Bluetooth earphone automatic pairing method for multi-device intelligent switching

Abstract

The invention discloses an automatic pairing method for a Bluetooth headset with multi-device intelligent switching. The method comprises the technical steps of collection and analysis of historical operation data of a user, dynamic adjustment of device priorities, optimization of a self-adaptive pairing protocol and the like. By establishing a user behavior prediction model based on a hidden Markov model (HMM) or a support vector machine (SVM), the switching requirements of the user equipment can be accurately predicted, and rapid and stable automatic switching between the equipment can be realized. According to the technical scheme, the switching accuracy and response speed are remarkably improved, wrong switching and switching delay are reduced, and smooth and seamless user experience is provided. In addition, by optimizing the pairing protocol and power consumption management, the power consumption can be reduced, the cruising ability of the equipment is enhanced, and the service life is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of Bluetooth headset pairing connection in wireless communications, and in particular to a Bluetooth headset automatic pairing method for intelligent switching of multiple devices. Background Art With the widespread use of mobile devices, Bluetooth headsets play an increasingly important role in users' daily lives, especially in the switching scenarios between multiple devices. Usually, users need to frequently switch Bluetooth headset connections between different devices, such as switching from a mobile phone to a tablet, and then to a computer. The existing Bluetooth headset switching methods mainly include manual switching and automatic switching.

[0002] 1. Manual switching: The manual switching method requires the user to operate between the headset and the device every time, select the device and confirm the connection. Although this method is reliable, it is particularly cumbersome for users who switch frequently, which increases the burden of use.

[0003] 2. Automatic switching: Automatic switching attempts to achieve automatic switching between devices by intelligently predicting the user's operation intention. However, existing automatic switching technologies often fail to accurately predict user needs, resulting in erroneous switching. False switching not only affects the user experience, but may also interrupt ongoing tasks, such as phone calls or video playback.

[0004] 3. Defects of existing technologies: In order to avoid mis-switching, the industry usually adopts device identification priority sorting or distance-based connection strategies, but these methods still have the following problems: they cannot accurately predict the user's historical operation steps and behavior habits, resulting in inaccurate automatic switching; device identification priority sorting is difficult to adapt to the situation of diversified devices and changing usage scenarios; manual switching still cannot completely solve the operational burden caused by users frequently switching devices; Although existing technologies have certain solutions, these methods still fail to effectively combine the user's operating habits, device switching frequency, and accuracy of automatic switching, resulting in high switching delays, unnecessary mis-switching, and a decline in user experience. Therefore, there is an urgent need for a technical solution that can intelligently learn user behavior, predict and avoid mis-switching based on historical operation steps, so as to improve the switching efficiency and user experience of Bluetooth headsets in a multi-device environment. Summary of the invention

[0005] The technical problem solved by the present invention is to provide a method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices in response to the defects existing in the above-mentioned prior art, so as to solve the () problem raised in the above-mentioned background technology.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows: A method for automatically pairing Bluetooth headsets with intelligent switching of multiple devices, comprising the following steps: S1, historical connection data collection and user behavior model construction: Bluetooth headsets record and collect user connection data between different devices through built-in sensors and software modules, including but not limited to: Device connection sequence, i.e. the record of users connecting to different devices in sequence; The switching interval between devices, that is, the time the user stays connected each time during the device switching process; The user confirmation method for device switching, including whether the user performs a confirmation operation during the switching process and the method used for confirmation; Connection duration, which is the average connection time for each device during user use; Device switching frequency, that is, the number of times a user changes devices within a certain period of time; The collected data is analyzed by a data processing unit in the headset and transmitted to a computing module of the headset through a data transmission protocol. The data is modeled using a hidden Markov model (HMM) or a support vector machine (SVM) algorithm. During the training process, the historical records of the connection data are divided into training sets. The model is gradually optimized using an incremental learning algorithm to learn the user's device switching pattern and time characteristics, and generate a device switching prediction model based on a time series. The model is used to predict the user's future target device and the order and time window of device switching; S2, behavior prediction and pre-switching mechanism: Based on the user behavior model, the headset predicts the target device that the user may switch to after operating on the current device, and enters the pre-switching state; the pre-switching state is triggered by the signal receiving module and the pairing module of the headset. When the target device sends a signal and meets the preset device switching conditions, the headset starts to prepare for connection, including adjusting the transmission parameters of the pairing signal to ensure low latency and high stability during the device switching process; when the user interacts with the target device in the pre-switching state, such as opening the audio playback software on the target device or performing other input operations, the headset confirms the user's switching intention and immediately completes the device switching; if no user interaction behavior is detected within the preset time, the headset maintains the current device connection state to avoid accidental switching; S3, intelligent device identification and dynamic priority sorting: In a multi-device environment, the headset automatically identifies the user's currently frequently used target device through an optimized device identification algorithm. The identification process includes: Statistics on the connection frequency of user devices and calculate the connection frequency of different devices in the past Number of times used within a time period; Record the user's choice every time they switch devices, and calculate the switching weights of different devices in historical data; Combine device connection preferences for specific time periods, such as differences in device connections during working hours and non-working hours; By real-time collection and analysis of the above information, a dynamic priority is assigned to each device, and the priority is calculated according to the following formula:

[0007] in: For equipment in the past Frequency of use in secondary connections; Representative equipment Historical connection probability during the current time period; For equipment The number of manual confirmations by users; is the normalization adjustment coefficient; Dynamic priority adjustment is based on user behavior patterns. If a device is frequently used within a certain period of time, the priority of the device will be automatically increased, thereby improving the response speed of device switching; S4, adaptive pairing protocol optimization: During multi-device switching, the headset dynamically adjusts the pairing protocol based on the user behavior model and device characteristics. During the pairing process: When the headset recognizes that the target device belongs to the Apple ecosystem, it automatically adjusts to Apple-specific pairing mode; When the headset recognizes that the target device is an Android system, it automatically switches to the standard universal Bluetooth protocol; During this process, pairing parameters are dynamically optimized based on the compatibility of the target device, including: Adjust data transmission rate to meet the transmission requirements of different devices; Adapt signal power to ensure that the device maintains a stable connection under different signal strengths; Optimize connection stability parameters to reduce possible signal loss during device switching; S5, power consumption management and signal stability optimization: During the multi-device switching process, the headset dynamically manages power consumption according to the connection status of the target device to reduce invalid power consumption. The power consumption management method includes: When the signal strength of the target device is detected to be lower than the set threshold, the Bluetooth power output is automatically reduced to reduce signal interference; When the device is not in use, it enters low-power standby mode to extend the battery life of the headset; The adaptive frequency hopping (AFH) algorithm is used to optimize Bluetooth signal transmission, reduce interference and improve connection stability.

[0008] S6, Implementation path of model training and behavior prediction: The training process of the user behavior prediction model includes the following steps: Data preprocessing: Extract characteristic data from historical operation records, including but not limited to device switching duration and connection times; Model training: Use incremental learning methods to train HMM or SVM models, optimize state transfer matrix and decision boundary to improve the accuracy of device switching prediction; Prediction optimization: Calculate the time window for device switching through regression analysis and optimize the device connection sequence to make the device switching process smooth and low-latency; S7, parameter optimization and model dynamic adjustment: In actual application, the headset dynamically updates the behavior prediction model based on new connection data and adjusts the algorithm parameters to improve prediction accuracy and response speed. The optimization process includes: After each device switch, the headset updates the user behavior data in real time to correct the device switching priority; An incremental learning algorithm is used to dynamically update HMM or SVM model parameters without retraining the entire dataset to ensure rapid adaptation to new user behavior patterns.

[0009] As a further solution of the present invention, the user behavior prediction model is established using a hidden Markov model HMM, and the state of the HMM includes but is not limited to a device connection state, a device disconnection state, and a device switching state.

[0010] As a further solution of the present invention, the device switching prediction module generates a target device prediction list based on historical data, and the historical data includes but is not limited to the user's device connection frequency, switching period, and device signal strength.

[0011] As a further solution of the present invention, the confirmation mechanism when switching devices includes but is not limited to the user's confirmation of the selection of the switching device, the comparison of signal strengths between devices, and the response time of the user's interactive operation.

[0012] As a further solution of the present invention, the smart device identification and dynamic priority sorting module adjusts the priority of each device in real time by analyzing the connection history and usage period of each device of the user, so as to improve the prediction accuracy of device switching.

[0013] As a further solution of the present invention, the optimization of the pairing protocol includes but is not limited to automatically adjusting the data transmission rate, connection delay and signal power of the Bluetooth protocol to ensure low power consumption and high stability when switching between multiple devices.

[0014] As a further solution of the present invention, the power consumption management module dynamically adjusts the power consumption mode according to the signal strength of the target device and the current battery level of the headset, and automatically reduces power consumption to extend the usage time of the headset when the signal strength is low or the device switches frequently.

[0015] As a further solution of the present invention, the device switching user confirmation operation is performed in at least one manner, including but not limited to touch, voice or confirmation through a headphone button, to ensure the effectiveness of the switching operation and user experience.

[0016] As a further solution of the present invention, the model training module adopts an incremental learning method to automatically update the prediction model each time the user device is switched to reflect the changes in the user device usage behavior in real time.

[0017] As a further solution of the present invention, the device switching prediction model is trained using a support vector machine (SVM), and input parameters include but are not limited to device connection duration, device switching frequency, and user interaction response time.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. By introducing the user's historical operation steps memory and behavior prediction mechanism, the present invention can intelligently predict the next device switching needs based on the user's past operation habits. When the user triggers the initial operation, the system enters the "pre-switching" mode, and the confirmation mechanism ensures that the device connection is only executed when the user explicitly indicates the switch. This intelligent pre-switching solution greatly reduces the interference caused by false switching, improves the user experience, and avoids the false triggering problem caused by automatic switching.

[0019] 2. Adaptive pairing protocol optimization improves connection stability: The present invention dynamically optimizes the adaptive pairing protocol, allowing the headset to adjust connection parameters according to the user's device switching habits, device priority, and usage scenarios. This mechanism not only reduces connection failures caused by device compatibility issues, but also ensures faster and more stable seamless switching between different devices, thereby improving the overall adaptability of the device and the user's long-term usage experience.

[0020] 3. Multi-dimensional user behavior analysis improves device response speed and accuracy: This technical solution uses multi-dimensional data analysis and machine learning algorithms, combined with the user's operating rules and habits between different devices, to establish an accurate user behavior model. This model can not only predict the user's next operation, but also dynamically adjust the device's connection priority based on factors such as device usage frequency and time sequence. Compared with existing technologies, this multi-level prediction mechanism improves the response speed and accuracy of device switching, significantly shortens switching time and reduces latency.

[0021] 4. Comprehensive synergy improves overall system efficiency: By combining user behavior models, device identification optimization and adaptive pairing protocols, the present invention achieves synergy effects at multiple technical levels and significantly improves the working efficiency of headphones in a multi-device environment. The user behavior model ensures the accuracy and timeliness of device switching, while the dynamic adjustment of device identification optimization and pairing protocols enhances the compatibility and stability of the system, and solves the operational complexity of users when switching between multiple devices. It also significantly reduces the power consumption of headphones by optimizing pairing protocols and reducing unnecessary device searches. Since the system can adjust the working mode of device connection according to real-time needs, it reduces frequent device scanning and connection operations, thereby effectively extending the battery life of the headphones, reducing the problem of device heating caused by excessive work, and improving the service life of the equipment.

[0022] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0024] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 In an embodiment of the present invention, a method for automatically pairing a Bluetooth headset with intelligent switching of multiple devices includes the following steps: S1, historical connection data collection and user behavior model construction: Bluetooth headsets record and collect user connection data between different devices through built-in sensors and software modules, including but not limited to: Device connection sequence, i.e. the record of users connecting to different devices in sequence; The switching interval between devices, that is, the time the user stays connected each time during the device switching process; The user confirmation method for device switching, including whether the user performs a confirmation operation during the switching process and the method used for confirmation; Connection duration, which is the average connection time for each device during user use; Device switching frequency, that is, the number of times a user changes devices within a certain period of time; The collected data is analyzed by a data processing unit in the headset and transmitted to a computing module of the headset through a data transmission protocol. The data is modeled using a hidden Markov model (HMM) or a support vector machine (SVM) algorithm. During the training process, the historical records of the connection data are divided into training sets. The model is gradually optimized using an incremental learning algorithm to learn the user's device switching pattern and time characteristics, and generate a device switching prediction model based on a time series. The model is used to predict the user's future target device and the order and time window of device switching; S2, behavior prediction and pre-switching mechanism: Based on the user behavior model, the headset predicts the target device that the user may switch to after operating on the current device, and enters the pre-switching state; the pre-switching state is triggered by the signal receiving module and the pairing module of the headset. When the target device sends a signal and meets the preset device switching conditions, the headset starts to prepare for connection, including adjusting the transmission parameters of the pairing signal to ensure low latency and high stability during the device switching process; when the user interacts with the target device in the pre-switching state, such as opening the audio playback software on the target device or performing other input operations, the headset confirms the user's switching intention and immediately completes the device switching; if no user interaction behavior is detected within the preset time, the headset maintains the current device connection state to avoid accidental switching; S3, intelligent device identification and dynamic priority sorting: In a multi-device environment, the headset automatically identifies the user's currently frequently used target device through an optimized device identification algorithm. The identification process includes: Statistics on the connection frequency of user devices and calculate the connection frequency of different devices in the past Number of times used within a time period; Record the user's choice every time they switch devices, and calculate the switching weights of different devices in historical data; Combine device connection preferences for specific time periods, such as differences in device connections during working hours and non-working hours; By real-time collection and analysis of the above information, a dynamic priority is assigned to each device, and the priority is calculated according to the following formula:

[0027] in: For equipment in the past Frequency of use in secondary connections; Representative equipment Historical connection probability during the current time period; For equipment The number of manual confirmations by users; is the normalization adjustment coefficient; Dynamic priority adjustment is based on user behavior patterns. If a device is frequently used within a certain period of time, the priority of the device will be automatically increased, thereby improving the response speed of device switching; S4, adaptive pairing protocol optimization: During multi-device switching, the headset dynamically adjusts the pairing protocol based on the user behavior model and device characteristics. During the pairing process: When the headset recognizes that the target device belongs to the Apple ecosystem, it automatically adjusts to Apple-specific pairing mode; When the headset recognizes that the target device is an Android system, it automatically switches to the standard universal Bluetooth protocol; During this process, pairing parameters are dynamically optimized based on the compatibility of the target device, including: Adjust data transmission rate to meet the transmission requirements of different devices; Adapt signal power to ensure that the device maintains a stable connection under different signal strengths; Optimize connection stability parameters to reduce possible signal loss during device switching; S5, power consumption management and signal stability optimization: During the multi-device switching process, the headset dynamically manages power consumption according to the connection status of the target device to reduce invalid power consumption. The power consumption management method includes: When the signal strength of the target device is detected to be lower than the set threshold, the Bluetooth power output is automatically reduced to reduce signal interference; When the device is not in use, it enters low-power standby mode to extend the battery life of the headset; The adaptive frequency hopping (AFH) algorithm is used to optimize Bluetooth signal transmission, reduce interference and improve connection stability.

[0028] S6, Implementation path of model training and behavior prediction: The training process of the user behavior prediction model includes the following steps: Data preprocessing: Extract characteristic data from historical operation records, including but not limited to device switching duration and connection times; Model training: Use incremental learning methods to train HMM or SVM models, optimize state transfer matrix and decision boundary to improve the accuracy of device switching prediction; Prediction optimization: Calculate the time window for device switching through regression analysis and optimize the device connection sequence to make the device switching process smooth and low-latency; S7, parameter optimization and model dynamic adjustment: In actual application, the headset dynamically updates the behavior prediction model based on new connection data and adjusts the algorithm parameters to improve prediction accuracy and response speed. The optimization process includes: After each device switch, the headset updates the user behavior data in real time to correct the device switching priority; An incremental learning algorithm is used to dynamically update HMM or SVM model parameters without retraining the entire dataset to ensure rapid adaptation to new user behavior patterns.

[0029] As a further solution of the present invention, the user behavior prediction model is established using a hidden Markov model HMM, and the state of the HMM includes but is not limited to a device connection state, a device disconnection state, and a device switching state.

[0030] The device switching prediction module generates a target device prediction list based on historical data, and the historical data includes but is not limited to the user's device connection frequency, switching period and device signal strength; the confirmation mechanism during device switching includes but is not limited to the user's selection confirmation of the switching device, the comparison of signal strengths between devices and the response time of user interaction operations; the intelligent device identification and dynamic priority sorting module adjusts the priority of each device in real time by analyzing the connection history and usage period of each device of the user, so as to improve the prediction accuracy of device switching.

[0031] The optimization of the pairing protocol includes but is not limited to automatically adjusting the data transmission rate, connection delay and signal power of the Bluetooth protocol to ensure low power consumption and high stability when switching between multiple devices; the power consumption management module dynamically adjusts the power consumption mode according to the signal strength of the target device and the current battery level of the headset, and automatically reduces power consumption when the signal strength is low or the device switching is frequent to extend the usage time of the headset; the device switching user confirmation operation is performed in at least one way, including but not limited to touch, voice or confirmation through the headset button to ensure the effectiveness of the switching operation and user experience; the model training module adopts an incremental learning method to automatically update the prediction model each time the user device switches to reflect changes in the user's device usage behavior in real time; the device switching prediction model is trained using a support vector machine SVM, and the input parameters are not limited to device connection duration, device switching frequency and user interaction response time.

[0032] Embodiment 1: In the actual application scenarios of smart homes, users use multiple smart devices (such as smart phones, smart speakers, smart appliances, etc.) to improve the convenience of life. However, due to frequent switching between devices and signal interference, users often encounter delays, device failure to connect or connection interruptions during the experience. In order to solve these problems, this embodiment implements a device switching optimization method to achieve a smoother device connection experience and more efficient energy consumption management, significantly improving the stability and user experience of the smart home system. Specifically, the technical solution collects the connection data of the device in real time, including device connection time, signal strength, connection frequency, etc., and uses these data as input to train the hidden Markov model. The model can predict the next state of the device based on the current state (for example, the device switches to the target device, the device exits the network, etc.), and adjust the priority and switching strategy of the device connection in advance accordingly.

[0033] For example, the system first collects the operation data of each device in real time, including the order of device connection, the switching time interval between devices, signal strength, connection duration, user confirmation operation during switching, etc. Every time the system detects a change in the state of device connection, it will update the relevant data and provide real-time information for device switching prediction, and then use the collected historical data (including information such as device connection duration and switching interval) to train the hidden Markov model. Based on past device switching data, the model can predict the future connection behavior and switching state of the device. For example, the model may predict that when the signal of the current device is weak, the user will switch to another device, or a device is about to be disconnected. Based on this prediction, the system can adjust the priority of the device in advance to make the switching operation smoother, and in some cases, the user needs to confirm whether to switch the device. By combining the user's operation data, such as the frequency of device switching and the user's habit of selecting devices, the system can optimize the priority sorting of devices. When the user confirms to switch the device, the system will give priority to connecting to the device with the strongest signal and the fastest response speed. By monitoring the power consumption of the device in real time, the system can automatically adjust the power consumption of inactive devices while ensuring smooth device connection. For example, when a device is in standby mode, the system will reduce its power consumption to a minimum, thereby extending the device's battery life and reducing household electricity consumption. The system will also adjust the priority of the device based on the frequency of use to avoid frequently used devices being in low-power mode.

[0034] In practical applications, the introduction of hidden Markov models significantly improves the accuracy and real-time performance of device switching. Traditional smart home systems often experience freezes or interruptions when devices are frequently switched, but this embodiment avoids these problems through intelligent prediction and optimization mechanisms, thereby improving the user experience.

[0035] Embodiment 2: In a smart office environment, fast switching and collaborative work of devices are crucial to improving work efficiency. Traditional smart device switching solutions often lead to poor device experience due to unstable device connection, network delays, and cumbersome user interactions, which in turn affects office efficiency. In order to improve the stability of device switching and user experience, this embodiment, based on the above technical solution, uses a hidden Markov model (HMM) combined with real-time device monitoring data to optimize the device switching strategy, thereby achieving high efficiency and stability of device switching in a smart office environment.

[0036] For example, in a modern smart office environment, multiple smart devices are arranged in the office, including smart desktops, smart lights, smart projectors, smart speakers, etc. When employees enter a meeting room or office, smart devices need to be able to automatically switch according to needs in order to provide a comfortable working or meeting environment.

[0037] The system continuously collects various data related to device status through embedded sensors and network devices, including device connection duration, signal strength, switching time interval between devices, device usage frequency, etc. The data of all devices is uploaded to the central processing unit (CPU) through the local area network and analyzed in real time. The system can sense which devices are being used frequently and which devices have weak signal strength, and optimize device connection and switching strategies based on this information.

[0038] After collecting enough historical data, the hidden Markov model is used to predict the future state of the device. Each time a device switch occurs, the model calculates the next optimal device switching path based on the signal status of the current device, the connection duration, the historical data of frequent switching, and the user's behavior habits. For example, when an employee enters a meeting room, the smart audio system predicts the switching needs of the upcoming projector and audio through the model, and adjusts the audio priority to the highest in advance, avoiding work interruptions caused by delayed device response.

[0039] When switching devices, the system automatically adjusts the priority of the devices to ensure smooth switching operations. For example, when an employee walks from the office to the meeting room, the system first detects the signal strength of the smart device (such as a smartphone or tablet) carried by the employee, and then selects the appropriate device for switching. For devices on the desk, the system will set smart speakers, lights, and projectors to a higher priority based on historical data of frequent use, ensuring that delays are minimized during the switching process.

[0040] During the device switching process, users will still occasionally perform manual operations. In order to reduce manual intervention and improve the level of automation, the system will adjust the device switching strategy in real time based on user feedback (such as the confirmation operation of device switching). For example, if the user has selected a device as the priority device, the system will automatically set it as the preferred option the next time the device is switched, thereby reducing the user's additional operations.

[0041] In order to verify the effectiveness of the technical solution, this embodiment conducted a comparative experiment to compare the performance differences between the traditional intelligent office equipment switching method and the optimization method based on the hidden Markov model in actual applications.

[0042] In the experiment, two office environments were selected, using the traditional device switching method and the device switching optimization method proposed in this embodiment. The goal of the experiment is to test the response time, stability, and user experience of device switching. Specific experimental indicators include device switching response time: the time required from triggering a switching request to successfully connecting the device; connection stability: the frequency of device disconnection during the connection process; user satisfaction: a questionnaire survey is used to evaluate user satisfaction with the device switching experience.

[0043] By collecting data and analyzing the experimental results, the following comparative data were obtained: device switching response time: when using the traditional method, the average device switching response time is 15 seconds, while the response time after adopting the optimization method of this embodiment is 6 seconds, an improvement of 60%; connection stability: under the traditional method, the frequency of device connection interruption is 8%, while the interruption frequency of the optimized solution is reduced to 1.5%, reducing about 81% of connection interruptions.

[0044] Through the above comparative experiments, it can be clearly seen that the device switching optimization solution proposed in this embodiment has significant improvements in many aspects compared with the traditional method. First, the significant reduction in device switching response time means that employees almost do not need to wait for device switching at work, which improves work efficiency. Secondly, the improvement in connection stability greatly reduces device failures caused by signal interference or unstable connections, ensuring the efficient operation of the equipment. Finally, the improvement in user satisfaction proves the optimization of the device switching experience, allowing users to use smart office equipment more smoothly without interference, thereby improving the overall intelligence level of the office environment, greatly reducing waiting time and improving office efficiency.

[0045] Embodiment 3: This embodiment proposes a multi-device intelligent switching method based on a user behavior model. By optimizing data collection, predictive analysis, and dynamic adjustment of device priorities, efficient, accurate, and stable automatic pairing of Bluetooth headsets in a multi-device environment is ensured. This embodiment refines the operation path of each step and dynamically optimizes device connections through incremental learning and adaptive mechanisms, thereby improving the response speed and stability of device switching.

[0046] For example, in the collection of historical connection data and the construction of user behavior models: the built-in sensors and software modules of the Bluetooth headset will record the user's device connection history in real time, including the order of device connection, switching time interval, user confirmation method of device switching, etc. The collected data is preliminarily analyzed by the headset's data processing unit and then transmitted to the headset's computing module. This process uses the hidden Markov model (HMM) or support vector machine (SVM) algorithm to model the data. The historical connection data is divided into training sets, and the model is gradually optimized through incremental learning methods, eventually forming a device switching prediction model based on time series, thereby accurately predicting the user's future device switching needs. Its variable definitions and functions are as follows, :equipment in the past The usage frequency in the connection indicates the activity of the device; :equipment The historical connection probability in the current time period reflects the time-period correlation between the device's connection frequency and user behavior; :equipment The number of manual confirmations by users is used to measure the user's acceptance of the device switching; these variables are weighted by the weight coefficient Perform normalization adjustments to optimize the connection priority of devices.

[0047] Its behavior prediction and pre-switching mechanism: Based on the trained user behavior model, after detecting user operation, the Bluetooth headset enters the pre-switching state through the signal receiving module and the pairing module. In this state, the headset predicts the need for device switching based on the user's operating habits and the status of the target device. When the signal strength of the target device reaches the preset threshold and meets the conditions for device switching, the headset begins to prepare for connection. The pre-switching process optimizes the transmission parameters of the pairing signal while ensuring low latency and high stability. The pre-switching mechanism ensures that device switching no longer relies on a single user interaction confirmation, but automatically prepares for connection when a device change is detected, thereby avoiding false switching. By optimizing signal parameters, the stability and response speed of the device switching process are further improved. In a multi-device environment, the headset uses an optimized device identification algorithm to dynamically adjust the priority of the device based on historical data and real-time collected information. The priority of each device is calculated using the following formula:

[0048] in: For equipment Priority; , , They are the device usage frequency, historical connection probability, and the number of manual confirmations by the user; , , is the adjustment coefficient, which is optimized through actual data. Specifically, , , They correspond to factors such as device usage frequency, historical connection probability, and the number of manual confirmations by users. Through optimization learning of actual historical data, the values ​​of these coefficients are dynamically adjusted to optimize the priority of device switching. The optimization process uses an incremental learning method to gradually update the coefficients based on information such as the device's usage history, switching frequency, and operation period, to ensure the accuracy and efficiency of the device switching process.

[0049] Dynamically adjust the priority to ensure that the device switching response is faster and can accurately match the user's current needs and device status; Adaptive pairing protocol optimization: This module automatically adjusts the pairing protocol according to the device characteristics. If the target device is an Apple device, the headset automatically switches to Apple's dedicated pairing mode; if it is an Android device, it switches to the standard Bluetooth protocol. During the pairing process, the system dynamically optimizes the data transmission rate, signal power, and connection stability according to the compatibility of the target device to ensure a smooth connection between devices. Formula and parameter description: Adjustments during the pairing process are based on the specific needs of the device. For example, for low-power devices, the system will optimize power consumption management, reduce interference through adaptive channel selection algorithms, and improve signal stability.

[0050] Power management and signal stability optimization: The power management and signal stability optimization module of Bluetooth headsets dynamically adjusts the power consumption mode by monitoring the signal strength of the target device and the current power of the headset in real time. When the device is in low signal strength or not in use, the system will automatically adjust the Bluetooth power output or enter low-power standby mode; through adaptive power management, the system can extend the battery life of the headset, reduce ineffective power consumption, and ensure signal stability during device switching.

[0051] Dynamic adjustment of model training and behavior prediction: After each device switch, the headset will update the user behavior model based on the new connection data and adjust the prediction algorithm parameters. The incremental learning algorithm ensures that the model can adapt to the user's new behavior pattern in a short time without retraining the entire data set, improving prediction accuracy and response speed. In actual applications, the system always maintains the efficiency and accuracy of device switching through real-time learning and optimization, reducing the problem of false switching caused by behavior changes.

[0052] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices, characterized in that: The following steps are involved: S1, historical connection data collection and user behavior model construction: Bluetooth headsets record and collect user connection data between different devices through built-in sensors and software modules, including but not limited to: Device connection sequence, i.e. the record of users connecting to different devices in sequence; The switching interval between devices, that is, the time the user stays connected each time during the device switching process; The user confirmation method for device switching, including whether the user performs a confirmation operation during the switching process and the method used for confirmation; Connection duration, which is the average connection time for each device during user use; Device switching frequency, that is, the number of times a user changes devices within a certain period of time; The collected data is analyzed by the data processing unit in the headset and transmitted to the computing module of the headset through the data transmission protocol. The connection data is modeled using the hidden Markov model HMM or the support vector machine SVM algorithm. During the training process, the historical records of the connection data are divided into training sets, and the model is gradually optimized using the incremental learning algorithm to learn the user's device switching mode and time characteristics, and generate a device switching prediction model based on time series. The model is used to predict the user's future target device and the order and time window of device switching; S2, behavior prediction and pre-switching mechanism: Based on the user behavior model, the headset predicts the target device that the user may switch to after operating on the current device, and enters the pre-switching state; the pre-switching state is triggered by the signal receiving module and the pairing module of the headset. When the target device sends a signal and meets the preset device switching conditions, the headset starts to prepare for connection, including adjusting the transmission parameters of the pairing signal to ensure low latency and high stability during the device switching process; when the user interacts with the target device in the pre-switching state, the headset confirms the user's switching intention and immediately completes the device switching; If no user interaction is detected within the preset time, the headset maintains the current device connection status to avoid accidental switching; S3, intelligent device identification and dynamic priority sorting: In a multi-device environment, the headset automatically identifies the user's currently frequently used target device through an optimized device identification algorithm. The identification process includes: Statistics on the connection frequency of user devices and calculate the connection frequency of different devices in the past Number of times used within a time period; Record the user's choice every time they switch devices, and calculate the switching weights of different devices in historical data; Combine device connection preferences for specific time periods, such as differences in device connections during working hours and non-working hours; By real-time collection and analysis of the above information, a dynamic priority is assigned to each device, and the priority is calculated according to the following formula: in: For equipment in the past Frequency of use in secondary connections; Representative equipment Historical connection probability during the current time period; For equipment The number of manual confirmations by users; is the normalization adjustment coefficient; Dynamic priority adjustment is based on user behavior patterns. If a device is frequently used within a certain period of time, the priority of the device will be automatically increased; S4, adaptive pairing protocol optimization: During multi-device switching, the headset dynamically adjusts the pairing protocol based on the user behavior model and device characteristics. During the pairing process: When the headset recognizes that the target device belongs to the Apple ecosystem, it automatically adjusts to Apple-specific pairing mode; When the headset recognizes that the target device is an Android system, it automatically switches to the standard universal Bluetooth protocol; During this process, pairing parameters are dynamically optimized based on the compatibility of the target device, including: Adjust data transmission rate to meet the transmission requirements of different devices; Adapt signal power to ensure that the device maintains a stable connection under different signal strengths; Optimize connection stability parameters to reduce possible signal loss during device switching; S5, power consumption management and signal stability optimization: During the multi-device switching process, the headset dynamically manages power consumption according to the connection status of the target device to reduce invalid power consumption. The power consumption management method includes: When the signal strength of the target device is detected to be lower than the set threshold, the Bluetooth power output is automatically reduced to reduce signal interference; When the device is not in use, it enters low-power standby mode to extend the battery life of the headset; S6, Implementation path of model training and behavior prediction: The training process of the user behavior prediction model includes the following steps: Data preprocessing: Extract characteristic data from historical operation records, including but not limited to device switching duration and connection times; Model training: Use incremental learning methods to train HMM or SVM models and optimize state transfer matrices and decision boundaries; Prediction optimization: Calculate the time window for device switching through regression analysis and optimize the device connection sequence to make the device switching process smooth and low-latency; S7, parameter optimization and model dynamic adjustment: In actual application, the headset dynamically updates the behavior prediction model based on new connection data and adjusts the algorithm parameters to improve prediction accuracy and response speed. The optimization process includes: After each device switch, the headset updates the user behavior data in real time to correct the device switching priority; An incremental learning algorithm is used to dynamically update HMM or SVM model parameters without retraining the entire dataset to ensure rapid adaptation to new user behavior patterns.

2. According to claim 1, a method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices, characterized in that: The user behavior prediction model is established using a hidden Markov model HMM, and the state of the HMM includes but is not limited to a device connection state, a device disconnection state, and a device switching state.

3. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The device switching prediction module generates a target device prediction list based on historical data, where the historical data includes but is not limited to the user's device connection frequency, switching period, and device signal strength.

4. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The confirmation mechanism when switching devices includes, but is not limited to, user confirmation of the selection of the switching device, comparison of signal strengths between devices, and response time of user interaction operations.

5. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The smart device identification and dynamic priority sorting module adjusts the priority of each device in real time by analyzing the connection history and usage period of each device of the user.

6. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The optimization of the pairing protocol includes, but is not limited to, automatically adjusting the data transmission rate, connection delay, and signal power of the Bluetooth protocol.

7. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The power consumption management module dynamically adjusts the power consumption mode according to the signal strength of the target device and the current battery level of the headset, and automatically reduces power consumption to extend the usage time of the headset when the signal strength is low or the device switches frequently.

8. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The device switching user confirmation operation is performed through at least one method, including but not limited to touch, voice or confirmation through a headphone button.

9. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The model training module adopts an incremental learning method to automatically update the prediction model every time the user device switches to reflect the changes in user device usage behavior in real time.

10. The method for automatic pairing of Bluetooth headsets with intelligent switching of multiple devices according to claim 1, characterized in that: The device switching prediction model is trained using a support vector machine (SVM), and input parameters include but are not limited to device connection duration, device switching frequency, and user interaction response time.

Images