Seat air bag control method and system based on music

Abstract

The invention provides a seat air bag control method and system based on music, and belongs to the field of air bag control. The method comprises the steps that a rhythm signal of target music is extracted, and a first control signal is generated according to the rhythm signal; extracting a vibration signal of the target music, and generating a second control signal according to the vibration signal; and controlling an air bag of the target seat according to the first control signal, and controlling an exciter of the target seat according to the second control signal, so that the target seat executes a massage action. According to the music-based seat air bag control method and system provided by the invention, the association degree of the music and the air bag can be improved, and immersive experience of the music is provided for customers.

Description

Technical Field

[0001] The present disclosure belongs to the field of airbag control, and more specifically, to a music-based seat airbag control method and system. Background Art

[0002] With the continuous development and innovation of the automotive industry, seat massage airbags have gradually begun to be widely used in car seats of various brands to enhance the user experience in the cockpit. Most of the current airbag massage methods are to inflate and deflate the airbags one by one or in groups at fixed time intervals or regularly changing time intervals, which has a low correlation with music. Therefore, when using the current airbags, it cannot provide an immersive experience linked to music.

[0003] Nowadays, music is not often associated with airbags. Summary of the invention

[0004] The purpose of the present disclosure is to provide a music-based seat airbag control method and system to enhance the correlation between music and airbags and provide customers with an immersive music experience.

[0005] According to a first aspect of an embodiment of the present disclosure, a music-based seat airbag control method is provided, comprising: Extracting a rhythm signal of the target music, and generating a first control signal according to the rhythm signal; Extracting a vibration signal of the target music, and generating a second control signal according to the vibration signal; The airbag of the target seat is controlled according to the first control signal, and the actuator of the target seat is controlled according to the second control signal, so that the target seat performs a massage action.

[0006] A second aspect of the embodiments of the present disclosure provides a music-based seat airbag control system, comprising: A music rhythm extraction module, used for generating a first control signal according to the rhythm signal; A music vibration extraction module, used to generate a second control signal according to the vibration signal; The airbag control module is used to control the airbag of the target seat according to the first control signal, and to control the actuator of the target seat according to the second control signal, so that the target seat performs a massage action.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned music-based seat airbag control method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned music-based seat airbag control method are implemented.

[0009] The music-based seat airbag control method and system provided by the embodiments of the present disclosure have the following beneficial effects: The present disclosure can generate a control signal that matches the rhythm of the music by extracting the rhythm signal and vibration signal of the target music, thereby providing users with a personalized massage experience. It not only enhances the immersion of the music, but also allows users to relax their bodies while enjoying the music. By extracting the rhythm signal and vibration signal of the target music to control the airbag and exciter of the seat, the rhythm and dynamic characteristics of the music can be converted into physical feedback of the seat in real time. Users can get a seat massage experience that is more in line with the music atmosphere according to their favorite music type and rhythm, thereby enhancing entertainment and immersion. The present disclosure is applicable to various types of music, including pop, classical, rock, etc., and can accurately extract the rhythm and vibration signals of different types of music and generate corresponding control signals. It has a wide range of applicability, so that the present disclosure can be applied to different user groups and scene requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of an application scenario of a music-based seat airbag control method provided in an embodiment of the present disclosure; Figure 2 A flowchart of a music-based seat airbag control method provided in one embodiment of the present disclosure; Figure 3 A schematic diagram of a process for extracting Mel-frequency cepstral coefficients provided by an embodiment of the present disclosure; Figure 4 A structural diagram of a diffuse attention mechanism provided by an embodiment of the present disclosure; Figure 5 A schematic diagram of a neural network architecture based on a sound source provided in one embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of a deep learning network model for rhythm extraction provided by an embodiment of the present disclosure; Figure 7A flowchart of another music-based seat airbag control method provided in an embodiment of the present disclosure; Figure 8 A structural block diagram of a music-based seat airbag control system provided by an embodiment of the present disclosure; Fig. 9 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic diagram of an application scenario of a music-based seat airbag control method provided in one embodiment of the present disclosure.

[0015] The disclosed embodiment can be implemented by a music airbag seat, such as Figure 1 (a) and Figure 1 As shown in (b), Figure 1 (a) is a three-dimensional diagram of a music airbag seat provided by an embodiment of the present disclosure, Figure 1 (b) is a rear view of a music airbag seat provided by an embodiment of the present disclosure.

[0016] like Figure 1 As shown in (a), the music airbag seat includes: massage airbags (1)-(14), actuators I-IV, ECU and air pipes. The massage airbags (1)-(14) are used to provide massage for the user and are widely distributed on the shoulders, waist and seat cushion of the music airbag seat. The essence of the massage airbag is the airbag. The gas in the massage airbag comes from Figure 1 (b) The transmission of the air tube, one air tube can correspond to one or more massage air bags, and the inflation and deflation of the massage air bags and the degree of inflation and deflation are controlled by Figure 1 ECU in (b).

[0017] Whether the actuators I to IV vibrate and the intensity of the vibration are controlled by the built-in control chip.

[0018] When the ECU receives the first control signal, the ECU controls the air pipe to inflate or deflate the corresponding massage air bag according to the first control signal. When the exciter receives the second control signal, the ECU controls its own vibration and vibration intensity according to the second control signal.

[0019] Please refer to Figure 2 , Figure 2 A flowchart of a music-based seat airbag control method provided in an embodiment of the present disclosure is provided. The method includes: S101: extracting a rhythm signal of target music, and generating a first control signal according to the rhythm signal.

[0020] In this embodiment, the target music is the music being played or the music according to which the user wants to perform massage, and the rhythm signal is a signal used to represent various characteristics and information of the rhythm.

[0021] Rhythmic signals can be expressed as changes in sound volume, timbre, and periodic characteristics of audio. For example, drum beats are usually an important sign of rhythm. Strong drum beats are louder and have a certain periodicity. These characteristics constitute rhythmic signals, which include beats and re-beats.

[0022] The first control signal is a signal for controlling whether the airbag is inflated and the degree of inflation and deflation. In this embodiment, the first control signal can be obtained through the beats and re-beats in the rhythm signal.

[0023] This embodiment can extract the target music according to the improved deep learning network model or music rhythm extraction algorithm to obtain the rhythm signal of the target music. It can be based on the beat, beat or other features and information used to represent the rhythm in the rhythm signal. Before using the deep learning network model to extract the target signal, the model can be trained using a public data set, and the public data set includes at least one of Ballroom, Hainsworth, RWC, Popular, Harmonix, Carnetic, SMC and GTZAN. This improvement is based on a deep neural network.

[0024] The music in the dataset can be processed by speeding up, slowing down, increasing or decreasing the volume, cutting out a portion of it, or adding random disturbances to expand the number of datasets in order to train a more accurate and reliable deep learning network model.

[0025] S102: extracting a vibration signal of the target music, and generating a second control signal according to the vibration signal.

[0026] In this embodiment, the target music can be transmitted via Bluetooth, ZigBee or data line transmission. Vibration signal refers to the physical vibration generated by music during the transmission process, which can be transmitted through media such as air, solid or liquid, and received by the human ear or other sensors. In order to better understand and process the vibration signal of music, this embodiment can use vibration signal extraction algorithm, neural network model, fast Fourier transform and other methods to process the target music and obtain the vibration signal of the target music.

[0027] The vibration signal includes: amplitude, period, phase, frequency, etc. of the target music.

[0028] According to the rhythmic characteristics of music and the vibration characteristics of objects, a suitable control algorithm is designed to generate a control signal. The control algorithm can be a proportional-integral-differential (PID) control, fuzzy control, neural network control and other methods. For example, PID control can adjust the control signal according to the error (the difference between the rhythm of music and the vibration of the object) so that the vibration of the object gradually approaches the rhythm of music. Fuzzy control can generate control signals according to fuzzy rules and fuzzy reasoning to adapt to different music and vibration conditions. Neural network control can learn the relationship between the rhythm of music and the vibration of objects by training neural networks to achieve more intelligent control. The rhythmic characteristics of music and the vibration characteristics of objects can be used to generate control signals. The control signal can be a voltage signal, a current signal, a pulse signal, etc., which is used to control the output of the vibration source, and the vibration source can be an exciter.

[0029] For example, the larger the vibration amplitude in the vibration signal, the greater the vibration intensity of the exciter will be; the larger the vibration frequency in the vibration signal, the greater the vibration frequency of the exciter will be. The corresponding vibration intensity can be obtained based on the vibration amplitude based on the first mapping table, and the corresponding vibration frequency can be obtained based on the vibration frequency based on the second mapping table. The mapping relationship between the first mapping table and the second mapping table can be set manually.

[0030] S103: Controlling the airbag of the target seat according to the first control signal, and controlling the actuator of the target seat according to the second control signal, so that the target seat performs a massage action.

[0031] In this embodiment, the first control signal is a signal for controlling whether the airbag is inflated and the degree of inflation. The first control signal includes information such as the beat, beat and frequency of the target music. The beat and beat of the target music can be used to control the degree of inflation of the airbag, and the frequency of the target music can be used to control the inflation and deflation speed of the airbag.

[0032] For example, when the beat of the target music appears, the airbag can be controlled to inflate, and the inflation degree of the airbag is 40% of the maximum inflation amount of the airbag. When the beat of the target music appears, the inflation degree of the airbag is 80% of the maximum inflation amount of the airbag.

[0033] In response to the frequency of the target music being greater than a first frequency threshold, controlling the air tube to inflate the airbag at a first rate and to deflate the airbag at a second rate; In response to the frequency of the target music being greater than the second frequency threshold, the air pipe is controlled to inflate the airbag at a third rate and to deflate the airbag at a fourth rate.

[0034] In this embodiment, the second control signal is a signal for controlling whether the exciter vibrates and the vibration intensity, and the second control signal includes the amplitude, period, phase, frequency, etc. of the target music. The amplitude of the target music can be used to control the vibration intensity of the exciter, the frequency of the target music can be used to control the vibration frequency of the exciter, and the period and phase of the target music can be used to control the vibration period of the exciter and the vibration state at a specific moment in a period.

[0035] It can be concluded from the above that the present disclosure can generate a control signal that matches the rhythm of the music by extracting the rhythm signal and vibration signal of the target music, thereby providing users with a personalized massage experience. It not only enhances the immersion of the music, but also allows users to relax their bodies while enjoying the music. By extracting the rhythm signal and vibration signal of the target music to control the airbag and exciter of the seat, the rhythm and dynamic characteristics of the music can be converted into physical feedback of the seat in real time. Users can get a seat massage experience that is more in line with the music atmosphere according to their favorite music type and rhythm, thereby enhancing entertainment and immersion. The present disclosure is applicable to various types of music, including pop, classical, rock, etc., and can accurately extract the rhythm and vibration signals of different types of music and generate corresponding control signals. It has a wide range of applicability, so that the present disclosure can be applied to different user groups and scene requirements.

[0036] In one embodiment of the present disclosure, before extracting the rhythm signal of the target music, the method further includes: Speed ​​up or slow down the music in the dataset based on the first step length; Based on the second step length being equal to the music in the data set, the volume is increased or decreased; Add random perturbations to the music in the dataset; Randomly sample the music in the dataset.

[0037] In this embodiment, the first step length and the second step length can be set manually. You can choose to add random noise to the audio signal, or randomly modulate the frequency of the audio signal to process the music in the data set. The random disturbance can be Gaussian white noise, uniformly distributed noise, etc. The length of the random intercept can be between 10% and 70% of the original music length, or any value between 0% and 100%.

[0038] From the above, it can be concluded that the present invention can increase the diversity of the data set by speeding up, slowing down, increasing the volume, decreasing the volume, adding random perturbations and random interceptions, so that the deep learning model can learn the rhythm characteristics of music at different speeds, which helps to improve the robustness and accuracy of the model.

[0039] In one embodiment of the present disclosure, extracting a rhythm signal of target music includes: Separate the sound source of the target music to obtain multiple sound source signals; determining Mel-frequency cepstral coefficients of a plurality of sound source signals; Determine the Mel-frequency cepstral coefficients of the target music; A rhythm signal of the target music is determined based on the mel-frequency cepstral coefficients of the plurality of sound source signals and the mel-frequency cepstral coefficients of the target music.

[0040] In this embodiment, the input of the deep learning model is the target music signal, with a sampling rate of 48k and a single channel. The music can be separated from the sound source based on the sound source separation technology or the audio source separation tool to obtain the sound sources of five channels, namely, human voice, piano sound, drum sound, bass guitar and others. The audio source separation tool can be spleeter. Then, the Mel-Frequency Cepstral Coefficients (MFCC) are extracted from the sound sources of the five channels and the original sound of the music, respectively, as shown in FIG. Figure 3 As shown, Figure 3 A schematic flow chart of a method for extracting Mel-frequency cepstral coefficients provided in an embodiment of the present disclosure, the method comprising: S201: Perform pre-emphasis processing on the sound source signal to increase the energy of the high-frequency signal.

[0041] S202: Perform frame division processing to divide the audio signal into short-time frames.

[0042] S203: Using a Hamming window function, the short time frame is processed to reduce edge effects.

[0043] S204: Perform Fourier transform on each frame to calculate the frequency spectrum of each frame.

[0044] S205: Perform filtering processing on the spectrum using a Mel frequency (Mel) scale filter bank to better simulate the auditory characteristics of the human ear.

[0045] S206: Perform logarithmic compression and take the logarithm of each filter output.

[0046] S207: Calculate Discrete Cosine Transform (DCT) to obtain MFCC coefficients.

[0047] In this embodiment, the obtained MFCC coefficients may be subjected to convolution and pooling processing to obtain their corresponding features, and the corresponding features may be subjected to feature recognition to obtain the rhythm signal of the target music.

[0048] From the above, it can be concluded that the present invention decomposes the target music into multiple sound source signals through the sound source separation technology, which helps to more accurately analyze the various components of the music. Sound source separation can reduce the interference between different sound sources, making the subsequent rhythm signal extraction more accurate. The accuracy and reliability of music rhythm extraction are improved.

[0049] In one embodiment of the present disclosure, determining a rhythm signal of target music based on Mel-frequency cepstral coefficients of a plurality of sound source signals and Mel-frequency cepstral coefficients of target music includes: Performing convolution and pooling processing on the Mel-frequency cepstral coefficients of multiple sound source signals to obtain multiple first sub-features; Convolution and pooling are performed on the Mel frequency cepstral coefficients of the target music to obtain multiple second sub-features; Using the first network to extract the plurality of first features, to obtain a plurality of second features, wherein the plurality of first features include: a plurality of first sub-features and a plurality of second sub-features; The second network is used to extract the plurality of second features to obtain the rhythm signal of the target music.

[0050] In this embodiment, both the first sub-feature and the second sub-feature can be in the form of a vector or a matrix. For example, after convolution and pooling processing, the time dimension information is retained, and the first sub-feature may be a three-dimensional matrix, for example, the shape may be [number of feature channels, number of time frames, feature dimension]. Among them, the number of feature channels depends on the number of filters used in the convolution operation, the number of time frames corresponds to the number of frames after the audio signal is framed, and the feature dimension is related to the specific processing and design.

[0051] The MFCC coefficients of the sound sources of the five channels are respectively subjected to three convolutions and pooling processes to obtain multiple first sub-features. The processing order is first convolution-first pooling-second convolution-second pooling-third convolution-third pooling. The MFCC coefficients of the original sound are subjected to three convolutions and pooling processes to obtain multiple second sub-features.

[0052] The first network can be a time-domain attention network, which uses the time-domain attention network to process each sound source channel and the original sound channel after convolution and pooling three times to obtain output features (multiple second features), so that the output features can take into account the information before and after the current time point, and also fully consider the information of each sound source and the original sound. In the time-domain attention network, conventional convolution is not used, but a diffusion attention mechanism is used. Figure 4 A structural diagram of a diffuse attention mechanism provided by an embodiment of the present disclosure is shown in FIG. Figure 4 As shown: In the first layer (layer1) of this structure, the convolution of the original input is still calculated, and the stride between columns is 1.

[0053] In the second layer (layer2) of this structure, the stride of the convolution between columns is twice as large as before, that is, 2.

[0054] In the third layer (layer3) of this structure, the stride of the convolution between columns is twice as large as before, that is, 4.

[0055] From the above, it can be concluded that the present disclosure can deeply explore the local features in the audio signal by convolution and pooling the MFCCs of multiple sound source signals and the MFCCs of the target music, and reduce the feature dimension through pooling operations to improve the computational efficiency. It not only retains the time dimension information, but also makes the feature extraction more accurate and detailed, providing strong support for the subsequent rhythm signal recognition. The present disclosure uses a time domain attention network to process each sound source channel and original sound channel after convolution and pooling, so that the output features can fully consider the information before and after the current time point, as well as the interaction between each sound source and the original sound. This mechanism has significant advantages in processing audio signals, and can capture the temporal dependencies in the audio signal and the associations between different sound sources. The present disclosure greatly increases the feature coverage of a fixed time point without increasing the amount of computation by applying an improved diffuse attention mechanism.

[0056] In one embodiment of the present disclosure, a second network is used to extract a plurality of second features to obtain a rhythm signal of the target music, including: Using the second network to extract the plurality of second features, to obtain a plurality of third features; The multiple third features are processed using a feedforward neural network to obtain the rhythm signal of the target music.

[0057] In one embodiment of the present disclosure, a plurality of third features are processed using a feedforward neural network to obtain a rhythm signal of the target music, including: Performing linear transformation on the plurality of third features to obtain a plurality of first feature vectors; Performing nonlinear activation on the multiple first eigenvectors to obtain multiple second eigenvectors; A rhythm signal of the target music is obtained based on the multiple second feature vectors.

[0058] In this embodiment, the second network may be a sound source attention network. The attention network at the sound source level processes the output results of the six channels three times respectively to obtain output features (multiple third features), so that the output features can take into account the influence of different sound sources, such as Figure 5 As shown, Figure 5 A schematic diagram of a structure of a neural network architecture based on a sound source provided in one embodiment of the present disclosure, wherein the structure used here is a Transformer structure based on a sound source channel, and the architecture is specifically explained as follows: First, the Query coefficient matrix is ​​obtained according to the input (multiple second features).

[0059] Secondly, the Key coefficient matrices of the six channels are obtained according to the input (multiple second features).

[0060] Secondly, according to the Query and Key matrices, the attention coefficients of the six channels are calculated.

[0061] Finally, the output of the temporal attention network is multiplied by its corresponding attention coefficient to output features (multiple third features).

[0062] In this embodiment, the feedforward neural network can perform step-by-step nonlinear transformation and combination processing on the features. For example, each neuron of the feedforward neural network performs weighted summation on the input of multiple third features to obtain multiple first feature vectors. This is a linear transformation operation, in which the weight parameter determines the importance of different input features. The activation function is used to perform nonlinear transformation on multiple first feature vectors, introduce nonlinear factors, and obtain multiple second feature vectors. The activation function can be a sigmoid function or a ReLU function, etc.

[0063] From the above, it can be concluded that the present disclosure processes multiple second features through the sound source attention network, so that the output features can fully take into account the influence of different sound sources, and can automatically learn the importance and correlation of different sound sources in the audio signal, thereby extracting more accurate and comprehensive feature information. The present disclosure can perform gradual nonlinear transformation and combination processing on multiple third features through the forward neural network, so as to further explore the complex relationship between the features. The present disclosure realizes the refined processing of audio signal features through the combined processing of the sound source attention network and the forward neural network. The accuracy and reliability of music rhythm extraction are improved.

[0064] In one embodiment of the present disclosure, controlling an airbag of a target seat according to a first control signal includes: The airbag of the target seat is controlled according to the main frequency of the target music and the first control signal.

[0065] In one embodiment of the present disclosure, the airbags of the target seat include shoulder airbags, waist airbags, and seat cushion airbags; Controlling an air bag of a target seat according to a main frequency of target music and a first control signal includes: In response to the main frequency of the target music being in the first range, the first control signal controls the shoulder airbag of the target seat; In response to the main frequency of the target music being in the second range, the first control signal controls the lumbar airbag of the target seat; In response to the main frequency of the target music being in the third range, the first control signal controls the seat cushion airbag of the target seat.

[0066] In this embodiment, the main frequency of the target music can be obtained by fast Fourier transform, autocorrelation analysis or harmonic analysis. The first range, the second range and the third range can be set manually by the user according to their needs. For example, the first range is 800Hz (not included) and above, the second range is 200Hz (inclusive) to 800Hz (inclusive), and the third range is 200Hz (not included) and below. The first range can also be defined as high frequency, the second range as medium frequency, and the third range as low frequency.

[0067] For example, in response to the main frequency of the audio being high frequency (>800 Hz), the control signal acts on the shoulder airbag; In response to the main frequency of the audio being the intermediate frequency (200-800 Hz), the control signal acts on the waist airbag; In response to the main frequency of the audio being low frequency (<200 Hz), the control signal acts on the seat cushion airbag.

[0068] The fullness of the airbag inflation and deflation can be determined dynamically based on the amplitude of the audio signal. The larger the amplitude, the fuller the airbag is inflated.

[0069] From the above, it can be concluded that the present invention realizes dynamic adjustment of seat comfort by responding to different main frequency ranges of the target music and controlling the inflation and deflation states of the shoulder airbags, waist airbags and seat cushion airbags respectively. At the same time, it can provide passengers with support and comfort that better suits their body needs according to the rhythm and melody changes of the music, thereby improving the degree of refined control of the airbag control.

[0070] Please refer to Figure 6 , Figure 6 A schematic diagram of the structure of a deep learning network model for rhythm extraction provided by an embodiment of the present disclosure, the structure is specifically explained as follows: First, the sound source is separated according to the audio signal to obtain the sounds of five channels: vocal, piano, drum, bass, and other. Secondly, the Mel-frequency cepstral coefficients (MFCC) of the above five channels and audio signals are calculated respectively; Secondly, the MFCC of the sound source of the five channels and the MFCC of the original sound (audio signal) are convolved and pooled three times respectively; Secondly, the time-domain attention network is used to process each sound source channel and original sound channel after convolution and pooling three times to obtain output features (multiple second features), so that the output features can take into account the information before and after the current time point, and also fully consider the information of each sound source and original sound. It should be noted that in the time-domain attention network, conventional convolution is not used, but a diffusion attention mechanism is used; Secondly, the output results of the six channels are processed separately through the sound source level attention model network to obtain output features (multiple third features), so that the output features can take into account the influence of different sound sources; Secondly, a feed-forward neural network (FNN) is used to process the results of the sound source attention network. In the feed-forward neural network, the output can be linearly transformed and calculated using the sigmoid activation function. The output result is used as the emission probability distribution in the hidden Markov model, and the loss function of the model here is the cross entropy function.

[0071] Finally, the obtained probability distribution is input into the Dynamic Bayesian Network (DBN) model to obtain the final beat and downbeat estimation results.

[0072] Please refer to Figure 7 , Figure 7A flowchart of another music-based seat airbag control method provided in an embodiment of the present disclosure is specifically explained as follows: First, deploy the music rhythm extraction algorithm and vibration signal extraction algorithm based on deep learning on the host computer; Secondly, input music, extract the rhythm signal of the music through the music rhythm extraction algorithm, and extract the vibration signal of the music through the vibration signal extraction algorithm; Secondly, Lin signal, which is the airbag control signal, is generated according to the rhythm signal of the music. The host computer transmits the Lin signal to the airbag control ECU through the Lin Box, thereby controlling the inflation and deflation of the massage airbag, making the massage rhythm the same as the music rhythm; Lin is a low-cost serial communication protocol used in distributed electronic systems in automobiles; Secondly, the extracted low-level music vibration signal is sent to the power amplifier to be converted into a high-level signal, and then the high-level signal is transmitted from the power amplifier to the exciter, thereby providing a vibration massage effect of the exciter; Finally, when the host computer plays music, the music rhythm signal and the music vibration signal are extracted at the same time, and the low-level signal of the music signal itself is also transmitted to the power amplifier. The power amplifier transmits the high-level signal of the music itself to the speaker, combining the music itself, the vibration effect of the exciter provided by the music vibration signal, and the massage effect provided by the music rhythm signal to provide users with an immersive experience.

[0073] Corresponding to the music-based seat airbag control method of the above embodiment, Figure 8 This is a structural block diagram of a music-based seat airbag control system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 8 The music-based seat airbag control system 20 includes: a music rhythm extraction module 21, a music vibration extraction module 22 and an airbag control module 23.

[0074] Wherein, the music rhythm extraction module 21 is used to generate a first control signal according to the rhythm signal; A music vibration extraction module 22, used to generate a second control signal according to the vibration signal; The airbag control module 23 is used to control the airbag of the target seat according to the first control signal, and to control the actuator of the target seat according to the second control signal, so that the target seat performs a massage action.

[0075] In one embodiment of the present disclosure, the music-based seat airbag control system 20 further includes: a music preprocessing module, the music preprocessing module being used to speed up or slow down the music in the data set based on the first step length; Based on the second step length being equal to the music in the data set, the volume is increased or decreased; Add random perturbations to the music in the dataset; Randomly sample the music in the dataset.

[0076] In one embodiment of the present disclosure, the music rhythm extraction module 21 is specifically used to separate the sound source of the target music to obtain multiple sound source signals; determining Mel-frequency cepstral coefficients of a plurality of sound source signals; Determine the Mel-frequency cepstral coefficients of the target music; A rhythm signal of the target music is determined based on the mel-frequency cepstral coefficients of the plurality of sound source signals and the mel-frequency cepstral coefficients of the target music.

[0077] In one embodiment of the present disclosure, the music rhythm extraction module 21 is further configured to perform convolution and pooling processing on the Mel-frequency cepstral coefficients of the plurality of sound source signals to obtain a plurality of first sub-features; Convolution and pooling are performed on the Mel frequency cepstral coefficients of the target music to obtain multiple second sub-features; Using the first network to extract the plurality of first features, to obtain a plurality of second features, wherein the plurality of first features include: a plurality of first sub-features and a plurality of second sub-features; The second network is used to extract the plurality of second features to obtain the rhythm signal of the target music.

[0078] In one embodiment of the present disclosure, the music rhythm extraction module 21 is further configured to extract the plurality of second features using the second network to obtain a plurality of third features; The multiple third features are processed using a feedforward neural network to obtain the rhythm signal of the target music.

[0079] In one embodiment of the present disclosure, the music rhythm extraction module 21 is further configured to perform a linear transformation on the plurality of third features to obtain a plurality of first feature vectors; Performing nonlinear activation on the multiple first eigenvectors to obtain multiple second eigenvectors; A rhythm signal of the target music is obtained based on the multiple second feature vectors.

[0080] In one embodiment of the present disclosure, the airbag control module 23 is specifically configured to control the airbag of the target seat according to the main frequency of the target music and the first control signal.

[0081] The airbag control module 23 is also specifically used in one embodiment of the present disclosure, where the airbags of the target seat include shoulder airbags, waist airbags, and seat cushion airbags; In response to the main frequency of the target music being in the first range, the first control signal controls the shoulder airbag of the target seat; In response to the main frequency of the target music being in the second range, the first control signal controls the lumbar airbag of the target seat; In response to the main frequency of the target music being in the third range, the first control signal controls the seat cushion airbag of the target seat.

[0082] See also Fig. 9 , Fig. 9 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Fig. 9 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 8 The functions of modules 21 to 23 are shown.

[0083] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0084] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0085] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0086] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the music-based seat airbag control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0087] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0088] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0089] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0093] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A music-based seat airbag control method, characterized in that: include: Extracting a rhythm signal of the target music, and generating a first control signal according to the rhythm signal; Extracting a vibration signal of the target music, and generating a second control signal according to the vibration signal; The airbag of the target seat is controlled according to the first control signal, and the actuator of the target seat is controlled according to the second control signal, so that the target seat performs a massage action.

2. The music-based seat airbag control method according to claim 1, characterized in that: The step of extracting the rhythm signal of the target music comprises: Performing sound source separation on the target music to obtain multiple sound source signals; Determining Mel-frequency cepstral coefficients of the plurality of sound source signals; Determining Mel-frequency cepstral coefficients of the target music; The rhythm signal of the target music is determined based on the mel-frequency cepstral coefficients of the plurality of sound source signals and the mel-frequency cepstral coefficients of the target music.

3. The music-based seat airbag control method according to claim 2, characterized in that: The step of determining the rhythm signal of the target music based on the Mel-frequency cepstral coefficients of the plurality of sound source signals and the Mel-frequency cepstral coefficients of the target music comprises: Performing convolution and pooling processing on the Mel-frequency cepstral coefficients of the multiple sound source signals to obtain multiple first sub-features; Performing convolution and pooling processing on the Mel-frequency cepstral coefficients of the target music to obtain a plurality of second sub-features; Using the first network to extract features from the plurality of first features to obtain a plurality of second features, wherein the plurality of first features include: a plurality of first sub-features and a plurality of second sub-features; The second network is used to extract the plurality of second features to obtain a rhythm signal of the target music.

4. The music-based seat airbag control method according to claim 3, characterized in that: The step of extracting the plurality of second features by using the second network to obtain the rhythm signal of the target music includes: Using the second network to extract features from the plurality of second features to obtain a plurality of third features; The plurality of third features are processed using a feedforward neural network to obtain a rhythm signal of the target music.

5. The music-based seat airbag control method according to claim 4, characterized in that: The method of processing the plurality of third features by using a feedforward neural network to obtain a rhythm signal of the target music includes: Performing a linear transformation on the plurality of third features to obtain a plurality of first feature vectors; Performing nonlinear activation on the multiple first eigenvectors to obtain multiple second eigenvectors; A rhythm signal of the target music is obtained based on the multiple second feature vectors.

6. The music-based seat airbag control method according to claim 1, characterized in that: The step of controlling the airbag of the target seat according to the first control signal comprises: The airbag of the target seat is controlled according to the main frequency of the target music and the first control signal.

7. The music-based seat airbag control method according to claim 6, characterized in that: The airbags of the target seat include shoulder airbags, waist airbags and seat cushion airbags; The method of controlling the airbag of the target seat according to the main frequency of the target music and the first control signal comprises: In response to the main frequency of the target music being in a first range, the first control signal controls the shoulder airbag of the target seat; In response to the main frequency of the target music being in a second range, the first control signal controls the lumbar airbag of the target seat; In response to the main frequency of the target music being in a third range, the first control signal controls a seat cushion airbag of the target seat.

8. A music-based seat airbag control system, characterized in that: include: A music rhythm extraction module, used for generating a first control signal according to the rhythm signal; A music vibration extraction module, used to generate a second control signal according to the vibration signal; The airbag control module is used to control the airbag of the target seat according to the first control signal, and to control the actuator of the target seat according to the second control signal, so that the target seat performs a massage action.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images