Display adjustment method and terminal of smart wearable device

Abstract

The application discloses a display adjustment method and a terminal of an intelligent wearable device, receives an audio signal, extracts multi-dimensional audio features of the audio signal, and performs weighted fusion on the multi-dimensional audio features to obtain first fused audio features. The first fused audio features are analyzed and adjusted in combination with historical display preference information of a user of the intelligent wearable device and a use scenario of the intelligent wearable device, and then a display adjustment scheme of the intelligent wearable device is calculated according to the adjusted second fused audio features. In this way, the features of multiple dimensions of the audio signal can be adjusted according to historical preference data of the user, and the display of the intelligent wearable device is personalized configured according to the adjusted multi-dimensional features, so that the technical effect that the display color of the intelligent wearable device is dynamically and flexibly adjusted according to the music style is realized.

Description

Technical Field

[0001] This invention relates to the technical field of device display, and in particular to a display adjustment method and terminal for a smart wearable device. Background Technology

[0002] Currently, wearable devices that can interact with music include, for example: (1) Audio-responsive LED lighting clothing: This type of clothing usually uses embedded LED light strips, which capture audio signals in the environment through built-in microphones, and then control the brightness or flashing frequency of the lights according to the intensity or frequency of the audio.

[0003] (2) Smart bracelets with music sensing function: Some smart bracelet products can connect to the user's mobile phone or other audio devices via Bluetooth and make simple light feedback based on the rhythm of the music, such as flashing or color change.

[0004] (3) Music-interactive dance costumes: Some costumes used for stage performances have built-in LED lights and can be synchronized with the stage sound through preset programming, with lighting effects coordinated with the performance rhythm.

[0005] However, current wearable devices that can interact with music have the following problems: (1) Most existing wearable devices only make simple flashing or color changes based on the loudness or rhythm of the audio, and cannot deeply analyze the complex characteristics of music such as frequency, pitch, and dynamic changes. Such response effects can only achieve relatively monotonous lighting effects.

[0006] (2) The color or light changes of many existing wearable devices are controlled by preset programs, lacking real-time music feedback capabilities, especially in complex music scenes, and cannot be flexibly adjusted according to the real-time changes in music. This limits the personalized interactive experience of users in different music genres. In addition, the lighting effects of many devices are fixed and cannot be flexibly changed according to different music styles. To achieve rich lighting effects, a large number of complex static display rules need to be stored. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to provide a display adjustment method and terminal for a smart wearable device, which can dynamically and flexibly adjust the display color of the smart wearable device according to the music style.

[0008] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for adjusting the display of a smart wearable device, comprising the steps of: S1. Receive an audio signal, extract multi-dimensional audio features from the audio signal, and perform weighted fusion of the multi-dimensional audio features to obtain a first fused audio feature; S2. Combine the user's historical display preference information and usage scenarios of the smart wearable device to analyze and adjust the first fused audio features to obtain the second fused audio features; S3. Calculate the display adjustment scheme of the smart wearable device based on the second fused audio features.

[0009] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is as follows: A display adjustment terminal for a smart wearable device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps of the aforementioned display adjustment method for a smart wearable device.

[0010] The beneficial effects of this invention are as follows: After receiving an audio signal, multi-dimensional audio features of the audio signal are extracted, and these multi-dimensional audio features are weighted and fused to obtain a first fused audio feature. Combining the user's historical display preference information and usage scenarios of the smart wearable device, the first fused audio feature is analyzed and adjusted. Then, a display adjustment scheme for the smart wearable device is calculated based on the adjusted second fused audio feature. In this way, multiple dimensions of the audio signal can be adjusted based on user historical preference data, and the display of the smart wearable device can be personalized based on the adjusted multi-dimensional features, thereby achieving the technical effect of dynamically and flexibly adjusting the display color of the smart wearable device according to the music style. Attached Figure Description

[0011] Figure 1 This is a flowchart of a display adjustment method for a smart wearable device according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a display adjustment terminal for a smart wearable device according to an embodiment of the present invention; Label Explanation: 1. A display adjustment terminal for a smart wearable device; 2. A memory; 3. A processor. Detailed Implementation

[0012] To explain in detail the technical content, objectives, and effects of the present invention, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0013] Please refer to Figure 1 This invention provides a display adjustment method for a smart wearable device, comprising the following steps: S1. Receive an audio signal, extract multi-dimensional audio features from the audio signal, and perform weighted fusion of the multi-dimensional audio features to obtain a first fused audio feature; S2. Combine the user's historical display preference information and usage scenarios of the smart wearable device to analyze and adjust the first fused audio features to obtain the second fused audio features; S3. Calculate the display adjustment scheme of the smart wearable device based on the second fused audio features.

[0014] As described above, the beneficial effects of this invention are as follows: After receiving an audio signal, multi-dimensional audio features of the audio signal are extracted, and these multi-dimensional audio features are weighted and fused to obtain a first fused audio feature. The first fused audio feature is analyzed and adjusted based on the user's historical display preference information and usage scenarios of the smart wearable device. Then, a display adjustment scheme for the smart wearable device is calculated based on the adjusted second fused audio feature. In this way, multiple dimensions of the audio signal can be adjusted according to the user's historical preference data, and the display of the smart wearable device can be personalized based on the adjusted multi-dimensional features, thereby achieving the technical effect of dynamically and flexibly adjusting the display color of the smart wearable device according to the music style.

[0015] Further, step S1 includes: Receive audio signals and extract the spectral features of the audio signals through Fourier transform; The pitch change features of notes in the audio signal are detected by pitch tracking, and the pitch change features of notes are converted into chord structure features by chord recognition. Extract the timbre features of the audio signal; The spectral features, pitch variation features, chord structure features, and timbre features of the audio signal are weighted and fused to obtain the first fused audio feature.

[0016] As described above, by analyzing spectral features, chord features, and rhythmic features, multi-dimensional fusion features can be obtained, which can then be used to make personalized and flexible adjustments to the display lights of smart wearable devices based on these multi-dimensional features.

[0017] Further, step S2 includes: Analyze the user's historical display preference information of the smart wearable device, and learn from the user's historical display preference information to obtain an audio processing prediction model; The first fused audio feature is input into the audio processing prediction model to obtain an audio processing scheme. The first fused audio feature is then adjusted according to the audio processing scheme to obtain a second fused audio feature.

[0018] As described above, by learning users' historical display preferences, audio processing predictions can be made based on users' historical preferences, thereby optimizing and adjusting the first fused audio features. In this way, the audio features are automatically adjusted according to user preferences to obtain personalized lighting display effects.

[0019] Furthermore, analyzing the user's historical display preference information of the smart wearable device includes: Collect user history data of the smart wearable device, including historical audio data, historical display data, user history operation data, and usage scenario data; By clustering and machine learning on the user's historical data, user historical display preference information can be obtained.

[0020] As described above, by learning from historical data, the user's historical display preferences for smart wearable devices can be analyzed, thereby ensuring personalized adjustments to the smart wearable devices.

[0021] Further, step S3 includes: The display color corresponding to the spectral feature of the second fused audio feature is determined according to the preset mapping function between the spectrum and the display color. The rhythm feature and volume feature are obtained from the audio signal corresponding to the second fused audio feature. The display frequency corresponding to the rhythm feature is determined according to the preset mapping function between rhythm and display frequency. The display brightness corresponding to the volume feature is determined according to the preset mapping function between volume and display brightness.

[0022] As described above, the display color, frequency, and brightness of the lights on smart wearable devices can be adjusted according to different audio characteristics, enabling flexible and personalized adjustments to the light display.

[0023] Please refer to Figure 2 Another embodiment of the present invention provides a display adjustment terminal for a smart wearable device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps of the above-described display adjustment method for a smart wearable device.

[0024] The display adjustment method and terminal for a smart wearable device described above are applicable to dynamically and flexibly adjusting the display color of a smart wearable device according to music style. The following is a detailed description of the specific implementation: Please refer to Figure 1 Embodiment 1 of the present invention is as follows: A method for adjusting the display of a smart wearable device, preferably a smart vest, includes the following steps: S1. Receive an audio signal, extract multi-dimensional audio features from the audio signal, and perform weighted fusion of the multi-dimensional audio features to obtain a first fused audio feature.

[0025] S11. Receive the audio signal and extract the spectral features of the audio signal through Fourier transform.

[0026] Specifically, it captures ambient music via a built-in microphone or wirelessly connects to the user's music device (such as a mobile phone or speakers) via Bluetooth to receive audio signals. The audio signals are then converted into digital signals by an analog-to-digital converter (ADC) and input to the processor for further processing.

[0027] The audio signal is sampled and Fourier Transform (FFT) is applied to extract spectral features. This step provides frequency domain information for subsequent algorithms and is mainly used to analyze the frequency components of the audio.

[0028] S12. The pitch change features of the notes in the audio signal are detected by pitch tracking, and the pitch change features of the notes are converted into chord structure features by chord recognition.

[0029] Specifically, a pitch tracking algorithm is used to detect changes in note height, and a chord recognition algorithm is then used to convert the pitch pattern into a chord structure. This stage identifies chord changes and modes by analyzing the temporal and frequency relationships of notes, helping to extract harmonic information from the music.

[0030] S13. Extract the timbre features of the audio signal.

[0031] Specifically, using Mel frequency cepstral coefficients to extract timbre features can capture subtle changes and emotional nuances in sound. By applying a Mel filter bank to the short-time Fourier transform (STFT) of the audio signal, timbre features are extracted and combined with other pitch and rhythm features for more precise control over the tone and effects of lighting.

[0032] S14. The spectral features, pitch variation features, chord structure features, and timbre features of the audio signal are weighted and fused to obtain the first fused audio feature.

[0033] Specifically, features from multiple dimensions, such as pitch, chords, frequency, and timbre, are fused together. A weighting mechanism is designed based on the importance of different features, adjusting the weights of different audio elements to better influence lighting effects. For example, in chord recognition, major triads can be given a stronger weight to trigger more vibrant lighting effects, while low-frequency rhythmic variations affect the brightness and flashing frequency of the lights.

[0034] S2. Combining the user's historical display preference information and usage scenarios of the smart wearable device, the first fused audio feature is analyzed and adjusted to obtain the second fused audio feature.

[0035] S21. Analyze the user's historical display preference information of the smart wearable device, and learn from the user's historical display preference information to obtain an audio processing prediction model.

[0036] The process involves collecting historical user data for the smart wearable device, including historical audio data, historical display data, historical user operation data, and usage scenario data; and then performing clustering and machine learning on the historical user data to obtain historical user display preference information.

[0037] Specifically, the analysis of users' historical preferences and usage scenarios is achieved through machine learning techniques combined with audio and environmental data. The specific analysis process can be divided into the following steps: S211, Collection of user historical data.

[0038] User historical data includes the following: Audio data, specifically, refers to the audio data collected from the user's device or system during music playback, including information such as music style, rhythm, chords, and pitch. Lighting control data specifically involves collecting user lighting control settings for different music scenarios, including parameters such as light color, brightness, and flashing frequency. Usage scenario data specifically records user interaction data with music and light under different environmental conditions, such as the playback environment (home, party, work, etc.), time period (daytime, nighttime), and device type (speakers, headphones, etc.). User preference data specifically includes user feedback, preference for manually adjusting lighting, frequently selected lighting modes, and favorite music genres.

[0039] S212, Data Preprocessing and Feature Extraction.

[0040] Audio feature extraction specifically involves using audio analysis techniques (such as MFCC, spectrum analysis, etc.) to extract multidimensional features (such as pitch, rhythm, chords, timbre, etc.) from music. Lighting data processing specifically involves organizing and standardizing user-adjusted lighting data, converting it into a format that can be used to train machine learning models (e.g., quantifying color, brightness, frequency, etc. into numerical values). Scene tagging settings specifically involve tagging data based on user device and environmental characteristics (such as time, location, audio equipment used, etc.).

[0041] S213, Model Training and User Preference Analysis.

[0042] Cluster analysis, specifically, involves grouping user historical data into groups using clustering algorithms (such as K-means or DBSCAN). Each cluster represents a typical user behavior pattern or scenario (such as parties, family entertainment, etc.). Cluster analysis can help discover user preferences in different contexts; Predictive models, specifically, use supervised learning (such as regression, decision trees, or neural networks) to build models that predict the lighting effects a user might prefer in a particular scenario. For example, based on a user's historical preferences, they can predict lighting settings for a specific music style.

[0043] S214, Adaptive Optimization and Real-time Feedback Real-time data streams specifically involve dynamically adjusting lighting effects by monitoring user audio input and environmental changes (e.g., changes in music style, changes in ambient light) in real time, combined with real-time user behavior data (e.g., manual adjustment of lights, feedback on lighting effects).

[0044] Based on machine learning models, the system automatically recommends lighting effects that match users' historical preferences, while also allowing users to manually adjust and optimize them.

[0045] S22. Input the first fused audio feature into the audio processing prediction model to obtain an audio processing scheme, and adjust the first fused audio feature according to the audio processing scheme to obtain a second fused audio feature.

[0046] By analyzing user history and usage scenarios, a feedback loop can be created between audio processing and lighting effects, optimizing the audio processing and resulting in more precise and personalized synchronization between lighting and music. The optimization process can be as follows: S221, Adaptive adjustment of audio features.

[0047] Real-time audio processing specifically involves adjusting audio signal processing parameters in real time based on the user's historical preferences and current audio characteristics (such as chords, pitch, and rhythm). For example, if a user prefers more detail in the high frequencies within a certain musical style, the high-frequency audio processing can be enhanced to increase the brightness of the timbre. If a user prefers a strong bass response in electronic music, the bass response can be strengthened, and bass volume and effects can be dynamically adjusted.

[0048] S222, Dynamic lighting control and audio feature matching.

[0049] Multi-dimensional audio analysis and lighting adjustment specifically involves adjusting the lighting's multi-dimensional performance based on the music's spectrum, rhythm, and chord characteristics. For different musical elements (such as melody, rhythm, and chord changes), a dynamic lighting control system can be designed to respond to frequency changes and note durations. The color or brightness of the lights can be adjusted according to pitch changes; for example, lower frequencies might trigger a darker blue or green, while higher frequencies might trigger a bright red or yellow. Faster rhythms might trigger more frequent flashing effects, while slower rhythms might trigger smooth, gradual lighting effects.

[0050] S223, Machine learning model and dynamic optimization of audio effects.

[0051] Machine learning models can predict the optimal audio processing effect based on real-time input audio features and the user's historical preferences. For example, in some scenarios, users may prefer clearer sound details, and the system can automatically enhance the high-frequency components of the spectrum. For chord or melody changes in music, the system can optimize the audio output by adjusting audio signal filtering, resampling, and other methods to better suit the user's listening preferences.

[0052] S224, Optimize audio-lighting linkage effect: Real-time adjustment of lighting response specifically involves dynamically adjusting lighting effects through real-time analysis of audio signals. For example, when the rhythm of the music accelerates, the brightness and flashing frequency of the lights increase accordingly; changes in chords may trigger changes in the color of the lights, while subtle changes in timbre will affect the transition effects of the lights.

[0053] Through these steps, machine learning can not only capture users' historical preferences and scene characteristics, but also adaptively optimize audio processing and lighting effects, so that the lighting effects can accurately match the music content every time music is played, enhancing the user's immersion and experience.

[0054] S3. Calculate the display adjustment scheme of the smart wearable device based on the second fused audio features.

[0055] Step S3 includes: determining the display color corresponding to the spectral feature of the second fused audio feature according to a preset mapping function between the spectrum and display color; obtaining rhythm and volume features from the audio signal corresponding to the second fused audio feature; determining the display frequency corresponding to the rhythm feature according to a preset mapping function between rhythm and display frequency; and determining the display brightness corresponding to the volume feature according to a preset mapping function between volume and display brightness.

[0056] Specifically, the method for calculating the frequency of light changes based on sound rhythm is as follows: To calculate the frequency of light changes based on sound attribute information, the audio signal needs to be analyzed, and the rhythm and frequency characteristics of the music need to be extracted. The calculation process is as follows: (1) Spectral analysis of audio signals: The spectral information of an audio signal is extracted by Fourier transform. The spectrum represents the energy distribution of the signal at different frequencies.

[0057] (2) Extract rhythm information: Use rhythm detection algorithms (such as onset detection) to identify rhythm fluctuations. When the rhythm changes rapidly, the frequency of light changes should be increased, and vice versa. For example, the tempo of music can be determined by calculating the time interval (tempo speed, BPM) of each beat in the audio signal.

[0058] (3) Calculation of light change frequency: Based on the extracted rhythm information, a mapping function is set. For example, if the music rhythm is in a faster range (e.g., BPM > 120), the light change frequency can be set higher (e.g., updating 4 times per second). If the music rhythm is in a slower range (e.g., BPM < 80), the light change frequency can be set lower (e.g., updating once per second). The formula for calculating the light change frequency (LampChange Frequency) is: Lamp Change Frequency = Max Frequency – (BPM – MinBPM) × Frequency Factor; where Max Frequency represents the preset maximum light change frequency, Min BPM represents the minimum rhythm BPM value, and Frequency Factor represents the coefficient for adjusting the frequency.

[0059] Secondly, the method for calculating the RGB values ​​of light color based on the spectrum: The mapping between sound frequency and light color can be achieved by adjusting the color using the frequency range (high and low frequencies) of the audio signal. The calculation process is as follows: (1) Extract the spectral information of the audio. Frequency information of audio signals can be extracted using FFT or Mel frequency cepstral coefficients (MFCC).

[0060] (2) Determine the relationship between frequency range and color mapping High-frequency frequencies (such as 2000Hz and above) can be mapped to warm colors (red, yellow).

[0061] Low-frequency ranges (such as 20Hz to 200Hz) can be mapped to cool colors (blue, green).

[0062] (3) Mapping of frequency to RGB values High-frequency notes (above 1kHz): correspond to brighter hues, mainly red (#FF0000) or yellow (#FFFF00), with the RGB components adjusted according to the frequency.

[0063] Low-frequency notes (below 200Hz): correspond to darker hues, mainly blue (#0000FF) or green (#00FF00), adjust the RGB value according to the frequency.

[0064] The specific calculation formula is as follows: For high-frequency mapping, i.e., when the frequency f is between 1000Hz and 5000Hz, the RGB values ​​are calculated as follows: R=min(255,f×0.1); R=min(255,f×0.05); B=0.

[0065] For low-frequency mapping, i.e., when the frequency f is between 20Hz and 200Hz, the RGB values ​​are calculated as follows: R=0; G=min(255,f×1.5); B=min(255,f×2).

[0066] Furthermore, the method for calculating light brightness based on sound intensity: sound intensity is usually expressed by volume (or amplitude), and light brightness can be calculated by adjusting the amplitude of the audio signal.

[0067] (1) Calculate the loudness (volume) of the audio signal. The loudness of an audio signal can be calculated by its root mean square (RMS) value or peak amplitude. The RMS value reflects the energy level of the audio signal and is a commonly used indicator for measuring audio intensity.

[0068] (2) Mapping loudness to brightness A mapping relationship can be established between the loudness of an audio signal and the brightness of a light source. The higher the loudness, the brighter the light; the lower the loudness, the lower the brightness of the light.

[0069] Furthermore, in order to integrate the rhythm, frequency, and loudness information of the audio to generate a comprehensive lighting effect, we can perform a weighted fusion of the above three results.

[0070] (1) Calculate the light change frequency, color and brightness independently, that is, use the calculation process described above to obtain the light change frequency, color and brightness respectively.

[0071] (2) Weighted fusion adjustment Color blending: The final RGB value can be determined by calculating the proportion of low-frequency and high-frequency components in the audio signal. For example, the higher the frequency, the more red or yellow the light color leans; the lower the frequency, the more blue or green the light color leans.

[0072] Frequency and rhythm integration: The speed of light changes is determined by changes in rhythm. The faster the music rhythm, the higher the light update frequency; the slower the music rhythm, the lower the light change frequency.

[0073] Brightness adjustment: The light brightness is dynamically adjusted according to the loudness (RMS value). When the loudness is strong, the light brightness increases, and when the loudness is weak, the brightness decreases.

[0074] (3) Calculation of final lighting effect The final lighting effect is generated by combining the calculation results of frequency, color, and brightness: specifically, the color is dynamically adjusted according to the frequency and pitch of the music, the brightness of the light is adjusted according to the intensity (RMS value) of the music, and the frequency of the light flashing is dynamically adjusted according to the rhythm.

[0075] The final blending formula is: Final RGB = f(Frequency, Intensity), where f(Frequency, Intensity) is a mapping function that combines frequency, volume, and rhythm to calculate the final lighting effect. The mapping function is expressed as follows: f(Frequency, Intensity) = W f ·F freq +W i ·F int W r ·F rhythm In the formula, W f W i and W r F represents the weighting factor for frequency, volume intensity, and rhythm. freq F represents the RGB color mapping coefficients calculated from audio frequencies. int F represents the luminance mapping coefficient calculated from the volume intensity. rhythm This represents the adjustment coefficient for the frequency of light changes calculated from the rhythm.

[0076] In this way, the lighting effects can not only be dynamically adjusted according to the high and low frequencies, loudness, and rhythm of the sound, but also take into account the combined effect of these three factors to generate highly synchronized and personalized lighting effects with the music.

[0077] Compared with existing smart home lighting control systems, this embodiment has the following key differences: First, existing technologies mainly rely on manual operation by users and fixed scene modes, while this embodiment automatically adjusts the color, brightness and flicker of the lights by analyzing the frequency, rhythm and pitch of the music signal in real time. The lights can change dynamically with the music, which enhances automation and interactivity.

[0078] Second, based on the multi-dimensional features of music (such as frequency, chord, rhythm), this embodiment generates rich lighting effects through complex algorithms, such as triggering different color changes according to the chord structure, while most existing systems only control based on simple volume or frequency.

[0079] Third, users can perform highly personalized lighting settings through a mobile application, and combined with machine learning algorithms, the system can automatically recommend lighting effects according to user preferences, while existing technologies have lower personalization and flexibility.

[0080] Fourth, this embodiment integrates multi-dimensional perception functions (such as user actions, positions, etc.), adapts to different scenario requirements, enhances the interactive experience, and surpasses the single control method of existing technologies.

[0081] Please refer to Figure 2 , Embodiment 2 of the present invention is: A display adjustment terminal 1 of a smart wearable device, including a memory 2, a processor 3, and a computer program stored on the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, it implements each step of the display adjustment method of a smart wearable device in Embodiment 1.

[0082] In summary, for a display adjustment method and terminal of a smart wearable device provided by the present invention, after receiving an audio signal, multi-dimensional audio features of the audio signal are extracted, and the multi-dimensional audio features are weighted and fused to obtain a first fused audio feature. Combining the user's historical display preference information of the smart wearable device and its usage scenario, the first fused audio feature is analyzed and adjusted, and then a display adjustment scheme for the smart wearable device is calculated according to the adjusted second fused audio feature. In this way, it is possible to adjust the features of multiple dimensions of the audio signal according to the user's historical preference data, and then perform personalized configuration of the display of the smart wearable device according to the adjusted multi-dimensional features, thereby achieving the technical effect of dynamically and flexibly adjusting the display color of the smart wearable device according to the music style.

[0083] Therefore, through real-time synchronization with music, the smart wearable device changes lights according to rhythm, frequency, and pitch, providing dynamic visual feedback, enabling users to more intuitively feel the rhythm and changes of music, and enhancing the interactive experience. Moreover, the smart wearable device can be widely applied to multiple fields such as entertainment, fitness, education, and fashion, suitable for scenarios such as concerts, parties, and fitness training, providing personalized and immersive usage experiences. Users can perform personalized settings through a mobile application or buttons, customize the light color and mode, meet the aesthetic and functional needs of different users, and improve the flexibility of the device and user satisfaction. Through the linkage effect of lights and music, the vest provides a new form of expression for art performers in performances, exhibitions, etc., increasing the layering of the works and the sense of participation of the audience.

[0084] The invention can also employ low-power LED light strips and an intelligent power management system to effectively reduce energy consumption, extend battery life, and meet the needs of long-term use.

[0085] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent modifications made based on the content of the present invention specification and drawings, or direct or indirect applications in related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1.A display adjustment method of a smart wearable device, the method comprising: Including the following steps: S1. Receive an audio signal, extract multi-dimensional audio features from the audio signal, and perform weighted fusion of the multi-dimensional audio features to obtain a first fused audio feature; S2. Combine the user's historical display preference information and usage scenarios of the smart wearable device to analyze and adjust the first fused audio features to obtain the second fused audio features; S3. Calculate the display adjustment scheme of the smart wearable device based on the second fused audio features. 2.The display adjustment method of an intelligent wearable device according to claim 1, wherein, Step S1 includes: Receive audio signals and extract the spectral features of the audio signals through Fourier transform; The pitch change features of notes in the audio signal are detected by pitch tracking, and the pitch change features of notes are converted into chord structure features by chord recognition. Extract the timbre features of the audio signal; The spectral features, pitch variation features, chord structure features, and timbre features of the audio signal are weighted and fused to obtain the first fused audio feature. 3.The display adjustment method of an intelligent wearable device according to claim 2, wherein, Step S2 includes: Analyze the user's historical display preference information of the smart wearable device, and learn from the user's historical display preference information to obtain an audio processing prediction model; The first fused audio feature is input into the audio processing prediction model to obtain an audio processing scheme. The first fused audio feature is then adjusted according to the audio processing scheme to obtain a second fused audio feature. 4.The display adjustment method of an intelligent wearable device according to claim 3, characterized in that, The analysis of user history display preference information of the smart wearable device includes: Collect user history data of the smart wearable device, including historical audio data, historical display data, user history operation data, and usage scenario data; By clustering and machine learning on the user's historical data, user historical display preference information can be obtained. 5.The display adjustment method of an intelligent wearable device according to claim 3, characterized in that, Step S3 includes: The display color corresponding to the spectral feature of the second fused audio feature is determined according to the preset mapping function between the spectrum and the display color. The rhythm feature and volume feature are obtained from the audio signal corresponding to the second fused audio feature. The display frequency corresponding to the rhythm feature is determined according to the preset mapping function between rhythm and display frequency. The display brightness corresponding to the volume feature is determined according to the preset mapping function between volume and display brightness. 6.A display adjustment terminal of a smart wearable device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the processor executes the computer program, it performs the following steps: S1. Receive an audio signal, extract multi-dimensional audio features from the audio signal, and perform weighted fusion of the multi-dimensional audio features to obtain a first fused audio feature; S2. Combine the user's historical display preference information and usage scenarios of the smart wearable device to analyze and adjust the first fused audio features to obtain the second fused audio features; S3. Calculate the display adjustment scheme of the smart wearable device based on the second fused audio features. 7.The display adjustment terminal of the smart wearable device of claim 6, wherein, Step S1 includes: Receive audio signals and extract the spectral features of the audio signals through Fourier transform; The pitch change features of notes in the audio signal are detected by pitch tracking, and the pitch change features of notes are converted into chord structure features by chord recognition. Extract the timbre features of the audio signal; The spectral features, pitch variation features, chord structure features, and timbre features of the audio signal are weighted and fused to obtain the first fused audio feature. 8.The display adjustment terminal of the smart wearable device of claim 7, wherein, Step S2 includes: Analyze the user's historical display preference information of the smart wearable device, and learn from the user's historical display preference information to obtain an audio processing prediction model; The first fused audio feature is input into the audio processing prediction model to obtain an audio processing scheme. The first fused audio feature is then adjusted according to the audio processing scheme to obtain a second fused audio feature. 9.The display adjustment terminal of the smart wearable device of claim 8, wherein, The analysis of user history display preference information of the smart wearable device includes: Collect user history data of the smart wearable device, including historical audio data, historical display data, user history operation data, and usage scenario data; By clustering and machine learning on the user's historical data, user historical display preference information can be obtained. 10.The display adjustment terminal of the smart wearable device of claim 8, wherein, Step S3 includes: The display color corresponding to the spectral feature of the second fused audio feature is determined according to the preset mapping function between the spectrum and the display color. The rhythm feature and volume feature are obtained from the audio signal corresponding to the second fused audio feature. The display frequency corresponding to the rhythm feature is determined according to the preset mapping function between rhythm and display frequency. The display brightness corresponding to the volume feature is determined according to the preset mapping function between volume and display brightness.

Images