Parameter adjustment method and system based on intelligent wearable device

Abstract

The embodiment of the invention provides a parameter adjustment method based on intelligent wearable equipment, and the method comprises the steps: obtaining current scene information which comprises motion state information, task complexity information of a current execution task, and external environment state information; generating a current scene complexity score through a predefined calculation model based on the current scene information; according to the current scene complexity score, matching a corresponding target working parameter mode from a plurality of preset parameter configuration modes, and applying the target working parameter mode; during operation of the target working parameter mode, operation state parameters of the intelligent wearable device are monitored, and the operation state parameters comprise performance parameters, power consumption parameters and temperature parameters; if it is monitored that any running state parameter meets the corresponding preset adjustment condition, the working parameters are adjusted on the basis of the target working parameter mode.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a parameter adjustment method and system based on a smart wearable device. Background Technology

[0002] With the deep integration of the Internet of Things (IoT) and mobile computing technologies, smart wearable devices have become key carriers for health monitoring, sports assistance, and instant communication. However, to achieve wearing comfort and portability, devices must maintain a miniaturized and lightweight physical form, which directly limits battery capacity and heat dissipation space, creating a fundamental conflict with the development trend of continuously integrating complex application functions.

[0003] Under this constraint, the inherent computing performance, power consumption, and chip junction temperature of a device system form a tightly coupled and mutually restrictive triangular relationship. Existing technical solutions often employ static or single-dimensional control strategies based on threshold triggering. For example, increasing the operating frequency to ensure instantaneous performance leads to a surge in power consumption and heat; or forcibly reducing the frequency and locking the cores to avoid overheating results in a sharp drop in performance and a sluggish user experience. Such localized optimization methods disrupt the dynamic balance of the system state, making it difficult to achieve global optimization of battery life, smoothness, and wearing comfort in diverse and rapidly changing user scenarios.

[0004] In particular, existing solutions exhibit significant delays in their perception and response mechanisms to user scenarios and system load. This lag prevents devices from immediately providing matching performance support when user demands change rapidly, or from reducing power consumption in a timely manner during low-demand scenarios, resulting in sluggish response and wasted energy.

[0005] Therefore, there is a need for an intelligent resource scheduling method and system that can perceive user intent and system internal state in real time and with high accuracy. Summary of the Invention

[0006] This application aims to address the problem in existing technologies where smart wearable devices exhibit lag in their perception and response to user scenarios and system loads, making it difficult to achieve a dynamic optimal balance between battery life, operational smoothness, and wearing comfort in diverse and rapidly changing usage scenarios. To address this, a parameter adjustment method and system based on smart wearable devices are proposed, which achieves adaptive intelligent resource scheduling by accurately perceiving user intent and internal system states in real time.

[0007] In a first aspect, embodiments of this application provide a parameter adjustment method based on a smart wearable device, including: Obtain current context information, which includes motion state information, task complexity information of the currently executed task, and external environment state information; Based on the current context information, a current context complexity score is generated using a predefined computational model. Based on the current scenario complexity score, the corresponding target working parameter mode is matched from multiple preset parameter configuration modes, and the target working parameter mode is applied. During the operation of the target working parameter mode, the operating status parameters of the smart wearable device are monitored, including performance parameters, power consumption parameters, and temperature parameters. If any operating status parameter is detected to meet its corresponding preset adjustment conditions, the operating parameters will be adjusted based on the target operating parameter mode.

[0008] In some embodiments, a current scenario complexity score is generated using a predefined computational model, including: Weights are assigned to motion state information, task complexity information, and external environment state information, and a weighted calculation is performed to generate a scenario complexity score. The corresponding scenario complexity level is determined based on the numerical range to which the scenario complexity score belongs.

[0009] In some embodiments, based on the current scenario complexity score, a corresponding target working parameter mode is matched from a set of preset parameter configuration modes, including: Based on the level of scenario complexity, the corresponding target operating parameter mode is matched from the parameter configuration mode; the target operating parameter mode includes multiple hardware operating parameters. Hardware operating parameters include CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate.

[0010] In some embodiments, the target operating parameter mode is applied, specifically as follows: The hardware operating parameters contained in the target operating parameter mode are converted into control commands corresponding to the hardware of the smart wearable device. According to the control instructions, at least one of the following settings for the smart wearable device is configured: CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate.

[0011] In some embodiments, monitoring the operating status parameters of a smart wearable device includes: In the first cycle, temperature parameters of the CPU, GPU, and battery in the smart wearable device are collected; In the second cycle, the battery power and consumption parameters of the smart wearable device are collected; In the third cycle, performance parameters of CPU and GPU load in smart wearable devices are collected.

[0012] In some embodiments, the preset adjustment conditions include: When the temperature parameters of the CPU, GPU, or battery exceed the preset temperature threshold, reduce the CPU frequency or GPU frequency. When the remaining battery power is detected to be lower than the preset power threshold, the overall power consumption of the smart wearable device is reduced. When the CPU or GPU load is detected to be consistently higher than the first performance threshold or consistently lower than the second performance threshold, the CPU frequency or GPU frequency will be adjusted accordingly.

[0013] In some embodiments, the method further includes: During operation, it continuously acquires updated current scenario information; When the complexity level corresponding to the scenario complexity score determined based on the updated current scenario information changes, the target working parameter mode corresponding to the new complexity level is rematched to switch the working mode of the smart wearable device.

[0014] Secondly, embodiments of this application provide a parameter adjustment system based on a smart wearable device, including: The context awareness module is used to acquire current context information, including motion state information, task complexity information of the currently executed task, and external environment state information; based on the current context information, it generates a current context complexity score through a predefined calculation model; The dynamic scheduling module is used to match the corresponding target working parameter mode from multiple preset parameter configuration modes based on the current scenario complexity score. The execution module is used to apply the target working parameter mode; The status monitoring module is used to monitor the operating status parameters of the smart wearable device during the operation of the target operating parameter mode. The operating status parameters include performance parameters, power consumption parameters, and temperature parameters. If any operating status parameter is detected to meet its corresponding preset adjustment conditions, the dynamic scheduling module will adjust the operating parameters based on the target operating parameter mode; the execution module will then apply the target operating parameter mode.

[0015] In some embodiments, the context-aware module includes: An environmental sensor unit is used to acquire motion state information and external environment state information; The task analyzer unit is used to obtain task complexity information; The complexity evaluator unit is used to assign weights to motion state information, task complexity information and external environment state information respectively and perform weighted calculations to generate a scenario complexity score.

[0016] Thirdly, embodiments of this application provide a smartwatch, including the parameter adjustment system described above.

[0017] This application reduces unnecessary computation and minimizes heat generation at the source by employing context awareness and on-demand resource scheduling. Simultaneously, it improves device heat dissipation through proactive temperature monitoring and predictive adjustment mechanisms, significantly enhancing user comfort. By transforming static performance configuration into a context-driven, dynamically adaptable resource allocation mode, the system can automatically switch to a matching operating state under different load scenarios, avoiding energy waste caused by performance redundancy and achieving a significant reduction in power consumption and an effective extension of battery life. Furthermore, when the device is in critical conditions such as low battery or high temperature, the system can smoothly and gradually adjust performance output according to preset strategies, prioritizing the continued availability of core functions and enhancing the system's robustness under extreme conditions and the consistency of user experience. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a parameter adjustment method based on a smart wearable device according to an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the parameter adjustment system based on a smart wearable device according to an embodiment of this application. Detailed Implementation

[0020] The following specific embodiments illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Although the description of this application will be presented in conjunction with some embodiments, this does not mean that the features of this application are limited to this embodiment. On the contrary, the purpose of describing the application in conjunction with embodiments is to cover other options or modifications that may be derived based on the claims of this application. To provide a thorough understanding of this application, many specific details will be included in the following description. This application may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of this application, some specific details will be omitted in the description. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0021] It should be noted that in this specification, similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0022] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0023] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0024] In the description of this application, it should be understood that "electrical connection" can be understood as physical contact and electrical conduction between components; it can also be understood as the form of connection between different components in a circuit structure through physical lines that can transmit electrical signals, such as copper foil or wires on a printed circuit board (PCB). "Coupled through..." can be understood as electrical conduction through indirect coupling. Indirect coupling can be understood as contactless coupling. Those skilled in the art will understand that coupling refers to a phenomenon where there is close cooperation and mutual influence between the inputs and outputs of two or more circuit elements or electrical networks, and energy is transferred from one side to the other through interaction. To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0025] like Figure 1As shown, in a first aspect, embodiments of this application provide a parameter adjustment method based on a smart wearable device, comprising: acquiring current scenario information, including motion state information, task complexity information of the currently executed task, and external environment state information; generating a current scenario complexity score based on the current scenario information using a predefined calculation model; matching a corresponding target working parameter mode from a set of preset parameter configuration modes according to the current scenario complexity score, and applying the target working parameter mode; monitoring the operating status parameters of the smart wearable device during the operation of the target working parameter mode, including performance parameters, power consumption parameters, and temperature parameters; and adjusting the working parameters based on the target working parameter mode if any operating status parameter is found to meet its corresponding preset adjustment conditions.

[0026] like Figure 2 As shown, in a second aspect, embodiments of this application provide a parameter adjustment system based on a smart wearable device, comprising: The context awareness module is used to acquire current context information, including motion state information, task complexity information of the currently executed task, and external environment state information; based on the current context information, it generates a current context complexity score through a predefined calculation model; The dynamic scheduling module is used to match the corresponding target working parameter mode from multiple preset parameter configuration modes based on the current scenario complexity score. The execution module is used to apply the target working parameter mode; The status monitoring module is used to monitor the operating status parameters of the smart wearable device during the operation of the target operating parameter mode. The operating status parameters include performance parameters, power consumption parameters, and temperature parameters. If any operating status parameter is detected to meet its corresponding preset adjustment conditions, the dynamic scheduling module will adjust the operating parameters based on the target operating parameter mode; the execution module will then apply the target operating parameter mode.

[0027] In this embodiment, the context awareness module includes: an environment sensor unit for acquiring motion state information and external environment state information; a task analyzer unit for acquiring task complexity information; and a complexity evaluator unit for assigning weights to the motion state information, task complexity information, and external environment state information respectively and performing weighted calculations to generate a context complexity score.

[0028] The dynamic scheduling module includes a parameter selector unit, which matches the corresponding target working parameter mode from multiple preset parameter configuration modes based on the current scenario complexity score; a resource scheduler unit, which converts the hardware working parameters contained in the target working parameter mode into control instructions corresponding to the hardware of the smart wearable device; and a strategy decision-maker unit, which sets at least one of the CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate of the smart wearable device according to the control instructions.

[0029] Step S1: Obtain current scenario information.

[0030] The context-aware module in the smart wearable device is activated and begins to work.

[0031] The environmental sensor unit collects multidimensional sensing data at a predetermined sampling frequency (e.g., 10 times per second), including but not limited to: three-axis accelerometer and gyroscope data (for identifying the user's motion state, such as stationary, walking, running), ambient light sensor data (for determining indoor / outdoor lighting conditions), and optional microphone noise level or barometer data (for assisting in determining the environmental scene, such as commuting, office work, or exercise).

[0032] The task analyzer unit monitors foreground applications, background services, and system processes in real time. By parsing application identifiers, window focus, triggered system events, and resource usage, and combining this with a pre-built application feature library, it identifies the task type (e.g., navigation, music playback, health monitoring, payment) and its corresponding task complexity level. Task complexity is predefined based on factors such as required computing power, real-time requirements, and screen refresh needs.

[0033] Step S2: Generate a complexity score for the current scenario.

[0034] The complexity estimator unit receives processed data (i.e., motion state information, external environment state information, and task complexity information) from the environmental sensor unit and the task analyzer unit. This unit contains a pre-built computational model (e.g., a weighted scoring function) or is trained using a machine learning algorithm.

[0035] In one implementation, weights are assigned to the three types of information, and each input is quantified into a score between 0 and 100. A current scenario complexity score is calculated, and a discrete scenario complexity level (e.g., "low," "medium," or "high") is determined based on the score's value falling within a preset range. This level identifier is then sent to the dynamic scheduling module.

[0036] Step S3: Match and apply the target working parameter pattern.

[0037] After receiving the scenario complexity level identifier, the parameter selector unit in the dynamic scheduling module queries the preset parameter configuration library.

[0038] The parameter configuration library stores parameter configuration patterns corresponding to each complexity level. Each pattern is a set of pre-optimized hardware operating parameters. For example: High complexity mode: CPU frequency = 2.0GHz, GPU frequency = 1000MHz, sensor sampling rate = 100Hz, display refresh rate = 90Hz.

[0039] Medium complexity mode: CPU frequency = 1.5GHz, GPU frequency = 700MHz, sensor sampling rate = 50Hz, display refresh rate = 60Hz.

[0040] Low complexity mode: CPU frequency = 1.0GHz, GPU frequency = 400MHz, sensor sampling rate = 20Hz, display refresh rate = 30Hz.

[0041] The parameter selector selects the target operating parameter mode that matches the complexity level of the current scenario. Subsequently, the resource scheduler unit converts this mode into control instructions that can be recognized by the underlying hardware.

[0042] The hardware drivers or controllers of the execution module receive instructions and take effect, thereby completing the switching of the working mode.

[0043] Step S4: Monitor operating status parameters and determine adjustment conditions.

[0044] While operating in the target parameter mode, the status monitoring module begins its work. It comprises multiple monitoring units that collect key system operating status parameters in parallel at different intervals: Temperature monitoring unit: Reads the values ​​of CPU, GPU core temperature sensors and battery thermistors in a first cycle (e.g., per second).

[0045] Battery monitoring unit: Reads the battery's instantaneous current and voltage in a second cycle (e.g., every 5 seconds) and calculates the remaining battery percentage.

[0046] Performance monitoring unit: It obtains the CPU load rate, GPU rendering queue depth, and available memory ratio of each core through the operating system kernel in a third cycle (e.g., every 2 seconds).

[0047] This real-time data is aggregated and continuously compared with preset adjustment conditions. Preset adjustment conditions include, for example: Temperature conditions: Temperature > 40℃.

[0048] Power consumption condition: Remaining battery charge < 20%.

[0049] Performance conditions: CPU load > 80% for 3 consecutive cycles (indicating potential underperformance), or < 20% for 5 consecutive cycles (indicating overperformance).

[0050] Step S5: Trigger working parameter adjustment.

[0051] Once any monitoring unit detects that its parameters meet the preset adjustment conditions (for example, the temperature monitoring unit reports that the CPU temperature has reached 40°C), it will send an alarm or suggestion signal to the policy decision-maker unit of the dynamic scheduling module.

[0052] The policy decision-maker takes action based on a predefined library of adjustment policies. For example, in response to a temperature alarm, the policy might be to "limit the CPU's maximum frequency to 90% of its current value and reduce the GPU frequency by one level."

[0053] Based on the output of the policy decision-maker, the resource scheduler unit generates new, partially modified hardware control instructions (e.g., adjusting only the CPU and GPU frequencies while keeping other parameters unchanged) on the target working parameter mode, and then sends them back to the execution module.

[0054] After the hardware parameters are dynamically adjusted, status monitoring continues. If the adjusted temperature begins to decrease and returns below the safe threshold, the system maintains the adjusted state; if the problem persists, further adjustments are triggered. Simultaneously, steps S1-S3 are continuously executed in a loop. When the user scenario changes (e.g., stopping running), a new scenario complexity level is calculated, triggering a completely new operating mode switch (e.g., switching from "high" to "medium" complexity mode), thereby overriding or combining with the state-based fine-tuning performed in step S5.

[0055] Through the cyclical execution of steps S1 to S5 described above, this implementation method achieves a two-layer optimization closed loop of "scenario-predictive scheduling" and "state-responsive adjustment". The system can not only configure resources according to user intentions, but also make real-time corrections based on actual physical conditions (temperature, power consumption) during operation, thereby achieving a dynamic and global balance among performance, power consumption, and heat dissipation, significantly improving the battery life, wearing comfort, and smooth and stable user experience of smart wearable devices.

[0056] In this embodiment of the application, the current scenario complexity score is generated through a predefined calculation model, including: assigning weights to motion state information, task complexity information and external environment state information respectively and performing weighted calculation to generate a scenario complexity score; and determining the corresponding scenario complexity level according to the numerical range to which the scenario complexity score belongs.

[0057] In one implementation, motion state information is derived in real time by a motion recognition algorithm based on sensor data streams (acceleration, angular velocity), and quantified into a continuous or discrete intensity score. For example, it can be defined as: stationary = 0 points, slow walking = 30 points, brisk walking = 60 points, running = 85 points, and high-intensity interval training = 100 points.

[0058] Task complexity information is assigned a comprehensive complexity score to the current task by the task analyzer based on characteristics such as application type, process priority, graphics rendering requirements, and real-time requirements, combined with a pre-set complexity lookup table. For example, screen-off standby = 10 points, music playback = 30 points, continuous heart rate monitoring = 50 points, map navigation = 80 points, and high-definition video call = 100 points.

[0059] External environmental status information is derived through fusion analysis by environmental sensor units. For example, factors such as light intensity, ambient noise levels (decibels), and network connectivity are used to comprehensively assess the environmental requirements for equipment performance. A quiet indoor environment = 20 points, outdoor sunlight = 60 points, and a noisy sports field = 90 points.

[0060] The computational model assigns configurable weights to the three types of information mentioned above. For example, the motion state weight W_m = 0.3, the task complexity weight W_t = 0.4, and the external environment weight W_e = 0.3. These weights can be adjusted based on device type or user mode (e.g., "power saving mode" increases the weight of W_t).

[0061] The current scenario complexity score is calculated using the following formula: Score = (S_m × W_m) + (S_t × W_t) + (S_e × W_e) Where S_m, S_t, and S_e represent the quantified scores of motion state, task complexity, and external environment state, respectively. The calculated result, Score, is a numerical value (e.g., ranging from 0 to 100).

[0062] The system predefines several complexity level ranges to map continuous scores to discrete operation levels. For example: Low complexity level: Score 0 ≤ Score < 30; Medium complexity level: Score 30 ≤ Score < 70; High complexity level: Score 70 ≤ 100; When the score falls within a certain range, it is determined to be the corresponding scenario complexity level. This level will serve as a key index for subsequently selecting the parameter configuration mode.

[0063] In one implementation, the computational model is adaptive. For example, the system can record the frequency of user manual intervention (such as forced mode switching) at different levels, or monitor the occurrence of performance insufficiency (sustained high load) at a certain level, and fine-tune the weighting coefficients or boundary values ​​of the level range accordingly, so that the evaluation results are more in line with the user's actual usage habits and perceptions.

[0064] In this embodiment of the application, a target working parameter mode is matched from a set of preset parameter configuration modes based on the current scenario complexity score. This includes: matching the target working parameter mode from the parameter configuration modes based on the scenario complexity level; the target working parameter mode includes multiple hardware working parameters; the hardware working parameters include CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate.

[0065] In this embodiment of the application, the target operating parameter mode is applied, specifically by converting the hardware operating parameters included in the target operating parameter mode into control instructions corresponding to the hardware of the smart wearable device; and setting at least one of the CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate of the smart wearable device according to the control instructions.

[0066] The parameter configuration strategy library is stored in the form of a data structure (such as a lookup table or configuration file). Each record in the library corresponds to a scenario complexity level and is associated with a complete set of parameter configuration patterns. Each set of parameter configuration patterns defines a set of collaborative working parameters that operate on multiple key hardware subsystems of the smart wearable device, typically including but not limited to: CPU operating frequency, number of enabled cores; and GPU operating frequency and core enable status. Sampling frequency (e.g., accelerometer adjustable from 10Hz to 200Hz) and operating mode (e.g., low-power monitoring mode or high-precision measurement mode) of various motion, environmental, and biosensors. Display refresh rate (e.g., 30Hz, 60Hz, 90Hz), brightness adjustment curve, touch sampling rate, and Always-on Display (AOD) update frequency.

[0067] Upon receiving a scenario complexity level identifier (such as "medium complexity") from the complexity evaluator unit, the parameter selector unit within the dynamic scheduling module immediately uses this identifier as a key index to query the parameter configuration strategy library. This matching process is deterministic, aiming to quickly locate the preset parameter combination that best matches the performance level of the currently evaluated user scenario requirements. This combination is then determined as the target working parameter mode.

[0068] After a successful match, the resource scheduler unit is responsible for converting the abstract "target operating parameter mode" into a sequence of specific, hardware-executable operation instructions. This process involves: Instruction translation: Converting parameter values ​​into dedicated calling instructions for the corresponding hardware driver or controller. For example, setting a specific frequency value through the operating system's CPU frequency adjustment interface; changing the refresh rate through display service interface commands; and configuring the sampling period through the sensor HAL layer.

[0069] Coordinated scheduling: To ensure smooth mode switching and system stability, the resource scheduler issues instructions in a specific order and timing. For example, it first slightly reduces the current load, then switches the display refresh rate, and finally adjusts the CPU / GPU frequency to reduce visual stuttering and performance glitches.

[0070] Atomized application: The hardware control units of the execution module (such as CPU frequency modulation driver, display controller, sensor management chip) receive and execute instructions, so that all target hardware parameters switch to the new mode almost synchronously, thereby completing the transition of the entire system's working state.

[0071] In one implementation, the matching process is not entirely static. The system can integrate a lightweight feedback learning module that monitors the actual performance (such as frame rate stability) and power consumption data achieved under a specific target parameter configuration mode. If a long-term deviation from expectations is detected (e.g., frequent temperature alarms still being triggered in "medium complexity" mode), the system can suggest or automatically fine-tune the specific parameter values ​​for that mode (e.g., fine-tuning the CPU frequency from 1.5GHz to 1.4GHz), achieving online, small-scale optimization of the configuration strategy to better suit the hardware differences of specific devices or the unique usage habits of users.

[0072] Through the steps described above, this embodiment discloses a complete link from scenario assessment results to precise, efficient, and controllable hardware parameter settings. This not only ensures a high degree of matching between resource allocation and scenario requirements but also improves system stability.

[0073] In this embodiment of the application, monitoring the operating status parameters of the smart wearable device includes: In the first cycle, temperature parameters of the CPU, GPU, and battery in the smart wearable device are collected; In the second cycle, the battery power and consumption parameters of the smart wearable device are collected; In the third cycle, performance parameters of CPU and GPU load in smart wearable devices are collected.

[0074] To balance monitoring real-time performance with system overhead, different data collection periods are used for different types of parameters: The first cycle (short cycle, e.g., 500ms-1s) is used to collect temperature parameters: Since the chip junction temperature responds quickly to changes in load, short cycle monitoring helps to detect temperature rise trends in a timely manner and provides a basis for adjustment.

[0075] The second cycle (medium cycle, e.g., 3s-5s) is used to collect power consumption parameters: battery level changes relatively slowly, and the reading of a high-precision fuel gauge itself consumes some power. Setting a slightly longer cycle helps reduce the energy consumption caused by frequent access to peripherals.

[0076] The third cycle (variable cycle, e.g., 1s-2s) is used to collect performance parameters: performance load changes rapidly, but reading and aggregating raw performance counter data itself consumes CPU resources. The system dynamically fine-tunes this cycle according to the complexity of the current scenario—using a shorter cycle (e.g., 1s) in high-complexity mode to achieve fine control, and using a longer cycle (e.g., 2s) in low-complexity mode to save computing power.

[0077] In one implementation, the monitoring system itself can adaptively adjust according to system load and equipment operating conditions: when the system is about to trigger or has already triggered adjustment conditions, the acquisition frequency of relevant parameters can be temporarily increased to obtain higher resolution decision data; when the device enters deep sleep or extremely low power consumption state, the monitoring frequency of non-critical parameters can be paused or significantly reduced, and only the wake-up signal can be monitored.

[0078] In this embodiment of the application, the preset adjustment conditions include: When the temperature parameters of the CPU, GPU, or battery exceed the preset temperature threshold, reduce the CPU frequency or GPU frequency. When the remaining battery power is detected to be lower than the preset power threshold, the overall power consumption of the smart wearable device is reduced. When the CPU or GPU load is detected to be consistently higher than the first performance threshold or consistently lower than the second performance threshold, the CPU frequency or GPU frequency will be adjusted accordingly.

[0079] In one implementation, when any of the CPU core temperature, GPU core temperature, or battery temperature exceeds a preset first-level temperature threshold, the temperature adjustment condition is determined to be met. A tiered frequency reduction and cooling strategy is then triggered. The strategy decision-maker unit first locates the primary heat source and takes action based on a preset adjustment mapping table. For example: If the temperature exceeds the threshold by a small margin, the instruction resource scheduler unit will limit the CPU's maximum frequency to 90% of the current level and simultaneously reduce the GPU frequency by one level. If the temperature continues to rise or exceeds a higher threshold, one or more large CPU cores will be further shut down, and the GPU will be switched to its lowest performance state. Simultaneously, the screen's peak brightness will be reduced, and non-critical background services will be paused to collaboratively reduce overall heat generation. After adjustments, the temperature will be continuously monitored. Once the temperature falls below the safe threshold and stabilizes for a certain period, the system will gradually and tentatively restore performance until it matches the mode corresponding to the current scenario's complexity level.

[0080] In one implementation, the system is triggered when the remaining battery charge (SOC) falls below a preset tiered power threshold. For example, multiple threshold points are set: 20% (light power saving), 10% (deep power saving), and 5% (extreme power saving). A tiered global power consumption suppression strategy is then triggered. The adjustment is not limited to the computing unit but extends to the system level. In Mild Power Saving Mode (SOC < 20%), the maximum available CPU / GPU frequency is reduced; the screen refresh rate is forced to 60Hz; the sensor sampling rate is reduced to the baseline level; and background network activity is limited. In Deep / Extreme Power Saving Mode (SOC < 10% or SOC < 5%), in addition to Mild Power Saving Mode, high-frequency power-consuming modules such as GPS and mobile data are further disabled; a dark theme and the lowest screen brightness are enabled; and only core communication and health monitoring functions are retained.

[0081] In one implementation, when the total CPU load or GPU rendering load is detected to be higher than a first performance threshold (e.g., 80%) for N sampling cycles (e.g., 3 cycles), it indicates that the current parameter mode may not meet the actual computing power requirements, posing a risk of stuttering. When the above load is lower than a second performance threshold (e.g., 20%) for M sampling cycles (e.g., 5 cycles), it indicates that the resources allocated to the current task are too high, resulting in energy waste. At this time, a frequency calibration strategy is triggered: To address performance issues, the strategy decision-maker unit slightly increases the CPU / GPU frequency (e.g., by 0.1GHz or one level) within the current target operating parameter mode and observes subsequent load changes. To address performance overkill, while ensuring smooth operation, the CPU / GPU frequency is gradually reduced in small steps until the load returns to an efficient range (e.g., 20%-80%). This fine-tuning strategy ensures that the system's actual operating state always remains near the optimal range of the "performance-energy efficiency" curve.

[0082] Through the above implementation methods, this embodiment not only makes the system response more intelligent, but also ensures the safety and stability of the adjustment decision itself in a complex and ever-changing operating environment.

[0083] In this embodiment of the application, the parameter adjustment method further includes: continuously acquiring updated current scenario information during operation; when the complexity level corresponding to the scenario complexity score determined based on the updated current scenario information changes, re-matching the target working parameter mode corresponding to the new complexity level, so as to switch the working mode of the smart wearable device.

[0084] Each time the system obtains updated scenario information, it re-executes the scoring calculation process and intelligently determines the level change: it inputs the updated motion state, task complexity, and environmental state information into the predefined calculation model, generates a new scenario complexity score, and determines its corresponding new complexity level (such as changing from "high" to "medium").

[0085] In one implementation, to prevent frequent pattern oscillations caused by minor data fluctuations near grade boundaries, the system introduces a hysteresis interval or settling time determination. For example, a "grade change" is only determined when a new score remains stable in another grade range for more than a preset time (e.g., 3 seconds), or when the difference between the new and old scores exceeds a certain threshold. This enhances the system's decision-making stability.

[0086] Once the complexity level is confirmed to have changed, the mode switch is initiated: the parameter selector unit of the dynamic scheduling module uses the new complexity level as an index to retrieve the new target working parameter mode from the parameter configuration library. The resource scheduler unit compares the new target mode with the currently effective mode and generates an incremental instruction set containing only the parameters that need to be changed. For example, if only the CPU frequency and display refresh rate need to be reduced, only these two instructions will be generated.

[0087] This embodiment achieves real-time synchronization of resource allocation and scenario requirements, fundamentally ensuring a consistent and comfortable user experience.

[0088] Thirdly, embodiments of this application provide a smartwatch, including the parameter adjustment system described above.

[0089] Example 1 This embodiment uses a smartwatch as an example to illustrate the application process of the parameter adjustment method described in this application in typical daily use scenarios.

[0090] When users are in an office environment and primarily check the time and message notifications intermittently: The system uses sensors and task analysis to identify that the user is currently stationary (motion intensity score ≈ 0), performing a time / message viewing task (task complexity score ≈ 15), and is located in an indoor environment (environmental requirements score ≈ 20). Substituting these values ​​into a predefined weighted calculation model, the system calculates the current scenario complexity score to be approximately 12 points, which falls into the low complexity category.

[0091] The dynamic scheduling module matches and applies low-power operating parameter modes accordingly, such as setting the CPU operating frequency to 1.0GHz, the GPU frequency to 400MHz, the sensor sampling rate to 20Hz, and the display refresh rate to 30Hz.

[0092] In this mode, the overall power consumption of the device can be significantly reduced (for example, to about 50mW), which is about 67% lower than the fixed working mode that always maintains high performance (for example, power consumption of 150mW), thus extending the theoretical battery life of the device in this scenario by more than twice.

[0093] When a user starts an outdoor run and launches the activity tracking app: The user enters running mode (exercise intensity score ≈ 100), the task switches to exercise recording (task complexity score ≈ 70), and the environment changes to strong outdoor light (environmental requirements score ≈ 100). The recalculated scenario complexity score rises to approximately 88 points, corresponding to a high complexity level.

[0094] The system then switches to a high-performance operating parameter mode, for example, increasing the CPU frequency to 2.0GHz, the GPU frequency to 1000MHz, the sensor sampling rate to 100Hz (to ensure the accuracy of GPS, heart rate and other data), and the display refresh rate to 90Hz (to ensure a smooth sports interface).

[0095] This mode provides ample computing power and a smooth interactive experience for high-load tasks such as GPS positioning, continuous heart rate monitoring, and trajectory recording, meeting the high-performance requirements in sports scenarios.

[0096] After running in high-performance mode for a period of time (e.g., 20 minutes): The status monitoring module detected that the CPU temperature reached 43°C (exceeding the preset 40°C threshold), while the battery level dropped to 18% (below the preset 20% threshold).

[0097] The strategy decision-making unit integrates temperature and power alarms, triggering a composite adjustment strategy. While maintaining the "high complexity" scenario matching framework, it performs a superimposed dynamic adjustment: to control temperature, the CPU frequency is reduced by 10% from 2.0GHz to 1.8GHz. To extend battery life, overall power consumption suppression is initiated, uniformly reducing parameters such as GPU frequency, sensor sampling rate, and display refresh rate by approximately 20% from the current high-performance mode benchmark (e.g., GPU reduced to 800MHz, sampling rate reduced to 80Hz, and refresh rate reduced to 72Hz).

[0098] After adjustment, the CPU temperature dropped to 38°C within about 2 minutes, and the overall system power consumption decreased by about 30%. This process effectively controlled the device temperature rise and slowed down power consumption while ensuring the continuous operation of the core sports recording functions, thus avoiding the risk of device interruption due to overheating or power depletion.

[0099] When the user finishes running and returns indoors to rest, the device returns to standby mode, and the scenario complexity score drops to a low level. The system automatically switches back to ultra-low power mode (e.g., CPU frequency 0.8GHz, sensor sampling rate 10Hz, display off), reducing device power consumption to below 30mW, allowing for a long-lasting standby state for several days.

[0100] As can be seen from the above cross-scenario application process, the method described in this application, through a two-layer mechanism combining "scenario predictive initial matching" and "state-triggered closed-loop adjustment," enables smart wearable devices to dynamically adapt to various complex scenario changes, from static office work to high-intensity exercise, and then to handling extreme states. While ensuring the core experience required for each scenario, the system achieves a balance between performance, power consumption, and heat dissipation, resulting in a comprehensive improvement in device battery life, wearing comfort, and reliability.

[0101] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A parameter adjustment method based on a smart wearable device, characterized in that, include: Obtain current context information, which includes motion state information, task complexity information of the currently executed task, and external environment state information; Based on the current scenario information, a current scenario complexity score is generated using a predefined computational model; Based on the current scenario complexity score, the corresponding target working parameter mode is matched from multiple preset parameter configuration modes, and the target working parameter mode is applied. During the operation of the target operating parameter mode, the operating status parameters of the smart wearable device are monitored, including performance parameters, power consumption parameters, and temperature parameters; If any of the aforementioned operating status parameters is detected to meet its corresponding preset adjustment conditions, then the operating parameters are adjusted based on the target operating parameter mode. The process of generating a current scenario complexity score using a predefined computational model includes: The motion state information, task complexity information, and external environment state information are each assigned weights and weighted calculations are performed to generate a scenario complexity score. The corresponding scenario complexity level is determined based on the numerical range to which the scenario complexity score belongs.

2. The parameter adjustment method of claim 1, wherein, The step of matching the corresponding target working parameter mode from a set of preset parameter configuration modes based on the current scenario complexity score includes: Based on the level of scenario complexity, a corresponding target operating parameter mode is matched from the parameter configuration modes; the target operating parameter mode includes multiple hardware operating parameters. The hardware operating parameters include CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate.

3. The parameter adjustment method of claim 2, wherein, The application of the target working parameter mode is specifically as follows: The hardware operating parameters contained in the target operating parameter mode are converted into control instructions corresponding to the hardware of the smart wearable device. According to the control command, at least one of the following parameters of the smart wearable device is set: CPU frequency, GPU frequency, sensor sampling rate, and display refresh rate.

4. The parameter adjustment method of claim 2, wherein, The monitoring of the operating status parameters of the smart wearable device includes: In the first cycle, the temperature parameters of the CPU, GPU and battery in the smart wearable device are collected; In the second cycle, the battery power consumption parameters of the smart wearable device are collected; In the third cycle, the performance parameters of the CPU and GPU load in the smart wearable device are collected.

5. The parameter adjustment method of claim 4, wherein, The preset adjustment conditions include: When the temperature parameters of the CPU, GPU, or battery are detected to exceed a preset temperature threshold, the CPU frequency or GPU frequency is reduced. When the remaining battery power is detected to be lower than a preset power threshold, the overall power consumption of the smart wearable device is reduced. When the CPU load or GPU load is detected to be consistently higher than the first performance threshold or consistently lower than the second performance threshold, the CPU frequency or GPU frequency is adjusted accordingly.

6. The parameter adjustment method as described in claim 1, characterized in that, The method further includes: During operation, it continuously acquires updated current scenario information; When the complexity level corresponding to the scenario complexity score determined based on the updated current scenario information changes, the target working parameter mode corresponding to the new complexity level is rematched to switch the working mode of the smart wearable device.

7. A parameter adjustment system based on a smart wearable device, characterized in that, include: The context awareness module is used to acquire current context information, which includes motion state information, task complexity information of the currently executed task, and external environment state information. Based on the current scenario information, a current scenario complexity score is generated using a predefined computational model; The dynamic scheduling module is used to match the corresponding target working parameter mode from a set of preset parameter configuration modes based on the current scenario complexity score. The execution module is used to apply the target working parameter mode; The status monitoring module is used to monitor the operating status parameters of the smart wearable device during the operation of the target operating parameter mode. The operating status parameters include performance parameters, power consumption parameters, and temperature parameters. If any of the aforementioned operating status parameters is detected to meet its corresponding preset adjustment conditions, the dynamic scheduling module will adjust the operating parameters based on the target operating parameter mode. The target operating parameter mode is applied by the execution module; The context-aware module includes: An environmental sensor unit is used to acquire the motion state information and the external environment state information; The task analyzer unit is used to obtain task complexity information; The complexity evaluator unit is used to assign weights to the motion state information, task complexity information and external environment state information respectively and perform weighted calculations to generate a scenario complexity score.

8. A smartwatch, characterized in that, Includes the parameter adjustment system as described in claim 7.

Images