Personalized brain wave induction audio generation method and system

Abstract

The invention relates to the technical field of neuroacoustics, in particular to a personalized brain wave induced audio generation method and system, and the method comprises the steps: S1, extracting multi-dimensional features of an input audio signal, the extracted dimensions at least comprising a time domain feature, a frequency domain feature, a pitch feature, an emotion feature and a complex feature; s2, on the basis of the multi-dimensional features extracted in the step S1, parameters of four neuroacoustic induction mechanisms are calculated in parallel; and S3, according to the features obtained in the step S1 and the quadruple mechanism parameters obtained in the step S2, signals corresponding to the four mechanisms are fused through a weight distribution strategy and a signal synthesis formula to generate a final brain wave induction audio. The method has the advantages that four mechanisms of rhythm synchronization, harmonic resonance, neural oscillation coupling and binaural beat frequency effect are fused, parameters of all the mechanisms are dynamically adjusted by analyzing music characteristics, and efficient personalized brain wave induction is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of neuroacoustics, in particular to a personalized brainwave entrainment audio generation method and system. BACKGROUND

[0002] Brainwave is an electrical oscillation generated by the activity of neurons in the brain, which is divided into five types according to its frequency: delta (<4Hz), theta (4-8Hz), alpha (8-14Hz), beta (14-30Hz) and gamma (>30Hz), which correspond to different states of consciousness such as unconsciousness, subconsciousness, bridge consciousness, consciousness and high concentration, and directly determine the individual's mood, behavior and learning performance. Brainwave entrainment technology uses external rhythmic stimulation to synchronize brain electrical activity to the target frequency, thereby quickly adjusting the state of consciousness. Acoustic entrainment has become the mainstream method because of its convenience, among which the binaural beats have the longest history: in 1839, Dove discovered that when the left and right ears respectively listen to two sinusoidal sounds with a frequency difference of less than 30Hz and a carrier frequency of less than 1500Hz, the central auditory system will generate a "third sound" equal to the difference frequency, and then entrain the brain electrical activity to the difference frequency. After Oster confirmed in 1973 that it can quantitatively affect the brain electrical activity and the endocrine system, binaural beats have been used to assist meditation, pain relief, sleep and postoperative opioid reduction.

[0003] However, the existing technology generally directly uses a single-frequency sinusoidal wave as a carrier, which is monotonous and lacks musicality, and the brain is easy to adapt, so the entrainment efficiency decreases over time; and the frequency template is fixed (such as the general 10Hz), which does not consider the real-time brain electrical activity of individuals, and needs to rely on expert manual selection of parameters, which has high experimental and adjustment costs, and is difficult to meet the needs of personalized and continuous application. Therefore, there is an urgent need for a brainwave entrainment solution that combines music appreciation, real-time adaptive optimization of stimulation parameters, low cost, and is suitable for daily scenarios. And the existing brainwave entrainment technology mainly uses fixed frequency audio with a single mechanism, which fails to fully utilize the synergistic effect of multiple neuroacoustic mechanisms. The traditional method has the following technical problems: the single binaural beats mechanism has limited effect and lacks multi-mechanism synergy; it does not consider the synchronization coupling effect of music rhythm and neural oscillation; it ignores the enhancement effect of harmonic resonance on brainwave entrainment; and it lacks an adaptive adjustment mechanism based on individual neural characteristics. SUMMARY

[0004] The present application aims to overcome the shortcomings of the prior art and provide a personalized brainwave entrainment audio generation method and system, which realizes efficient personalized brainwave entrainment by fusing multiple neuroacoustic mechanisms and dynamically optimizing the parameters of each mechanism according to the music characteristics.

[0005] In order to achieve the above-mentioned purpose, a personalized brain wave induction audio generation method and system are designed, comprising: step S1, extracting multi-dimensional features of an input audio signal, the multi-dimensional features including but not limited to: time domain features, frequency domain features, pitch features, emotion features and complexity features; step S2, based on the multi-dimensional features extracted in step S1, the parameters of one or more neuroacoustic induction mechanisms are calculated in parallel, the parameters of the neuroacoustic induction mechanism including: rhythm synchronization mechanism parameters, harmonic resonance mechanism parameters, neural oscillation coupling mechanism parameters, binaural beat frequency effect parameters; step S3, the features obtained in step S1 and the parameters of one or more neuroacoustic induction mechanisms in step S2 are fused to generate the final brain wave induction audio through a weight distribution strategy and a signal synthesis formula.

[0006] Preferably, the present application further comprises: the time-domain features at least include: tempo, beat intensity, beat stability; the frequency-domain features at least include: fundamental frequency, harmonic structure; the pitch features at least include: musical tonality; the emotion features at least include: emotional value; the complexity features at least include: rhythm complexity, harmony complexity; the step 2 further comprises: step S2.1 calculating the rhythm synchronization mechanism parameters: calculating the main beat frequency f_rhythm based on the tempo, calculating the beat synchronization target frequency f_sync based on the set target brain wave frequency f_target and the main beat frequency f_rhythm, calculating the rhythm synchronization mechanism generated time-domain signal S_rhythm(t) based on the synchronization target frequency f_sync; step S2.2 calculating the harmonic resonance mechanism parameters: calculating the best harmonic match f_resonance with the target brain wave frequency based on the musical fundamental frequency f_fundamental and the set target brain wave frequency f_target; calculating the harmonic resonance mechanism generated time-domain signal S_harmonic(t) based on the best harmonic match f_resonance; step S2.3 calculating the neural oscillation coupling mechanism parameters: calculating the neural oscillation coupling frequency f_coupling based on the set target brain wave frequency f_target and the modulation frequency f_modulation set according to the specific induced task, calculating the neural oscillation coupling mechanism generated time-domain signal S_coupling(t) based on the neural oscillation coupling frequency f_coupling; step S2.4. Calculate the binaural beat effect parameter: calculate the basic carrier frequency f_carrier according to the music key music_key and the key frequency map key_frequency_map, calculate the binaural beat difference Δf_binaural based on the set target brain wave frequency f_target and the correction factor correction_factors, calculate the left ear frequency f_left based on the basic carrier frequency f_carrier, calculate the right ear frequency f_right based on the basic carrier frequency f_carrier and the binaural beat difference Δf_binaural, calculate the binaural beat effect mechanism to generate the time domain signal S_binaural(t) based on the left ear frequency f_left and the right ear frequency f_right; wherein the weight distribution strategy includes: calculating the rhythm synchronization mechanism weight W_rhythm according to the rhythm complexity rhythm_complexity, calculating the harmonic resonance mechanism weight W_harmonic according to the harmonic richness harmonic_richness, calculating the neural oscillation coupling mechanism weight W_coupling according to the neural compatibility neural_compatibility calculated by the system according to the user historical brain wave feedback data, calculating the binaural beat mechanism weight W_binaural according to the rhythm synchronization mechanism weight W_rhythm, the harmonic resonance mechanism weight W_harmonic, and the neural oscillation coupling mechanism weight W_coupling; finally, the final synthesized audio signal S_total(t) is obtained by jointly calculating the rhythm synchronization mechanism generated time domain signal S_rhythm(t), the harmonic resonance mechanism generated time domain signal S_harmonic(t), the neural oscillation coupling mechanism generated time domain signal S_coupling(t), the binaural beat effect mechanism generated time domain signal S_binaural(t), the rhythm synchronization mechanism weight W_rhythm, the harmonic resonance mechanism weight W_harmonic, the neural oscillation coupling mechanism weight W_coupling, and the binaural beat mechanism weight W_binaural.

[0007] Preferably, the present application further comprises: the step S1 specifically comprises: the extracted time domain features include: beat speed, beat intensity, beat stability, micro beat change; the extracted frequency domain features include: fundamental frequency, harmonic structure, spectral centroid, spectral bandwidth, spectral roll-off point; the extracted pitch features include: music key, mode type, chord progression, interval relationship; the extracted emotional features include: energy value, emotional value, tension, activity; the extracted complex features include: MFCC coefficient, tonal vector, rhythm complexity, harmonic richness.

[0008] Preferably, the application further comprises: the rhythm synchronization mechanism parameters in step S2 specifically include: the main rhythm frequency: f_rhythm=BPM / 60; wherein BPM represents the beat speed of music, the unit is beats per minute, which is obtained by step S1 of multi-dimensional music feature extraction; the beat harmonic sequence: f_harm_n=f_rhythm*n; wherein n represents the beat harmonic number, which takes values (1, 2, 3, 4, 5); calculate the beat synchronization strength: S_rhythm=beat_stability*beat_intensity; wherein beat_stability represents the beat stability, which is used to quantify the beat uniformity, beat_intensity represents the beat intensity, which is used to quantify the beat strength, both of which are obtained by step S1 of multi-dimensional music feature extraction; the beat synchronization target frequency: f_sync=f_target*(1+α*sin(2π*f_rhythm*t)); wherein f_target represents the target brain wave frequency, which is set by the specific induction task; α represents the synchronization depth coefficient, α∈[0.1, 0.3], t represents the time variable; rhythm synchronization mechanism generates time domain signal: S_rhythm(t)=sin(2π*f_sync*t).

[0009] Preferably, the application further comprises: the harmonic resonance mechanism parameters in step S2 specifically include: extracting the music fundamental frequency in multi-dimensional music features: f_fundamental; harmonic sequence: f_harmonic_k=f_fundamental*k; wherein k represents the harmonic number, which takes values 1, 2, 3, …, 10; the best harmonic matching with the target brain wave frequency: k_optimal=argmin|f_target-f_fundamental*k|; f_resonance=f_fundamental*k_optimal; wherein, k_optimal represents the harmonic number that minimizes |f_target-f_fundamental*k|, f_target represents the target brain wave frequency, which is set by the specific induction task, f_resonance represents the selected best harmonic resonance frequency; harmonic resonance strength: R_harmonic=1 / (1+|f_target-f_resonance|); wherein, R_harmonic represents the harmonic resonance strength, the value range is 0-1; harmonic resonance mechanism generates time domain signal: S_harmonic(t)=sin(2π*f_resonance*t).

[0010] Preferably, the present application further comprises: the neural oscillation coupling mechanism parameters in the step S2 specifically include: neural oscillation coupling frequency: f coupling = f target + β * cos (2π * f modulation * t); wherein, β represents a coupling strength coefficient, used to control the modulation amplitude; f target represents a target brain wave frequency, set by a specific induction task; f modulation represents a modulation frequency set according to a specific induction task; define the coupling phase relationship: φ coupling = 2π * f rhythm * t + φ offset; wherein, φ coupling represents the instantaneous phase of neural oscillation coupling; φ offset represents an initial phase offset, set by the system according to a specific induction task; coupling coefficient: C neural = tanh (|f target - f rhythm | / σ); wherein, C neural represents a neural oscillation coupling coefficient, with a value range of 0-1; σ is a coupling sensitivity parameter, used to determine the steepness of the output curve; neural oscillation coupling mechanism generates time domain signal: S coupling (t) = sin (2π * f coupling * t).

[0011] Preferably, the present application further comprises: the binaural beat effect parameters in the step S2 specifically include: calculate the base carrier frequency: f carrier = key_frequency_map (music_key); wherein, key_frequency_map () represents a base frequency table indexed by music tonality, and music_key is a music tonality; binaural beat difference: Δf binaural = f target * correction_factors; wherein, correction_factors represent correction coefficients for individual differences and hardware systems, and f target represents a target brain wave frequency, set by a specific induction task; left ear frequency: f left = f carrier; right ear frequency: f right = f carrier + Δf binaural; binaural beat modulation depth: M binaural = 0.3 + 0.4 * valence_factor; wherein, M binaural represents the binaural beat modulation depth; valence_factor represents a music emotional value factor, obtained by the multi-dimensional music feature extraction in step S1; binaural beat effect mechanism generates time domain signal: S binaural (t) = sin (2π * f left * t) - sin (2π * f right * t).

[0012] Preferably, the present application further comprises: the weight distribution strategy in S3 specifically comprises: dynamically distributing the weights of the four mechanisms according to the music features and target states extracted in step S1: W_rhythm=0.2+0.3*rhythm_complexity; W_harmonic=0.15+0.25*harmonic_richness; W_coupling=0.25+0.2*neural_compatibility; W_binaural=0.40.1*(W_rhythm+W_harmonic+W_coupling); wherein W_rhythm represents the weight of the rhythm synchronization mechanism; rhythm_complexity represents the rhythm complexity, obtained by multi-dimensional music feature extraction in step S1; W_harmonic represents the weight of the harmonic resonance mechanism; harmonic_richness represents the harmonic complexity, obtained by multi-dimensional music feature extraction in step S1; W_coupling represents the weight of the neural oscillation coupling mechanism; neural_compatibility represents the neural compatibility, calculated by the system according to the user's historical brain wave feedback data; W_binaural represents the weight of the binaural beat frequency mechanism, used to ensure that the sum of the four weights is 1.

[0013] Preferably, the present application further comprises: the signal synthesis formula in S3 specifically comprises: S_total(t)=W_rhythm*S_rhythm(t)+W_harmonic*S_harmonic(t)+W_coupling*S_coupling(t)+W_binaural*S_binaural(t); S_total(t) represents the final synthesized audio signal; S_rhythm(t) represents the time domain signal generated by the rhythm synchronization mechanism; W_rhythm represents the weight of the rhythm synchronization mechanism; S_harmonic(t) represents the time domain signal generated by the harmonic resonance mechanism; W_harmonic represents the weight of the harmonic resonance mechanism; S_coupling(t) represents the time domain signal generated by the neural oscillation coupling mechanism; W_coupling represents the weight of the neural oscillation coupling mechanism; S_binaural(t) represents the time domain signal generated by the binaural beat effect mechanism; W_binaural represents the weight of the binaural beat frequency mechanism; the final output signal S_total(t).

[0014] The present application also provides a personalized brain wave induction audio generation system for the method, comprising: a music feature analysis module for performing step S1; a four-mechanism parameter calculation module for performing step S2; a multi-mechanism fusion algorithm module for performing step S3; a signal synthesis and output module for outputting the final brain wave induction audio.

[0015] Preferably, the present application further comprises: wherein the music feature analysis module comprises: a time domain feature extraction submodule, a frequency domain feature extraction submodule, a pitch feature extraction submodule, an emotion feature extraction submodule, a complexity feature extraction submodule.

[0016] Compared with the prior art, the present application has the advantages that: The application discloses a personalized brain wave induction audio generation method and system based on multiple neuroacoustic mechanisms. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The figure is a block diagram of the personalized brain wave induction algorithm of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, principle and structure of the present application clearer and more comprehensible, the following specific embodiments are further described.

[0019] Reference Figure 1The application provides a personalized brain wave induction audio generation method and system, comprising the following steps: S1, extracting multi-dimensional features of an input audio signal, wherein the dimensions include at least time domain features, frequency domain features, pitch features, emotion features and complexity features; wherein the time domain features include at least beat speed, beat intensity and beat stability; the frequency domain features include at least fundamental frequency and harmonic structure; the pitch features include at least musical tonality; the emotion features include at least emotional value; and the complexity features include at least rhythm complexity and harmony complexity; S2, calculating rhythm synchronization mechanism parameters, harmonic resonance mechanism parameters, neural oscillation coupling mechanism parameters and binaural beat frequency effect parameters according to the features obtained in step S1; S2, based on the multi-dimensional features extracted in step S1, parallelly calculating parameters of four neuroacoustic induction mechanisms; S2.1, calculating rhythm synchronization mechanism parameters: calculating a main beat frequency f_rhythm based on the beat speed, calculating a beat synchronization target frequency f_sync based on a target brain wave frequency f_target and the main beat frequency f_rhythm, and calculating a rhythm synchronization mechanism generated time domain signal S_rhythm(t) based on the synchronization target frequency f_sync; S2.2, calculating harmonic resonance mechanism parameters: calculating an optimal harmonic matching f_resonance with the target brain wave frequency based on a music fundamental frequency f_fundamental and the target brain wave frequency f_target, and calculating a harmonic resonance mechanism generated time domain signal S_harmonic(t) based on the optimal harmonic matching f_resonance; S2.3, calculating neural oscillation coupling mechanism parameters: calculating a neural oscillation coupling frequency f_coupling based on the target brain wave frequency f_target and a modulation frequency f_modulation set according to a specific induction task, and calculating a neural oscillation coupling mechanism generated time domain signal S_coupling(t) based on the neural oscillation coupling frequency f_coupling; and S2.4. Calculate the binaural beat effect parameter: calculate the basic carrier frequency f_carrier according to the music key music_key and the key frequency map key_frequency_map, calculate the binaural beat difference Δf_binaural based on the set target brain wave frequency f_target and the correction factor correction_factors, calculate the left ear frequency f_left based on the basic carrier frequency f_carrier, calculate the right ear frequency f_right based on the basic carrier frequency f_carrier and the binaural beat difference Δf_binaural, and calculate the binaural beat effect mechanism to generate the time domain signal S_binaural(t) based on the left ear frequency f_left and the right ear frequency f_right; step S3, according to the characteristics obtained in step S1 and the four mechanism parameters obtained in step S2, the signals corresponding to the four mechanisms are fused to generate the final brain wave induction audio through the weight distribution strategy and the signal synthesis formula; wherein the weight distribution strategy includes: calculating the rhythm synchronization mechanism weight W_rhythm according to the rhythm complexity rhythm_complexity, calculating the harmonic resonance mechanism weight W_harmonic according to the harmonic richness harmonic_richness, calculating the neural oscillation coupling mechanism weight W_coupling according to the neural compatibility neural_compatibility calculated by the system according to the user's historical brain wave feedback data, and calculating the binaural beat mechanism weight W_binaural according to the rhythm synchronization mechanism weight W_rhythm, the harmonic resonance mechanism weight W_harmonic, the neural oscillation coupling mechanism weight W_coupling; finally, the final synthesized audio signal S_total(t) is obtained through the joint calculation of the rhythm synchronization mechanism generated time domain signal S_rhythm(t), the harmonic resonance mechanism generated time domain signal S_harmonic(t), the neural oscillation coupling mechanism generated time domain signal S_coupling(t), the binaural beat effect mechanism generated time domain signal S_binaural(t), the rhythm synchronization mechanism weight W_rhythm, the harmonic resonance mechanism weight W_harmonic, the neural oscillation coupling mechanism weight W_coupling, and the binaural beat mechanism weight W_binaural.

[0020] The step S1 specifically includes: the extracted time domain features include: beat speed, beat intensity, beat stability, micro beat change; the extracted frequency domain features include: fundamental frequency, harmonic structure, spectral centroid, spectral bandwidth, spectral roll-off point; the extracted pitch features include: music key, mode type, chord progression, interval relationship; the extracted emotional features include: energy value, emotional value, tension, activity; the extracted complex features include: MFCC coefficient, hue vector, rhythm complexity, harmonic complexity.

[0021] The rhythm synchronization mechanism parameters in step S2 specifically include: main beat frequency: f_rhythm=BPM / 60; wherein BPM represents the beat speed of music, with the unit of beats per minute, obtained through multi-dimensional music feature extraction in step S1; beat harmonic sequence: f_harm_n=f_rhythm*n; wherein n represents the beat harmonic number, taking values of (1, 2, 3, 4, 5); calculate the beat synchronization strength: S_rhythm=beat_stability*beat_intensity; wherein beat_stability represents the beat stability, which is used to quantify the beat uniformity, beat_intensity represents the beat intensity, which is used to quantify the beat strength, both of which are obtained through multi-dimensional music feature extraction in step S1; beat synchronization target frequency: f_sync=f_target*(1+α*sin(2π*f_rhythm*t)); wherein f_target represents the target brain wave frequency, which is set by the specific induction task; α represents the synchronization depth coefficient, α∈[0.1, 0.3], t represents the time variable; rhythm synchronization mechanism generates time domain signal: S_rhythm(t)=sin(2π*f_sync*t).

[0022] The harmonic resonance mechanism parameters in step S2 specifically include: extracting the music fundamental frequency in multi-dimensional music features: f_fundamental; harmonic sequence: f_harmonic_k=f_fundamental*k; wherein k represents the harmonic number, taking values of 1, 2, 3, …, 10; best harmonic matching with target brain wave frequency: k_optimal=argmin|f_target-f_fundamental*k|; f_resonance=f_fundamental*k_optimal; wherein k_optimal represents the harmonic number that minimizes |f_target-f_fundamental*k|, f_target represents the target brain wave frequency, which is set by the specific induction task, f_resonance represents the selected best harmonic resonance frequency; harmonic resonance strength: R_harmonic=1 / (1+|f_target-f_resonance|); wherein R_harmonic represents the harmonic resonance strength, with a value range of 0-1; harmonic resonance mechanism generates time domain signal: S_harmonic(t)=sin(2π*f_resonance*t).

[0023] The neural oscillation coupling mechanism parameters in step S2 specifically include: neural oscillation coupling frequency: f_coupling=f_target+β*cos(2π*f_modulation*t); wherein β represents a coupling strength coefficient for controlling the modulation amplitude; f_target represents a target brain wave frequency set by a specific induction task; f_modulation represents a modulation frequency set according to a specific induction task; define the coupling phase relationship: φ_coupling=2π*f_rhythm*t+φ_offset; wherein φ_coupling represents the instantaneous phase of neural oscillation coupling; φ_offset represents an initial phase offset set by the system according to a specific induction task; coupling coefficient: C_neural=tanh(|f_target-f_rhythm| / σ); wherein C_neural represents a neural oscillation coupling coefficient, the value range of which is 0-1; σ is a coupling sensitivity parameter for determining the steepness of the output curve; and the neural oscillation coupling mechanism generates a time domain signal: S_coupling(t)=sin(2π*f_coupling*t).

[0024] The binaural beat effect parameters in step S2 specifically include: calculating the base carrier frequency: f_carrier=key_frequency_map(music_key); wherein key_frequency_map() represents a base frequency reference table indexed by music tonality, and music_key is the music tonality; binaural beat difference: Δf_binaural=f_target*correction_factors; wherein correction_factors represent correction coefficients for individual differences and hardware systems, and f_target represents a target brain wave frequency set by a specific induction task; left ear frequency: f_left=f_carrier; right ear frequency: f_right=f_carrier+Δf_binaural; binaural beat modulation depth: M_binaural=0.3+0.4*valence_factor; wherein M_binaural represents the binaural beat modulation depth; valence_factor represents a music emotional value factor obtained through the multi-dimensional music feature extraction in step S1; and the binaural beat effect mechanism generates a time domain signal: S_binaural(t)=sin(2π*f_left*t)-sin(2π*f_right*t).

[0025] The weight distribution strategy in S3 specifically includes: dynamically distributing the weights of the four mechanisms according to the music features and target states extracted in step S1: W_rhythm=0.2+0.3*rhythm_complexity; W_harmonic=0.15+0.25*harmonic_richness; W_coupling=0.25+0.2*neural_compatibility; W_binaural=0.40.1*(W_rhythm+W_harmonic+W_coupling); wherein W_rhythm represents the weight of the rhythm synchronization mechanism; rhythm_complexity represents rhythm complexity, obtained by multi-dimensional music feature extraction in step S1; W_harmonic represents the weight of the harmonic resonance mechanism; harmonic_richness represents the complexity of the sound, obtained by multi-dimensional music feature extraction in step S1; W_coupling represents the weight of the neural oscillation coupling mechanism; neural_compatibility represents neural compatibility, calculated by the system according to user historical brain wave feedback data; W_binaural represents the weight of the binaural beat frequency mechanism, used to ensure that the sum of the four weights is 1.

[0026] The signal synthesis formula in S3 specifically includes: S_total(t)=W_rhythm*S_rhythm(t)+W_harmonic*S_harmonic(t)+W_coupling*S_coupling(t)+W_binaural*S_binaural(t); S_total(t) represents the final synthesized audio signal; S_rhythm(t) represents the time domain signal generated by the rhythm synchronization mechanism; W_rhythm represents the weight of the rhythm synchronization mechanism; S_harmonic(t) represents the time domain signal generated by the harmonic resonance mechanism; W_harmonic represents the weight of the harmonic resonance mechanism; S_coupling(t) represents the time domain signal generated by the neural oscillation coupling mechanism; W_coupling represents the weight of the neural oscillation coupling mechanism; S_binaural(t) represents the time domain signal generated by the binaural beat frequency effect mechanism; W_binaural represents the weight of the binaural beat frequency mechanism; the final output signal S_total(t).

[0027] Among them, it is worth mentioning: among them "f_harm_n=f_rhythm*n (n=1-5)", "S_rhythm=beat_stability*beat_intensity", "f_harmonic_k=f_fundamental*k (k=1-10)", "R_harmonic=1 / (1+|f_target-f_resonance|)", "φ_coupling=2π*f_rhythm*t+φ_offset", "C_neural=tanh(|f_target-f_rhythm| / σ)", "M_binaural=0.3+0.4*valence_factor" are not directly involved in the expression calculation of the final synthesis signal, but they all have corresponding effects.

[0028] The following item by item description of the above 7 parameters which do not directly participate in the final signal expression calculation in the invention The exact position, calculation purpose, data flow and use method.

[0029] 1. "f_harm_n=f_rhythm*n".

[0030] The design purpose is to generate a list of 1-5th harmonic frequencies of the beat frequency, which is used for the pool of alternative synchronization frequency points. Interface is reserved for future multi-order beat synchronization expansion (such as 2, 3 beat frequency coupling).

[0031] 2. "S_rhythm=beat_stability*beat_intensity".

[0032] The design purpose is to quantify the "beat salience" of the current segment. It can be mapped as one of the inputs of "rhythm_complexity" in weight allocation: "W_rhythm=0.2+0.3*rhythm_complexity". Among them, "rhythm_complexity" can be obtained by normalizing "S_rhythm" (which can be collectively expressed by "rhythm complexity"). It can be used to indirectly affect the weight and visualize the characteristic index of the audio.

[0033] 3. "f_harmonic_k=f_fundamental*k" (k=1-10).

[0034] The design purpose is to generate 10 candidate harmonic frequencies for finding the best match.

[0035] In data flow, it is consumed by "k_optimal=argmin|f_target−f_harmonic_k|" immediately to select a single "f_resonance", and discarded after selection, no longer participating in the operation. Its role is to search the space once and discard it after use.

[0036] 4. "R_harmonic=1 / (1+|f_target−f_resonance|)" Its design purpose is to measure the frequency distance between the selected harmonic and the target brain wave. Its data flow is: In the weight allocation stage, it can be mapped as a component of "harmonic_richness": "W_harmonic=0.15+0.25*harmonic_richness", where "harmonic_richness" can be directly taken "R_harmonic" or normalized from it. It can indirectly affect the weight and visualize the audio feature indicators.

[0037] 5. "φ_coupling=2π*f_rhythm*t+φ_offset".

[0038] Its design purpose is to give the instantaneous phase reference of the coupled oscillator. And it is used as a reserved phase interface and debugging visualization.

[0039] 6. "C_neural=tanh(|f_target−f_rhythm| / σ)".

[0040] Its design purpose is to quantify the frequency distance reliability of "target brain wave frequency" and "rhythm frequency". It can be applied to subsequent adaptive learning backup indicators and evaluation logs.

[0041] 7. "M_binaural=0.3+0.4*valence_factor".

[0042] Its design purpose is to determine the modulation depth (left-right ear amplitude difference) of the binaural beat signal. It can be used as a design reserved depth parameter and visualized / logged.

[0043] Therefore, these 7 parameters in the current disclosure scheme all belong to auxiliary quantitative indicators that "do not drive signals, but support weights, logs, or future extensions".

[0044] The application further provides a personalized brain wave induction audio generation system for the method, comprising: a music feature analysis module for performing step S1; a quadruple mechanism parameter calculation module for performing step S2; a multi-mechanism fusion algorithm module for performing step S3; and a signal synthesis and output module for outputting the final brain wave induction audio. The music feature analysis module comprises: a time domain feature extraction submodule, a frequency domain feature extraction submodule, a pitch feature extraction submodule, a sentiment feature extraction submodule, and a complexity feature extraction submodule.

[0045] The input audio is selected as a C major, four-four beat, speed BPM=80 piano solo segment, with a length of 5 minutes.

[0046] The system first performs step S1: through a conventional beat tracking algorithm, the beat speed BPM=80, the beat intensity beat_intensity=0.72, and the beat stability beat_stability=0.85 are extracted; through an autocorrelation method, the fundamental frequency f_fundamental=261.6Hz is obtained, and the first 10 harmonics are taken; through a tonality estimation module, music_key=“C” is confirmed; through a sentiment classification model, valence_factor=0.45 is obtained; through a rhythm complexity algorithm, rhythm_complexity=0.38 and harmonic_richness=0.52 are obtained; according to the average of the EEG similarity feedback of the user in the last 10 times, neural_compatibility=0.67 is calculated by the system.

[0047] Then step S2 is entered.

[0048] Rhythm synchronization mechanism: f_rhythm=BPM / 60=1.33Hz, the first 1-5 beat harmonics are taken, the synchronization depth coefficient α=0.2, f_sync=6*(1+0.2sin(2π*1.33t) is generated, and then S_rhythm(t)=sin(2πf_synct) is obtained.

[0049] Harmonic resonance mechanism: among the 1-10 harmonics of the fundamental frequency 261.6Hz, the 23rd harmonic 6016.8Hz has the smallest difference with the target 6Hz, so k_optimal=23, f_resonance=6016.8Hz, resonance intensity R_harmonic=0.98, and S_harmonic(t)=sin(2π*6016.8t) is generated.

[0050] Neural oscillation coupling mechanism: take modulation frequency f_modulation=0.1 Hz, coupling strength coefficient β=0.15, get f_coupling=6+0.15cos(2π*0.1t), coupling coefficient C_neural=tanh(|6-1.33| / 2)=0.94, generate S_coupling(t)=sin(2πf_couplingt).

[0051] Binaural beat mechanism: look up key_frequency_map, "C" corresponds to f_carrier=256 Hz, correction factor correction_factors is calibrated to 1.0, get Δf_binaural=6 Hz, so f_left=256 Hz, f_right=262 Hz, modulation depth M_binaural=0.3+0.4*0.45=0.48, generate S_binaural(t)=sin(2π*256t)-sin(2π*262t).

[0052] Enter step S3.

[0053] Weight distribution: W_rhythm=0.2+0.3*0.38=0.314.

[0054] W_harmonic=0.15+0.25*0.52=0.280.

[0055] W_coupling=0.25+0.2*0.67=0.384.

[0056] W_binaural=0.4-0.1*(0.314+0.280+0.384)=0.302.

[0057] The sum of the four weights is 1.000, which meets the normalization requirement.

[0058] Calculate S_total(t) according to the synthesis formula.

[0059] S_total(t)=0.314*S_rhythm(t)+0.280*S_harmonic(t)+0.384*S_coupling(t)+0.302S_binaural(t).

[0060] The final audio file with 48 kHz sampling and 16 bit level is obtained by the point-by-point superposition. The user wears a common stereo headphone to play the audio. The specific calculation process of the parameters and the experimental results in the sleep-aiding scenario are given in this embodiment. For other induction tasks, such as concentration, relaxation or analgesia, only the f_target, the modulation frequency, the correction coefficient and the music input need to be replaced by the corresponding values, and the above steps can be repeated without additional hardware or algorithm modification.

[0061] Preferably, based on the present application, one or more parameters of the neuro-acoustic induction mechanism can be selected by the skilled person in the art according to the needs to participate in the operation, and the specific method is: in the signal synthesis of step S3, the weight corresponding to the parameter of a certain neuro-acoustic induction mechanism can be set to 0, and the weights corresponding to the parameters of other neuro-acoustic induction mechanisms are adaptively adjusted, so that the parameter of the neuro-acoustic induction mechanism does not participate in the operation of the final audio signal synthesis. Thus, the skilled person can select one or more parameters of the neuro-acoustic induction mechanism to participate in the operation of the final audio signal synthesis of the brain wave induction audio according to the specific needs.

[0062] Embodiment 1: Concentration state induction (classical music scenario).

[0063] Music feature input: track: Bach's Well-Tempered Clavier in C major Prelude, beat: 72 BPM, beat stability: 0.95, tonality: C major, fundamental frequency: 261.63 Hz, harmonic complexity: 0.8, rhythm complexity: 0.3, energy value: 0.6, emotional value: 0.7.

[0064] Four-mechanism parameter calculation: 1. Rhythm synchronization mechanism.

[0065] Main beat frequency: f_rhythm=72 / 60=1.2 Hz.

[0066] Beat harmonics: 1.2 Hz, 2.4 Hz, 3.6 Hz, 4.8 Hz, 6.0 Hz.

[0067] Synchronization strength: S_rhythm=0.95*0.6=0.57.

[0068] Target beta wave frequency selection: 20 Hz.

[0069] Beat synchronization modulation: f_sync=20*(1+0.2*sin(2*pi*1.2*t)).

[0070] 2. Harmonic resonance mechanism.

[0071] Music fundamental frequency: 261.63 Hz.

[0072] Finding the best harmonic match: 20 Hz ≈ 261.63 Hz / 13.08.

[0073] Selecting the 13th harmonic: f_resonance = 261.63 / 13 = 20.13 Hz.

[0074] Resonance strength: R_harmonic = 1 / (1 + |20 - 20.13|) = 0.885.

[0075] 3. Neural oscillation coupling mechanism.

[0076] Modulation frequency: f_modulation = 1.2 Hz (synchronized with the beat).

[0077] Coupling frequency: f_coupling = 20 + 1.5 * cos(2π * 1.2 * t).

[0078] Coupling coefficient: C_neural = tanh(|20 - 1.2| / 5) = 0.967.

[0079] 4. Binaural beat effect.

[0080] Carrier frequency: f_carrier = 261.63 Hz.

[0081] Beat frequency difference: Δf_binaural = 20 Hz.

[0082] Left ear: 261.63 Hz, right ear: 281.63 Hz.

[0083] Modulation depth: M_binaural = 0.3 + 0.4 * 0.7 = 0.58.

[0084] 5. Weight distribution.

[0085] W_rhythm = 0.2 + 0.3 * 0.3 = 0.29 W_harmonic = 0.15 + 0.25 * 0.8 = 0.35 W_coupling = 0.25 + 0.2 * 0.8 = 0.41 W_binaural = 0.4 - 0.1 * (0.29 + 0.35 + 0.41) = 0.05 → 0.05 (minimum value limit).

[0086] 6. Final output signal.

[0087] S_focus(t) = 0.29 * sin(2π * f_sync * t) + 0.35 * sin(2π * f_resonance * t) + 0.41 * sin(2π * f_coupling * t) + 0.05 * [sin(2π * 261.63 * t) sin(2π * 281.63 * t)].

[0088] Example 2: Deep relaxation state induction (ambient music scenario).

[0089] Music feature input: Track: Brian Eno ambient music piece Tempo: 60 BPM, Tempo stability: 0.7 Key: Am (A minor), Fundamental frequency: 220 Hz, Chord complexity: 0.3, Rhythm complexity: 0.1 Energy value: 0.3, Emotional value: 0.4 Four-mechanism parameter calculation: 1. Rhythm synchronization mechanism: Main tempo frequency: f_rhythm=60 / 60=1.0 Hz Target alpha wave frequency: 10 Hz Tempo synchronization modulation: f_sync=10*(1+0.15*sin(2*pi*1.0*t)) 2. Harmonic resonance mechanism: Music fundamental frequency: 220 Hz Best harmonic match: 10 Hz ≈ 220 Hz / 22 Select 22nd harmonic: f_resonance=220 / 22=10 Hz Perfect resonance: R_harmonic=1.0 3. Neural oscillation coupling mechanism: Modulation frequency: 0.5 Hz (slow modulation, enhance relaxation effect) Coupling frequency: f_coupling=10+0.8*cos(2*pi*0.5*t) Coupling coefficient: C_neural=tanh(|101.0| / 3)=0.996 4. Binaural beat frequency effect: Carrier frequency: f_carrier=220 Hz Beat frequency difference: Delta f_binaural=10 Hz Modulation depth: M_binaural=0.3+0.4*0.4=0.46 5. Weight distribution: W_rhythm=0.2+0.3*0.1=0.23 W_harmonic=0.15+0.25*0.3=0.225 W_coupling=0.25+0.2*0.9=0.43 W_binaural=0.4 0.1*0.885=0.315.

[0090] Example 3: Creativity stimulation state induction (jazz music scenario).

[0091] Music feature input: Track: Miles Davis "Kind of Blue" Tempo: 120 BPM, Tempo stability: 0.8 Key: D Dorian mode, Fundamental frequency: 293.66 Hz, Harmonic complexity: 0.9, Rhythmic complexity: 0.7 Energy value: 0.8, Emotional value: 0.75.

[0092] Innovative technology points.

[0093] Composite rhythm synchronization: Main tempo: 2 Hz, Subdivision tempo: 1.33 Hz (triplets).

[0094] Multi-layer rhythm synchronization: f_sync_composite = f_target * [1 + α1 * sin(2π * 2 * t) + α2 * sin(2π * 1.33 * t)]. Where α1 = 0.2, α2 = 0.15.

[0095] Dynamic harmonic tracking: Real-time tracking of chord changes, dynamically adjusting resonance frequency: f_resonance(t) = chord_fundamental(t) / harmonic_order.

[0096] Cross-frequency coupling: θa cross-coupling (optimal state of creativity).

[0097] Target frequency: 6 Hz (theta wave) + 10 Hz (alpha wave).

[0098] Coupling function: f_cross_coupling = 6 * cos(φ1) + 10 * cos(φ2). Where φ2 = φ1 + π / 4 (phase difference 45°).

[0099] Example 4: Sleep-inducing state (natural sound scenario).

[0100] Music feature input: Track: Ocean waves + soft piano Tempo: 40 BPM (extremely slow), Tempo stability: 0.9 Main frequency component: 80 Hz (low-frequency ocean waves) Harmonic complexity: 0.1, Rhythmic complexity: 0.05 Energy value: 0.2, Emotional value: 0.3.

[0101] Deep sleep optimization technology: Ultra-low frequency synchronization: Target delta wave: 1.5 Hz. Respiratory rhythm synchronization: 0.25 Hz (15 times / minute). Composite synchronization signal: f_sleep_sync = 1.5 + 0.3 * cos(2π * 0.25 * t). Pink noise harmonics: Based on the 1 / f spectral characteristics of natural sounds. Harmonic attenuation: A_n = A O / √n. Sleep optimization spectrum: S_pink(f) = A0 / f^0.5*window_function(f).

[0102] Exponential decay function: f_progressive(t) = 8*exp(t / τ) + 1. Where τ = 900s (15 minute time constant).

[0103] Exponential decay function: f_progressive(t) = 8*exp(t / τ) + 1. Where τ = 900s (15 minute time constant).

[0104] Example 5: Multi-stage dynamic transition (full experience flow).

[0105] Scenario: 60 minute full meditation experience.

[0106] Stage 1 (0-10 minutes): Entry preparation goal: Transition from beta (25Hz) to alpha (12Hz) Music: Gentle new age music Main mechanism: Binaural beats + Rhythm synchronization Transition function: f(t) = 25 - 13*(t / 600).

[0107] Stage 2 (10-25 minutes): Light meditation goal: Stable alpha (10Hz) Music: Tibetan singing bowl music Main mechanism: Harmonic resonance + Neural oscillation coupling Resonance frequency: 440Hz / 44 = 10Hz (perfect match).

[0108] Stage 3 (25-45 minutes): Deep meditation goal: Theta (6Hz) Music: Natural ambient sounds Main mechanism: Full mechanism fusion Special technique: Theta-gamma coupling (40Hz modulating 6Hz).

[0109] Stage 4 (45-55 minutes): Consciousness return goal: From theta to alpha Music: Light instrumental music Gradual rise: f(t) = 6 + 4*sin²(π*(t-2700) / 600).

[0110] Stage 5 (55-60 minutes): Wakeful integration goal: Easy beta (15Hz) Music: Upbeat music Final stabilization: 15Hz ± 1Hz.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any skilled person in the art, according to the technical solution and concept of the present application, makes equivalent replacement or change within the technical range disclosed by the present application, should be covered within the protection scope of the present application.

Claims

1. A method for generating personalized brainwave-induced audio, characterized in that, include: Step S1: Extract multidimensional features of the input audio signal, including but not limited to: time domain features, frequency domain features, pitch features, emotional features, and complex features; Step S2: Based on the multidimensional features extracted in step S1, calculate the parameters of one or more neuroacoustic induction mechanisms in parallel. The parameters of the neuroacoustic induction mechanisms include: rhythm synchronization mechanism parameters, harmonic resonance mechanism parameters, neural oscillation coupling mechanism parameters, and binaural beat frequency effect parameters. Step S3: Combine the features obtained in step S1 with the parameters of one or more neuroacoustic induction mechanisms in step S2, and fuse the corresponding audio signals using a weighting strategy and a signal synthesis formula to generate the final brainwave-induced audio.

2. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The time-domain features include at least: beat speed, beat intensity, and beat stability; The frequency domain features include at least: fundamental frequency and harmonic structure; The pitch characteristics include at least: musical tonality; The emotional characteristics include at least: emotional value; The complex features include at least: rhythmic complexity and harmonic complexity; Step 2 also includes: Step S2.1 Calculate the rhythm synchronization mechanism parameters: Calculate the main beat frequency f_rhythm based on the beat speed, calculate the beat synchronization target frequency f_sync based on the set target brainwave frequency f_target and the main beat frequency f_rhythm, and calculate the time domain signal S_rhythm(t) generated by the rhythm synchronization mechanism based on the synchronization target frequency f_sync. Step S2.2 Calculate the harmonic resonance mechanism parameters: Calculate the optimal harmonic match f_resonance with the target brainwave frequency based on the music fundamental frequency f_fundamental and the set target brainwave frequency f_target; calculate the harmonic resonance mechanism to generate the time-domain signal S_harmonic(t) based on the optimal harmonic match f_resonance. Step S2.3 Calculate the parameters of the neural oscillation coupling mechanism: Calculate the neural oscillation coupling frequency f_coupling based on the set target brainwave frequency f_target and the modulation frequency f_modulation set according to the specific induction task, and calculate the time domain signal S_coupling(t) generated by the neural oscillation coupling mechanism based on the neural oscillation coupling frequency f_coupling. Step S2.4 Calculate the binaural beat frequency effect parameters: Calculate the fundamental carrier frequency f_carrier based on the music key and the fundamental frequency lookup table key_frequency_map; calculate the binaural beat frequency difference Δf_binaural based on the set target brainwave frequency f_target and correction coefficients correction_factors; calculate the left ear frequency f_left based on the fundamental carrier frequency f_carrier; calculate the right ear frequency f_right based on the fundamental carrier frequency f_carrier and the binaural beat frequency difference Δf_binaural; and calculate the time-domain signal S_binaural(t) based on the left ear frequency f_left and the right ear frequency f_right. The weight allocation strategies include: The weights of the rhythm synchronization mechanism (W_rhythm) are calculated based on the rhythm complexity (rhythm_complexity), the weights of the harmonic resonance mechanism (W_harmonic) are calculated based on the harmonic richness (harmonic_richness), the weights of the neural oscillation coupling mechanism (W_coupling) are calculated based on the neural compatibility (neural_compatibility) calculated by the system based on the user's historical brainwave feedback data, and the weights of the binaural beat frequency mechanism (W_binaural) are calculated based on the weights of the rhythm synchronization mechanism (W_rhythm), the harmonic resonance mechanism (W_harmonic), and the neural oscillation coupling mechanism (W_coupling). Finally, the time-domain signal S_total(t) is obtained by jointly calculating the time-domain signal generated by the rhythm synchronization mechanism, the harmonic resonance mechanism, the neural oscillation coupling mechanism, and the binaural beat effect mechanism.

3. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The specific parameters of the rhythm synchronization mechanism in step S2 include: Main beat frequency: f_rhythm=BPM / 60; BPM represents the tempo of the music, measured in beats per minute, and is obtained through multi-dimensional music feature extraction in step S1. Beat harmonic sequence: f_harm_n = f_rhythm * n; Where n represents the harmonic order of the beat, and takes the value (1, 2, 3, 4, 5). Calculate beat synchronization strength: S_rhythm=beat_stability*beat_intensity; Where beat_stability represents beat stability and is used to quantify the uniformity of beats, and beat_intensity represents beat intensity and is used to quantify the strength of beats, both of which are obtained through multi-dimensional music feature extraction in step S1; Target frequency for beat synchronization: f_sync=f_target*(1+α*sin(2π*f_rhythm*t)); Where f_target represents the target brainwave frequency, which is set by the specific induction task; α represents the synchronization depth coefficient, α∈[0.1,0.3], and t represents the time variable; The rhythm synchronization mechanism generates time-domain signals: S_rhythm(t)=sin(2π*f_sync*t).

4. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The harmonic resonance mechanism parameters in step S2 specifically include: Extracting the fundamental frequency of music from multidimensional music features: f_fundamental; Harmonic sequences: f_harmonic_k=f_fundamental*k; Where k represents the harmonic index, and its value is 1, 2, 3, ..., 10; Optimal harmonic matching with the target brainwave frequency: k_optimal=argmin|f_target-f_fundamental*k|; f_resonance=f_fundamental*k_optimal; Where, k_optimal represents the harmonic index that minimizes |f_target-f_fundamental*k|, f_target represents the target brainwave frequency, which is set by the specific induction task, and f_resonance represents the selected optimal harmonic resonance frequency; Harmonic resonance intensity: R_harmonic=1 / (1+|f_target-f_resonance|); Where R_harmonic represents the harmonic resonance intensity, with a value range of 0-1; Harmonic resonance mechanism generates time-domain signals: S_harmonic(t)=sin(2π*f_resonance*t).

5. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The parameters of the neural oscillation coupling mechanism in step S2 specifically include: Neural oscillation coupling frequency: f_coupling=f_target+β*cos(2π*f_modulation*t); Where β represents the coupling strength coefficient, used to control the modulation amplitude; f_target represents the target brainwave frequency, set by the specific induction task; and f_modulation represents the modulation frequency set according to the specific induction task. Define the coupling phase relationship: φ_coupling=2π*f_rhythm*t+φ_offset; Where φ_coupling represents the instantaneous phase of neural oscillation coupling; φ_offset represents the initial phase offset, which is set by the system according to the specific induction task. Coupling coefficient: C_neural=tanh(|f_target-f_rhythm| / σ); Where C_neural represents the neural oscillation coupling coefficient, with a value range of 0-1; σ is the coupling sensitivity parameter, used to determine the steepness of the output curve; Neural oscillatory coupling mechanism generates time-domain signals: S_coupling(t)=sin(2π*f_coupling*t).

6. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The binaural beat frequency effect parameters in step S2 specifically include: Calculate the fundamental carrier frequency: f_carrier=key_frequency_map(music_key); Here, key_frequency_map() represents a fundamental frequency lookup table indexed by musical key, where music_key is the musical key; Binaural beat frequency difference: Δf_binaural=f_target*correction_factors; Wherein, correction_factors represents the correction coefficients for individual differences and hardware system, and f_target represents the target brainwave frequency, which is set by the specific induction task; Left ear frequency: f_left = f_carrier; Right ear frequency: f_right=f_carrier+Δf_binaural; Binaural beat modulation depth: M_binaural=0.3+0.4*valence_factor; Where M_binaural represents the binaural beat modulation depth; valence_factor represents the music emotional value factor, which is obtained through multi-dimensional music feature extraction in step S1; Binaural beat frequency effect mechanism generates time-domain signals: S_binaural(t)=sin(2π*f_left*t)-sin(2π*f_right*t).

7. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The weight allocation strategy in S3 specifically includes: The weights of the four mechanisms are dynamically assigned based on the music features extracted in step S1 and the target state: W_rhythm=0.2+0.3*rhythm_complexity; W_harmonic=0.15+0.25*harmonic_richness; W_coupling=0.25+0.2*neural_compatibility; W_binaural=0.4-0.1*(W_rhythm+W_harmonic+W_coupling); Wherein, W_rhythm represents the weight of the rhythm synchronization mechanism; rhythm_complexity represents the rhythm complexity, which is obtained through multi-dimensional music feature extraction in step S1; W_harmonic represents the harmonic resonance mechanism weight; harmonic_richness represents the harmonic complexity, which is obtained through multi-dimensional music feature extraction in step S1. W_coupling represents the weight of the neural oscillation coupling mechanism; neural_compatibility represents neural compatibility, which is calculated by the system based on the user's historical brainwave feedback data. W_binaural represents the binaural beat frequency mechanism weights, used to ensure that the sum of the four weights is 1.

8. The personalized brainwave-induced audio generation method as described in claim 1, characterized in that, The signal synthesis formula in S3 specifically includes: S_total(t)=W_rhythm*S_rhythm(t)+W_harmonic*S_harmonic(t)+W_coupling*S_coupling(t)+W_binaural*S_binaural(t); S_total(t) represents the final synthesized audio signal; S_rhythm(t) represents the time-domain signal generated by the rhythm synchronization mechanism; W_rhythm represents the weight of the rhythm synchronization mechanism; S_harmonic(t) represents the time-domain signal generated by the harmonic resonance mechanism; W_harmonic represents the weight of the harmonic resonance mechanism; S_coupling(t) represents the time-domain signal generated by the neural oscillation coupling mechanism; W_coupling represents the weights of the neural oscillation coupling mechanism. S_binaural(t) represents the time-domain signal generated by the binaural beat frequency effect mechanism; W_binaural represents the weight of the binaural beat frequency mechanism; The final output signal is S_total(t).

9. A personalized brainwave-induced audio generation system for implementing the method of any one of claims 1-8, characterized in that, include: The music feature analysis module is used to execute step S1; The quadruple mechanism parameter calculation module is used to execute step S2; The multi-mechanism fusion algorithm module is used to execute step S3; The signal synthesis and output module is used to output the final brainwave-induced audio.

10. A personalized brainwave-induced audio generation system according to claim 9, characterized in that, The music feature analysis module includes: a time-domain feature extraction submodule, a frequency-domain feature extraction submodule, a pitch feature extraction submodule, an emotion feature extraction submodule, and a complex feature extraction submodule.

Images