle can directly obtain the first sound wave parameter corresponding to the first user according to the first user group, and then determine the sound source generation parameter from the first sound wave parameter, without calculating the sound source generation parameter on the vehicle side, which greatly saves the generation speed of the sound wave signal and saves computing resources.

[0119] Optionally, the process of obtaining the acoustic parameters corresponding to the order method can be expressed as:

[0120]

[0121] Where Sig is the single-track signal, Amp n is the harmonic amplitude, k is the frequency conversion rate, rpm is the motor speed, Ord n is the order of each harmonic.

[0122] Where Ord n affects the frequency component distribution of the sound source, k affects the speed of frequency change of the sound source with the change of the vehicle motor speed, and Amp n affects the speed of loudness change of the single-track signal with the change of the vehicle speed.

[0123] Optionally, the process of obtaining the acoustic parameters corresponding to the frequency conversion method can be expressed as:

[0124]

[0125] Where, is the phase difference before and after frequency shift. Modulating the sound source signal with this phase difference can achieve the frequency shift effect. f0 is the initial frequency, R0 is the initial distance, R0 = 0, v r is the frequency shift speed, t is the time scale, Gain r is the loudness of the sound source.

[0126] Where, v r affects the speed of change of the sound source signal frequency with the change of the vehicle motor speed, and Gain r affects the speed of loudness change of the sound source signal with the change of the vehicle speed.

[0127] S502. Mix the sound source signals of multiple audio tracks according to the sound source mixing parameter in the first sound wave parameter to obtain a sound source mixed signal.

[0128] Optionally, the sound source mixing parameter can be obtained from the first sound wave parameter, and based on the sound source mixing parameter, the sound source signals of multiple audio tracks are mixed to obtain a sound source mixed signal. For example, the sound source signals of multiple audio tracks can be adjusted based on the sound source mixing parameter, and the adjusted sound source signals are combined to mix the sound source signals of multiple audio tracks, thereby obtaining a sound source mixed signal.

[0129] Optionally, the sound source mixing parameter at least includes the sound source loudness corresponding to each audio track respectively.

[0130] Optionally, taking the sound source loudness corresponding to each audio track respectively as the mixing coefficient of the sound source signals of multiple audio tracks, a multiplication operation is performed on the sound source signals of multiple audio tracks to obtain processed audio signals of multiple audio tracks. For example, by multiplying the sound source signal of each audio track by its corresponding mixing coefficient, processed audio signals of multiple audio tracks can be obtained.

[0131] Furthermore, the processed audio signals of multiple audio tracks are summed to obtain a sound source mixed signal. For example, according to the mixer, the processed audio signals of each audio track are summed to obtain a sound source mixed signal.

[0132] Based on the above embodiments, the embodiments of the present disclosure can explain the process of determining the sound source mixing parameter. It should be noted that the process of calculating the first sound wave parameter is executed on the cloud server. The vehicle can directly obtain the first sound wave parameter corresponding to the first user according to the first user group, and then determine the sound source mixing parameter from the first sound wave parameter, without calculating the sound source mixing parameter at the vehicle end, which greatly saves the generation speed of the sound wave signal and saves computing resources.

[0133] Optionally, the process of obtaining the sound source mixing parameter can be expressed as:

[0134] Sig M =∑Gain m ×Sig m (4)

[0135] Where Sig M is the sound source mixed signal, m is the number of single tracks, Gain m is the sound source loudness corresponding to the sound source signal of each audio track, and Sig m is the signal of the sound source component of each audio track.

[0136] Where Gain m affects the mixing ratio of each sound source signal.

[0137] S503, according to the post-processing parameter in the first sound wave parameter, post-process the sound source mixed signal to obtain and play the sound wave signal.

[0138] Optionally, post-processing parameters can be obtained from the first sound wave parameters, and based on the post-processing parameters, post-processing is performed on the sound source mixed signal to obtain and play the sound wave signal. Optionally, the post-processing includes loudness adjustment, pitch adjustment, and sound effect adjustment.

[0139] Optionally, the first sound wave parameters include a loudness adjustment curve and a pitch adjustment curve. According to the adjustment curves, loudness adjustment and pitch adjustment can be performed on the sound source mixed signal.

[0140] That is to say, the post-processing parameters include adjustment curves, and the adjustment curves are used to reflect the mapping relationship between the adjustment gain of at least one of loudness and pitch and the vehicle speed.

[0141] It can be understood that there are n equally spaced preset sampling points on the adjustment curve, which are respectively: (v1, Gv1), (v2, Gv2), …, (v n , Gv n ), and based on the preset sampling points of the adjustment curve, the adjustment gain used for post-processing can be determined according to the vehicle speed.

[0142] For example, according to the vehicle speed at the first time and the adjustment curve, the adjustment gain corresponding to the sound source mixed signal can be determined, and based on the adjustment gain corresponding to the sound source mixed signal, gain processing is performed on the sound source mixed signal. Optionally, by determining the preset sampling points on the adjustment curve and performing interpolation calculation based on the vehicle speed at the first time, the adjustment gain corresponding to the sound source mixed signal can be obtained. Further, based on the adjustment gain, gain processing is performed on the sound source mixed signal to obtain the sound wave signal.

[0143] Optionally, the first time can be the current real-time time, and the vehicle speed at the first time is the real-time vehicle speed. For example, the real-time vehicle speed can be obtained from the user's driving data as the vehicle speed at the first time.

[0144] Optionally, the first time can also be the first moment when the sound wave playback instruction is received, and the vehicle speed at the first time is the vehicle speed corresponding to the first moment when the user's sound wave playback instruction is received. For example, the vehicle speed corresponding to the first moment can be obtained from the user's driving data as the vehicle speed at the first time.

[0145] Optionally, the first moment can exist in different time periods. For example, it includes a first time period and a second time period. Among them, the first time period includes the first moment, that is to say, the first time period covers the first moment when the sound wave playback instruction is received and a period of time before and after the first moment.

[0146] For example, the first moment when the sound wave playback instruction is received is 8:00 p.m., and the first time period can be from 7:55 p.m. to 8:05 p.m., and these 10 minutes is a first time period including the first moment.

[0147] Optionally, the end time of the second time period is the first time. That is to say, the second time period is a time period starting from the start time and ending at the first time.

[0148] For example, if the first time when the sound wave playing instruction is received is 8:00 p.m., the second time period can start from 7:30 p.m. and end at 8:00 p.m. These 30 minutes are a second time period with the first time as the end time.

[0149] Optionally, the first time can also be the middle time when the user's driving data is acquired, and the vehicle speed at the first time is the vehicle speed corresponding to the middle time when the user's driving data is acquired. For example, in response to receiving the user's sound wave playing instruction, the user's driving data is acquired. The start time when the user's driving data is acquired is the first time, and the end time when the acquisition of the user's driving data ends is the second time. Then, by averaging the first time and the second time, the middle time can be obtained, so that the vehicle speed at the first time can be more in line with the user's driving data.

[0150] Optionally, the first time can also be the time corresponding to a set duration after the user accelerates or decelerates, and the vehicle speed of the vehicle at the first time is the vehicle speed at the time corresponding to the set duration after the user accelerates or decelerates. For example, if the first time is the time corresponding to 30 seconds after the user accelerates or decelerates, the vehicle speed at the first time is the vehicle speed at the time corresponding to 30 seconds after the user accelerates or decelerates.

[0151] Optionally, before performing the interpolation calculation, it can be determined whether there is a preset sampling point corresponding to the vehicle speed at the first time on the adjustment curve. In response to the absence of a preset sampling point corresponding to the vehicle speed at the first time on the adjustment curve, the first sampling point and the second sampling point on the adjustment curve are determined according to the vehicle speed at the first time, where the vehicle speed at the first time is between the vehicle speed corresponding to the first sampling point and the vehicle speed corresponding to the second sampling point. For example, let the current vehicle speed be v, the vehicle speed corresponding to the first sampling point be v i , and the vehicle speed corresponding to the second sampling point be v i+1 , then v i ≤v≤v i+1 .

[0152] Optionally, by performing interpolation calculation on the vehicle speed at the first time, the first sampling point, and the first sampling point, the adjustment gain corresponding to the sound source mixing signal is obtained. The formula for the interpolation calculation is as follows:

[0153]

[0154] where G v is the adjustment gain corresponding to the sound source mixing signal, v i is the vehicle speed corresponding to the first sampling point, and v i+1is the vehicle speed corresponding to the second sampling point, G vi is the adjustment gain corresponding to the first sampling point, G vi+1 is the adjustment gain corresponding to the second sampling point.

[0155] Optionally, the post-processing parameters further include sound effect parameters. By using the sound effect parameters, the sound components of different frequencies are enhanced or attenuated to achieve purposes such as improving sound quality, adapting to different listening environments, or meeting personal auditory preferences.

[0156] Optionally, the sound source mixed signal can be processed according to the adjustment gain and the sound effect parameters to obtain a sound wave signal. That is to say, the sound source mixed signal after gain processing can be subjected to sound effect processing according to the sound effect parameters. For example, the sound source mixed signal is subjected to gain processing according to the adjustment gain to obtain a sound source mixed signal after gain processing, and the sound source mixed signal after gain processing is subjected to sound effect processing according to the sound effect parameters to obtain and play a sound wave signal.

[0157] It should be noted that the process of calculating the sound effect parameters is executed on the cloud server. The vehicle can directly obtain the first sound wave parameters corresponding to the first user according to the first user group, and then determine the sound effect parameters from the first sound wave parameters, without the need to perform calculations on the vehicle side, which greatly saves the generation speed of the sound wave signal and saves computing resources.

[0158] Based on the above embodiments, the embodiments of the present disclosure can explain the process of calculating the sound effect parameters. Optionally, a sound effect algorithm can be used to calculate the sound effect parameters. Optionally, the sound effect algorithms include: (Equalizer, EQ) algorithm, echo algorithm, reverberation algorithm, filter algorithm, dynamic range compression and expansion algorithm, etc. The embodiments of the present disclosure do not specifically limit the sound effect algorithms.

[0159] For example, taking the EQ algorithm as an example of the sound effect algorithm, the process of obtaining the sound effect parameters is explained. For example, taking the second-order band-pass filter of the EQ algorithm as an example, the process of obtaining the sound effect parameters can be expressed as:

[0160]

[0161] where H(f) is the filter parameter, f c is the center frequency point of the filter, and Q is the quality factor.

[0162] For example, the quality factor in the EQ algorithm can be used as the sound effect parameter.

[0163] The sound wave generation method provided by the embodiments of the present disclosure generates sound source signals for multiple tracks according to the sound source generation parameters in the first sound wave parameters, mixes the sound source signals of multiple tracks according to the sound source mixing parameters to obtain a sound source mixed signal, and then performs post-processing on the sound source mixed signal according to the post-processing parameters to obtain and play a sound wave signal. Thus, according to different parameters in the first sound wave parameters, sound source signals are generated and processed to obtain sound wave signals, providing the ability to generate sound waves that can adapt to different driving habits, making the sound wave signals differentiated and personalized, and meeting the driving preferences of users.

[0164] Figure 6 is a flowchart of a sound wave generation method shown according to an exemplary embodiment, as Figure 6 shown, the sound wave generation method of the embodiments of the present disclosure includes the following steps:

[0165] S601, in response to receiving a sound wave play instruction from a user, determine a first user group to which the user belongs according to the driving data of the user.

[0166] S602, according to the first user group to which the user belongs and the mapping relationship between the user group and the sound wave parameters pre-constructed, obtain the first sound wave parameters corresponding to the first user group.

[0167] S603, generate sound source signals for multiple tracks according to the sound source generation parameters in the first sound wave parameters.

[0168] S604, mix the sound source signals of multiple tracks according to the sound source mixing parameters in the first sound wave parameters to obtain a sound source mixed signal.

[0169] S605, perform post-processing on the sound source mixed signal according to the post-processing parameters in the first sound wave parameters to obtain and play a sound wave signal.

[0170] For the relevant content of steps S601 - S605, reference can be made to the above embodiments and will not be elaborated here.

[0171] The sound wave generation method provided by the embodiments of the present disclosure, in response to receiving a sound wave play instruction from a user, determines a first user group to which the user belongs according to the driving data of the user, and determines the first sound wave parameters corresponding to the user according to the first user group, so that a sound wave signal can be generated and played according to the first sound wave parameters. Thus, by determining the first user group to which the user belongs and generating a sound wave signal based on the first sound wave parameters of the first user group, the sound wave style preferences of different users are considered, realizing the adaptive adjustment of the sound wave and the personalized adaptation of the sound wave style, greatly improving the universality of the sound wave for users with different driving habits, and bringing a more immersive and personalized sound wave experience that fits the user's own driving style to the user.

[0172] Figure 7 The structure diagram for generating a sound wave signal is shown, Figure 7 which includes a user driving data acquisition module, a user clustering module, a sound wave generation module, a sound wave parameter acquisition module, and a sound wave signal output module.

[0173] Optionally, the user driving data acquisition module collects the driving data of the user and transmits the driving data to the user clustering module. The user clustering module clusters and divides the users according to the driving data to determine the first user group to which the user belongs. Further, according to the mapping relationship between the first user group and the sound wave parameters in the sound wave parameter acquisition module, the first sound wave parameters corresponding to the first user group can be determined. The sound wave generation module generates a sound wave signal according to the first sound wave parameters, and the sound wave signal output module outputs the sound wave signal.

[0174] Figure 8 The flowchart for generating a sound wave signal is shown. By collecting the driving data of the user and determining the first user group to which the user belongs according to the driving data. By obtaining the pre-constructed mapping relationship between the user group and the sound wave parameters and querying this mapping relationship, the first sound wave parameters corresponding to the first user group, that is, the first sound wave parameters corresponding to the user, can be determined. Further, an architecture of a sound wave generation algorithm is established, where the architecture of the sound wave generation algorithm is used to generate a sound wave signal according to the first sound wave parameters.

[0175] Optionally, the architecture of the sound wave generation algorithm includes a sound source / track module, a track mixing module, and a post-processing module. Among them, the sound source / track module is used to generate the sound source signals of multiple tracks according to the sound source generation parameters in the first sound wave parameters. For example, the order harmonics can be input into the sound source / track module, and the sound source / track module outputs in digital audio form through sampling quantization coding as the sound source signals of multiple tracks. The track mixing module is used to mix the sound source signals of multiple tracks according to the sound source mixing parameters in the first sound wave parameters to obtain a sound source mixed signal. For example, determine the mixing coefficients corresponding to each track respectively and mix the sound source signals of multiple tracks according to the mixing coefficients. The post-processing module is used to perform post-processing on the sound source mixed signal according to the post-processing parameters in the first sound wave parameters to obtain a sound wave signal. For example, adjust the curve and sound effect parameters to process the sound source mixed signal to obtain a sound wave signal.

[0176] It should be noted that all operations involved in the various embodiments of the present disclosure are carried out under the authorization of the user and strictly comply with relevant laws and regulations such as privacy and security.

[0177] Figure 9 is a block diagram of a sound wave generation device shown according to an exemplary embodiment. Refer to Figure 9, the sound wave generating device 900 according to the embodiments of the present disclosure includes: a playback module 901.

[0178] The playback module 901 is configured to play a sound wave signal corresponding to a user in response to receiving a sound wave playback instruction of the user, and a first sound wave parameter of the sound wave signal corresponding to the user is associated with a first user group to which the user belongs.

[0179] In an embodiment of the present disclosure, the playback module 901 is further configured to: determine the first user group to which the user belongs according to the driving data of the user.

[0180] In an embodiment of the present disclosure, the playback module 901 is further configured to: obtain a first feature vector corresponding to the driving data of the user according to the driving data; obtain the similarity between the second feature vector corresponding to each of at least one candidate user group and the first feature vector; and determine the first user group to which the user belongs among the at least one candidate user group according to the similarity.

[0181] In an embodiment of the present disclosure, the playback module 901 is further configured to: obtain a first sound wave parameter corresponding to the first user group according to the first user group to which the user belongs and a pre-constructed mapping relationship between the user group and the sound wave parameter; and play the sound wave signal corresponding to the user according to the first sound wave parameter.

[0182] In an embodiment of the present disclosure, the playback module 901 is further configured to: obtain candidate sound wave parameters; generate a candidate sound wave signal according to the candidate sound wave parameters and play the candidate sound wave signal; receive an operation of the input matching degree of the user sample, and determine the matching degree corresponding to the candidate sound wave parameters based on the operation, where the matching degree is used to jointly construct a mapping relationship with the historical driving data of the user sample.

[0183] In an embodiment of the present disclosure, the playback module 901 is further configured to: generate sound source signals of multiple tracks according to the sound source generation parameters in the first sound wave parameter; mix the sound source signals of multiple tracks according to the sound source mixing parameters in the first sound wave parameter to obtain a sound source mixed signal; and perform post-processing on the sound source mixed signal according to the post-processing parameters in the first sound wave parameter to obtain and play the sound wave signal.

[0184] In an embodiment of the present disclosure, the sound source mixing parameters at least include the sound source loudness corresponding to each track respectively. The playback module 901 is further configured to: use the sound source loudness corresponding to each track respectively as a mixing coefficient of the sound source signals of multiple tracks, perform a multiplication operation on the sound source signals of multiple tracks to obtain processed audio signals of multiple tracks; and sum the processed audio signals of multiple tracks to obtain a sound source mixed signal.

[0185] In an embodiment of the present disclosure, the post-processing parameter includes an adjustment curve, and the adjustment curve is used to reflect the mapping relationship between the adjustment gain of at least one of loudness and pitch and the vehicle speed; the playback module 901 is further configured to: determine the adjustment gain corresponding to the sound source mixing signal according to the vehicle speed at the first time and the adjustment curve; perform gain processing on the sound source mixing signal according to the adjustment gain corresponding to the sound source mixing signal; wherein, the vehicle speed at the first time is the real-time vehicle speed, or the first time is determined based on at least one of the following: the first moment when the user's sound wave playback instruction is received; the first time period, which includes the first moment within the first time period; the second time period, and the end moment of the second time period is the first moment.

[0186] In an embodiment of the present disclosure, the playback module 901 is further configured to: in response to the absence of a preset sampling point corresponding to the vehicle speed at the first time on the adjustment curve, determine the first sampling point and the second sampling point on the adjustment curve according to the vehicle speed at the first time, wherein the vehicle speed at the first time is between the vehicle speed corresponding to the first sampling point and the vehicle speed corresponding to the second sampling point; perform interpolation calculation on the vehicle speed at the first time, the first sampling point, and the first sampling point to obtain the adjustment gain corresponding to the sound source mixing signal.

[0187] In an embodiment of the present disclosure, the post-processing parameter further includes a sound effect parameter, and the playback module 901 is further configured to: perform sound effect processing on the sound source mixing signal that has undergone gain processing according to the sound effect parameter.

[0188] In an embodiment of the present disclosure, the sound source generation parameter at least includes at least one of the acoustic parameters corresponding to the order method and the acoustic parameters corresponding to the frequency conversion method; wherein, the acoustic parameters corresponding to the order method at least include harmonic amplitude, frequency conversion rate, motor speed, and harmonic order; the acoustic parameters corresponding to the frequency conversion method at least include the sound source frequency shift speed and the sound source loudness.

[0189] The sound wave generation device provided by the embodiment of the present disclosure plays the sound wave signal corresponding to the user in response to receiving the user's sound wave playback instruction, and the first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs. Thus, by determining the first user group to which the user belongs and generating a sound wave signal based on the first sound wave parameter of the first user group, the sound wave style preferences of different users are considered, the adaptive adjustment of the sound wave and the personalized adaptation of the sound wave style are realized, the universality of the sound wave for users with different driving habits is greatly improved, a more immersive and personalized sound wave experience that fits the user's own driving style is brought to the user, and the playback effect of the sound wave is improved.

[0190] Figure 10It is a block diagram of a vehicle shown according to an exemplary embodiment. For example, the vehicle 1000 can be a hybrid vehicle, a non - hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 1000 can be an autonomous vehicle, a semi - autonomous vehicle, or a non - autonomous vehicle.

[0191] Referring to Figure 10 , the vehicle 1000 can include various subsystems. For example, the infotainment system 1001, the perception system 1002, the decision - making and control system 1003, the drive system 1004, and the computing platform 1005. Among them, the vehicle 1000 can also include more or fewer subsystems, and each subsystem can include multiple components. In addition, each subsystem and each component of the vehicle 1000 can be interconnected by wired or wireless means.

[0192] In some embodiments, the infotainment system 1001 can include a communication system, an entertainment system, a navigation system, etc.

[0193] The perception system 1002 can include several sensors for sensing information about the environment around the vehicle 1000. For example, the perception system 1002 can include a global positioning system (the global positioning system can be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter - wave radar, ultrasonic radar, and a camera device.

[0194] The decision - making and control system 1003 can include a computing system, a vehicle controller, a steering system, an accelerator, and a braking system.

[0195] The drive system 1004 can include components that provide motive power for the vehicle 1000. In one embodiment, the drive system 1004 can include an engine, an energy source, a transmission system, and wheels. The engine can be one or a combination of an internal combustion engine, an electric motor, and an air - compression engine. The engine can convert the energy provided by the energy source into mechanical energy.

[0196] Some or all of the functions of the vehicle 1000 are controlled by the computing platform 1005. The computing platform 1005 can include at least one processor 1051 and a memory 1052. The processor 1051 can execute instructions 1053 stored in the memory 1052.

[0197] The processor 1051 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0198] The memory 1052 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0199] In addition to the instructions 1053, the memory 1052 can also store data, such as road maps, route information, data on the position, direction, speed, etc. of the vehicle. The data stored in the memory 1052 can be used by the computing platform 1005.

[0200] In the embodiments of the present disclosure, the processor 1051 can execute the instructions 1053 to implement all or part of the steps of the sound wave generation method provided by the present disclosure.

[0201] To implement the above embodiments, the present disclosure also proposes a computer-readable storage medium, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the sound wave generation method provided by the present disclosure are implemented.

[0202] Optionally, the computer-readable storage medium can be ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0203] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and embodiments are only to be regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0204] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A sound wave generation method, characterized in that, The method includes: In response to receiving a sound wave playback instruction from a user, playing the sound wave signal corresponding to the user, where the first sound wave parameter of the sound wave signal corresponding to the user is associated with the first user group to which the user belongs.

2. The method according to claim 1, wherein Determining the first user group to which the user belongs includes: Determining the first user group to which the user belongs according to the driving data of the user.

3. The method according to claim 2, wherein The determining the first user group to which the user belongs according to the driving data of the user includes: According to the driving data, obtaining a first feature vector corresponding to the driving data of the user; Obtaining the similarity between the first feature vector and the second feature vectors respectively corresponding to at least one candidate user group; According to the similarity, determining the first user group to which the user belongs among at least one candidate user group.

4. The method according to any one of claims 1 to 3, characterized in that, The playing the sound wave signal corresponding to the user includes: According to the first user group to which the user belongs and the pre-constructed mapping relationship between the user group and the sound wave parameter, obtaining a first sound wave parameter corresponding to the first user group; According to the first sound wave parameter, playing the sound wave signal corresponding to the user.

5. The method according to claim 4, characterized in that, Before obtaining the first sound wave parameter corresponding to the first user group according to the first user group to which the user belongs and the pre-constructed mapping relationship between the user group and the sound wave parameter, the method further includes: Obtaining candidate sound wave parameters; Generating a candidate sound wave signal according to the candidate sound wave parameters and playing the candidate sound wave signal; Receiving an operation of the matching degree of the user sample input, and based on the operation, determining the matching degree corresponding to the candidate sound wave parameter, where the matching degree is used to jointly construct the mapping relationship with the historical driving data of the user sample.

6. The method according to any one of claims 1-5, characterized in that, The playing the sound wave signal corresponding to the user includes: Generating sound source signals of multiple tracks according to the sound source generation parameter in the first sound wave parameter; Mixing the sound source signals of the multiple tracks according to the sound source mixing parameter in the first sound wave parameter to obtain a sound source mixed signal; Performing post-processing on the sound source mixed signal according to the post-processing parameter in the first sound wave parameter to obtain and play the sound wave signal.

7. The method according to claim 6, characterized in that The sound source mixing parameter at least includes the sound source loudness corresponding to each track respectively. The mixing the sound source signals of the multiple tracks according to the sound source mixing parameter in the first sound wave parameter to obtain a sound source mixed signal includes: Using the sound source loudness corresponding to each track respectively as the mixing coefficient of the sound source signals of the multiple tracks, performing a multiplication operation on the sound source signals of the multiple tracks to obtain the processed audio signals of the multiple tracks; Summing the processed audio signals of the multiple tracks to obtain the sound source mixed signal.

8. The method according to claim 6 or 7, characterized in that, The post-processing parameter includes an adjustment curve, where the adjustment curve is used to reflect the mapping relationship between the adjustment gain of at least one of the loudness and the pitch and the vehicle speed; the performing post-processing on the sound source mixed signal according to the post-processing parameter in the first sound wave parameter includes: Determining the adjustment gain corresponding to the sound source mixed signal according to the vehicle speed at the first time and the adjustment curve; Perform gain processing on the sound source mixed signal according to the adjustment gain corresponding to the sound source mixed signal; wherein the vehicle speed at the first time is the real-time vehicle speed, or the first time is determined based on at least one of the following: The first moment when a sound wave playing instruction from the user is received; A first time period, where the first moment is included within the first time period; A second time period, where the end moment of the second time period is the first moment.

9. The method according to claim 8, wherein The determining the adjustment gain corresponding to the sound source mixed signal according to the vehicle speed at the first time and the adjustment curve includes: In response to the non-existence of a preset sampling point corresponding to the vehicle speed at the first time on the adjustment curve, determining a first sampling point and a second sampling point on the adjustment curve according to the vehicle speed at the first time, where the vehicle speed at the first time is between the vehicle speed corresponding to the first sampling point and the vehicle speed corresponding to the second sampling point; Performing interpolation calculation on the vehicle speed at the first time, the first sampling point, and the first sampling point to obtain the adjustment gain corresponding to the sound source mixed signal.

10. The method according to claim 8 or 9, characterized in that The post-processing parameters further include sound effect parameters, and the performing post-processing on the sound source mixed signal according to the post-processing parameters in the first sound wave parameters further includes: Performing sound effect processing on the sound source mixed signal that has undergone gain processing according to the sound effect parameters.

11. The method according to any one of claims 6-10, characterized in that, The sound source generation parameters at least include at least one type of acoustic parameters corresponding to the order method and acoustic parameters corresponding to the frequency conversion method; wherein the acoustic parameters corresponding to the order method at least include harmonic amplitude, frequency conversion rate, motor speed, and harmonic order; The acoustic parameters corresponding to the frequency conversion method at least include sound source frequency shift speed and sound source loudness.

12. An acoustic wave generating device, characterized in that, The device includes: A playback module, configured to play the sound wave signal corresponding to the user in response to receiving a sound wave playing instruction from the user, where the first sound wave parameters of the sound wave signal corresponding to the user are associated with a first user group to which the user belongs.

13. A vehicle, characterized in that, including: A processor; A memory for storing instructions executable by the processor; wherein the processor is configured to: Implement the steps of the method according to any one of claims 1-11.

14. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, the steps of the method according to any one of claims 1-11 are implemented.

Images