Control methods for wearable devices, wearable devices, and computer-readable storage media

Abstract

This application discloses a control method for a wearable device, the wearable device itself, and a computer-readable storage medium, relating to the field of smart device technology. The wearable device includes a target sensor, which is a sensor that provides decision support data to an AI assistant within the wearable device. The method includes: acquiring the brainwave signal of a target user; identifying the current state of the target user based on the brainwave signal; and adjusting the data acquisition frequency of the target sensor based on the current state. The adjustment of the data acquisition frequency includes decreasing the data acquisition frequency when the current state is relaxed and increasing the data acquisition frequency when the current state is active. This application improves the battery life of the wearable device without significantly affecting the AI ​​assistant's service capabilities.

Description

Technical Field

[0001] This application relates to the field of smart device technology, and in particular to a control method for a wearable device, a wearable device, and a computer-readable storage medium. Background Technology

[0002] In recent years, with the rapid development of artificial intelligence (AI) technology, wearable devices have gradually become an important carrier for personal AI assistants. These devices can provide users with a real-time and natural interactive experience, and achieve a deep understanding of user intentions and proactive services by continuously sensing user status and environmental information.

[0003] However, in order to achieve the aforementioned continuous and intelligent service functions, wearable devices need to continuously collect and process multimodal data (such as voice, ambient sound, location information, etc.), which usually results in high power consumption and poor battery life.

[0004] Therefore, how to improve the battery life of wearable devices while minimizing the impact on the service capabilities of AI assistants has become an urgent technical problem to be solved. Summary of the Invention

[0005] The main objective of this application is to provide a control method for a wearable device, a wearable device, and a computer-readable storage medium, aiming to solve the technical problem of how to improve the battery life of a wearable device while reducing the impact on the service capabilities of AI assistants.

[0006] To achieve the above objectives, this application provides a control method for a wearable device, the wearable device including a target sensor, the target sensor being a sensor that provides decision support data to an artificial intelligence assistant within the wearable device, and the control method for the wearable device including the following steps:

[0007] Acquire the brainwave signals of the target user, and identify the current state of the target user based on the brainwave signals;

[0008] The data acquisition frequency of the target sensor is adjusted according to the current state, wherein the adjustment of the data acquisition frequency includes reducing the data acquisition frequency when the current state is a relaxed state and increasing the data acquisition frequency when the current state is an active state.

[0009] In one embodiment, the step of identifying the current state of the target user based on the electroencephalogram (EEG) signal includes:

[0010] Identify the dominant brainwave in the said brainwave signal;

[0011] If the dominant brainwave is a Delta wave, Theta wave, or Alpha wave, then the relaxed state is determined as the current state of the target user.

[0012] If the dominant brainwave is a Beta wave or a Gamma wave, then the active state is determined as the current state of the target user.

[0013] In one embodiment, the step of identifying the current state of the target user based on the electroencephalogram (EEG) signal includes:

[0014] The brainwave signal is input into a pre-trained user state recognition model, and the current state of the target user is output.

[0015] The user state recognition model is used to identify the state of the target user through the electroencephalogram (EEG) signal in order to obtain and output the current state.

[0016] In one embodiment, after the step of identifying the current state of the target user based on the electroencephalogram (EEG) signal, the method further includes:

[0017] During the data acquisition process of the target sensor, the sensor data acquired by the target sensor is obtained;

[0018] Based on the sensor data, identify the target user's current activity and obtain the appropriate state corresponding to the current activity;

[0019] If the suitable state does not match the current state, a prompt message is output to the target user.

[0020] In one embodiment, after the step of adjusting the data acquisition frequency of the target sensor according to the current state, the method further includes:

[0021] If the current state is a relaxed state, monitor whether the target user has entered a sleep state;

[0022] If the target user is detected to have entered a sleep state, the target sensor is controlled to stop data collection.

[0023] In one embodiment, the step of adjusting the data acquisition frequency of the target sensor according to the current state includes:

[0024] Identify secondary brainwaves in the said brainwave signals;

[0025] The brainwave power of the dominant brainwave and the secondary brainwave are calculated separately to obtain the dominant brainwave power and the secondary brainwave power.

[0026] State confidence is determined based on the dominant brainwave power and the secondary brainwave power, wherein the state confidence is positively correlated with the dominant brainwave power and negatively correlated with the secondary brainwave power.

[0027] The frequency adjustment step size is determined based on the state confidence level, wherein the frequency adjustment step size is positively correlated with the state confidence level;

[0028] The data acquisition frequency of the target sensor is adjusted based on the frequency adjustment step size.

[0029] In one embodiment, the step of adjusting the data acquisition frequency of the target sensor based on the frequency adjustment step size includes:

[0030] Obtain the current data acquisition frequency of the target sensor;

[0031] If the current state is a relaxed state and the current data acquisition frequency is greater than the preset lower limit acquisition frequency, then the data acquisition frequency of the target sensor is reduced based on the frequency adjustment step size.

[0032] If the current state is active and the current data acquisition frequency is less than the preset upper limit acquisition frequency, then the data acquisition frequency of the target sensor is increased based on the frequency adjustment step size.

[0033] In one embodiment, the target sensor includes a sound pickup sensor, and prior to the step of adjusting the data acquisition frequency of the target sensor according to the current state, the method further includes:

[0034] If the current state is active, then the audio signal collected by the pickup sensor is acquired;

[0035] If a preset AI wake-up keyword is identified in the audio signal, then the step of adjusting the data acquisition frequency of the target sensor according to the current state is executed;

[0036] If no preset AI wake-up keyword is detected in the audio signal, the target sensor is controlled to maintain the current data acquisition frequency for data acquisition.

[0037] In addition, to achieve the above objectives, this application also provides a wearable device, the wearable device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the control method for the wearable device as described above.

[0038] In addition, to achieve the above objectives, this application also provides a readable storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of the control method for the wearable device as described above.

[0039] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the control method for wearable devices as described above.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] This application's embodiments utilize electroencephalogram (EEG) signals, an indicator directly reflecting a user's neurophysiological state, to identify whether the user is in a "relaxed state" or an "active state." This is more accurate and efficient than relying on motion sensors, geographic location, or other indirect judgment methods, providing a foundation for subsequent intelligent power consumption management. When a user is in a relaxed state, it indicates a lower demand for environmental awareness and AI interaction. In this case, the data acquisition frequency of the target sensors is automatically reduced, significantly decreasing static power consumption in unnecessary scenarios. Conversely, when the user is detected to be in an active state, indicating a higher likelihood of needing AI assistant intervention and services, the sensor acquisition frequency is increased to ensure sufficient decision support data is captured, maintaining the continuity and intelligence level of its service capabilities. This creates an adaptive resource allocation strategy that matches the user's actual intentions and state. Instead of sacrificing user experience for global energy saving, it achieves precise "on-demand" energy control, significantly reducing system energy consumption without substantially affecting the continuity and accuracy of AI services. This improves the wearable device's battery life while minimizing the impact on the AI ​​assistant's service capabilities. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating the first embodiment of the control method for the wearable device of this application;

[0045] Figure 2This is a flowchart illustrating a specific embodiment of the control method for a wearable device according to this application;

[0046] Figure 3 This is a flowchart illustrating the third embodiment of the control method for wearable devices according to this application;

[0047] Figure 4 This is another flowchart illustrating a third embodiment of the control method for a wearable device according to this application;

[0048] Figure 5 This is a schematic diagram of the hardware operating environment involved in the control method device for wearable devices in the embodiments of this application.

[0049] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0050] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] As a wearable AI device, the ultimate goal of smart glasses is to provide 24 / 7 service, allowing users to converse with the AI ​​at any time without needing to provide background information for each interaction. For example, if a user has just finished eating at a restaurant and tells the AI ​​to "check in" (to record their visit for future reference), the AI ​​automatically understands that they are checking in at the restaurant, not clocking out. However, in real-world use, due to weight limitations and to ensure a comfortable user experience, the device's battery life cannot support 24 / 7 data collection.

[0052] Based on this, the main solution of this application is: to acquire the brainwave signal of the target user, and to identify the current state of the target user based on the brainwave signal; to adjust the data acquisition frequency of the target sensor according to the current state, wherein the adjustment of the data acquisition frequency includes reducing the data acquisition frequency when the current state is a relaxed state and increasing the data acquisition frequency when the current state is an active state, wherein the target sensor is a sensor that provides decision support data to the artificial intelligence assistant in the wearable device.

[0053] This application utilizes electroencephalogram (EEG) signals, an indicator directly reflecting a user's neurophysiological state, to accurately and with low latency identify whether a user is in a "relaxed" or "active" state. This is more accurate and efficient than relying on motion sensors, geolocation, or other indirect methods, providing a foundation for subsequent intelligent power management decisions. When a user is in a relaxed state, it indicates a lower demand for environmental awareness and AI interaction. In this case, the data acquisition frequency of the target sensors is automatically reduced, significantly decreasing static power consumption in unnecessary scenarios. Conversely, when an active state is detected, indicating a higher likelihood of needing AI assistant intervention and services, the sensor acquisition frequency is increased to ensure sufficient decision support data is captured, maintaining the continuity and intelligence of the service capabilities. This creates an adaptive resource allocation strategy that matches the user's actual intentions and state. Instead of sacrificing user experience for global energy saving, it achieves precise "on-demand" power control, significantly reducing system power consumption without substantially affecting the continuity and accuracy of AI services. This improves the battery life of wearable devices while minimizing the impact on AI assistant service capabilities.

[0054] It should be noted that the execution subject of the various embodiments of the wearable device control method of this application can be a wearable device capable of realizing the above functions, such as smart glasses, smart helmets, etc. The various embodiments of the wearable device control method of this application do not impose specific limitations on this. For example, smart glasses are used as the execution subject for the description and explanation of the various embodiments of this application.

[0055] Based on this, this application proposes a control method for a wearable device according to a first embodiment. The wearable device includes a target sensor, which is a sensor that provides decision support data to an artificial intelligence assistant within the wearable device. (Refer to...) Figure 1 As shown, the control method for the wearable device includes the following steps S10~S20:

[0056] Step S10: Acquire the brainwave signal of the target user, and identify the current state of the target user based on the brainwave signal;

[0057] The target users refer to those who wear smart glasses. Electroencephalogram (EEG) signals are the weak bioelectrical potential changes generated by the electrical activity of neuronal groups in the user's cerebral cortex. Their amplitude is typically in the microvolt range, and their frequency components are mainly distributed in the 0.5Hz to 30Hz range, encompassing various rhythmic waves such as delta, theta, alpha, and beta. These signals can be collected continuously or periodically via EEG acquisition modules built into or connected to smart glasses, such as flexible dry electrodes attached to the temples or nose pads.

[0058] Current EEG signal acquisition technology is relatively mature, capable of accurately detecting five major frequency bands of brainwaves, including delta (δ), theta (θ), alpha (α), beta (β), and gamma (γ). These acquisition modules consume extremely low power, with a typical operating current of approximately 5mA, and can fully utilize the contact between the glasses structure and the human head to achieve stable signal acquisition. Combinations of different frequency bands of brainwaves can effectively characterize various cognitive and physiological states of the user. Based on this, this embodiment achieves real-time, high-precision, and low-latency identification of the user's state by selectively acquiring and analyzing the user's EEG signals.

[0059] Furthermore, after acquiring the raw EEG signals, a series of preprocessing operations are performed on them, including but not limited to filtering and denoising (such as bandpass filtering to remove power frequency interference and baseline drift), artifact removal (such as using independent component analysis to remove eye movement and electromyography artifacts), and signal amplification, in order to extract pure EEG data with a higher signal-to-noise ratio and provide reliable input for subsequent state recognition.

[0060] After acquiring the brainwave signal, the current state of the target user is identified based on the brainwave signal. Specifically, as one embodiment, the step of identifying the current state of the target user based on the brainwave signal includes steps S1011~S1013:

[0061] Step S1011: Identify the dominant brainwave in the brainwave signal;

[0062] Spectral analysis techniques, such as the Fast Fourier Transform (FFT), can be used to convert brainwave signals from the time domain to the frequency domain. Digital filters (such as Butterworth filters) can then be used to segment frequency bands, allowing analysis of their frequency distribution characteristics and identification of the dominant brainwave type in the current signal. For example, the power spectral density of a specific frequency band (e.g., Delta waves: 0.5-4Hz, Theta waves: 4-8Hz, Alpha waves: 8-13Hz, Beta waves: 13-30Hz, Gamma waves: >30Hz) can be calculated. By comparing the relative power intensity of each frequency band, the band with the highest power percentage or whose absolute power value exceeds a set threshold is identified as the dominant brainwave.

[0063] Step S1012: If the dominant brainwave is a Delta wave, Theta wave, or Alpha wave, then the relaxed state is determined as the current state of the target user.

[0064] Delta waves typically appear during deep sleep; Theta waves are common in relaxation, meditation, or mild drowsiness; Alpha waves mostly appear in a state of wakefulness and relaxation, such as when resting with eyes closed. When one of these three wave types is detected as the dominant brainwave, it can be determined that the user is in a relaxed state, at which time the user has a lower need to perceive the surrounding environment, and brain activity is relatively calm.

[0065] Step S1013: If the dominant brainwave is a Beta wave or a Gamma wave, then the active state is determined as the current state of the target user.

[0066] Beta waves typically appear when the user is awake and focused, such as during complex thinking, learning, or working. Gamma waves, on the other hand, are associated with higher-level brain functions, such as cognitive processing, memory retrieval, and rapid reaction, and are commonly seen in highly active brain states. When Beta or Gamma waves are detected as the dominant brainwaves, it indicates that the user is in an active state, with frequent brain activity and a high need for awareness of their surroundings, requiring more timely and accurate services from the AI ​​assistant.

[0067] As another implementation, the step of identifying the current state of the target user based on the electroencephalogram signal includes step S1021:

[0068] Step S1021: Input the EEG signal into a pre-trained user state recognition model and output the current state of the target user. The user state recognition model is used to identify the state of the target user through the EEG signal to obtain and output the current state.

[0069] This user state recognition model is trained on a large amount of labeled EEG signal data, which covers the EEG characteristics of users in different states (such as relaxed and active). By learning the mapping relationship between these features and user states, the model can accurately classify the input EEG signals. In practical applications, the collected EEG signals are input into the model, or the collected EEG signals are preprocessed before being input into the model. The model automatically analyzes the signal characteristics and outputs the target user's current state (relaxed or active), thus providing a basis for adjusting the subsequent sensor data acquisition frequency.

[0070] Specifically, the user state recognition model can be a classification machine learning model, such as a convolutional neural network, a long short-term memory network, a support vector machine, etc. This embodiment does not impose any specific restrictions on it.

[0071] Step S20: Adjust the data acquisition frequency of the target sensor according to the current state, wherein the adjustment of the data acquisition frequency includes reducing the data acquisition frequency when the current state is a relaxed state and increasing the data acquisition frequency when the current state is an active state.

[0072] A target sensor is a sensor that provides decision support data for the AI ​​assistant in smart glasses. This data can be raw data directly input into the AI ​​assistant as a basis for decision-making, or it can be derived data input after certain preprocessing (such as signal noise reduction, feature extraction, and data fusion). For example, data collected by the target sensor can be directly input into the AI ​​assistant for decision-making reference; alternatively, data collected by the target sensor can be processed before being input into the AI ​​assistant for decision-making reference.

[0073] A dynamic mapping relationship can be established between user status and sensor power consumption strategy, and the data acquisition frequency of the target sensor can be adjusted based on this dynamic mapping relationship.

[0074] In this embodiment, the user's state is divided into a relaxed state and an active state. The relaxed state refers to a state in which the user's brain activity is relatively calm, characterized by physiological mental relaxation and low cognitive load. This state is commonly seen in scenarios such as meditation, rest, or low-attention work. In this state, the EEG signal usually shows a significant increase in alpha wave activity and a decrease in beta wave activity. The active state refers to a state in which the user's brain activity is frequent, characterized by physiological mental tension, cognitive focus, or physical activity. This state is commonly seen in scenarios such as reading and studying, exercising, interpersonal conversation, or entering a new environment. In this state, the EEG signal usually shows a significant increase in beta wave activity and a decrease in alpha wave activity.

[0075] When a user is detected to be relaxed, indicating a lower need for environmental interaction, the AI ​​assistant does not require frequent updates to environmental information. In this case, control commands are sent to the target sensor to reduce its data acquisition frequency, thereby lowering the sensor's power consumption. Conversely, when a user is detected to be active, suggesting a potential need for more timely and precise proactive services from the AI ​​assistant, the data acquisition frequency of the target sensor is increased to a higher level. This ensures the AI ​​assistant can acquire sufficiently rich and real-time high-quality data to support its decision-making and guarantee service continuity. Through this dynamic adjustment mechanism, system energy consumption is optimized to the maximum extent possible while meeting the user's contextual needs, fundamentally improving the device's battery life.

[0076] It should be noted that the adjustment of the target sensor's data acquisition frequency can be implemented based on two strategies. One is event-triggered adjustment, which activates the adjustment mechanism when a change in user state is detected. For example, when the user's state changes from relaxed to active, the target sensor's data acquisition frequency is increased; conversely, when the state changes from active to relaxed, the frequency is decreased accordingly. During the period when the state remains unchanged, the sensor's current acquisition frequency is maintained until the next state change event occurs.

[0077] The second method is periodic triggering adjustment, which periodically identifies the user's current state and determines whether to adjust the frequency based on that state. Each time the user is identified as relaxed, if the current sampling frequency is higher than the preset minimum frequency (lower limit), it is lowered; conversely, each time the user is identified as active, if the current sampling frequency is lower than the preset maximum frequency (upper limit), it is increased. This strategy ensures that the sensor frequency continuously approaches the optimal value for the current state until it reaches the adjustable frequency limit.

[0078] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. Based on this, after the step of identifying the current state of the target user based on the electroencephalogram signal, the method further includes:

[0079] Step A10: During the data acquisition process of the target sensor, acquire the sensor data collected by the target sensor;

[0080] The target sensor can include various types of sensors, such as image sensors, ambient light sensors, accelerometers, and microphones. These sensors continuously collect data according to a pre-set acquisition frequency. For example, an image sensor collects image data of the surrounding environment, an ambient light sensor collects data on the light intensity of the surrounding environment, an accelerometer collects data on the user's motion acceleration, and a microphone collects ambient sound signals.

[0081] Step A20: Identify the target user's current activity based on the sensor data, and obtain the appropriate state corresponding to the current activity;

[0082] By analyzing sensor data, it's possible to identify the user's current activity, i.e., the ongoing task. For example, accelerometer data can determine if the user is moving; microphone-collected sound signals can determine if the user is conversing or in a noisy environment; and ambient light sensor data can determine if the user is indoors or outdoors. Based on these indicators, the appropriate state for each activity can be determined. For instance, if the user is in a meeting or driving, the appropriate state might be an active state; if the user is in a quiet indoor environment, the appropriate state might be a relaxed state.

[0083] Step A30: If the suitable state does not match the current state, then output a prompt message to the target user.

[0084] The system compares the appropriate state identified through sensor data with the current state previously identified through EEG signals. If the two do not match, it indicates a potential error in the user's state perception or an inconsistency between the user's behavior and their current state. In this case, a prompt will be displayed to the user to remind them to check or adjust their state. For example, if the system detects that the user is currently in a meeting or driving, and the user is in a relaxed state, a prompt will be displayed via voice, interactive lights, and / or vibration to prevent the loss of critical information or the occurrence of accidents.

[0085] Furthermore, if the suitable state does not match the current state, the data acquisition frequency of the target sensor can be left unadjusted until the user confirms that the current state is correct, at which point the data acquisition frequency of the target sensor can be adjusted; if the user does not provide feedback or the user confirms that the current state is incorrect, the data acquisition frequency of the target sensor will not be adjusted at this time.

[0086] It should be noted that if the suitable state matches the current state, no prompt message will be output, and the data acquisition frequency of the target sensor will be adjusted.

[0087] This embodiment, after initially determining the user's state based on EEG signals, utilizes multimodal environmental and behavioral data continuously collected by target sensors (such as images, ambient light, acceleration, microphones, etc.) to independently identify and interpret the user's actual "current task," and infers the theoretically corresponding "appropriate state" for that task. By comparing the "current state" based on physiological signals with the "appropriate state" based on environmental context in real time, it intelligently detects inconsistencies between the two. For example, EEG may indicate the user is relaxed, but microphone and acceleration data may show the user is driving. This mismatch usually means that the initial state perception may be flawed, or that the user's behavior is unconventionally disconnected from their physiological state, such as fatigued driving. In this case, a human-computer interaction verification is proactively initiated by outputting prompts to the user, such as voice, light, or vibration. This mechanism not only effectively prevents the risk of sensors operating under incorrect power consumption strategies due to misinterpretation of a single EEG signal—for example, in driving scenarios requiring high alertness, the sensor frequency might be reduced due to misinterpretation as "relaxation," thus missing critical road information and avoiding potential safety hazards and service failures—but more importantly, it incorporates the user into the decision-making loop, using their subjective judgment to calibrate the state in real time. This greatly enhances the robustness, reliability, and security of the entire control strategy, ultimately providing crucial reliability assurance for achieving a high degree of unity between range optimization and service assurance in complex and ever-changing real-world application scenarios.

[0088] In one possible implementation, after the step of adjusting the data acquisition frequency of the target sensor according to the current state, the method further includes:

[0089] Step B10: If the current state is a relaxed state, monitor whether the target user has entered a sleep state;

[0090] Once the user is identified as relaxed, sensors in smart glasses or other monitoring devices, such as heart rate sensors, respiratory rate sensors, and body motion sensors, combined with electroencephalogram (EEG) signals, are used to monitor whether the user has entered a sleep state. For example, a heart rate sensor detects changes in the user's heart rate; during sleep, the heart rate typically gradually decreases and stabilizes. A respiratory rate sensor monitors the frequency and depth of breathing; during sleep, breathing becomes slow and regular. A body motion sensor detects body movement; during sleep, physical activity significantly decreases. By combining these changes in physiological parameters, it can be determined whether the user has entered a sleep state. For example, if Delta waves dominate the EEG and breathing becomes slow and regular, it can be confirmed that the user has entered a sleep state.

[0091] Step B20: If the target user is detected to have entered a sleep state, control the target sensor to stop data acquisition.

[0092] Once the monitoring system detects that the user has entered a sleep state, the final power-saving strategy can be triggered. This means that a control command will be generated and sent, ordering all or designated non-essential target sensors (such as cameras, microphones, GPS, etc.) to completely stop data collection, rather than simply maintaining a low-frequency operating state. This aims to achieve two purposes: first, to completely eliminate the power consumption of sensor operation during the stage when the user is completely unaware and has no need for interaction, achieving maximum power saving and extending the device's battery life to the extreme; second, this also constitutes a strong privacy and security barrier, ensuring that sensitive environmental information (such as conversations and images) around the user will not be unintentionally recorded by the device during the user's unconscious sleep, thus providing the user with deeper privacy and security protection.

[0093] For example, in order to help understand the technical concept or technical principle of the control method of the wearable device after combining this embodiment with the first embodiment described above, a specific embodiment is now listed. In this specific embodiment, refer to Figure 2 As shown, the control process of wearable devices includes:

[0094] 1. Brainwave signal acquisition:

[0095] In non-invasive EEG (electroencephalography) electrodes, patch-type flexible dry electrodes are 5-10 mm in size and less than 1 mm in thickness. This size allows for easy integration into the inner side of the temples of smart glasses where they fit against the head, enabling the acquisition of brainwave signals through the integrated EEG electrodes within the smart glasses.

[0096] 2. Noise filtering:

[0097] After acquiring the raw EEG signals, they first need to be filtered for noise, as the raw signals are susceptible to interference from ambient noise and power line noise. Using a bandpass filter can preserve the effective frequency bands in the raw EEG, such as the five common EEG frequency bands from 0.5 to 50 Hz.

[0098] 3. Brainwave separation:

[0099] Brainwaves are the result of superimposing various frequency bands. Digital filtering (such as Butterworth filters) can be used to divide the frequency bands. Specifically, Delta waves (0.5–4Hz), Theta waves (4–8Hz), Alpha waves (8–13Hz), Beta waves (13–30Hz), and Gamma waves (>30Hz) can be separated.

[0100] 4. User Status Recognition:

[0101] Method 1: Identify the dominant brainwave in the EEG signal. If the dominant brainwave is a Delta wave, Theta wave, or Alpha wave, the user is considered to be in a relaxed state. If the dominant brainwave is a Beta wave or Gamma wave, the user is considered to be in an active state.

[0102] Method Two: Continuously capture the user's brainwave state and interactions with the smart glasses using machine learning. Feed the user's relaxed state (such as when daydreaming or with eyes closed) and active state (such as during client meetings or reading / studying) along with corresponding EEG data into the machine learning model for training, resulting in a personalized user state recognition model. This model is then used to identify the user's current state. Furthermore, this model can be continuously updated and iterated using new data as the user continues to use the device.

[0103] 5. Controlling smart glasses:

[0104] When the user is relaxed, the frequency of AI environmental data acquisition (such as from cameras and microphones) is reduced, or the AI ​​environmental data acquisition function is stopped altogether; that is, the data acquisition frequency of the target sensor is reduced, or the target sensor is controlled to stop data acquisition. When the user is active (such as in a meeting or checking bills), AI environmental data acquisition is activated. This improves the operational efficiency of AI environmental data acquisition and reduces operating costs by lowering the cost of environmental recognition.

[0105] 6. User Reminder:

[0106] When a user's current state is not suitable for the task at hand, prompts are output via voice, interactive lights, or vibration. For example, if a user is distracted, drowsy, dozing off, or losing focus while performing an important event (meeting, driving), the system will remind the user in real time via voice, interactive lights, or vibration to prevent the loss of critical information or accidents.

[0107] It should be noted that the above examples are only used to help understand this embodiment and do not constitute a limitation on the control process of the wearable device in this embodiment. Any simple modifications based on this technical concept are within the protection scope of this application.

[0108] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. On this basis, refer to Figure 3 As shown, the step of adjusting the data acquisition frequency of the target sensor according to the current state includes:

[0109] Step C10: Identify secondary brainwaves in the brainwave signal;

[0110] When analyzing brainwave signals, in addition to identifying the dominant brainwaves, it is also necessary to identify the secondary brainwaves present in the signal. This can be achieved through spectral analysis techniques, such as using Fast Fourier Transform (FFT) to convert the brainwave signal from the time domain to the frequency domain, thereby identifying brainwave components in different frequency ranges, including secondary brainwaves. Secondary brainwaves refer to brainwave types that are present in the signal but have relatively low power. For example, in a signal dominated by alpha waves, there may also be a small number of beta waves or theta waves.

[0111] Step C20: Calculate the brainwave power of the dominant brainwave and the secondary brainwave respectively to obtain the dominant brainwave power and the secondary brainwave power.

[0112] By calculating the power of each brainwave frequency band, the intensity of dominant and secondary brainwaves can be quantified. This is typically achieved by calculating the power spectral density (PSD) of the signal after spectral analysis. For example, if the dominant brainwave is an alpha wave and the secondary brainwave is a beta wave, then calculating the power spectral density of the alpha and beta waves separately yields their respective power values, which are the dominant and secondary brainwave powers.

[0113] Step C30: Determine the state confidence level based on the dominant brainwave power and the secondary brainwave power, wherein the state confidence level is positively correlated with the dominant brainwave power and negatively correlated with the secondary brainwave power;

[0114] State confidence is an indicator that measures the reliability of the judgment of a user's current state. If the power of the dominant brainwave is much higher than the power of the secondary brainwave, it indicates that the user's state is relatively clear, and the state confidence is high; conversely, if the power of the secondary brainwave is close to or exceeds the power of the dominant brainwave, it indicates that the user's state may be uncertain, and the state confidence is low. State confidence can be calculated using a preset function or formula, for example, State Confidence = Dominant Brainwave Power / (Dominant Brainwave Power + Secondary Brainwave Power).

[0115] Step C40: Determine the frequency adjustment step size based on the state confidence level, and adjust the data acquisition frequency of the target sensor based on the frequency adjustment step size, wherein the frequency adjustment step size is positively correlated with the state confidence level.

[0116] Frequency adjustment step size refers to the adjustment range of the target sensor data acquisition frequency. If the state confidence level is high, it indicates that the judgment of the user's state is relatively reliable, and the acquisition frequency can be adjusted in larger steps; if the state confidence level is low, it indicates that the user's state may have changed, and the acquisition frequency needs to be adjusted in smaller steps to avoid over-adjustment.

[0117] The step size is adjusted based on the calculated frequency to regulate the data acquisition frequency of the target sensor. If the user is relaxed, the step size is adjusted to decrease the acquisition frequency; if the user is active, the step size is adjusted to increase the acquisition frequency.

[0118] It should be noted that the target sensor can specifically be one or more sensors. Therefore, the frequency adjustment step size for each sensor can be calculated separately, and the data acquisition frequency of that sensor can be adjusted based on the frequency adjustment step size corresponding to each sensor in the target sensor. For example, when the state confidence level is a value between 0 and 1, the frequency adjustment step size can be the state confidence level multiplied by the preset upper limit acquisition frequency corresponding to the sensor.

[0119] This embodiment effectively improves the accuracy and robustness of power consumption control in wearable devices by introducing a state confidence assessment based on EEG power spectrum analysis and an associated adaptive frequency adjustment step size mechanism, thereby optimizing device battery life at a deeper level. Specifically, it calculates the power of dominant and secondary EEG waves and quantifies the confidence level of state determination accordingly, enabling the differentiation of the clarity of the user's state. When the dominant EEG power is significantly higher than the secondary EEG power (i.e., high state confidence), the sensor frequency is adjusted with a larger step size, thereby quickly reaching the optimal power consumption configuration when the state is certain, achieving timely energy saving or performance improvement. Conversely, when the user's state is ambiguous and multiple EEG components are intertwined (i.e., low state confidence), a smaller step size is used for fine adjustment to avoid drastic fluctuations in sensor acquisition frequency due to misjudgment, preventing the loss of key environmental information due to excessive frequency reduction, or unnecessary power waste due to premature frequency increase. This confidence-based fine-tuning strategy enables sensor power management to respond proactively to clear state changes while carefully handling boundary and transitional states. Ultimately, it achieves more precise and smooth dynamic optimization of the overall energy consumption of smart glasses while maximizing the continuity and accuracy of AI assistant services, significantly enhancing the reliability of wearable device battery life and the consistency of user experience.

[0120] In one possible implementation, the step of adjusting the data acquisition frequency of the target sensor based on the frequency adjustment step size includes:

[0121] Step D10: Obtain the current data acquisition frequency of the target sensor;

[0122] The current data acquisition frequency of the target sensor can be read from its configuration parameters. This frequency is the actual data acquisition frequency of the sensor before adjustment; for example, the current sampling rate of a microphone might be 44.1 kHz per second, and the current reading interval of an ambient light sensor might be once per second.

[0123] Step D20: If the current state is a relaxed state and the current data acquisition frequency is greater than the preset lower limit acquisition frequency, then the data acquisition frequency of the target sensor is reduced based on the frequency adjustment step size.

[0124] When the system detects that the user is in a relaxed state, it checks whether the current data acquisition frequency of the target sensor is higher than a preset lower limit. The preset lower limit is a pre-defined lower limit value for the acquisition frequency; typically, it's set to the frequency at which the sensor can still provide basic environmental awareness with minimal power consumption. If the current data acquisition frequency is higher than this lower limit, the system will adjust the step size based on the previously calculated frequency to reduce the data acquisition frequency.

[0125] Step D30: If the current state is an active state and the current data acquisition frequency is less than the preset upper limit acquisition frequency, then increase the data acquisition frequency of the target sensor based on the frequency adjustment step size.

[0126] When an active user is detected, the system checks whether the current data acquisition frequency of the target sensor is lower than a preset upper limit. The preset upper limit is a pre-defined upper limit value for the acquisition frequency; typically, it's set to the acquisition frequency that allows the AI ​​assistant to perceive environmental information in real-time while the sensor is active. If the current data acquisition frequency is lower than this upper limit, the system will adjust the step size to increase the data acquisition frequency.

[0127] In one possible implementation, the target sensor includes a sound pickup sensor, referring to... Figure 4 As shown, before the step of adjusting the data acquisition frequency of the target sensor according to the current state, the method further includes:

[0128] Step E10: If the current state is an active state, then acquire the audio signal collected by the pickup sensor;

[0129] When an active user is detected, the microphone sensor can be triggered to start collecting audio signals. The microphone sensor can be a microphone or other audio acquisition device.

[0130] Step E20: If a preset AI wake-up keyword is identified in the audio signal, then the step of adjusting the data acquisition frequency of the target sensor according to the current state is executed.

[0131] The system analyzes the collected audio signals in real time to identify whether they contain preset AI wake-up keywords. These keywords can be specific words or phrases pre-set by the user to activate the AI ​​assistant's service functions. For example, if the user sets the wake-up word to "Hey AI," when this keyword is detected in the audio signal, it confirms that the user needs the AI ​​assistant's service and then performs the step of adjusting the target sensor's data acquisition frequency based on the current state to ensure that the AI ​​assistant can provide more timely and accurate services.

[0132] Step E30: If no preset AI wake-up keyword is identified in the audio signal, control the target sensor to maintain the current data acquisition frequency for data acquisition.

[0133] If no preset AI wake-up keywords are detected in the acquired audio signal, it is assumed that the user does not currently need to interact with the AI ​​assistant, and therefore the data acquisition frequency of the target sensor will not be adjusted. The target sensor will continue to operate at its current acquisition frequency to maintain normal device operation while avoiding unnecessary power consumption. For example, if the user is simply playing music in the background or in a generally noisy environment without mentioning any wake-up keywords, the data acquisition frequency of the target sensor will remain unchanged.

[0134] In this embodiment, when the user is determined to be in an "active state," the acquisition frequency of all sensors is not immediately and unconditionally increased. Instead, audio signals are first acquired through the sound pickup sensor and analyzed in real time. Only after recognizing the preset AI wake-up keyword issued by the user is the data acquisition frequency increased. This design ensures that the increase in device power consumption is tied to the user's explicit interaction intent, effectively preventing the sensor module from entering an unnecessary high-power operating mode in scenarios where the user is active but has no intention of interacting with the AI ​​assistant. By verifying the specific wake-up command in the audio stream, background noise and genuine interaction intent can be effectively distinguished, thus preventing power waste caused by misjudgment of environmental sounds. This secondary confirmation mechanism based on explicit interaction intent enables the AI ​​assistant to be ready at any time and respond quickly while minimizing the high-power window during non-active interactions. This achieves refined control of power consumption in the "active state," further extending the actual battery life of the device in complex environments and optimizing the overall energy efficiency ratio.

[0135] Furthermore, this application also proposes a wearable device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the control method for the wearable device as described above.

[0136] refer to Figure 5The diagram illustrates a structural schematic suitable for implementing the embodiments of this application. The wearable devices in the embodiments of this application may also include, but are not limited to, smart glasses, AI helmets, etc. Figure 5 The wearable device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0137] like Figure 5 As shown, the wearable device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the wearable device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the wearable device to communicate wirelessly or wiredly with other devices to exchange data. While wearable devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0138] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0139] The wearable device provided in this application, employing the control method of the wearable device in the above embodiments, can solve the technical problem of how to improve the battery life of the wearable device while reducing the impact on the service capabilities of the AI ​​assistant. Compared with the prior art, the beneficial effects of the wearable device provided in this application are the same as the beneficial effects of the control method of the wearable device provided in the above embodiments, and other technical features in this wearable device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0140] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0141] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0142] In addition, to achieve the above objectives, this application also provides a readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the control method of the wearable device in the above embodiments.

[0143] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0144] The aforementioned computer-readable storage medium may be included in the wearable device; or it may exist independently and not assembled into the wearable device.

[0145] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a wearable device, cause the wearable device to: acquire brainwave signals of a target user; identify the current state of the target user based on the brainwave signals; and adjust the data acquisition frequency of a target sensor based on the current state, wherein the adjustment of the data acquisition frequency includes decreasing the data acquisition frequency when the current state is a relaxed state and increasing the data acquisition frequency when the current state is an active state, and the target sensor is a sensor that provides decision support data to an artificial intelligence assistant within the wearable device.

[0146] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0148] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the modules themselves.

[0149] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the control method of the wearable device described above. This addresses the technical problem of improving the battery life of wearable devices while minimizing the impact on AI assistant service capabilities. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the control method for the wearable device provided in the above embodiments, and will not be elaborated upon here.

[0150] Furthermore, embodiments of this application also propose a computer program product, including a computer program that, when executed by a processor, implements the steps of the control method for a wearable device as described above.

[0151] The specific implementation of the computer program product in this application is basically the same as the various embodiments of the control method for the wearable device described above, and will not be repeated here.

[0152] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0153] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0154] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software sensor. This computer software sensor is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a wearable device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0155] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A control method of a wearable device, the method comprising: The wearable device comprises a target sensor, which is a sensor providing decision support data to an artificial intelligence assistant in the wearable device, and the control method of the wearable device comprises the following steps: obtaining an electroencephalogram signal of a target user, and identifying a current state of the target user according to the electroencephalogram signal; adjusting a data collection frequency of the target sensor according to the current state, wherein the adjustment of the data collection frequency comprises reducing the data collection frequency when the current state is a relaxed state, and increasing the data collection frequency when the current state is an active state; wherein the step of adjusting the data collection frequency of the target sensor according to the current state comprises: identifying a dominant brain wave and a secondary brain wave in the electroencephalogram signal; calculating brain wave power of the dominant brain wave and the secondary brain wave respectively to obtain dominant brain wave power and secondary brain wave power; determining a state confidence based on the dominant brain wave power and the secondary brain wave power, wherein the state confidence is positively correlated with the dominant brain wave power and negatively correlated with the secondary brain wave power; determining a frequency adjustment step based on the state confidence, and adjusting the data collection frequency of the target sensor based on the frequency adjustment step, wherein the frequency adjustment step is positively correlated with the state confidence, and when the state confidence is a value between 0 and 1, the frequency adjustment step is the state confidence multiplied by a preset upper limit collection frequency corresponding to the sensor. 2.The control method of a wearable device of claim 1, wherein, The step of identifying the current state of the target user according to the electroencephalogram signal comprises: if the dominant brain wave is a delta wave, a theta wave or an alpha wave, determining the relaxed state as the current state of the target user; if the dominant brain wave is a beta wave or a gamma wave, determining the active state as the current state of the target user. 3.The control method of a wearable device of claim 1, wherein, The step of identifying the current state of the target user according to the electroencephalogram signal comprises: inputting the electroencephalogram signal into a pre-trained user state recognition model to output the current state of the target user; wherein the user state recognition model is used to recognize the state of the target user through the electroencephalogram signal to obtain and output the current state. 4.The control method of a wearable device of claim 1, wherein, After the step of identifying the current state of the target user according to the electroencephalogram signal, the method further comprises: acquiring sensor data collected by the target sensor during the data collection process of the target sensor; identifying a current ongoing matter of the target user according to the sensor data, and acquiring a suitable state corresponding to the current ongoing matter; if the suitable state does not match the current state, outputting a prompt information to the target user. 5.The control method of a wearable device of claim 1, wherein, After the step of adjusting the data collection frequency of the target sensor according to the current state, the method further comprises: monitoring whether the target user enters a sleep state when the current state is a relaxed state; if it is monitored that the target user enters a sleep state, controlling the target sensor to stop data collection. 6.The control method of a wearable device of claim 1, wherein, The step of adjusting the data collection frequency of the target sensor based on the frequency adjustment step length comprises: acquiring a current data collection frequency of the target sensor; if the current state is a relaxed state and the current data collection frequency is greater than a preset lower limit collection frequency, decreasing the data collection frequency of the target sensor based on the frequency adjustment step length; if the current state is an active state and the current data collection frequency is less than a preset upper limit collection frequency, increasing the data collection frequency of the target sensor based on the frequency adjustment step length. 7.The control method of a wearable device of claim 1, wherein, The target sensor comprises a sound pickup sensor, and before the step of adjusting the data collection frequency of the target sensor according to the current state, the method further comprises: if the current state is an active state, acquiring an audio signal collected by the sound pickup sensor; if a preset AI wake-up keyword is recognized in the audio signal, performing the step of adjusting the data collection frequency of the target sensor according to the current state; if no preset AI wake-up keyword is recognized in the audio signal, controlling the target sensor to maintain the current data collection frequency for data collection.

8. A wearable device, comprising: comprise: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program, when executed by the processor, implements the control method of the wearable device according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a control program of the wearable device, and the control program of the wearable device, when executed by the processor, implements the steps of the control method of the wearable device according to any one of claims 1 to 7.

Images