Multi-mode interaction method for Bluetooth sound box and smart phone

Abstract

The invention relates to a multi-mode interaction method of a Bluetooth sound box and a smart phone. The sound box is provided with an angle-adjustable first magnet ring which is magnetically adsorbed with a second magnet ring on the smart phone, so that physical connection of equipment is realized; wireless connection between the sound box and the smart phone is established through a Bluetooth protocol, and physical adsorption states of the equipment are detected, including a first adsorption state, a second adsorption state and a third adsorption state. In the first adsorption state, a video watching angle of 50-70 degrees is formed between the smart phone and the horizontal plane; in the second adsorption state, a video call angle of 0-15 degrees is formed between the smart phone and the horizontal plane; the third adsorption state is that the sound box is not adsorbed with the mobile phone. And switching to the corresponding interaction mode according to the adsorption state, analyzing the use data of the user in different modes by utilizing a machine learning algorithm, generating a personalized parameter scheme, and automatically applying in the corresponding state to optimize the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of Bluetooth speakers, and in particular to a multi-mode interaction method between a Bluetooth speaker and a smart phone. Background Art

[0002] At present, the interaction between Bluetooth speakers and smartphones mainly relies on wireless connection to achieve audio playback or call functions. Such speakers are usually equipped with different brackets or accessories to fix the phone on the speaker, so that users can get a better visual experience when watching videos or making video calls. At the same time, some speakers improve the audio effect through preset sound effect modes to meet different usage scenarios.

[0003] However, the physical combination of speakers and smartphones in the prior art often lacks flexibility and cannot achieve precise support angle adjustment in different adsorption states. In addition, the interaction mode in the prior art is relatively simple and lacks personalized adaptation to different user behaviors and environmental conditions, and cannot fully optimize the user's audio and video experience. This results in users having to manually adjust the sound effects when switching scenes, which makes the user experience more cumbersome.

[0004] Therefore, there is an urgent need to develop a new multi-mode interaction method between Bluetooth speakers and smart phones. Summary of the invention

[0005] The present application provides a multi-mode interaction method between a Bluetooth speaker and a smart phone to improve the user's audio and video experience.

[0006] The present application provides a multi-mode interaction method between a Bluetooth speaker and a smart phone, comprising:

[0007] A first magnet ring capable of adjusting an angle is arranged on the Bluetooth speaker, and the first magnet ring is used to magnetically adsorb with a second magnet ring on the smart phone, so as to realize a physical connection between the Bluetooth speaker and the smart phone;

[0008] Establish a wireless connection between the Bluetooth speaker and the smartphone via the Bluetooth protocol;

[0009] Detecting the physical adsorption state of the smart phone and the Bluetooth speaker, the physical adsorption state includes a first adsorption state, a second adsorption state and a third adsorption state; wherein the first adsorption state refers to the smart phone being adsorbed on the Bluetooth speaker, the first magnet ring and the second magnet ring being magnetically adsorbed, and the smart phone being at a video viewing angle of 50-70 degrees to the horizontal plane; the second adsorption state refers to the smart phone being adsorbed on the Bluetooth speaker, the first magnet ring and the second magnet ring being magnetically adsorbed, and the smart phone being at a video call angle of 0-15 degrees to the horizontal plane; the third adsorption state refers to the Bluetooth speaker not being adsorbed on the smart phone;

[0010] According to the detected physical adsorption state, enter the corresponding interaction mode;

[0011] Use machine learning algorithms to analyze the collected user usage data in different interaction modes and generate personalized parameter solutions for different physical adsorption states;

[0012] When the corresponding physical adsorption state is detected, the corresponding personalized parameter scheme is applied to optimize the user experience.

[0013] The beneficial effects of the technical solution provided by this application include:

[0014] (1) Through machine learning algorithms, the user's usage data in different interaction modes is analyzed, and personalized parameter solutions are generated for each physical adsorption state, which realizes the intelligent adjustment of parameters such as sound effects, and improves the user's audio and video experience in different scenarios. (2) When the system detects different physical adsorption states, it can apply the corresponding personalized parameter solutions in real time, so that the device can make adaptive adjustments according to the user's usage habits and environmental changes, thereby significantly improving the user's overall experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flowchart of a multi-mode interaction method between a Bluetooth speaker and a smart phone provided in the first embodiment of the present application.

[0016] Figure 2 This is a schematic diagram of the connection between the Bluetooth speaker and the smart phone involved in the first embodiment of the present application. DETAILED DESCRIPTION

[0017] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0018] The first embodiment of the present application provides a multi-mode interaction method between a Bluetooth speaker and a smart phone. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 A first embodiment of the present application provides a multi-mode interaction method between a Bluetooth speaker and a smart phone for detailed description.

[0019] Step S101: a first magnet ring capable of adjusting an angle is provided on the Bluetooth speaker, wherein the first magnet ring is used for magnetically adsorbing with a second magnet ring on the smart phone, thereby achieving a physical connection between the Bluetooth speaker and the smart phone.

[0020] In step S101, a first magnet ring with an adjustable angle is firstly provided at the bottom or side of the Bluetooth speaker. The material of the magnet ring should be a material with strong magnetism, such as a neodymium magnet or a similar high magnetic alloy, to ensure that it can generate stable magnetic adsorption with the second magnet ring on the smartphone at different angles.

[0021] During the specific installation process, the first magnet ring can be embedded in the shell structure of the Bluetooth speaker to ensure that it can be rotated or tilted in different directions. This design can be achieved by setting an adjustable hinge mechanism or sliding guide inside the speaker, so as to allow the first magnet ring to align with the second magnet ring on the smartphone at an appropriate angle. The adjustment mechanism should have sufficient damping force to ensure that the adjusted angle can remain stable during the adsorption process without displacement or sliding due to the weight of the smartphone.

[0022] During implementation, the first magnet ring on the Bluetooth speaker should be aligned with the second magnet ring on the smartphone to ensure that the two magnet rings can generate sufficient magnetic attraction when close to achieve a quick and secure physical connection. During the adsorption process of the smartphone and Bluetooth speaker, the weight and size differences of different smartphone models should be taken into account. The adsorption force of the magnet ring should be able to adapt to a wide range of device types and ensure stability in various physical adsorption states.

[0023] In practical applications, in order to enhance the user experience, a layer of anti-slip material (such as silicone or rubber coating) can be covered on the surface of the first magnet ring to prevent the smartphone from sliding in the adsorption state. At the same time, in order to prevent the potential interference of magnetism on the internal electronic components of the smartphone, a shielding layer (such as an aluminum foil layer or a conductive foam layer) can be added between the magnet ring and the speaker housing to effectively shield unnecessary magnetic field leakage.

[0024] The implementation of this step needs to take into account the impact of magnetic adsorption on the physical connection between the smartphone and the Bluetooth speaker, ensuring stable physical support during the adsorption process while allowing flexible adjustment at different angles. Through the above method, this step can provide a reliable physical connection foundation for the multi-mode interaction between the Bluetooth speaker and the smartphone.

[0025] Figure 2 It is a schematic diagram of the connection between the Bluetooth speaker 2 and the smart phone 100 involved in the first embodiment of the present application. Figure 2 In the embodiment, the smart phone 100 is physically connected to the Bluetooth speaker 2. The magnetic ring 1 of the Bluetooth speaker 2 is connected to the magnetic ring of the smart phone ( Figure 2The magnetic ring is placed on the back of the mobile phone (not shown), and is the same shape as the magnetic ring 11). The magnetic ring 1 can adjust the angle along the rotation axis inside the connecting part 11. The Bluetooth speaker 2 has a multi-function switch button 224, which has functions such as opening, closing, Bluetooth connection, pausing, and playing. The upper shell of the Bluetooth speaker 2 is provided with a middle hole 223 that runs through from top to bottom, and the sound output direction of the speaker 23 faces upward, and the sound outlet of the speaker 23 is located in the middle hole 223 of the upper shell. A gasket 12 is provided on the side of the mobile phone magnetic ring 1 facing the Bluetooth speaker 2.

[0026] Step S102: Establishing a wireless connection between the Bluetooth speaker and the smart phone through the Bluetooth protocol.

[0027] In step S102, establishing a wireless connection between a Bluetooth speaker and a smartphone through the Bluetooth protocol is a key step in achieving multi-mode interaction. First, the Bluetooth modules need to be started on the smartphone and the Bluetooth speaker respectively. On the smartphone side, the Bluetooth module is usually activated through an API call built into the operating system. Users can turn on the Bluetooth function in the settings menu, or automatically start the Bluetooth search function through an application. At the same time, the Bluetooth module on the Bluetooth speaker also needs to enter a discoverable pairing mode, which is usually achieved by pressing a specific button or switch on the speaker.

[0028] When a Bluetooth speaker enters pairing mode, it broadcasts its device name and MAC address. When the smartphone receives this information within the search range, it displays a list of available devices on the user interface. The user can select the speaker to make a pairing request. At this point, the smartphone and the Bluetooth speaker communicate through the device discovery process of the Bluetooth protocol stack, including the exchange of device names, identification of device types, and confirmation of connection methods.

[0029] Once the speaker accepts the pairing request from the smartphone, the two parties begin the Bluetooth protocol connection process. First, the speaker and smartphone negotiate the communication parameters of the devices through the Link Management Protocol (LMP), such as the Maximum Transmission Unit (MTU), flow control method, error detection and correction method, etc. Next, through the Service Discovery Protocol (SDP), the smartphone obtains the service types supported by the Bluetooth speaker, such as audio playback, microphone input and other functional modules. This step ensures that the two devices can communicate using the same protocol standard in subsequent interactions.

[0030] After completing the above protocol negotiation, a secure wireless connection is established between the smartphone and the Bluetooth speaker. To ensure communication security, encryption is usually used during the connection process, such as AES encryption of the Bluetooth channel to protect the privacy of data transmission. This encryption process is automatically started when pairing is successful, without manual user intervention. After the connection is successfully established, the Bluetooth speaker will emit a prompt tone to inform the user that the device has been successfully connected and entered normal working mode.

[0031] Step S103: Detecting the physical adsorption state between the smart phone and the Bluetooth speaker, wherein the physical adsorption state includes a first adsorption state, a second adsorption state and a third adsorption state; wherein the first adsorption state refers to that the smart phone is adsorbed on the Bluetooth speaker, the first magnet ring is magnetically adsorbed to the second magnet ring, and the smart phone is at a video viewing angle of 50-70 degrees to the horizontal plane; the second adsorption state refers to that the smart phone is adsorbed on the Bluetooth speaker, the first magnet ring is magnetically adsorbed to the second magnet ring, and the smart phone is at a video call angle of 0-15 degrees to the horizontal plane; the third adsorption state refers to that the Bluetooth speaker is not adsorbed to the smart phone.

[0032] In step S103, detecting the physical adsorption state of the smartphone and the Bluetooth speaker is a key step in achieving multi-mode interaction. First, the adsorption state of the smartphone is monitored in real time by using an angle sensor, a pressure sensor, and a magnetic sensor integrated inside the Bluetooth speaker. These sensors work together to determine the angle and adsorption state between the smartphone and the speaker.

[0033] When the smartphone is attached to the Bluetooth speaker through the magnet ring, the angle sensor will immediately sense the tilt angle of the smartphone relative to the horizontal plane. If the smartphone is detected to be at an angle between 50 and 70 degrees with the horizontal plane, it is determined to be the first attachment state, that is, the angle of the video viewing mode. In this state, the Bluetooth speaker will receive the feedback signal from the sensor and record the current attachment state information.

[0034] If the angle sensor detects that the smartphone is tilted at an angle of 0-15 degrees to the horizontal plane, it can be identified as the second adsorption state, that is, the video call mode. At this time, the Bluetooth speaker system will mark this state as the corresponding physical adsorption state, and further confirm the adsorption position of the smartphone in combination with the information from the magnetic sensor. The magnetic sensor can accurately sense the adsorption position of the smartphone and ensure that the two magnet rings can still achieve stable magnetic adsorption at different angles.

[0035] When the smartphone is not physically attached to the Bluetooth speaker, the angle sensor will detect that the Bluetooth speaker is not within the preset angle range, and the pressure sensor does not sense the pressure change from the smartphone. In this case, the system determines that it is in the third attachment state, that is, the Bluetooth speaker is in an independent placement state.

[0036] To ensure the accuracy of the detection, the system will sample and average the sensor data multiple times to eliminate short-term jitter or misjudgment. During the above detection process, the processor of the Bluetooth speaker will transmit the data collected by the sensor to the central control module in real time. The module is responsible for determining the current physical adsorption state and passing the state information to the subsequent interactive mode control module to realize the next interactive operation.

[0037] Step S104: Entering a corresponding interactive mode according to the detected physical adsorption state.

[0038] In step S104, the system automatically switches to the corresponding interaction mode according to the detected physical adsorption state. Specifically, when the physical adsorption state is determined, the control module of the Bluetooth speaker will immediately identify the state and start the audio and video processing modules corresponding to the state, thereby entering the interaction mode suitable for the current usage scenario.

[0039] When the first adsorption state is detected, that is, the smartphone and the Bluetooth speaker are adsorbed together at an angle of 50-70 degrees, the system will automatically enter the video playback mode. In this mode, the Bluetooth speaker will switch the sound effect mode to the cinema sound effect mode, and turn on the stereo sound enhancement function to provide better surround sound effects. At this time, the system will also dynamically adjust the audio parameters according to the type of video content currently being played (such as movies, TV series or music videos) to optimize the user's viewing experience.

[0040] When the second adsorption state is detected, that is, the smartphone and the Bluetooth speaker are adsorbed together at an angle of 0-15 degrees, the system will switch to video call mode. In this mode, the microphone sensitivity of the Bluetooth speaker will be automatically increased to ensure that the user's voice signal can be clearly captured during voice input. At the same time, the system will enable the call noise reduction function to reduce the interference of environmental noise and optimize the voice clarity during calls. The system will also adjust the voice processing parameters in real time to cope with different changes in the voice environment to ensure stable voice output under various call conditions.

[0041] When the third adsorption state is detected, that is, the smartphone is not physically adsorbed to the Bluetooth speaker, the system will enter the music playback mode. In this mode, the sound effect setting of the Bluetooth speaker will be adjusted to the omnidirectional stereo sound effect mode to enhance the spatial sense of the sound effect. In addition, the system will automatically optimize the balance of bass and treble to ensure a richer sound quality performance when playing music. The speaker will also enable the spatial sound optimization function to enhance the surround effect of music through the multi-directional propagation of sound, increasing the user's auditory enjoyment.

[0042] During the whole process, the control module of the Bluetooth speaker monitors the current physical adsorption state changes in real time, and quickly adjusts the audio and video parameters according to the switching of each state. In this way, the system can quickly and accurately switch to the corresponding interactive mode according to different adsorption states, achieving seamless conversion of multiple modes and optimal audio and video effects.

[0043] When the system enters the corresponding interactive mode according to the detected physical adsorption state, the specific sound effect adjustment and function optimization will be implemented according to the different adsorption states. When the first adsorption state is detected, that is, when the smartphone and the Bluetooth speaker are adsorbed together at an angle of 50-70 degrees, the system will automatically switch to the video playback mode. In this mode, the system first adjusts the Bluetooth speaker to the cinema sound effect mode. This sound effect mode is specifically used to enhance the sound effect of the video, making the sound effect of the low-frequency part more shocking, while improving the clarity of the high-frequency part. At this time, the system will turn on the stereo sound effect enhancement function, so that the surround and spatial sense of the sound are significantly improved, thereby enhancing the user's audio-visual experience. In addition, the system will dynamically adjust the audio parameters according to the type of video content, such as strengthening the low-frequency impact in action movies and enhancing the clarity of the human voice in dialogue clips, thereby optimizing the user's perception during video playback.

[0044] When the system detects the second adsorption state, that is, when the smartphone and the Bluetooth speaker are adsorbed at an angle of 0-15 degrees, the system will enter the video call mode. In this mode, the system will automatically increase the microphone sensitivity of the Bluetooth speaker so that the microphone can capture the user's voice signal more clearly. This adjustment is particularly suitable for users' voice input needs in a quiet environment or at a larger call distance. At the same time, the system will enable the call noise reduction function to reduce the interference of environmental noise on call quality by real-time analysis of environmental noise and dynamic noise reduction processing. In terms of voice clarity, the system will optimize audio processing parameters, such as enhancing voice signals in the mid-frequency band, and make real-time adjustments based on the user's speaking speed and tone to ensure the stability and clarity of voice output, thereby providing users with a more natural and high-quality video call experience.

[0045] When the system detects the third adsorption state, that is, when the smartphone is not physically adsorbed to the Bluetooth speaker, the system will automatically switch to music playback mode. In this mode, the system will adjust the Bluetooth speaker to omnidirectional stereo sound mode. This mode can spread the sound evenly all around, creating a stronger sense of space and surround. In addition, the system will optimize the balance of bass and treble according to the user's sound preferences, making the bass thicker and the treble clearer. During playback, the system will also enable the spatial sound optimization function to further enhance the distribution and layering of music in the space, thereby enhancing the overall auditory effect.

[0046] Through the above mechanism, different physical adsorption states will trigger corresponding interaction mode switching, and each mode contains a series of optimized settings for sound effects and functions to ensure that users get the best audio experience in different scenarios. The system can not only automatically adjust according to the adsorption state, but also dynamically optimize according to environmental changes and user preferences, making multi-mode interaction more intelligent and personalized.

[0047] When the first adsorption state is detected, that is, when the smartphone and the Bluetooth speaker are adsorbed at an angle of 50-70 degrees, the system will enter the video playback mode. To further optimize the user's viewing experience in this mode, the system will dynamically select the most suitable cinema sound mode based on the audio characteristics of the video content. First, the system will analyze the audio signal of the video content in real time and extract feature information from the audio. This feature information may include vocal dialogue, background music, and sound effect details. By analyzing these features, the system can determine the type of the current video, such as a feature film mainly based on vocals, an action film with rich sound effects, or a musical with a large proportion of music.

[0048] Based on the analysis results, the system will automatically select the most appropriate cinema sound mode. If it is detected that the video content is mainly vocal dialogue, the system will switch to the dialogue clarity mode. In this mode, the Bluetooth speaker will enhance the output of the vocal frequency to make the dialogue part clearer and more prominent. If the music accounts for a large proportion of the video content, the system will switch to the music enhancement mode. In this mode, the Bluetooth speaker will enhance the performance of the low-frequency and high-frequency parts, making the music effect fuller and more three-dimensional. For content with a large proportion of sound effects and background sounds (such as action movies or science fiction movies), the system will select the stereo surround mode to enhance the surround sound effect, so that users can get a more immersive audio-visual experience.

[0049] In terms of volume adjustment, the system will use the user's historical volume adjustment habit data to set the initial volume value. This initial volume value is set based on the user's volume preference in the past video playback mode, ensuring that the user can obtain a suitable volume level without manual adjustment each time they enter this mode. In addition, the system will automatically fine-tune the volume according to real-time changes in ambient noise. Ambient noise detection is usually achieved through the microphone of a smartphone or an ambient noise sensor on a Bluetooth speaker. When the ambient noise increases, the system will automatically increase the volume output to ensure that the sound effects of the video content are not disturbed by background noise; when the ambient noise decreases, the system will appropriately reduce the volume to avoid excessive volume affecting the user's auditory comfort.

[0050] Through the above steps, the system can not only intelligently adjust the sound effects and volume according to the video content and user habits, but also respond to changes in the environment in real time, thereby providing users with a continuously optimized viewing experience. This dynamic sound effect and volume adjustment mechanism not only improves the intelligence level of the system, but also significantly enhances the user's audio-visual enjoyment in video playback mode.

[0051] When the second adsorption state is detected, that is, when the smartphone and the Bluetooth speaker are adsorbed at an angle of 0-15 degrees, the system will enter the video call mode. To optimize the audio quality in this mode, the system first uses a machine learning algorithm to analyze the frequency of users adjusting the microphone sensitivity during past video calls. This analysis is based on the user's historical audio settings and adjustment behaviors, and extracts the user's preference patterns in different environments and call situations. For example, if the user often lowers the microphone sensitivity in a quieter environment, the system will automatically set the initial sensitivity lower in similar environments in the future. On the contrary, if the user repeatedly increases the microphone sensitivity in a noisier environment, the system will automatically adjust the initial sensitivity higher accordingly to better adapt to the current call environment.

[0052] During real-time calls, the system will also dynamically adjust the noise reduction intensity according to changes in ambient noise. Specifically, the noise sensors on Bluetooth speakers and smartphones will continuously monitor the ambient noise level. If the noise increases, the system will increase the noise reduction function accordingly to ensure that the clarity of the voice is not disturbed by external noise. This adjustment is calculated and implemented in real time by an algorithm, which can respond to changes in ambient noise within milliseconds to ensure the stability of call quality. At the same time, when the ambient noise decreases, the system will automatically reduce the noise reduction intensity to avoid excessive processing of the voice signal by excessive noise reduction, thereby preserving the natural sound quality of the voice.

[0053] In addition, to further improve voice clarity and call quality, the system will use the multi-microphone array technology of smartphones and Bluetooth speakers. This multi-microphone array can not only identify and eliminate background noise through phase difference and signal strength difference, but also enhance the directionality of the user's voice through sound source localization technology. In actual applications, the multi-microphone array will first identify the direction of the user's voice, and then filter the background noise in other directions, so that the user's voice becomes clearer and more prominent during the call. This sound source localization technology can be adjusted in real time in a dynamic environment, so that the system can still maintain high-quality voice output when the user moves or the environment changes.

[0054] Through the above series of optimization steps, the system can not only automatically adjust the microphone sensitivity according to the user's habits in video call mode, but also respond to changes in environmental noise in real time, and improve the directionality and clarity of voice through multiple microphone arrays and sound source localization technology. In this way, users can get clearer and more natural voice effects during video calls, and the system can also stably provide high-quality audio performance in different environments.

[0055] When the third adsorption state is detected, that is, when the smartphone is not physically adsorbed to the Bluetooth speaker, the system will switch to music playback mode. To optimize the sound performance in this mode, the system will first select the appropriate equalizer preset mode by analyzing the user's sound preferences for different music types. Specifically, the system will analyze the user's historical playback records to identify the sound settings selected by the user for different types of music, such as pop music, classical music, jazz, and electronic music. This analysis involves not only historical data on volume and frequency adjustments, but also preferences for equalizer settings, such as bass enhancement, vocal clarity mode, or treble boost. Based on the results of this analysis, the system will automatically select the equalizer preset mode that best matches the user's current music type preference to ensure that the music played matches the user's hearing needs.

[0056] During music playback, the system will also dynamically adjust the spatial sound effect parameters according to the rhythm changes of the song. The spatial sound effect parameters are adjusted through real-time analysis of the music signal, with special attention paid to the rhythm, beat, and strength changes of the song. For example, when the system detects that the music rhythm is accelerated or the low-frequency components are enhanced, the surround effect of the spatial sound effect will be enhanced, so that the sound will have a greater sense of extension in the space, thereby enhancing the three-dimensional sense and immersion of hearing; when the music rhythm slows down or turns soft, the system will appropriately shrink the spatial sound effect so that the sound is concentrated in front of the listener, creating a more delicate and private listening experience. This dynamic adjustment mechanism can respond to changes in the song in real time, synchronize the sound effects with the rhythm of the music, thereby improving the auditory presence and musical expression.

[0057] In addition, the system sets the initial sound effect parameters by analyzing the user's historical bass and treble adjustment data. For example, if the user frequently increased the bass during past playback, the system will automatically set higher bass parameters at the beginning of a new round of music playback, and vice versa. As the music plays, the system monitors the current audio output in real time and makes further fine-tuning based on the user's real-time adjustment behavior. If the user adjusts the bass or treble parameters again during playback, the system will quickly respond to this change and update the sound effect parameters through algorithms to ensure continuous optimization of the listening experience.

[0058] Through the above steps, the system can not only automatically select the appropriate equalizer mode according to the user's sound effect preferences in music playback mode, but also adjust the sound effect parameters in real time to match the rhythm of the music and the user's immediate needs. This highly flexible and personalized sound effect optimization mechanism not only enhances the user's auditory experience, but also improves the overall sound quality of music playback, allowing users to enjoy the best sound effect experience in different types of music.

[0059] Step S105: Analyze the collected usage data of users in different interaction modes using a machine learning algorithm to generate personalized parameter solutions for different physical adsorption states.

[0060] In step S105, the system analyzes the user's usage data in different interaction modes through a machine learning algorithm to generate personalized parameter solutions for different physical adsorption states. First, the system obtains relevant usage data from the sensors, application interfaces, and user inputs of the Bluetooth speaker and smartphone. These data may include the user's volume adjustment habits, the selection frequency of the sound effect mode, the adjustment record of the microphone sensitivity, the adjustment history of the support angle, and environmental characteristics such as the ambient noise level and the ambient light intensity. This step can be performed in the processing unit of the Bluetooth speaker.

[0061] Once the data is collected, the system will preprocess it, including data standardization, denoising and normalization. The standardization process ensures that the numerical range of different data is the same, the denoising process is used to filter out outliers and invalid data, and normalization scales the data to the same range for subsequent machine learning algorithm processing.

[0062] Next, the preprocessed data will be fed into a pre-trained neural network model for analysis.

[0063] After completing the above feature analysis, the output layer of the neural network will generate personalized parameter solutions for different physical adsorption states based on the analysis results. Specifically, for the first adsorption state, the personalized parameter solution may include a specific enhancement level and optimal support angle for the video sound effect mode; for the second adsorption state, the solution may focus on optimizing voice clarity and adjusting noise reduction parameters; and for the third adsorption state, it may focus on adjusting the equalizer settings and enhancing spatial sound effects. Each personalized parameter solution contains a combination of multiple parameters, ensuring the optimal adjustment of the user experience in different interaction modes.

[0064] The entire process can be continuously optimized based on the user's historical usage data and environmental changes through the adaptive characteristics of the machine learning algorithm. This means that during the user's use, the system will continuously update the personalized parameter plan based on new data, so that it can be closer to the user's actual needs and preferences each time it is used. In this way, through in-depth analysis and feature extraction of user behavior data, the system can not only provide highly personalized settings for different physical adsorption states, but also achieve smooth transition when switching between multiple modes, ensuring continuous optimization of the user experience.

[0065] Furthermore, the machine learning algorithm is used to analyze the collected usage data of users in different interaction modes to generate personalized parameter solutions for different physical adsorption states, including:

[0066] Using a pre-trained neural network model, the collected user usage data in different interaction modes is processed to generate personalized parameter solutions for different physical adsorption states; wherein the neural network model includes an input encoding module, a multi-dimensional attention feature extraction module, an adaptive multi-state feature fusion module, and a multi-task optimization output module;

[0067] The input coding module is used to receive multiple types of input features, including user behavior features, physical adsorption state features and environmental features; the input coding module uses a convolutional coding network to perform preliminary extraction and nonlinear transformation on the input features, and maps the low-dimensional input features to a high-dimensional space, thereby obtaining a coding feature vector;

[0068] The multi-dimensional attention feature extraction module is used to receive the encoded feature vector provided by the input encoding module; the multi-dimensional attention feature extraction module is implemented by a recursive neural network based on a multi-dimensional attention mechanism, and is used to dynamically adjust the weight of features for different adsorption states and interaction modes to obtain a feature vector weighted by multi-dimensional attention;

[0069] The adaptive multi-state feature fusion module is used to receive the feature vector provided by the multi-dimensional attention feature extraction module; the adaptive multi-state feature fusion module uses a cross-feature combination strategy to cross-multiply and weighted sum features from different modes to generate a richer multi-mode feature representation; through a dynamic weighting function, the fusion weight of the feature is adjusted according to the current physical adsorption state and user preference to obtain a fused feature vector;

[0070] The multi-task optimization output module is used to receive the fused feature vector provided by the adaptive multi-state feature fusion module; the multi-task optimization output module is designed based on a multi-task learning framework, and decomposes the final personalized parameter scheme into multiple task outputs, and the multiple task outputs include:

[0071] Task 1: Parameter output of video playback mode, including sound enhancement and stereo enhancement;

[0072] Task 2: Parameter output of video call mode, including microphone sensitivity, noise reduction strength, and voice clarity parameters;

[0073] Task 3: Parameter output of music playback mode, including equalizer adjustment, spatial sound effects and bass enhancement parameters.

[0074] When implementing this multimodal interaction method, using machine learning algorithms to analyze user usage data in different interaction modes is a core step. First, the system collects various feature data of users in different physical adsorption states and interaction modes. These data include user behavior characteristics (such as volume adjustment, sound effect selection, microphone adjustment, etc.), physical adsorption state characteristics (such as angle change, adsorption position), and environmental characteristics (such as ambient noise, light intensity, etc.). The diversity of these data provides a sufficient basis for the subsequent generation of personalized parameter solutions.

[0075] After data collection is completed, these various types of input features will be received by the input encoding module. This module uses a convolutional coding network to perform preliminary extraction and nonlinear transformation of the input features, with the aim of mapping low-dimensional input features to high-dimensional space. The convolutional coding network extracts features of different dimensions layer by layer to ensure that the nonlinear relationship between features is fully captured and represented. In this way, the system can extract key features from complex user behavior patterns to obtain encoded feature vectors. This encoded feature vector has higher expressiveness and generalization, laying the foundation for subsequent in-depth analysis and processing.

[0076] Next, the encoded feature vector is further processed by the multi-dimensional attention feature extraction module. This module is implemented using a recursive neural network based on a multi-dimensional attention mechanism. The purpose of this process is to dynamically adjust the weights of the input features according to different physical adsorption states and interaction modes. The multi-dimensional attention mechanism can fine-tune the weights of the features to enhance the key features in a specific interaction mode. For example, in video playback mode, the attention mechanism will highlight sound effect-related features, while in video call mode, it will give higher weights to features related to microphone sensitivity and speech clarity. Through this dynamic weighting, the system is able to generate a feature vector weighted by multi-dimensional attention that can better adapt to the current physical adsorption state and interaction mode.

[0077] Subsequently, the adaptive multi-state feature fusion module fuses the feature vectors provided by the multi-dimensional attention feature extraction module. This module adopts a cross-feature combination strategy to cross-multiply and weighted sum features from different modes to generate a richer multi-modal feature representation. Through this cross-feature combination, the system can capture the interactive relationship between features in different modes, and adjust the fusion weight of the features according to the current physical adsorption state and user preferences through a dynamic weighting function to obtain the fused feature vector. This feature fusion strategy ensures the system's adaptability and personalized performance under different adsorption states.

[0078] Finally, the multi-task optimization output module decomposes the fused feature vector into multiple task outputs. These outputs are designed as personalized parameter solutions for different interaction modes. For video playback mode, the output includes parameter settings for sound enhancement and stereo enhancement; for video call mode, the output includes optimization parameters for microphone sensitivity, noise reduction strength, and voice clarity; and in music playback mode, the output includes settings for equalizer adjustment, spatial sound effects, and bass enhancement. Each task output is optimized for a specific physical adsorption state and user needs to ensure the best audio and video experience in different interaction modes.

[0079] Through the above implementation steps, the present invention can generate highly personalized parameter solutions based on the user's usage data in different modes, which not only improves the system's adaptability and intelligence level, but also significantly optimizes the user's overall experience in multi-mode interaction.

[0080] In this embodiment, the design and implementation of the multi-dimensional attention feature extraction module is a key part, the purpose of which is to calculate the attention weights of the input features at different time steps and use these weights to extract and adjust the temporal features. The whole process relies on a series of calculation steps, involving the specific application of multiple mathematical formulas and parameters.

[0081] First, the system calculates the multi-dimensional attention weight of each input feature at time step t through Formula 1. The specific form of Formula 1 is as follows:

[0082]

[0083] In formula 1, A t Represents the attention weight at time step t, which is used to reflect the importance of the current input feature in the multidimensional space. The attention weight is achieved by performing a nonlinear transformation on each input feature and normalizing it. Specifically:

[0084] W a is a multi-dimensional attention weight matrix, which is a trainable matrix used to transform the input feature vector X encThe elements in this matrix are automatically adjusted through the neural network training process to optimally extract different dimensions of features.

[0085] X enc It is the encoded feature vector generated by the input encoding module. It represents the feature result after being processed by the convolutional coding network. It is a high-dimensional representation of user behavior characteristics, physical adsorption state characteristics and environmental characteristics. This feature vector is extracted through multiple layers of the convolutional network, retaining the nonlinear relationship between different dimensions.

[0086] σ(z) is the standard Sigmoid activation function, which is defined as In this formula, the Sigmoid function is used to limit the input result to between (0,1), thereby converting the feature value into the basis of the attention weight, ensuring that the numerical range of the attention weight is suitable for subsequent normalization processing.

[0087] b a is the bias term, which is a parameter used to adjust the initial value of the input feature. The main function of the bias term is to balance the initial weights of different features, thereby ensuring that the model has better robustness and adaptability during feature processing.

[0088] X enc,j is the encoded feature vector generated by the input encoding module at time step j. It represents the input feature of the jth time step in the time series, and the feature X at time step t enc Its role is to provide a comparative reference during the attention weight normalization process to ensure that the sum of the attention scores of all time steps is 1.

[0089] T1 is the total number of time steps, that is, the length of the time series considered when calculating the attention weight. It represents the range of the time dimension of the input feature and is used in the formula to represent the end point of the time series. This parameter determines the range of normalization, thereby ensuring that the calculation of the attention weight covers the entire time series.

[0090] Once the attention weights A for all time steps t Calculated, they will be used to extract timing features. To this end, the system uses Formula 2 to extract timing features:

[0091] H t =tanh(W h ·(A t ⊙X enc,t )+U h ·H t-1 +b h )(2)

[0092] In Formula 2, H tThe time series feature vector representing time step t contains the evolution of multi-dimensional features in the time dimension. The specific explanation is as follows:

[0093] ⊙ is the element-wise Hadamard product, which is used to transform the attention weight A element by element. t With input feature X enc,t Multiply by , thereby adjusting the weight of each feature. This operation ensures that the attention weight plays a role in temporal feature extraction.

[0094] H t-1 is the time series feature state of the previous time step.

[0095] X enc,t is the encoded feature vector generated by the input encoding module at time step t.

[0096] W h It is the input weight matrix of the recurrent neural network, which is used to linearly transform the features adjusted by the attention weights. The weight values ​​in this matrix are optimized through training and used to extract features at the time step.

[0097] U h is the hidden layer weight matrix of the recurrent unit, which converts the feature state H of the previous time step t-1 Combined with the current feature, it is used to capture the long-term and short-term dependencies in the time series features. This process enables the recurrent network to model feature changes in the time dimension.

[0098] Tanh(z) is a hyperbolic tangent activation function, which is used to limit the eigenvalues ​​to the range of (-1,1) to ensure the nonlinear expression ability of the model.

[0099] b h It is the bias term of the recursive neural network, which is used to balance the initial value of the input feature during the recursive calculation process.

[0100] After completing the time series feature extraction, the system calculates the weighted feature vector using Formula 3:

[0101]

[0102] In formula 3, X att It is the feature vector weighted by the multi-dimensional master mind mechanism and used for the final feature fusion and output. The specific explanation is as follows:

[0103] Represents the accumulation of weighted features at all time steps. This accumulation process ensures the application of attention weights in the time dimension, so that the weighted feature vector can reflect the importance of multi-dimensional features. T represents the total number of time steps.

[0104] η is a periodic adjustment term, which is used to introduce a regulatory factor for periodic changes. This term remains fixed during the calculation process and is mainly used to adjust the periodic fluctuations of the feature in the time dimension.

[0105] is a periodic function, which is used to simulate the natural periodic changes of features in the time dimension. By introducing this term, the system can capture the periodic characteristics of features in the time dimension, thereby improving the response ability to periodic signals.

[0106] In this embodiment, the function of the adaptive multi-state feature fusion module is to achieve the fusion of multi-mode features through dynamic cross-feature combination and adaptive weight adjustment. This process uses formula 4 to perform complex combination of features, aiming to generate a more accurate and adaptable final fusion feature vector. The specific implementation steps are as follows.

[0107] During the feature fusion process, the system first obtains a series of weighted feature vectors from the multi-dimensional attention feature extraction module. Each feature vector represents the weighted result of the features in the current mode and contains important information extracted from multi-modal interactions. In order to enable these features to be optimally combined under different physical adsorption states, the adaptive multi-state feature fusion module adopts a dynamic cross-feature combination strategy to further fuse and optimize these features.

[0108] Formula 4 is used to implement the fusion strategy, and its specific form is:

[0109]

[0110] In this formula:

[0111] X fuse The feature vector representing the final fusion is the result of comprehensive processing of multi-dimensional features in different modes. This feature vector will be used to generate personalized parameter schemes for different physical adsorption states. Its calculation is achieved by cross-combining and adaptively adjusting all weighted features.

[0112] X att,i is the i-th weighted feature vector output by the multi-dimensional main feature extraction module. att,i It represents the feature weight distribution in a specific mode, which is generated by weighting the features through the attention mechanism. These feature vectors are the basis of the input data in the feature fusion process.

[0113] ⊙ is the element-level Hadamard product, which is used to cross-combine different features element by element. Through this element-by-element multiplication operation, the interaction between different features can be retained and enhanced during the fusion process, so that the combination effect of features in nonlinear space is strengthened.

[0114] tanh(γ i ·X att,i ) is the part that performs nonlinear transformation on the feature vector, where tanh(z) is the hyperbolic tangent activation function, which limits the input value to the range of (-1,1). This activation function is used to improve the nonlinear expression ability of the feature, and γ i is the adjustment coefficient used to control the nonlinear amplitude of the feature. Specifically, γ i It is a trainable parameter whose initial value is determined by the pre-training of the model and is dynamically adjusted according to the performance of the feature during the training process to ensure adaptability to the feature.

[0115] W fuse,i is the i-th element of the fusion weight matrix. Each weight element W fuse,i Used to control the proportion of different features in the final fusion feature. The initial weight value is determined by the model through learning large-scale data in the pre-training stage. During the model operation, these weights will be adaptively updated according to the current physical adsorption state and user behavior to achieve the optimal feature combination in different interaction modes.

[0116] is a periodic adjustment term used to introduce periodic changes in the time dimension. i is the periodic adjustment coefficient, which is an adjustable parameter used to control the amplitude of periodic changes. Specifically, β i Automatic optimization during the model training phase ensures that the periodicity adjustment matches the natural fluctuations of the features. By simulating the periodic characteristics of the feature changing over time, the dynamic adaptability of the feature is further improved, where t is the current timestamp and T is the specific adjustment period. The adjustment period T is set according to the time characteristics of the specific interaction mode to ensure that the feature maintains stable periodic changes in different time periods.

[0117] In this embodiment, the function and implementation of the input encoding module is a key part of the entire multi-modal interaction system. Its main purpose is to receive a variety of input data from user behavior, physical adsorption state and environmental characteristics, and perform necessary preprocessing and feature extraction on these data, so as to perform more accurate feature weighting and time series processing in subsequent steps.

[0118] First, the input encoding module receives three types of input features: user behavior features, physical adsorption state features, and environmental features. User behavior features include user operation records in different interaction modes, such as volume adjustment, sound effect selection, and microphone sensitivity setting. Physical adsorption state features describe the physical connection between the smartphone and the Bluetooth speaker, such as adsorption angle and position. Environmental features cover external conditions such as ambient noise, light intensity, and temperature. These input features come from a variety of sensors and user input interfaces, so they may have different value ranges and scales in their original state.

[0119] To ensure the consistency of these input data during model processing, the input encoding module first standardizes and normalizes the received feature data. The purpose of standardization is to make different features consistent in distribution by subtracting the mean and dividing by the standard deviation. Usually, their distribution is adjusted to a standard normal distribution with a mean of 0 and a standard deviation of 1. Normalization is to scale the values ​​of all features to the same range (for example, 0 to 1) to avoid biasing the model due to features with too large or too small values.

[0120] After preprocessing, the standardized and normalized features will be input into the convolutional coding network for feature extraction. The convolutional coding network is designed to map the input low-dimensional features to a high-dimensional feature space, thereby enhancing the ability to capture nonlinear relationships between multi-dimensional features. The convolutional coding network extracts complex relationships and patterns of input features layer by layer through the stacking and nonlinear activation of multiple convolutional layers.

[0121] Specifically, each layer of the convolutional coding network performs weighted processing on the input features through the convolution kernel and passes the result to the next layer for further nonlinear mapping. Through this layer-by-layer convolution and activation, the input features are gradually converted into high-dimensional feature vectors. The high-dimensional feature vector not only contains the basic information of the original input features, but also introduces the relationships and complex interactions between the features, which helps to perform more accurate feature weighting and time series processing in the subsequent multi-dimensional attention feature extraction module.

[0122] Finally, the extracted high-dimensional feature vector will be passed as output to the multi-dimensional attention feature extraction module. This output not only provides richer feature information for the multi-dimensional attention mechanism, but also lays the foundation for subsequent feature weighting and time series processing.

[0123] In this embodiment, the main function of the multi-task optimization output module is to decompose the multi-mode interaction task into multiple sub-tasks and dynamically adjust the priority and related settings of the output parameters according to the personalized needs in different modes. This module provides more accurate and personalized support for the multi-mode interaction between the Bluetooth speaker and the smartphone by decomposing the interaction tasks and optimizing the parameters.

[0124] First, during the multi-mode interaction process, the system will divide the overall task into multiple subtasks according to the user's operating behavior and physical adsorption status. These subtasks include sound enhancement, noise reduction intensity adjustment, equalizer settings, etc. This decomposition method enables each subtask to optimize parameters independently to ensure the best user experience in different interaction modes. For example, when the system is in video playback mode, the priority of the sound enhancement subtask may be higher than the noise reduction function, while in video call mode, noise reduction intensity and voice clarity will be optimized first. This dynamic adjustment of priorities ensures that the system can quickly adapt to changes in user needs in different modes.

[0125] When generating personalized parameter schemes for each subtask, the system refers to the user's historical preferences and current environmental conditions. For example, the output threshold of sound enhancement is set according to the user's sound preferences when using video playback mode in the past. If the user adjusts the bass enhancement multiple times in the historical record, the system will automatically set a higher bass output threshold; if the user lowers the volume multiple times in a quieter environment, the system will lower the threshold of sound enhancement accordingly when the current environmental noise is low. Similarly, the output parameters of noise reduction intensity are set according to the real-time changes in environmental noise and the user's historical preferences in similar environments. For example, in a noisy environment, the threshold of noise reduction intensity will be set higher to ensure that speech clarity is not disturbed. The output of the equalizer adjustment will be personalized according to the user's adjustment preferences under different music types, so that the sound performance in music playback mode can be consistent with the user's preferences.

[0126] Through the multi-task learning framework, the system can update the output weights of the model in real time during operation. Specifically, the multi-task learning framework optimizes the loss functions of multiple subtasks at the same time to ensure that the output parameters of each subtask can achieve the optimal configuration when switching between multiple modes. This real-time update mechanism enables the model to perform highly consistent in different modes, while having the ability to quickly respond to changes in user preferences. In actual operation, when the user's behavioral characteristics and environmental conditions change, the model automatically adjusts the output weights so that parameters such as sound enhancement, noise reduction intensity, and equalizer adjustment can quickly adapt to new usage scenarios. This real-time update not only improves the system's adaptability, but also ensures that the personalized performance in different modes always meets the needs of the user.

[0127] Through the above steps, the multi-task optimization output module can decompose complex tasks in multi-modal interaction into multiple sub-tasks, and dynamically adjust the output parameters of each sub-task according to the user's historical preferences and environmental conditions. At the same time, through the real-time update mechanism of the multi-task learning framework, the system can continuously optimize various parameter settings in different modes, thereby achieving a highly personalized and adaptive user experience.

[0128] The following is a reference implementation of the neural network model:

[0129]

[0130]

[0131]

[0132]

[0133]

[0134] In order to train the above neural network model, you need to build a valid dataset and perform multiple steps to optimize the weights of the model. The following are the brief training steps:

[0135] First, a multimodal dataset containing user behavior features, physical adsorption state features, and environmental features needs to be prepared. These data should include historical behavior records under multiple interaction modes and mark the corresponding target parameters (such as sound enhancement, noise reduction intensity, equalizer settings, etc.). The data should be preprocessed, including standardization and normalization, to ensure that the numerical range of the input features is consistent.

[0136] When initializing the model, select appropriate hyperparameters, such as learning rate, batch size, number of training rounds, etc. Instantiate the model and use an optimizer (such as Adam or SGD) to adjust the model weights, and select an appropriate loss function (such as mean square error) to evaluate the model's prediction effect. The calculation of the loss function can set weights for different task outputs to ensure the effect of multi-task learning.

[0137] During the training process, the input data is fed into the model in batches for forward propagation, and the loss of each batch is calculated. The loss value is based on the error between the parameter output and the true label of different modes such as video playback, video calls, and music playback. Based on the calculated total loss, the weights of the model are updated through the back propagation algorithm, so that the model can gradually learn to generate accurate personalized parameters in different modes.

[0138] After training, the model is tested on unseen data sets to ensure that the model can still output high-quality personalized parameter solutions under a variety of physical adsorption states and environmental conditions. The model weights can be further fine-tuned based on the test results to achieve the best results.

[0139] Step S106: When a corresponding physical adsorption state is detected, a corresponding personalized parameter solution is applied to optimize the user experience.

[0140] In step S106, after detecting the corresponding physical adsorption state, the system will immediately call and apply the previously generated personalized parameter solution to optimize the user experience. The key to this step is how to quickly and accurately apply the generated personalized parameter solution to the control system of the Bluetooth speaker and the smart phone.

[0141] When the physical adsorption state is determined, the central processing module of the system will automatically retrieve the personalized parameter scheme corresponding to the state. The scheme includes a variety of parameter settings, which involve sound mode, microphone sensitivity, support angle, noise reduction intensity, equalizer adjustment, etc. When entering different interaction modes, these parameters will be assigned to the corresponding functional modules to ensure that the device is adjusted according to the current physical state. For example, in the first adsorption state (video viewing mode), the system will adjust the sound mode of the Bluetooth speaker to the cinema sound mode according to the personalized scheme, and turn on the stereo sound enhancement function. At the same time, the screen support angle of the smartphone will also be fine-tuned according to the recommended value in the scheme to make it more compatible with the user's viewing angle.

[0142] In the second adsorption state (video call mode), the system will immediately increase the microphone sensitivity of the Bluetooth speaker by calling the parameter scheme and enable the noise reduction function. At this time, the noise reduction intensity of the speaker will be adjusted in real time according to user preferences and ambient noise levels. To ensure the best voice clarity, the system will also optimize the input voice through the real-time voice processing module to further improve the sound quality of the call.

[0143] In the third adsorption state (music playback mode), the system will adjust the equalizer settings of the Bluetooth speaker according to the personalized plan to improve the performance of bass and treble, and activate the spatial sound effect function to make the sound have a better surround feeling. The parameter adjustment in this mode focuses on the overall auditory effect of the music, so the omnidirectional stereo sound effect of the speaker will be activated first to increase the spatial sense and layering of the sound.

[0144] A second embodiment of the present application provides an electronic device, the electronic device comprising:

[0145] processor;

[0146] The memory is used to store a program. When the program is read and executed by the processor, the program executes the multi-mode interaction method between the Bluetooth speaker and the smart phone provided in the first embodiment of the present application.

[0147] The third embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the multi-mode interaction method between a Bluetooth speaker and a smart phone provided in the first embodiment of the present application is executed.

[0148] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A multi-mode interaction method between a Bluetooth speaker and a smart phone, characterized in that: include: A first magnet ring capable of adjusting an angle is arranged on the Bluetooth speaker, and the first magnet ring is used to magnetically adsorb with a second magnet ring on the smart phone, so as to realize a physical connection between the Bluetooth speaker and the smart phone; Establish a wireless connection between the Bluetooth speaker and the smartphone via the Bluetooth protocol; Detecting the physical adsorption state of the smart phone and the Bluetooth speaker, the physical adsorption state includes a first adsorption state, a second adsorption state and a third adsorption state; wherein the first adsorption state refers to the smart phone being adsorbed on the Bluetooth speaker, the first magnet ring and the second magnet ring being magnetically adsorbed, and the smart phone being at a video viewing angle of 50-70 degrees to the horizontal plane; the second adsorption state refers to the smart phone being adsorbed on the Bluetooth speaker, the first magnet ring and the second magnet ring being magnetically adsorbed, and the smart phone being at a video call angle of 0-15 degrees to the horizontal plane; the third adsorption state refers to the Bluetooth speaker not being adsorbed on the smart phone; According to the detected physical adsorption state, enter the corresponding interaction mode; Use machine learning algorithms to analyze the collected user usage data in different interaction modes and generate personalized parameter solutions for different physical adsorption states; When the corresponding physical adsorption state is detected, the corresponding personalized parameter scheme is applied to optimize the user experience.

2. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 1, characterized in that: The step of entering a corresponding interactive mode according to the detected physical adsorption state includes: When the first adsorption state is detected, the video playback mode is entered, and the Bluetooth speaker is adjusted to the cinema sound effect mode; the stereo sound effect enhancement function is turned on; and the audio parameters are dynamically adjusted according to the type of video content to optimize the viewing experience; When the second adsorption state is detected, the device enters the video call mode, improves the microphone sensitivity of the Bluetooth speaker, enables the call noise reduction function to reduce environmental noise interference, and optimizes the voice clarity parameters to enhance the call quality. When the third adsorption state is detected, the device enters the music playback mode and adjusts the Bluetooth speaker to the omnidirectional stereo sound mode; optimizes the balance between bass and treble to improve the sound quality; and enables the spatial sound optimization function to enhance the music playback effect.

3. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 2, characterized in that: When the first adsorption state is detected, the user experience of the video playback mode is further optimized through the following steps: Select different cinema sound modes based on the audio characteristics of the video content, including dialogue clarity mode, music enhancement mode, and stereo surround mode; The volume startup value is automatically set using the user's volume adjustment habit data, and is fine-tuned in real time based on the ambient noise level.

4. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 2, characterized in that: When the second adsorption state is detected, the audio quality of the video call mode is optimized, including: The machine learning algorithm analyzes how often users adjust the microphone sensitivity during video calls and automatically optimizes the initial microphone sensitivity setting. In real-time calls, the noise reduction intensity is dynamically adjusted according to the changes in ambient noise to ensure that voice clarity is not affected by ambient noise; Utilizes the multiple microphone arrays of smartphones and Bluetooth speakers to identify and eliminate background noise, and enhances the directionality of user voice through sound source localization technology.

5. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 2, characterized in that: When the third adsorption state is detected, the sound performance of the music playback mode is optimized, including: By analyzing the user's sound preferences for different music types, select the preset mode of the equalizer; During music playback, the spatial sound effect parameters are dynamically adjusted according to the changes in the song rhythm, so that the spatial sense of the sound effect matches the rhythm changes of the music; The system automatically sets the initial sound parameters based on the user's historical bass and treble adjustment data, and adjusts the bass and treble balance in real time during playback to enhance the user's auditory experience.

6. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 1, characterized in that: The method uses a machine learning algorithm to analyze the collected usage data of users in different interaction modes and generate personalized parameter solutions for different physical adsorption states, including: Using a pre-trained neural network model, the collected user usage data in different interaction modes is processed to generate personalized parameter solutions for different physical adsorption states; wherein the neural network model includes an input encoding module, a multi-dimensional attention feature extraction module, an adaptive multi-state feature fusion module, and a multi-task optimization output module; The input coding module is used to receive multiple types of input features, including user behavior features, physical adsorption state features and environmental features; the input coding module uses a convolutional coding network to perform preliminary extraction and nonlinear transformation on the input features, and maps the low-dimensional input features to a high-dimensional space, thereby obtaining a coding feature vector; The multi-dimensional attention feature extraction module is used to receive the encoded feature vector provided by the input encoding module; the multi-dimensional attention feature extraction module is implemented by a recursive neural network based on a multi-dimensional attention mechanism, and is used to dynamically adjust the weight of features for different adsorption states and interaction modes to obtain a feature vector weighted by multi-dimensional attention; The adaptive multi-state feature fusion module is used to receive the feature vector provided by the multi-dimensional attention feature extraction module; the adaptive multi-state feature fusion module uses a cross-feature combination strategy to cross-multiply and weighted sum features from different modes to generate a richer multi-mode feature representation; through a dynamic weighting function, the fusion weight of the feature is adjusted according to the current physical adsorption state and user preference to obtain a fused feature vector; The multi-task optimization output module is used to receive the fused feature vector provided by the adaptive multi-state feature fusion module; the multi-task optimization output module is designed based on a multi-task learning framework, and decomposes the final personalized parameter scheme into multiple task outputs, and the multiple task outputs include: Task 1: Parameter output of video playback mode, including sound enhancement and stereo enhancement; Task 2: Parameter output of video call mode, including microphone sensitivity, noise reduction strength, and voice clarity parameters; Task 3: Parameter output of music playback mode, including equalizer adjustment, spatial sound effects and bass enhancement parameters.

7. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 6, characterized in that: The multi-dimensional attention feature extraction module is specifically used for: The multi-dimensional attention weight of each input feature is calculated using the following formula 1: Among them, A t is the attention weight at time step t; W a is the multidimensional master attention weight matrix; X enc is the encoded feature vector generated by the input encoding module; σ(z) is the standard Sigmoid activation function; b a is a bias term used to balance the initial weights of different features; X enc,j is the encoded feature vector generated by the input encoding module at time step j; T1 is the total number of time steps; The following formula 2 is used to extract the time series features: H t =tanh(W h ·(A t ⊙X enc,t )+U h ·H t-1 +b h ) (2) Among them, H t is the time series feature vector at time step t; ⊙ is the element-wise Hadamard product, which is used to perform dot multiplication of the attention weight and the feature; W h is the input weight matrix of the recurrent neural network; U h is the hidden layer weight matrix of the recurrent unit; H t-1 is the time series characteristic state of the previous time step; b h is the bias term of the recurrent neural network; X enc,t is the encoded feature vector generated by the input encoding module at time step t; According to the following formula 3, the weighted feature vector is calculated: Among them, X att is the feature vector weighted by the multi-dimensional attention mechanism; η is the periodic adjustment term; T is the specific adjustment period.

8. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 6, characterized in that: The adaptive multi-state feature fusion module adopts a fusion strategy based on dynamic cross-feature combination and adaptive weight adjustment, and realizes fusion through the following formula 4: Among them, X fuse is the final fused feature vector; X att,i is the i-th weighted feature vector output by the multi-dimensional attention feature extraction module; ⊙ is the element-level Hadamard product, which is used to perform nonlinear cross-combination of features of different modes; γ i is the adjustment coefficient, which is used to control the nonlinear amplitude of the feature; W fuse,i is the i-th element of the fusion weight matrix. Its initial value is determined by the pre-training of the model and is dynamically updated through adaptive adjustment during operation. i is the periodic adjustment coefficient; t is the current timestamp; T is the specific adjustment period.

9. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 6, characterized in that: The input encoding module is specifically used for: Receiving user behavior characteristics, physical adsorption state characteristics and environmental characteristics, and performing data preprocessing on these characteristics, including standardization and normalization, to ensure that the input data are within the same numerical range; The normalized features are extracted through the convolutional coding network, and the input low-dimensional features are mapped to the high-dimensional feature space, thereby enhancing the ability to capture the nonlinear relationship between multi-dimensional features; The extracted high-dimensional feature vector is output to the multi-dimensional attention feature extraction module for subsequent feature weighting and time series processing.

10. The multi-mode interaction method between a Bluetooth speaker and a smart phone according to claim 6, characterized in that: The multi-task optimization output module is specifically used for: By decomposing the multimodal interaction task into multiple subtasks, the priority of output parameters is adjusted according to the personalized needs in different modes; When generating personalized parameter solutions for each subtask, the output thresholds for sound enhancement, noise reduction intensity, and equalizer adjustment are set according to the user's historical preferences and current environmental conditions. Through the multi-task learning framework, the output weights of the model are updated in real time.

Images