A power device control method and system of a smart wearable device
Through multi-dimensional data collection and feature fusion analysis, intelligent control of the power devices in smart wearable devices has been achieved throughout the entire process, solving the problem of power supply mismatch in traditional control modes and improving the stability and battery life of the devices.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- DONGGUAN TONGKE ELECTRONICS CO LTD
- Filing Date
- 2026-02-27
- Publication Date
- 2026-06-02
Smart Images
Figure CN122131900A_ABST
Abstract
Description
Technical Field
[0001] This invention proposes a power device control method and system for smart wearable devices, relating to the field of power device control technology, specifically to the field of power device control technology for smart wearable devices. Background Technology
[0002] Traditional smart wearable devices often employ a single-dimensional data-driven control model for power device control, making simple adjustments based solely on the device's own operating data without fully integrating multi-dimensional information such as user behavior and environmental parameters. This control method is prone to mismatches between power supply and actual demand, resulting in either power redundancy leading to shortened battery life or insufficient power affecting normal functioning. Furthermore, the control parameter adjustments lack dynamic adaptability, making it difficult to optimize in real time based on device operating status, user habits, and environmental changes, thus failing to meet the development needs of miniaturization, low power consumption, and personalization in smart wearable devices. Summary of the Invention
[0003] This invention provides a power device control method and system for smart wearable devices to solve the above-mentioned problems: This invention proposes a power device control method and system for a smart wearable device, the method comprising: S1. Collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data; S2. Perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data. Perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. S3. Analyze the control effect and adjust the control parameters based on the power device control feedback data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
[0004] Further, S1 includes: By using smart wearable devices to collect multi-dimensional operational data of devices, data can be obtained from the device itself. By retrieving multi-dimensional user behavior data through smart wearable devices, user-end collected data can be obtained. Environmental data is obtained by collecting multi-dimensional parameters of the environment through smart wearable devices. Preliminary analysis and processing are performed on the data collected from the device, user, and environment to obtain preliminary analysis and processing data.
[0005] Furthermore, the preliminary analysis and processing of the data collected from the device, the user, and the environment to obtain preliminary analysis and processing data includes: Invalid data is filtered from data collected from the device, user, and environment to obtain primary filtered data. The primary filtered data is subjected to interference filtering to obtain the secondary filtered data. Normalize the data processed by the secondary filtering to obtain normalized data; Based on the normalized data, equipment, users, and environment are classified to obtain equipment operation category, user behavior category, and environmental impact category; The normalized data is classified according to equipment operation, user behavior, and environmental impact to obtain the corresponding normalized data set, which is the preliminary analysis and processing data.
[0006] Further, S2 includes: Based on the preliminary analysis and processing of the data, feature extraction is performed to obtain various types of collected feature data; Feature fusion analysis is performed on feature data collected from multiple categories to obtain feature fusion analysis data; Power demand analysis is performed based on feature fusion analysis data to obtain power demand analysis data. Power device control analysis is performed based on power demand analysis data to obtain power device control analysis data. Power device control is performed based on the power device control analysis data to obtain power device control feedback data.
[0007] Furthermore, the step of performing feature fusion analysis based on feature data collected from multiple categories to obtain feature fusion analysis data includes: The various types of collected feature data are preprocessed to obtain various types of preprocessed data; Feature conflict identification is performed on the various types of preprocessed data to obtain feature conflict identification data; Obtain conflicting and non-conflicting data based on feature conflict identification data; Calculate the ratio of conflicting data to the total amount of feature data, and then invert the ratio to obtain the conflict weight coefficient. Calculate the ratio of non-conflicting data volume to the total feature data volume to obtain the non-conflicting weight coefficient; Feature requirement identification is performed on various feature extraction data to obtain feature requirement identification data; Based on characteristic requirements, identify data to obtain both required and non-required data; Calculate the ratio of the required data volume to the total feature data volume to obtain the demand weight coefficient; Calculate the ratio of non-demand data volume to feature data volume to obtain the non-demand weight coefficient; The preprocessed data of various types are weighted and multiplied by the corresponding conflict weight coefficient multiplied by the demand weight coefficient, and the non-conflict weight coefficient multiplied by the non-demand weight coefficient. The calculation results are then compared and fused using multi-dimensional features to obtain feature fusion analysis data.
[0008] Furthermore, the step of performing power demand analysis based on feature fusion analysis data to obtain power demand analysis data includes: Based on the feature fusion analysis data, feature power demand categories are decomposed to obtain equipment functional power demand information, user personalized power demand information, and environment adaptation power demand information. Generate characteristic power requirement information based on equipment functional power requirement information, user-personalized power requirement information, and environment-adaptive power requirement information; Based on the characteristic power demand information, and combined with the weight coefficients and feature correlations in the feature fusion analysis data, power demand threshold quantification and priority ranking are performed to generate power demand analysis data.
[0009] Further, the step of controlling the power device based on the power device control analysis data to obtain power device control feedback data includes: Power control commands are generated based on power device control analysis data, and power control is adjusted according to the power control commands to obtain power control adjustment data. Based on the power control adjustment data, a full-dimensional feedback acquisition mechanism is activated to collect three major categories of feedback data: equipment operation feedback data, power control effect feedback data, and demand matching degree feedback data. The three main categories of feedback data collected are preprocessed and integrated to obtain power device control feedback data.
[0010] Further, S3 includes: The control effect is analyzed based on the control feedback data of the power devices to obtain control effect analysis data. Determine the corresponding effect data of the control parameters based on the control effect analysis data; The corresponding effects are evaluated to determine their level, and then the control parameters are evaluated to determine their level, thus obtaining the effect parameter level data. Adjust the control parameters based on the effect parameter level data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
[0011] Furthermore, the step of analyzing the control effect based on the power device control feedback data to obtain control effect analysis data includes: Deep analysis of power device control feedback data is performed to obtain equipment operation deviation data, power control parameter deviation data, and demand matching deviation data. Calculate the corresponding effect deviation value based on the three types of deviation data; The three types of effect deviation values are weighted and fused to obtain control effect deviation data; The control effect deviation data is the control effect analysis data.
[0012] Furthermore, the system includes: The preliminary analysis module is used to collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data. The power control module is used to perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data, and to perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. The feedback adjustment module is used to analyze the control effect and adjust the control parameters based on the control feedback data of the power device until the control adjustment parameters of the power device meet the target requirements of the current smart wearable device.
[0013] The beneficial effects of this invention are as follows: This method solves the technical problems of existing smart wearable devices, such as single-dimensional control of power devices, lack of closed-loop adjustment, and poor adaptability, achieving intelligent control of power devices throughout the entire process. Through closed-loop logic, it avoids the problems of excessive or insufficient power supply caused by traditional fixed-parameter control, improving the accuracy and adaptability of power control. Simultaneously, it integrates multi-dimensional data for analysis, breaking the limitations of single-data control, improving the comprehensiveness and rationality of power control, thereby enhancing the operational stability of smart wearable devices, reducing battery life loss caused by ineffective power consumption, ensuring the stable operation of the device's core functions, and balancing user experience with device battery life. Attached Figure Description
[0014] Figure 1 This is a schematic diagram of a power device control method for a smart wearable device. Detailed Implementation
[0015] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.
[0016] In one embodiment of the present invention, a power device control method and system for a smart wearable device is provided, the method comprising: S1. Collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data; S2. Perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data. Perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. S3. Analyze the control effect and adjust the control parameters based on the power device control feedback data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
[0017] The working principle and technical effects of the above-mentioned technical solution are as follows: This method solves the problem of messy raw data that cannot be directly used for control analysis by completing the collection and preliminary processing of multi-dimensional data; by performing feature fusion on the pre-processed data, the discrete multi-dimensional data is transformed into comprehensive feature information that can be used for power control; then, based on this fused information, power demand analysis and power device control are completed, realizing the transformation from data to control commands; by monitoring and analyzing the actual effect of power control, it is determined whether the control parameters are suitable for the target requirements of the equipment (such as low power consumption, functional stability, etc.). If not, the parameters are continuously adjusted, forming a closed loop of collection, analysis, control, feedback, and adjustment, ensuring that the control effect always matches the actual operating requirements of the equipment. Among them, the target requirements refer to the core requirements of smart wearable devices in the current scenario, which take into account both normal operation and low power consumption, and cover the adaptation requirements of multiple dimensions of equipment, users, and environment.
[0018] This method addresses the technical problems of existing smart wearable devices, such as single-dimensional power device control, lack of closed-loop adjustment, and poor adaptability, achieving intelligent control of power devices throughout the entire process. Through closed-loop logic, it avoids the problems of excessive or insufficient power supply caused by traditional fixed-parameter control, improving the accuracy and adaptability of power control. Simultaneously, it integrates multi-dimensional data for analysis, breaking through the limitations of single-data control, enhancing the comprehensiveness and rationality of power control, thereby improving the operational stability of smart wearable devices, reducing battery life loss due to ineffective power consumption, ensuring the stable operation of core device functions, and balancing user experience with device battery life.
[0019] In one embodiment of the present invention, S1 includes: By using smart wearable devices to collect multi-dimensional operational data of devices, data can be obtained from the device itself. By retrieving multi-dimensional user behavior data through smart wearable devices, user-end collected data can be obtained. Environmental data is obtained by collecting multi-dimensional parameters of the environment through smart wearable devices. Preliminary analysis and processing are performed on the data collected from the device, user, and environment to obtain preliminary analysis and processing data.
[0020] The working principle and technical effects of the above technical solution are as follows: This method collects various data related to the device's own operation (such as battery status, functional module operating status, and current parameters of power devices) through components such as built-in sensors and main control chips, reflecting the device's real-time operating status; user-side data is obtained by retrieving user history records stored in the device and collecting user interaction behavior in real time, reflecting user habits and personalized needs; environmental-side data is collected through the device's built-in environmental sensors to collect relevant parameters of the environment in which the device is located (such as temperature, humidity, and electromagnetic interference), reflecting the impact of the environment on the operation of power devices. After collection, the three types of data undergo preliminary analysis and processing, eliminating invalid information, standardizing data formats, and classifying and organizing them to obtain preliminary analyzed and processed data, ensuring that the data can be directly used for feature extraction and fusion analysis.
[0021] This method addresses the technical problems of existing power control technologies, which rely on data from only a single device, resulting in narrow data coverage, biased control decisions, and poor adaptability. It achieves comprehensive collection and preliminary organization of multi-dimensional data. By simultaneously collecting data from devices, users, and the environment, it comprehensively captures various factors affecting power device control, improving the comprehensiveness and relevance of the data. Preliminary data processing removes invalid and non-functional information, reducing the computational load of analysis and improving efficiency and accuracy. Simultaneously, it provides a high-quality data foundation for feature fusion analysis, avoiding control decision errors caused by poor data quality, and further enhancing the adaptability of power control to actual equipment operation, user needs, and environmental changes.
[0022] In one embodiment of the present invention, the preliminary analysis and processing of data collected from the device, the user, and the environment to obtain preliminary analysis and processing data includes: Invalid data is filtered from data collected from the device, user, and environment to obtain primary filtered data. The primary filtered data is subjected to interference filtering to obtain the secondary filtered data. Normalize the data processed by the secondary filtering to obtain normalized data; Based on the normalized data, equipment, users, and environment are classified to obtain equipment operation category, user behavior category, and environmental impact category; The normalized data is classified according to equipment operation, user behavior, and environmental impact to obtain the corresponding normalized data set, which is the preliminary analysis and processing data.
[0023] The working principle and technical effect of the above technical solution are as follows: This method transforms the three types of raw data into standardized and usable preliminary analysis data through multi-step processing. Invalid data filtering removes meaningless data from the three data categories (such as blank data due to sensor malfunctions or incomplete data due to data acquisition interruptions), resulting in primary filtered data. This avoids invalid data consuming computing resources and affecting analysis results. Interference data filtering removes abnormal data caused by external interference from the primary filtered data (such as power consumption fluctuations due to electromagnetic interference or abnormal environmental data due to sudden environmental changes), resulting in secondary filtered data, improving data accuracy. Normalization processing transforms the three data categories after secondary filtering (different data types have different units, such as device power consumption in microamps and ambient temperature in degrees Celsius) into data with a unified unit and range, eliminating analytical biases caused by unit differences, resulting in normalized data. Classification processing categorizes the normalized data into three types based on their attributes: equipment operation, user behavior, and environmental impact. Each type of data is then organized into a corresponding normalized dataset, which serves as the preliminary analysis data, ensuring clear data classification and standardized format. Normalization processing refers to converting data from different ranges into data within the 0-1 interval, enabling horizontal comparison and fusion analysis of different data types.
[0024] This method addresses the technical challenges of raw data acquisition, such as disorder, interference, inconsistent dimensions, and inability to be directly used for analysis, achieving standardized and high-quality processing of raw data. Through two-stage filtering, invalid and interfering data are effectively eliminated, significantly improving data accuracy and reliability and avoiding subsequent analysis errors caused by invalid or interfering data. Normalization eliminates dimensional differences between different data types, resolving the issue of inability to perform fusion analysis due to different dimensions. Classification clarifies the data structure, facilitating targeted feature extraction for various data types, reducing the difficulty of feature extraction, and improving its efficiency and relevance. Overall, this method's preliminary processing transforms the raw, disordered data into high-quality, standardized, and clearly categorized preliminary analysis data, further enhancing the accuracy and reliability of the entire power control method.
[0025] In one embodiment of the present invention, S2 includes: Based on the preliminary analysis and processing of the data, feature extraction is performed to obtain various types of collected feature data; Feature fusion analysis is performed on feature data collected from multiple categories to obtain feature fusion analysis data; Power demand analysis is performed based on feature fusion analysis data to obtain power demand analysis data. Power device control analysis is performed based on power demand analysis data to obtain power device control analysis data. Power device control is performed based on the power device control analysis data to obtain power device control feedback data.
[0026] The working principle and technical effect of the above technical solution are as follows: This method completes the entire process from preliminary data analysis and processing to power control execution and feedback data acquisition, and is the core link connecting data acquisition and feedback regulation. Based on preliminary data analysis (normalized datasets for equipment, users, and environment), core features related to power device control are extracted from each data type (e.g., battery health features in equipment operation, high-frequency usage features in user behavior, and temperature features in environmental impact). This yields multi-category feature data, focusing on core influencing factors. The multi-category feature data is then fused and analyzed, integrating discrete, multi-dimensional feature data into comprehensive feature fusion analysis data. This eliminates redundancy and conflicts between features, reflecting the combined impact of multiple factors on power control. Based on this feature fusion analysis data, the current power demand of the equipment is analyzed, clarifying the power supply standards and requirements in the current scenario, resulting in power demand analysis data. Furthermore, based on the power demand analysis data and the inherent characteristics of the power devices (e.g., integrated modules, power consumption range), the control logic and parameters of the power devices are analyzed and determined, yielding power device control analysis data. Power control commands are generated based on the control analysis data, controlling the power devices to perform corresponding control operations (e.g., adjusting output voltage, switching operating modes), and collecting operational feedback data from the power devices during control execution, resulting in power device control feedback data.
[0027] This method addresses the technical problems of disconnect between power control data and control, lack of systematic feature analysis, and one-sided control logic in existing technologies. It achieves systematic processing from data features to power control execution and feedback. Through feature extraction, it focuses on core influencing features, reducing computational load and improving efficiency. Feature fusion analysis eliminates the limitations of single-dimensional features, enabling comprehensive utilization of multi-dimensional features and improving the comprehensiveness and accuracy of power demand analysis. Through power demand analysis and control analysis, it ensures that the control logic and parameters of power devices align with the actual needs of the current equipment, avoiding power waste or functional abnormalities caused by blind control. By collecting control feedback data, it achieves real-time monitoring of power control effects, improving the dynamic adaptability of power control and further ensuring the stability and rationality of power device operation.
[0028] In one embodiment of the present invention, the step of performing feature fusion analysis based on feature data collected from multiple types to obtain feature fusion analysis data includes: The various types of collected feature data are preprocessed to obtain various types of preprocessed data; Feature conflict identification is performed on the various types of preprocessed data to obtain feature conflict identification data; Obtain conflicting and non-conflicting data based on feature conflict identification data; Calculate the ratio of conflict data volume to feature data volume, invert it to obtain the conflict weight coefficient (value range 0, 1). Calculate the ratio of non-conflicting data volume to feature data volume to obtain the non-conflicting weight coefficient (value range 0, 1), and the conflict weight coefficient + non-conflicting weight coefficient = 1; Feature requirement identification is performed on various feature extraction data to obtain feature requirement identification data; Based on characteristic requirements, identify data to obtain both required and non-required data; Calculate the ratio of the required data volume to the total feature data volume to obtain the demand weight coefficient (value range 0, 1). Calculate the ratio of non-demand data volume to feature data volume to obtain non-demand weight coefficient (value range 0, 1), and demand weight coefficient + non-demand weight coefficient = 1; The preprocessed data of various types are weighted and multiplied by the corresponding conflict weight coefficient multiplied by the demand weight coefficient, and the non-conflict weight coefficient multiplied by the non-demand weight coefficient. The calculation results are then compared and fused using multi-dimensional features to obtain feature fusion analysis data.
[0029] The working principle and technical effect of the above technical solution are as follows: This method elaborates on the specific process of feature fusion analysis. The core is to transform discrete multi-dimensional feature data into comprehensive feature fusion analysis data that can be used for power control through weight quantization and fusion calculation, thereby solving the problems of conflict and redundancy among multiple features. Preprocessing of various types of collected feature data (redundancy removal, correction of minor deviations, etc.) yields multi-type preprocessed data, further improving the quality of feature data. Feature conflict identification is performed to identify contradictory information in feature data across different dimensions (e.g., conflicts between device-side display of sleep mode and user-side display of real-time interaction), resulting in conflict identification data, which is then separated into conflicting and non-conflicting data. The ratio of conflicting data, non-conflicting data, to the total number of features is calculated to determine conflict weighting coefficients and non-conflicting weighting coefficients (weighting coefficients reflect the importance of data, taking values of 0 and 1, with a sum of 1). Non-conflicting data has a higher weight, reducing the impact of conflicting data on the fusion result. Simultaneously, feature demand identification distinguishes between demand data related to power control and irrelevant non-demand data, calculating corresponding demand weighting coefficients and non-demand weighting coefficients. Demand data has a higher weight, highlighting core influencing factors. The multi-type preprocessed data is then weighted and multiplied with the corresponding combined weighting coefficients (conflict multiplied by demand, non-conflict multiplied by non-demand), and then integrated through multi-dimensional fusion comparison to obtain comprehensive feature fusion analysis data. This ensures that the fusion result comprehensively and accurately reflects the combined impact of multi-dimensional factors on power control. The weighting coefficients are set to 0 or 1, with a total value of 1, to ensure the rationality and comparability of the weighted calculation.
[0030] This method addresses the technical problems of existing feature fusion technologies, such as lack of conflict handling, lack of weight differentiation, and one-sided fusion results, achieving accurate and reasonable fusion of multi-dimensional feature data. Through feature conflict identification and weight quantization, it effectively resolves conflicts between features of different dimensions, reduces the interference of conflicting data on the fusion results, and improves the accuracy of the fused data. Through feature requirement identification and weight quantization, it highlights core features related to power control, eliminates interference from irrelevant features, and improves the relevance of the fused data. Through weighted multiplication and multi-dimensional fusion comparison, it achieves the systematic integration of discrete feature data, transforming multi-dimensional single features into comprehensive features, avoiding the limitations of single feature analysis, and improving the comprehensiveness and accuracy of feature fusion analysis. The final feature fusion analysis data further improves the accuracy and adaptability of power control, solving the control decision deviation problem caused by traditional feature fusion.
[0031] In one embodiment of the present invention, the step of performing power demand analysis based on feature fusion analysis data to obtain power demand analysis data includes: Based on the feature fusion analysis data, feature power demand categories are decomposed to obtain equipment functional power demand information, user personalized power demand information, and environment adaptation power demand information. Generate characteristic power requirement information based on equipment functional power requirement information, user-personalized power requirement information, and environment-adaptive power requirement information; Based on the characteristic power demand information, and combined with the weight coefficients and feature correlations in the characteristic fusion analysis data, power demand threshold quantification and priority ranking are performed to generate power demand analysis data that includes power demand thresholds, demand priorities, and supply constraints.
[0032] The working principle and technical effects of the above technical solution are as follows: This method describes the specific process of power demand analysis. The core is to decompose, integrate, and quantify the power demand of the equipment based on feature fusion analysis data. According to the feature fusion analysis data (multi-dimensional comprehensive features), three types of power demand information are decomposed according to different demand sources: equipment functional power demand (power required to ensure the normal operation of each core function of the equipment, such as heart rate monitoring, screen display, etc.), user personalized power demand (customized power demand based on user usage habits, such as power guarantee for frequently used functions), and environmental adaptation power demand (power adjustment demand based on current environmental parameters, such as power consumption limitations in high-temperature environments). The three types of power demand information are integrated to generate preliminary feature power demand information, which comprehensively covers the power demand of equipment, users, and environment. Combining the weight coefficients in the feature fusion analysis data (reflecting the importance of various features) and feature correlation relationships (mutual influence between various demands), the feature power demand information is threshold quantified (clarifying the power range of various demands) and prioritized (clarifying core demands and secondary demands), finally generating power demand analysis data that includes power demand thresholds, demand priorities, and supply constraints (such as battery power limitations).
[0033] This method addresses the technical problems of existing power demand analysis technologies, such as their single dimension, lack of quantitative standards, and lack of priority differentiation, leading to unreasonable power supply. It achieves comprehensive, accurate, and systematic power demand analysis. By breaking down demand into categories, it comprehensively covers power demands from three dimensions: equipment, users, and environment, avoiding the one-sidedness of single-dimensional demand analysis. Through threshold quantification, it clarifies the power range of various demands, providing quantifiable standards for power control and avoiding blind power supply. By prioritizing, it identifies core and secondary demands, ensuring that core demands (such as basic equipment functions and high-frequency user demands) receive priority power guarantees, while rationally allocating power to secondary demands, avoiding power waste. The resulting power demand analysis data ensures that power control aligns with actual needs, improving the rationality and accuracy of power supply, while also considering equipment functional stability, user experience, and environmental adaptability, reducing battery life loss caused by ineffective power supply.
[0034] In one embodiment of the present invention, the step of controlling the power device based on the power device control analysis data to obtain power device control feedback data includes: Power control commands are generated based on power device control analysis data, and power control is adjusted according to the power control commands to obtain power control adjustment data. Based on the power control adjustment data, a full-dimensional feedback acquisition mechanism is activated to collect three major categories of feedback data: equipment operation feedback data, power control effect feedback data, and demand matching degree feedback data. The three main categories of feedback data collected are preprocessed and integrated to obtain power device control feedback data.
[0035] The working principle and technical effects of the above technical solution are as follows: This method describes the specific process of power device control execution and feedback data acquisition. The core is to convert power control analysis data into control commands and execute them, while simultaneously collecting feedback data on the control effect. Based on the power device control analysis data (including control logic, control parameters, etc.), power control commands that can be recognized and executed by the power device are generated. The control commands correspond to various operations of the power device (such as adjusting output voltage, switching working modes, turning on / off redundant modules, etc.). Power control adjustment operations are executed according to the control commands, and relevant data during the adjustment process are recorded to obtain power control adjustment data, reflecting the execution status of the control operation. Then, a full-dimensional feedback acquisition mechanism is activated to simultaneously collect three types of feedback data: equipment operation feedback data (real-time operating status of each functional module and power device of the equipment), power control effect feedback data (power consumption, operating stability, etc. of the device after power control), and demand matching feedback data (the degree to which the control effect matches the needs of the equipment, user, and environment). The collected three types of feedback data are preprocessed (filtering invalid interference and correcting deviations) and integrated into unified power device control feedback data, clearly reflecting the actual effect and existing problems of the current power control.
[0036] This method addresses the technical problems of existing power control technologies, which only execute control commands, lack comprehensive feedback, and fail to provide insight into the control effect. It achieves coordinated power control execution and comprehensive feedback acquisition. By transforming control analysis data into specific control commands, it ensures the standardization and accuracy of power control operations, avoiding blind control. Through a comprehensive feedback acquisition mechanism, it fully captures various feedback information after control execution, overcoming the limitations of single feedback and enabling precise understanding of the actual effect of power control, equipment operating status, and demand matching. Preprocessing and integrating the feedback data improves its quality and usability, ensuring that subsequent adjustments can specifically address problems encountered during control, enhancing the dynamic adaptability and accuracy of power control, further guaranteeing the stability of power device operation, and reducing power consumption waste and equipment failure risks caused by improper control.
[0037] In one embodiment of the present invention, S3 includes: The control effect is analyzed based on the control feedback data of the power devices to obtain control effect analysis data. Determine the corresponding effect data of the control parameters based on the control effect analysis data; The corresponding effects are evaluated to determine their level, and then the control parameters are evaluated to determine their level, thus obtaining the effect parameter level data. Adjust the control parameters based on the effect parameter level data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
[0038] The working principle and technical effect of the above technical solution are as follows: This method completes the analysis and judgment of power control effect and the continuous adjustment of parameters, forming a closed-loop optimization to ensure that the control parameters always meet the target requirements of the equipment. Based on the collected power device control feedback data, a comprehensive analysis of the actual effect of the current power control is conducted (such as analyzing control deviation, demand matching degree, and equipment operation stability). This yields control effect analysis data, clarifying the strengths and weaknesses of the current control effect and identifying existing problems. Based on this data, the control effect corresponding to each set of control parameters is determined, obtaining corresponding effect data and establishing a correlation between control parameters and control effect. The control effect is graded (e.g., excellent, qualified, unqualified), and the grade of the corresponding control parameter is deduced from the effect grade, yielding effect parameter grade data and clarifying the suitability of the current control parameters. Based on the effect parameter grade data, the control parameters are adjusted accordingly (e.g., significantly adjusting parameters if the effect is unqualified, and fine-tuning parameters if the effect is basically qualified). The power control process is then re-executed after adjustment, collecting new feedback data, and the effect analysis and judgment are performed again. This process is repeated until the control adjustment parameters of the power device meet the target requirements of the current smart wearable device, achieving closed-loop optimization of power control.
[0039] This method addresses the technical problems of existing power control technologies, such as lack of effect analysis, lack of level determination, fixed parameters, and inability to dynamically adapt to changing demands. It achieves dynamic closed-loop adjustment and optimization of power control parameters. Through control effect analysis, it accurately identifies problems in the current control process, avoiding blind adjustments. By determining effect and parameter levels, it clarifies the adaptability of control parameters, improving the targeting of adjustments. Continuous parameter adjustment and closed-loop circulation ensure that control parameters dynamically adapt to changes in equipment operating status, user needs, and environmental changes, avoiding the poor adaptability problems caused by fixed parameters. Ultimately, it achieves optimal adaptation of power device control parameters, improving the accuracy and stability of power control, further reducing ineffective power consumption, ensuring the stable operation of core equipment functions, enhancing the user experience, and extending the equipment's battery life.
[0040] In one embodiment of the present invention, the step of analyzing the control effect based on the power device control feedback data to obtain control effect analysis data includes: Deep analysis of power device control feedback data is performed to obtain equipment operation deviation data, power control parameter deviation data, and demand matching deviation data. Calculate the corresponding effect deviation value based on the three types of deviation data; The three types of effect deviation values are weighted and fused to obtain control effect deviation data; The control effect deviation data is the control effect analysis data.
[0041] The working principle and technical effects of the above technical solution are as follows: This method elaborates on the specific process of control effect analysis. The core is to quantitatively evaluate the actual effect of current power control through deviation analysis. Deep analysis of power device control feedback data is performed, separating three types of core deviation data: equipment operation deviation data (device deviation between actual and expected operating states, such as power device temperature deviation, functional module operation deviation, etc.), power control parameter deviation data (device deviation between actual operating parameters and control command set parameters, such as output voltage deviation, current deviation, etc.), and demand matching deviation data (device deviation between control effect and equipment, user, and environmental requirements, such as power supply deviation and demand threshold deviation). For each type of deviation data, the corresponding effect deviation value is calculated to quantitatively reflect the severity of each type of deviation. Combining the importance of each type of deviation (e.g., power control parameter deviation has a higher weight), the three types of effect deviation values are weighted and fused to obtain comprehensive control effect deviation data. This control effect deviation data is the control effect analysis data, which can comprehensively and quantitatively reflect the overall situation of current power control effect, clearly identifying the core source and severity of deviations.
[0042] This method addresses the technical problems of existing technologies, such as limited analytical dimensions for control effects, lack of quantitative standards, and inability to accurately pinpoint issues. It achieves comprehensive, quantitative, and precise analysis of control effects. By separating three types of core deviation data, it comprehensively covers all evaluation dimensions of power control effects, avoiding the limitations of single-deviation analysis and accurately identifying core problems in the control process. Through calculating effect deviation values and weighted fusion, qualitative effect evaluations are transformed into quantitative deviation data, avoiding judgment bias and blind adjustment caused by subjective evaluations. In-depth analysis and deviation fusion clearly reveal the impact of various deviations on control effects, ensuring that parameter adjustments can specifically address core deviation problems, thus improving the accuracy and efficiency of parameter adjustments. Overall, the analysis using this method further improves the stability and adaptability of power control, reducing power consumption waste and equipment failure risks caused by control deviations.
[0043] According to one embodiment of the present invention, the system includes: The preliminary analysis module is used to collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data. The power control module is used to perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data, and to perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. The feedback adjustment module is used to analyze the control effect and adjust the control parameters based on the control feedback data of the power device until the control adjustment parameters of the power device meet the target requirements of the current smart wearable device.
[0044] The working principle and technical effects of the above-mentioned technical solution are as follows: This method solves the problem of messy raw data that cannot be directly used for control analysis by completing the collection and preliminary processing of multi-dimensional data; by performing feature fusion on the pre-processed data, the discrete multi-dimensional data is transformed into comprehensive feature information that can be used for power control; then, based on this fused information, power demand analysis and power device control are completed, realizing the transformation from data to control commands; by monitoring and analyzing the actual effect of power control, it is determined whether the control parameters are suitable for the target requirements of the equipment (such as low power consumption, functional stability, etc.). If not, the parameters are continuously adjusted, forming a closed loop of collection, analysis, control, feedback, and adjustment, ensuring that the control effect always matches the actual operating requirements of the equipment. Among them, the target requirements refer to the core requirements of smart wearable devices in the current scenario, which take into account both normal operation and low power consumption, and cover the adaptation requirements of multiple dimensions of equipment, users, and environment.
[0045] This method addresses the technical problems of existing smart wearable devices, such as single-dimensional power device control, lack of closed-loop adjustment, and poor adaptability, achieving intelligent control of power devices throughout the entire process. Through closed-loop logic, it avoids the problems of excessive or insufficient power supply caused by traditional fixed-parameter control, improving the accuracy and adaptability of power control. Simultaneously, it integrates multi-dimensional data for analysis, breaking through the limitations of single-data control, enhancing the comprehensiveness and rationality of power control, thereby improving the operational stability of smart wearable devices, reducing battery life loss due to ineffective power consumption, ensuring the stable operation of core device functions, and balancing user experience with device battery life.
[0046] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A power device control method for a smart wearable device, characterized in that, The method includes: S1. Collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data; S2. Perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data. Perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. S3. Analyze the control effect and adjust the control parameters based on the power device control feedback data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
2. The power device control method for a smart wearable device according to claim 1, characterized in that, S1 includes: By using smart wearable devices to collect multi-dimensional operational data of devices, data can be obtained from the device itself. By retrieving multi-dimensional user behavior data through smart wearable devices, user-end collected data can be obtained. Environmental data is obtained by collecting multi-dimensional parameters of the environment through smart wearable devices. Preliminary analysis and processing are performed on the data collected from the device, user, and environment to obtain preliminary analysis and processing data.
3. The power device control method for a smart wearable device according to claim 2, characterized in that, The preliminary analysis and processing of data collected from the device, user, and environment ends to obtain preliminary analysis and processing data includes: Invalid data is filtered from data collected from the device, user, and environment to obtain primary filtered data. The primary filtered data is subjected to interference filtering to obtain the secondary filtered data. Normalize the data processed by the secondary filtering to obtain normalized data; Based on the normalized data, equipment, users, and environment are classified to obtain equipment operation category, user behavior category, and environmental impact category; The normalized data is classified according to equipment operation, user behavior, and environmental impact to obtain the corresponding normalized data set, which is the preliminary analysis and processing data.
4. The power device control method for a smart wearable device according to claim 1, characterized in that, S2 includes: Based on the preliminary analysis and processing of the data, feature extraction is performed to obtain various types of collected feature data; Feature fusion analysis is performed on feature data collected from multiple categories to obtain feature fusion analysis data; Power demand analysis is performed based on feature fusion analysis data to obtain power demand analysis data. Power device control analysis is performed based on power demand analysis data to obtain power device control analysis data. Power device control is performed based on the power device control analysis data to obtain power device control feedback data.
5. The power device control method for a smart wearable device according to claim 4, characterized in that, The step of performing feature fusion analysis based on feature data collected from multiple types to obtain feature fusion analysis data includes: The various types of collected feature data are preprocessed to obtain various types of preprocessed data; Feature conflict identification is performed on the various types of preprocessed data to obtain feature conflict identification data; Obtain conflicting and non-conflicting data based on feature conflict identification data; Calculate the ratio of conflicting data to the total amount of feature data, and then invert the ratio to obtain the conflict weight coefficient. Calculate the ratio of non-conflicting data volume to the total feature data volume to obtain the non-conflicting weight coefficient; Feature requirement identification is performed on various feature extraction data to obtain feature requirement identification data; Based on characteristic requirements, identify data to obtain both required and non-required data; Calculate the ratio of the required data volume to the total feature data volume to obtain the demand weight coefficient; Calculate the ratio of non-demand data volume to feature data volume to obtain the non-demand weight coefficient; The preprocessed data of various types are weighted and multiplied by the corresponding conflict weight coefficient multiplied by the demand weight coefficient, and the non-conflict weight coefficient multiplied by the non-demand weight coefficient. The calculation results are then compared and fused using multi-dimensional features to obtain feature fusion analysis data.
6. The power device control method for a smart wearable device according to claim 4, characterized in that, The step of performing power demand analysis based on feature fusion analysis data to obtain power demand analysis data includes: Based on the feature fusion analysis data, feature power demand categories are decomposed to obtain equipment functional power demand information, user personalized power demand information, and environment adaptation power demand information. Generate characteristic power requirement information based on equipment functional power requirement information, user-personalized power requirement information, and environment-adaptive power requirement information; Based on the characteristic power demand information, and combined with the weight coefficients and feature correlations in the feature fusion analysis data, power demand threshold quantification and priority ranking are performed to generate power demand analysis data.
7. The power device control method for a smart wearable device according to claim 4, characterized in that, The step of controlling the power device based on the power device control analysis data to obtain power device control feedback data includes: Power control commands are generated based on power device control analysis data, and power control is adjusted according to the power control commands to obtain power control adjustment data. Based on the power control adjustment data, a full-dimensional feedback acquisition mechanism is activated to collect three major categories of feedback data: equipment operation feedback data, power control effect feedback data, and demand matching degree feedback data. The three main categories of feedback data collected are preprocessed and integrated to obtain power device control feedback data.
8. The power device control method for a smart wearable device according to claim 1, characterized in that, S3 includes: The control effect is analyzed based on the control feedback data of the power devices to obtain control effect analysis data. Determine the corresponding effect data of the control parameters based on the control effect analysis data; The corresponding effects are evaluated to determine their level, and then the control parameters are evaluated to determine their level, thus obtaining the effect parameter level data. Adjust the control parameters based on the effect parameter level data until the power device control adjustment parameters meet the target requirements of the current smart wearable device.
9. The power device control method for a smart wearable device according to claim 8, characterized in that, The step of analyzing the control effect based on the power device control feedback data to obtain control effect analysis data includes: Deep analysis of power device control feedback data is performed to obtain equipment operation deviation data, power control parameter deviation data, and demand matching deviation data. Calculate the corresponding effect deviation value based on the three types of deviation data; The three types of effect deviation values are weighted and fused to obtain control effect deviation data; The control effect deviation data is the control effect analysis data.
10. A power device control system for a smart wearable device, characterized in that, The system includes: The preliminary analysis module is used to collect and perform preliminary analysis and processing of various types of data through smart wearable devices to obtain preliminary analysis and processing data. The power control module is used to perform feature fusion analysis based on the preliminary analysis and processing data to obtain feature fusion analysis data, and to perform power analysis and control based on the feature fusion analysis data to obtain power device control feedback data. The feedback adjustment module is used to analyze the control effect and adjust the control parameters based on the control feedback data of the power device until the control adjustment parameters of the power device meet the target requirements of the current smart wearable device.