Sensor error calibration method and system of smart watch

Abstract

The invention provides a sensor error calibration method and system for a smart watch, and is applied to the field of data processing. The intelligent watch is used for monitoring the sensor in real time, collecting trend sensing data and detecting whether the data shows the deviation trend or not based on the preset standard, so that the accuracy of sensor anomaly detection is improved, when data deviation is detected, abnormal values are recognized through standard deviation calculation and classified, and the accuracy of sensor anomaly detection is improved. Comprising short-term sudden anomalies, long-term drift and outliers, so as to accurately analyze error sources, then judge whether abnormal values can be repaired or not, if yes, adopt linear, nonlinear or periodic drift compensation according to abnormal types, and dynamically adjust sensing error coefficients in combination with environmental factors to realize self-adaptive calibration, so that sensor drift can be effectively detected, and the detection accuracy is improved. Data error accumulation caused by long-term use is prevented, it is ensured that the smart watch can maintain high-precision measurement in various environments, and user experience and equipment reliability are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly to a method and system for calibrating sensor errors of a smart watch. Background Art

[0002] Sensors in smart watches (such as accelerometers, gyroscopes, heart rate sensors, temperature and humidity sensors, etc.) are used to detect and record various physiological and motion data of users. These sensors capture physical signals and convert them into electrical signals, which are then processed by the processing unit of the smart watch and finally provide feedback to the user.

[0003] However, over time and with changes in the usage environment, the performance of the sensors may change, which is usually manifested as a "drift" phenomenon. Because the micro-components inside the sensors may be physically damaged or aged, resulting in a drift of the output value. For example, the offset of the gyroscope will cause inaccurate direction calculation, and the drift of the accelerometer will cause errors in gait monitoring. Summary of the Invention

[0004] The present invention aims to solve the problem of how to effectively detect sensor drift and compensate it in a timely manner to ensure accurate data after long-term use, and provides a method and system for calibrating sensor errors of a smart watch.

[0005] The present invention adopts the following technical means to solve the technical problems: The present invention provides a method for calibrating sensor errors of a smart watch, including: Based on the preset usage duration of the smart watch, the smart watch monitors a preset sensor in real time and collects corresponding trend sensing data; Judge whether the trend sensing data shows a preset deviation trend; If so, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points that exceed the standard deviation range as outliers in the trend sensing data, and classify the outliers. Among them, the outlier classification specifically includes short-term sudden outliers, long-term drift, and outliers; Judge whether the outliers can be data-repaired; If it can, then according to the outlier classification, perform drift compensation on the outliers, dynamically calibrate the sensing error coefficient of the smart watch, use the environmental factors pre-collected by the smart watch as the compensation input of the sensing error coefficient, and adaptively correct the sensing error coefficient. Among them, the drift compensation specifically includes linear drift compensation, non-linear drift compensation, and periodic drift compensation, and the environmental factors specifically include temperature, humidity, and air pressure.

[0006] Further, in the step of marking the data points outside the standard deviation range as outliers in the trend sensing data, the following steps are also included: Based on the number of outliers, collect the proportion data of the number of outliers in the trend sensing data, and identify the distribution information of the outliers according to the proportion data; Judge whether the distribution information matches a preset specific condition, where the specific condition specifically includes outliers concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors; If so, detect the working environment of the sensor, calculate the accuracy error of the sensor based on the working environment, and obtain the corresponding abnormal pattern from the distribution information.

[0007] Further, before the step of classifying the outliers into different anomaly categories, the following steps are also included: Extract the data anomaly characteristics of the outliers, and compare the output data of different sensors in the smart watch, where the data anomaly characteristics specifically include the fluctuation amplitude, change speed, and change direction; Judge whether the output data detects a preset associated anomaly; If so, identify the communication protocol interface between the different sensors, obtain the bus communication status of the smart watch based on the communication protocol interface, and generate the network communication quality of the smart watch in real time according to the bus communication status, where the bus communication status specifically includes noise interference, data transmission delay, and connection loss, and the network communication quality is specifically the communication quality when data is transmitted between different sensors.

[0008] Further, in the step of using the environmental factors pre-collected by the smart watch as the compensation input of the sensing error coefficient, the following steps are also included: Based on the fluctuating changes of the environmental parameters, identify the compensation requirements of the sensing error coefficient, where the fluctuating changes specifically include the temperature and humidity fluctuation range, air pressure change, and electromagnetic interference; Judge whether the compensation requirements match a preset compensation strategy; If not, obtain the usage scenario of the smart watch by the user, adaptively optimize the compensation strategy according to the usage scenario, and dynamically adjust the influence coefficient of the error of a single sensor on the compensation strategy based on the preset complementarity between different sensors, where the usage scenario specifically includes a sports scenario, an office and daily life scenario, and an extreme weather scenario.

[0009] Further, in the step of judging whether the trend sensing data shows a preset deviation trend, the following steps are also included: Detect corresponding instantaneous abnormal events from the trend sensing data based on a preset trend period, where the trend period specifically includes a global trend and a local trend; Determine whether the instantaneous abnormal event exhibits a preset periodic fluctuation; If so, obtain the regular change information corresponding to the trend sensing data through the instantaneous abnormal event, and construct trend change points corresponding to the periodic fluctuation according to the regular change information.

[0010] Further, in the step of determining whether the outlier can be data-repaired, it further includes: Calculate the data missing rate of the time window based on the time window corresponding to the outlier; Determine whether the data missing rate exceeds a preset missing value; If so, identify the impact content of the missing data on the final sensing data through the outlier, and according to the impact content, guide the user to re-perform additional measurements on the final sensing data. Record the corresponding abnormal cause in the smart watch based on the abnormal data segment of the outlier, where the abnormal cause specifically includes sensor detachment, signal loss, and external environmental factors.

[0011] Further, in the step of collecting corresponding trend sensing data by the smart watch for real-time monitoring of a preset sensor based on a preset usage duration of the smart watch, it further includes: Detect the time window where the outlier occurs based on the preset statistical characteristics of the sensor data, where the statistical characteristics specifically include mean, variance, and standard deviation; Determine whether the number of the time windows reaches a preset threshold; If so, regularly trigger the self-calibration mode preset for the sensor according to the usage duration, reduce the error accumulation of the sensor through the self-calibration mode, activate the calibration tutorial preset for the smart watch, and guide the user to manually calibrate the smart watch according to the calibration tutorial.

[0012] The present invention also provides a sensor error calibration system for a smart watch, including: An acquisition module for collecting corresponding trend sensing data by the smart watch for real-time monitoring of a preset sensor based on a preset usage duration of the smart watch; A judgment module for judging whether the trend sensing data exhibits a preset deviation trend; An execution module, which is used to, if so, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points that exceed the standard deviation range as outliers in the trend sensing data, and classify the outliers, where the outlier classification specifically includes short-term sudden outliers, long-term drift, and outliers; A second judgment module, which is used to judge whether the outliers can be data-repaired; A second execution module, which is used to, if possible, perform drift compensation on the outliers according to the outlier classification, dynamically calibrate the sensing error coefficient of the smart watch, use the environmental factors pre-collected by the smart watch as the compensation input of the sensing error coefficient, and adaptively correct the sensing error coefficient, where the drift compensation specifically includes linear drift compensation, non-linear drift compensation, and periodic drift compensation, and the environmental factors specifically include temperature, humidity, and air pressure.

[0013] Further, the execution module further includes: An identification unit, which is used to collect the proportion data of the abnormal quantity in the trend sensing data based on the abnormal quantity of the outliers, and identify the distribution information of the outliers according to the proportion data; A judgment unit, which is used to judge whether the distribution information matches a preset specific condition, where the specific condition specifically includes abnormal fluctuations caused by outliers concentrated in a specific time period or specific environmental factors; An execution unit, which is used to, if so, detect the working environment of the sensor, calculate the precision error of the sensor according to the working environment, and obtain the corresponding abnormal rule from the distribution information.

[0014] Further, it further includes: An extraction module, which is used to extract the data abnormal characteristics of the outliers and compare the output data of different sensors in the smart watch, where the data abnormal characteristics specifically include fluctuation amplitude, change speed, and change direction; A third judgment module, which is used to judge whether the output data detects a preset associated abnormality; A third execution module, which is used to, if so, identify the communication protocol interface between the different sensors, obtain the bus communication status of the smart watch based on the communication protocol interface, and generate the network communication quality of the smart watch in real time according to the bus communication status, where the bus communication status specifically includes noise interference, data transmission delay, and connection loss, and the network communication quality is specifically the communication quality when data is transmitted between different sensors.

[0015] The present invention provides a method and system for calibrating the sensor error of a smart watch, which has the following beneficial effects: The present invention monitors sensors in real time through a smart watch, collects trend sensing data, and detects whether the data shows a deviation trend based on a preset standard, thereby improving the accuracy of sensor anomaly detection. When a data deviation is detected, outlier values are identified through standard deviation calculation and classified, including short-term sudden anomalies, long-term drifts, and outliers, to accurately analyze the error sources. Subsequently, it is determined whether the outlier values can be repaired. If they can be repaired, linear, non-linear, or periodic drift compensation is adopted according to the anomaly type, and the sensing error coefficient is dynamically adjusted in combination with environmental factors (such as temperature, humidity, and air pressure) to achieve adaptive calibration, which can effectively detect sensor drift, prevent data error accumulation caused by long-term use, ensure that the smart watch can maintain high-precision measurement in various environments, and improve user experience and device reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flowchart of an embodiment of the sensor error calibration method for the smart watch of the present invention; Figure 2 It is a structural block diagram of an embodiment of the sensor error calibration system for the smart watch of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments with reference to the drawings.

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0019] Referring to the attached Figure 1 , a sensor error calibration method for a smart watch in an embodiment of the present invention includes: S1: Based on the preset usage duration of the smart watch, the smart watch monitors a preset sensor in real time and collects corresponding trend sensing data; S2: Determine whether the trend sensing data shows a preset deviation trend; S3: If so, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points outside the standard deviation range as outlier values in the trend sensing data, and classify the outlier values, where the anomaly classification specifically includes short-term sudden anomalies, long-term drifts, and outliers; S4: Determine whether the outlier can be data-repaired; S5: If yes, perform drift compensation on the outlier according to the anomaly classification, dynamically calibrate the sensing error coefficient of the smartwatch, use the environmental factors pre-collected by the smartwatch as the compensation input for the sensing error coefficient, and adaptively correct the sensing error coefficient. Among them, the drift compensation specifically includes linear drift compensation, non-linear drift compensation, and periodic drift compensation, and the environmental factors specifically include temperature, humidity, and air pressure.

[0020] In this embodiment, the system, based on the preset used duration of the smartwatch, monitors the preset sensors in real time through the smartwatch, collects the corresponding trend sensing data, and then the system determines whether these trend sensing data show a preset deviation trend to execute corresponding steps. For example, when the system determines that the trend sensing data collected by the sensor does not show a preset deviation trend, the system will consider that the current measurement accuracy and stability of the sensor still meet the expectations, and there is no obvious drift or abnormal situation. The system will continue to record and store the measurement data according to the existing sensing data processing logic, ensure the continuity and integrity of the data, maintain the existing sensor error compensation strategy, and not perform additional compensation adjustments to avoid overcorrection affecting the measurement result. At the same time, the current measurement environment (such as temperature, humidity, air pressure) and device status are stored so that when an anomaly is detected in the future, it can be compared with the current state to analyze possible influencing factors, and a regular calibration interval is set. Even if there is no drift, a reference comparison can be made according to the preset period to detect potential subtle drift trends in advance. For example, when the system determines that the trend sensing data collected by the sensor shows a preset deviation trend, at this time, the system will consider that there may be drift or abnormal situation in the current measurement accuracy of the sensor. The system will select preset data points from the trend sensing data, calculate the standard deviation of these data points, mark the data points outside the standard deviation range as outliers in the trend sensing data, and classify these outliers. The anomaly classification specifically includes short-term sudden anomalies, long-term drifts, and outliers. By judging whether the trend sensing data deviates from the set standard, the system can timely identify the measurement error of the sensor, prevent incorrect data from affecting the final measurement result. The method of calculating the standard deviation and marking outliers helps to exclude occasional interferences, improve the stability and accuracy of the data. At the same time, classifying the outliers into short-term sudden anomalies, long-term drifts, and outliers enables the system to adopt corresponding processing strategies for different types of anomalies. Short-term sudden anomalies can be processed by smoothing filtering, long-term drifts can trigger an automatic compensation mechanism, and outliers can be used to warn of possible hardware failures of the sensor, improving the fault management ability of the smartwatch. And based on the anomaly classification, the system can adjust the sensor compensation strategy according to the anomaly type. For example, for long-term drifts, a trend compensation algorithm can be used for correction so that the sensor can still maintain high-precision measurement capabilities even after long-term use, thereby improving the reliability and user experience of the smartwatch in complex environments. Then the system determines whether the outliers in the trend sensing data can be data-repaired to execute corresponding steps;For example, when the system determines that the outliers in the trend sensing data cannot be repaired, the system will consider that it may be caused by sensor hardware failure, severe long-term drift, environmental interference exceeding the compensable range, or excessive data loss, resulting in ineffective compensation. The system will store the unrepaired data separately and mark it in the log or data record to avoid affecting the calculation of normal data. If the number of outliers is small, the system can use historical trend data, adjacent data interpolation, or preset default values for compensation to maintain measurement continuity. At the same time, if abnormal data continues to appear, the system can trigger a self-check mechanism to check the working status of the sensor and send a reminder to the user, such as suggesting recalibration, checking the hardware, or replacing the device. And if the smartwatch has multiple built-in sensors, the system can reduce the data weight of the faulty sensor, give priority to using the data of other sensors for calculation, or switch to an alternative measurement mode (such as using a different algorithm or data source); For example, when the system determines that the outliers in the trend sensing data can be repaired, at this time, the system will consider that the degree of data deviation is small and can be compensated in time. The system will perform drift compensation on the outliers according to different abnormal classifications. The drift compensation specifically includes linear drift compensation, non-linear drift compensation, and periodic drift compensation, dynamically calibrating the sensing error coefficient of the smartwatch, and using the environmental factors pre-collected by the smartwatch, which specifically include temperature, humidity, and air pressure, as the compensation input for the sensing error coefficient, and adaptively correcting the sensing error coefficient; By performing drift compensation on the outliers, the system can correct the data in time when the degree of data deviation is small, avoiding the influence of incorrect data on the final measurement result. Linear drift compensation is applicable to long-term stable offsets, non-linear drift compensation can correct complex error changes, and periodic drift compensation can adjust the errors with periodic fluctuations, thus ensuring the long-term stability and accuracy of the data. At the same time, using the environmental factors (such as temperature, humidity, and air pressure) pre-collected by the smartwatch as the compensation input enables the system to dynamically adjust the error calibration strategy under different environmental conditions. This mechanism can effectively reduce the measurement errors caused by external environmental changes, ensuring that the smartwatch can still maintain accurate measurement performance in different scenarios such as high temperature, low temperature, and high humidity. And by adopting an adaptive correction mechanism, the sensing error coefficient can be dynamically adjusted with real-time data, avoiding the influence of long-term error accumulation of the sensor on the measurement result. This not only improves the long-term stability of the data but also reduces the need for frequent calibration or replacement of the device due to the decline in sensor accuracy, thereby extending the service life of the smartwatch and improving the user experience and device reliability.

[0021] It should be noted that preset data points are selected from the trend sensing data, the standard deviation of the data points is calculated, and the data points outside the standard deviation range are marked as outliers in the trend sensing data, and the outliers are classified for anomalies. The specific examples are as follows: Suppose a user wears a smartwatch, and the heart rate sensor of the watch collects data once per second to record the user's heart rate changes; the analysis window set by the system is the data of the most recent 10 minutes (one data point is collected per second, so there are 600 data points), but for the sake of illustration, we only use 10 data points for example; The normal heart rate range of the user at rest is 60 - 80 bpm, but due to some external or internal factors, abnormal heart rate data may occur; for example, the watch is worn too loosely, the sensor ages, the user suddenly exercises vigorously, or there is signal interference, etc., all of which may cause abnormal fluctuations in heart rate data; Hypothetical heart rate data (unit: bpm): 70, 72, 71, 73, 150, 74, 70, 72, 71, 73; First, calculate the mean, Formula for calculating the mean (Mean, μ): where ∑X represents the sum of all data points, and N represents the number of data points; Then calculate the mean: Then calculate the standard deviation, Formula for calculating the standard deviation (Standard Deviation, σ): Calculate the square of the difference between each data point and the mean: (70 - 79.6)² = 92.16; (72 - 79.6)² = 57.76; (71 - 79.6)² = 73.96; (73 - 79.6)² = 43.56; (150 - 79.6)² = 4920.16; (74 - 79.6)² = 31.36; (70 - 79.6)² = 92.16; (72 - 79.6)² = 57.76; (71 - 79.6)² = 73.96; (73 - 79.6)² = 43.56; Sum: 92.16 + 57.76 + 73.96 + 43.56 + 4920.16 + 31.36 + 92.16 + 57.76 + 73.96 + 43.56 = 5486.24; Calculate the standard deviation: Subsequently, set the outlier detection threshold, The set abnormal detection range is as follows: Then the calculation range: Lower limit = 79.6 - 46.84 = 32.76 bpm Upper limit = 79.6 + 46.84 = 126.44 bpm That is, any data outside 32.76 - 126.44 bpm is marked as an outlier; Finally, mark the outliers. In the dataset, only 150 bpm exceeds the set range (greater than 126.44 bpm), so it is marked as an outlier. Classify the outlier 150 bpm: Short-term sudden anomaly: If only one data point is abnormal and the data before and after returns to normal, it may indicate a short-term anomaly caused by exercise, emotional fluctuations, or signal interference; in this case, the system can record it but not perform compensation to avoid interfering with the normal trend analysis; Long-term drift: If the next multiple sets of data are continuously higher than 126.44 bpm, for example, the subsequent data becomes 140, 145, 150, 155, it indicates that the sensor may have drifted or error accumulation occurred, and the system needs to dynamically calibrate the sensing error coefficient; Outlier: If the data point 150 bpm is far beyond the physiologically reasonable range (such as above 300 bpm), it may be due to sensor failure or improper wearing. The system will directly ignore this data point and may prompt the user to check the device; In summary, through the above method, the system can accurately identify outliers, set reasonable thresholds through the standard deviation to prevent false alarms, and classify different types of abnormal situations, enabling the system to adopt targeted compensation strategies to improve the reliability of the measured data. And if it is a short-term sudden anomaly, the system can temporarily not compensate to avoid affecting the overall trend judgment; if it is a long-term drift, the system can dynamically calibrate the sensing error coefficient to improve the data accuracy, while outliers can be directly excluded to prevent incorrect data from affecting the overall analysis result, ensuring the data quality and user experience of the smartwatch.

[0022] It should be added that according to the above abnormal classification, perform drift compensation on the outliers and dynamically calibrate the sensing error coefficient of the smartwatch. The specific example is as follows: Suppose a certain smartwatch is equipped with a temperature sensor to monitor the user's body temperature in order to provide health management suggestions; however, after long-term use, the system finds that the temperature measured by this sensor is 0.5°C higher in a high-temperature environment (such as a hot summer) and 0.4°C lower in a low-temperature environment (such as outdoors in winter); this indicates that there is a long-term drift phenomenon in the sensor, resulting in a large error in the body temperature data, which may mislead the health assessment; First, perform anomaly detection and classification. When analyzing historical data, the system found that the measured values of the temperature sensor continued to be high when the ambient temperature increased and continued to be low when the ambient temperature decreased, and this drift trend repeated continuously with seasonal changes. Therefore, the system marked this type of drift as **"long-term drift"**, rather than accidental short-term sudden anomalies or outliers. Then, formulate a drift compensation strategy. Based on the characteristics of long-term drift, the system adopts a periodic drift compensation method and combines environmental factors (temperature, humidity) to calibrate the error coefficient of the sensor: Establish a temperature-error curve: Through regression analysis of historical data, calculate the error range of the sensor under different ambient temperature conditions; for example: When the ambient temperature is 10°C, the measured body temperature value is 0.4°C lower. When the ambient temperature is 35°C, the measured body temperature value is 0.5°C higher. When the ambient temperature is 22°C, the measurement error is close to 0°C (i.e., no deviation). Adaptive correction of the sensing error coefficient: Combined with the temperature and humidity sensors built into the smartwatch, each time the body temperature is measured, the system will: Read the current ambient temperature; Find the corresponding deviation value in the temperature-error curve; Automatically compensate and calibrate the measurement result of the sensor; For example, at 35°C, the measured body temperature of 37.5°C is automatically corrected to 37.0°C; Finally, check the running effect. After drift compensation, the body temperature values measured by the smartwatch at different ambient temperatures are closer to the true body temperature, improving the accuracy of health monitoring; since the system can dynamically calibrate the sensing error, even after long-term use, the measurement deviation caused by sensor aging can be effectively compensated, extending the service life of the device. In summary, through the above content, by classifying outliers and combining historical trend analysis, the system can adopt linear, non-linear or periodic drift compensation methods to correct the sensing error coefficient; for example, for the long-term drift problem of the temperature sensor in high or low temperature environments, the system constructs a temperature-error curve and adaptively adjusts the measurement data, enabling the smartwatch to maintain high-precision body temperature measurement under different environmental conditions; this compensation mechanism improves the stability of the data and the long-term reliability of the device.

[0023] In this embodiment, in step S3 of marking the data points that exceed the standard deviation range and marking them as outliers in the trend sensing data, it further includes: S31: Based on the number of anomalies of the outliers, collect the proportion data of the number of anomalies in the trend sensing data, and identify the distribution information of the outliers according to the proportion data; S32: Determine whether the distribution information matches a preset specific condition, where the specific condition specifically includes abnormal fluctuations caused by outliers concentrated in a specific time period or specific environmental factors; S33: If so, detect the working environment of the sensor, calculate the accuracy error of the sensor based on the working environment, and obtain the corresponding abnormal pattern from the distribution information.

[0024] In this embodiment, the system collects the proportion data of these outlier quantities in the trend sensing data based on the number of outliers, identifies the distribution information of these outliers according to different proportion data, and then the system determines whether this distribution information matches a pre-set specific condition. The specific condition specifically includes outliers concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors, so as to execute corresponding steps. For example, when the system determines that the distribution information of the outliers cannot match the pre-set specific condition, the system will consider that the occurrence of these outliers is not caused by known patterns or predictable external environmental factors (such as specific time periods, specific environmental factors). The system will appropriately increase the time window or the number of data points to improve the accuracy of the system's judgment. For example, if the current data analysis is based on 10 minutes, it can be changed to 30 minutes or 1 hour of data analysis to capture a wider trend. At the same time, if the distribution of outliers is relatively scattered, it may be necessary to adjust the weight of the standard deviation calculation or the threshold for outlier judgment to prevent over-screening or missing abnormal reports. And if the proportion of outliers continues to increase but the reason is unknown, the system can enter a warning mode, reducing the data credibility, or only for user reference without directly affecting key decisions (such as health warnings). For example, when the system determines that the distribution information of the outliers can match the pre-set specific condition, the system will consider that the occurrence of these outliers is caused by known factors. The system will detect the working environment of the sensor, calculate the accuracy error of the sensor according to different working environments, and obtain the corresponding abnormal pattern from the distribution information. By detecting the working environment of the sensor and calculating the accuracy error according to different environmental conditions, the system can dynamically adjust the calibration parameters of the sensor. For example, if the system detects that the environmental temperature increases by 5°C, resulting in a 0.2% increase in the measurement error, this error can be compensated in real time to ensure that the measurement result is not affected by environmental fluctuations. At the same time, by analyzing the distribution pattern of outliers, the system can identify long-term trends and adjust the error compensation strategy. For example, if the system finds that a certain sensor has a high measurement value in a high-humidity environment, a specific humidity calibration algorithm can be automatically enabled to maintain the accuracy of the measurement data for a long time and extend the effective service life of the device. And if the system cannot determine the source of the abnormality, it may mis-trigger the data repair or compensation mechanism, resulting in unnecessary computational consumption and even data distortion. Based on matching outliers with known environmental factors, the system can perform compensation under the correct conditions, avoiding interference with normal data, thereby improving the overall energy efficiency and reliability of the system.

[0025] It should be noted that detecting the working environment of the sensor, calculating the accuracy error of the sensor according to the working environment, and obtaining the corresponding abnormal pattern from the distribution information are specifically exemplified as follows: Suppose the barometric pressure sensor built into the smartwatch is used to measure the user's altitude; however, in some extreme environments (such as rainy days or humid areas), users report abnormal drift in altitude measurement values; for example, a user is at an altitude of 100 meters, but the watch shows 120 meters, with an error of 20%, seriously affecting the watch's navigation and motion monitoring functions; Problem analysis: The system records the user's historical measurement data and combines it with the environmental sensors to detect the following situations: Abnormal environmental humidity: Through the temperature and humidity sensor built into the smartwatch, it is detected that the humidity of the current environment is as high as 90% (usually when the humidity exceeds 85%, it may affect the reading of the barometric pressure sensor); in contrast, in a normal environment (such as 50% humidity), the measurement error of the watch is smaller and the data is more stable; Subsequently, sensor accuracy error calculation: By analyzing the long-term trend data, the system finds that when the humidity exceeds 85%, the barometric pressure value measured by the sensor is lower than the actual value, resulting in a higher altitude calculated by the watch; further analyzing the historical data, the system fits the relationship between humidity and measurement error: Error = 0.1×(Humidity - 50%); Calculated, when the humidity increases from 50% to 90%, it results in an additional error: 0.1×(90 - 50) = 4 hPa; Since a decrease of 1 hPa in atmospheric pressure will cause the altitude measurement value to increase by 8.3 meters, a 4 hPa error makes the measured height 33.2 meters higher, which is close to the 20% error (i.e., 20 meters) reported by the user; Obtain abnormal patterns: By analyzing the trend sensing data, the system finds that this anomaly only occurs in environments where the humidity is higher than 85%, meeting the preset abnormal classification conditions; the system further analyzes and finds that the higher the humidity, the greater the measurement deviation, but this phenomenon has a stable trend and can be corrected through environmental compensation; Subsequently, implement compensation measures: After the smartwatch identifies the anomaly, it activates the humidity compensation mechanism: According to the humidity value of 90% measured by the environmental sensor, apply the compensation model: Altitude correction = Calculated altitude - (Error × 8.3) Altitude correction = Calculated altitude - (Error × 8.3) Altitude correction = Calculated altitude - (Error × 8.3) where the error = 4 hPa, and the corresponding altitude error is approximately 33.2 meters; After compensation, the altitude measured by the watch is corrected from 120 meters to 100 meters, returning to normal; Finally, dynamically adjust the sensor error coefficient: The system records the current humidity information of 90% in the error compensation database and automatically applies the correction parameters in future similar environmental conditions to improve the compensation accuracy; if the humidity reaches 95% or 100% in the future, the system can predict in advance that the error may intensify and adaptively adjust the compensation parameters to further optimize the data accuracy; That is, in a high-humidity environment, the smart watch can still obtain accurate altitude data without affecting functions such as outdoor navigation and sports recording. At the same time, the compensation mechanism can adaptively correct sensing errors, avoid the accumulation of measurement drifts caused by environmental changes, and the watch can automatically adjust sensor data without manual calibration by the user, enhancing the level of intelligence. In summary, through the above content, the system detects the working environment (such as humidity) of the sensor, calculates the error and extracts the abnormal pattern. The system can accurately identify the source of the abnormality and optimize the data quality through automatic compensation. This method is applicable to various environment-sensitive sensors (such as temperature, pressure, humidity, acceleration sensors, etc.), ensuring high-precision measurement under different environmental conditions and improving the intelligence level and long-term stability of the device.

[0026] In this embodiment, before step S3 of classifying the abnormal values, the following steps are further included: S301: Extract the data abnormal characteristics of the abnormal values and compare the output data of different sensors in the smart watch. Among them, the data abnormal characteristics specifically include the fluctuation amplitude, change speed, and change direction. S302: Determine whether a preset associated abnormality is detected in the output data. S303: If so, identify the communication protocol interface between the different sensors, obtain the bus communication status of the smart watch based on the communication protocol interface, and generate the network communication quality of the smart watch in real time according to the bus communication status. Among them, the bus communication status specifically includes noise interference, data transmission delay, and connection loss, and the network communication quality is specifically the communication quality when data is transmitted between different sensors.

[0027] In this embodiment, the system extracts the data anomaly features of the outliers. The data anomaly features specifically include the fluctuation amplitude, change speed, and change direction. By comparing the output data of different sensors in the smartwatch, the system then determines whether these output data detect a preset associated anomaly to execute corresponding steps. For example, when the system determines that the output data of different sensors in the smartwatch do not detect a preset associated anomaly, the system will consider that the current outlier may be a short-term error or accidental fluctuation, rather than being caused by environmental factors, equipment failures, or systematic errors. The system will temporarily store the current outlier and continue to collect data within the subsequent time window to observe whether there is a persistent deviation. For example, if the heart rate sensor reading suddenly soars to 180 bpm during a certain measurement, but there are no anomalies in the acceleration sensor and skin resistance sensor, it may be a mismeasurement. The system will verify whether the data returns to normal within the next 10 seconds. At the same time, if the outlier does not trigger an associated anomaly but appears multiple times in a short period, the system will record this data and mark it as a "low-priority anomaly" for review during subsequent data analysis. For example, if the smartwatch of a certain user shows short-term heart rate jumps during morning measurements for three consecutive days, although no associated anomaly is detected, the system will still record it for further analysis. For example, when the system determines that the output data of different sensors in the smartwatch detect a preset associated anomaly, the system will consider that the current outlier is caused by environmental factors, equipment failures, or systematic errors. The system will identify the communication protocol interfaces between different sensors and, based on these communication protocol interfaces, obtain the bus communication status of the smartwatch. The bus communication status specifically includes noise interference, data transmission delay, and connection loss. According to different bus communication statuses, the system will generate the network communication quality of the smartwatch in real time. The network communication quality is specifically the communication quality when data is transmitted between different sensors. By analyzing the communication protocol interfaces and bus communication statuses between different sensors, the system can determine whether the anomaly is caused by environmental factors, equipment failures, or systematic errors. This process helps to accurately locate the source of the anomaly, avoid misidentifying hardware failures or communication anomalies as sensor drift or short-term fluctuations, and at the same time can dynamically evaluate the integrity and accuracy of sensor data during transmission. If the system finds that the data is affected by poor communication quality, it can take measures such as redundant verification, automatic retransmission, or signal enhancement to ensure data stability. For example, if the data transmission of a certain sensor has a high delay, the system can preferentially use the data of other sensors or perform data compensation to reduce the impact of the anomaly, and can automatically adjust the data processing strategy based on the real-time communication quality assessment. For example, in an environment with high signal noise, the system can reduce the sensor sampling rate to reduce false alarms, or enable redundant sensors for data compensation, thereby improving the measurement accuracy. This adaptive optimization ability enables the smartwatch to maintain high-precision operation in complex environments and improve the user experience.

[0028] In this embodiment, in step S5 of using the environmental factors pre-collected by the smart watch as the compensation input of the sensing error coefficient, the following steps are further included: S51: Based on the fluctuating changes of the environmental parameters, identify the compensation requirements of the sensing error coefficient, where the fluctuating changes specifically include the temperature and humidity fluctuation range, air pressure change, and electromagnetic interference; S52: Determine whether the compensation requirements match a preset compensation strategy; S53: If not, obtain the usage scenario of the smart watch by the user, adaptively optimize the compensation strategy according to the usage scenario, and dynamically adjust the influence coefficient of the error of a single sensor on the compensation strategy based on the preset complementarity between different sensors, where the usage scenario specifically includes a sports scenario, an office and life scenario, and an extreme weather scenario.

[0029] In this embodiment, the system identifies the compensation requirements for the sensing error coefficient based on the fluctuating changes in environmental parameters, which specifically include the temperature and humidity fluctuation range, air pressure change, and electromagnetic interference. Then, the system determines whether the compensation requirements match the pre-set compensation strategy to execute corresponding steps. For example, when the system determines that the compensation requirements for the sensing error coefficient can match the pre-set compensation strategy, the system will consider that the source of the current error is known, and the system already has a corresponding compensation scheme for error correction. The system will calculate the optimal compensation parameters according to the matched compensation strategy and the current environmental parameter fluctuation situation. For example, if the temperature increase causes the sensor measurement value to be too high, the system can introduce a temperature compensation factor to dynamically adjust the measurement value. If the electromagnetic interference increases, the system can use a filtering algorithm to reduce the error, or temporarily increase the signal sampling times to improve data accuracy. At the same time, one or more of linear compensation, non-linear compensation, or periodic drift compensation are selected for adjustment. For example, it is applicable to the situation where the error changes linearly with the environmental parameters, such as the error drift caused by temperature changes, and is applicable to the situation where the error changes non-linearly with the environment, such as the unstable fluctuation of the sensor output in a high-humidity environment. When the environmental parameters change with periodic characteristics (such as the temperature difference between day and night), the error trend is predicted through historical data and the compensation value is dynamically adjusted. After executing the compensation strategy, the sensing error coefficient will be dynamically updated to ensure that subsequent data collection meets the corrected measurement standard. For example, the relationship between the current temperature and humidity and the error is recorded, the compensation model is optimized, and when the electromagnetic interference is strong, the signal processing algorithm is adjusted to ensure stable data collection. For example, when the system determines that the compensation requirements for the sensing error coefficient cannot match the pre-set compensation strategy, the system will consider that the source of the current error is unknown. The system will obtain the usage scenarios of the smart watch by the user, which specifically include sports scenarios, office and life scenarios, and extreme weather scenarios. According to different usage scenarios, the compensation strategy is adaptively optimized, and based on the complementarity between different sensors, the influence coefficient of the error of a single sensor on the compensation strategy is dynamically adjusted;By obtaining the user's usage scenarios, such as sports, office life, or extreme weather, the system can narrow down the possible causes of errors. For example, in a sports scenario, errors may be caused by severe shaking or posture changes, while in extreme weather, errors may be affected by environmental factors such as temperature and humidity. This approach helps the system more accurately determine the potential sources of errors, rather than relying on a fixed compensation mode. At the same time, according to different usage scenarios, the compensation strategy can be adaptively optimized, making the compensation scheme more flexible. For example, in a sports scenario, the system can perform more stringent filtering on the inertial sensor data to reduce errors caused by intense exercise. In an extreme weather scenario, the system can increase the data weight of environmental sensors to ensure that changes in the external environment are reasonably considered. This dynamic adjustment method enables the system to maintain high accuracy and reliability under different environmental conditions. Moreover, based on the complementarity between different sensors, the impact of a single sensor error on the overall compensation strategy can be optimized. For example, when the data of the acceleration sensor shows a deviation, the system can use the data of the gyroscope for cross-verification to avoid excessive influence of the data error of a single sensor on the final measurement result. Through multi-sensor data fusion, the system can more accurately calculate the source of errors and reduce unnecessary compensation corrections, improving the stability of the overall data.

[0030] It should be noted that the usage scenario of the smartwatch by the user is obtained, the compensation strategy is adaptively optimized according to the usage scenario, and based on the preset complementarity between different sensors, the influence coefficient of a single sensor error on the compensation strategy is dynamically adjusted. The specific examples are as follows: Suppose a user wears a smartwatch for high-intensity outdoor running training. During the running process, the acceleration sensor of the smartwatch is affected by severe shaking, resulting in abnormal deviations in step counting, movement trajectory, and speed measurement. For example, the acceleration data fluctuates significantly in a short period of time, causing the system to misjudge the step frequency and resulting in the user's steps being calculated too high or too low. In addition, due to environmental factors (such as wind speed changes and electromagnetic interference) affecting the GPS signal, the trajectory record may drift or have breakpoints, affecting the accuracy of the movement data. In this case, the system of the smartwatch will perform optimization compensation according to the following steps: Obtain the usage scenario information. By detecting that the user's heart rate has risen significantly through the heart rate sensor built into the smartwatch, it indicates that the user is performing high-intensity exercise. The GPS sensor data is continuously updated, showing that the user is moving quickly. Combining the acceleration sensor data, it can be confirmed that the user is in a running scenario. Combining the temperature and humidity sensor data, the system determines that the current environmental temperature is high and the humidity is low, and there is no extreme weather interference, ruling out the possibility of errors caused by weather factors. Sensor complementarity adjustment. Since the acceleration sensor is greatly affected by shaking, resulting in an increase in data noise, the system reduces the weight of the acceleration sensor in step counting. The gyroscope data is relatively more stable and can provide angular velocity information. Therefore, the system increases the weight of the gyroscope in step counting and trajectory correction to optimize the accuracy of step counting. The data of the GPS sensor drifts due to signal fluctuations. After the system detects an abnormal trajectory, it combines the GPS with the barometric altimeter and uses the barometric change trend to judge the altitude change to reduce the impact of GPS data drift on trajectory recording. Dynamic adjustment compensation strategy. In the step counting model of the smart watch, the system reduces its dependence on the large fluctuations of the acceleration sensor in a short period of time and instead estimates the steps based on the gyroscope angular velocity and step model. The calculation of the movement trajectory uses a multi-sensor fusion algorithm to filter the GPS data and correct the trajectory in combination with the gyroscope data, making the trajectory curve smoother and reducing the errors caused by signal drift. In terms of speed calculation, the system estimates the speed based on the step frequency detected by the gyroscope and the step model, and at the same time compares it with the speed calculated by the GPS. When the error between the two is too large, the system will dynamically adjust the trust level of the GPS data to make the finally calculated speed more stable and accurate. In summary, through the above optimization and compensation strategies, the smart watch can reduce the impact of sensor errors in high-intensity running scenarios, make step counting more accurate, the movement trajectory more realistic, avoid data distortion caused by abnormal single sensors, and improve the user's trust in and experience of sports data.

[0031] In this embodiment, in step S2 of determining whether the trend sensing data shows a preset deviation trend, it further includes: S21: Based on a preset trend period, detect corresponding instantaneous abnormal events from the trend sensing data, where the trend period specifically includes a global trend and a local trend; S22: Determine whether the instantaneous abnormal event shows a preset periodic fluctuation; S23: If so, obtain the regular change information corresponding to the trend sensing data through the instantaneous abnormal event, and construct trend change points corresponding to the periodic fluctuation according to the regular change information.

[0032] In this embodiment, the system detects corresponding instantaneous abnormal events from trend sensing data based on a preset trend period, which specifically includes a global trend and a local trend. Then, the system determines whether these instantaneous abnormal events exhibit a preset periodic fluctuation to execute corresponding steps. For example, when the system determines that the instantaneous abnormal events do not exhibit a preset periodic fluctuation, the system will consider that these abnormal events may be caused by accidental factors, environmental interference, or device errors, rather than systematic or periodic abnormalities. The system will combine the trend sensing data, trace back the environmental parameters (such as temperature and humidity, electromagnetic interference, pressure changes, etc.) when the abnormal events occur, determine whether there is a sudden external interference, and detect the status of the sensors inside the smartwatch, including battery power, transmission signal quality, and hardware operation status, to rule out the possibility of device failures. At the same time, if the abnormality involves multiple sensors and has a greater impact, it may be necessary to further calibrate the sensor parameters of the smartwatch, such as adjusting the sensor sensitivity, optimizing the data sampling frequency, etc., and provide user prompts, record the time, location, and possible environmental factors of the abnormality, and allow the user to input supplementary information to help the system optimize the anomaly detection strategy. For example, when the system determines that the instantaneous abnormal events exhibit a preset periodic fluctuation, the system will consider that these abnormal events are not accidental factors and may be systematic or periodic abnormalities. The system will obtain the regular change information corresponding to the trend sensing data through these instantaneous abnormal events, and construct trend change points corresponding to the periodic fluctuation according to different regular change information. By determining the periodic fluctuation of the instantaneous abnormal events, the system can distinguish accidental abnormalities from systematic abnormalities, avoid misinterpreting normal fluctuations as sudden abnormalities, which can improve the accuracy of the smartwatch sensing data, make the system more reliable in data analysis and processing, ensure that users obtain high-quality health monitoring or sports data feedback. At the same time, by extracting the regular change information in the trend sensing data, the system can construct trend change points corresponding to the periodic fluctuation, which enables the smartwatch to predict possible future abnormal situations, such as data fluctuations at specific times or under specific conditions, so as to optimize the working mode of the sensor in advance, reduce errors, and improve the intelligence level of the device. And according to different regular change information, the system can optimize the compensation strategy for sensing errors. For example, when a long-term periodic fluctuation is detected, the smartwatch can automatically adjust the sensor sensitivity, data filtering method, or calibration parameters to reduce error accumulation and improve the stability of long-term use, which is particularly important for high-precision scenarios (such as heart rate monitoring, step frequency calculation, etc.).

[0033] It should be noted that obtaining the regular change information corresponding to the trend sensing data through the instantaneous abnormal events and constructing the trend change points corresponding to the periodic fluctuation according to the regular change information are specifically exemplified as follows: Suppose a user wears a smartwatch for round-the-clock health monitoring. The watch is equipped with a blood oxygen sensor that records blood oxygen saturation (SpO2) data every 5 minutes. Generally, the user's blood oxygen level remains stable between 95% and 98%. However, within the past week, the system has found that the user's blood oxygen data frequently shows a brief decline during the time period from 2:00 to 3:00 in the morning, dropping as low as 89% at its lowest point, and then returning to the normal level around 3:30. First, data collection and anomaly detection are carried out. The blood oxygen sensor continuously monitors the user's blood oxygen level and records all data points. The system has found that during the period from 2:00 to 3:00 in the morning, the blood oxygen level frequently drops, and the lowest value on some nights even drops to 89%. This phenomenon has persisted for several days, and the system determines that this abnormal data point does not occur by chance but has a certain degree of repeatability. Subsequently, the extraction of regular change information is carried out. The system compares the data of the past week and finds that the occurrence time of this abnormal value is almost fixed between 2:00 and 3:00, with a brief decline occurring every night and then gradually recovering. Further analysis of environmental data (such as temperature, humidity, sleep posture, etc.) reveals that the user may be at risk of sleep apnea during this time period. The accelerometer data shows that the user's number of body turns increases during this time period, possibly due to discomfort caused by the drop in blood oxygen level. Then, a trend change point is constructed. After data analysis, the system marks this time period as the "prone period for blood oxygen decline" and establishes a trend change point to improve the accuracy of anomaly recognition when similar situations are detected in the future. The system will combine historical data to predict the future blood oxygen fluctuation pattern and may adjust the blood oxygen measurement frequency, increasing the data sampling density during this time period to improve the monitoring accuracy. Next, intelligent optimization and user feedback are carried out. If this anomaly is related to certain adjustable factors, such as the user's sleeping posture, the system can prompt the user to adjust the sleeping posture or use a specific pillow to improve breathing patency. If this anomaly may involve health risks, the system can recommend that the user undergo a more in-depth health examination, such as sleep apnea monitoring, to confirm whether there is sleep apnea syndrome (SAS). In the future, the system can issue an early warning during this time period, such as reminding the user when they go to sleep, or linking with the medical system to trigger a health alert when a severe drop in blood oxygen is detected. In summary, by constructing trend change points, the system not only discovers instantaneous abnormal events but also successfully extracts potential periodic health problems (such as the risk of low blood oxygen at night); this provides early warnings for users and avoids possible health hazards; at the same time, by analyzing periodic fluctuations, the system can optimize the blood oxygen monitoring algorithm, increase the sampling frequency within a specific time period to obtain more accurate data; in the future, the system can even adaptively adjust the measurement mechanism. For example, when a downward trend in blood oxygen is detected, it automatically enables a higher-precision measurement mode; and the system provides personalized health advice based on trend change points. For example, for users with a drop in blood oxygen at night, the system can recommend suitable sleep postures, breathing training, or air quality optimization solutions; if the system discovers that an abnormal pattern persists for a long time, it can also recommend that the user seek medical advice and even connect to remote medical services through the smartwatch; traditional anomaly detection methods may ignore short-term fluctuations or misjudge them as accidental errors, while this system can incorporate these fluctuations into long-term analysis by constructing trend change points, reducing misjudgments and improving the reliability of detection; through this mechanism, the smartwatch is not just a simple health monitoring device but an intelligent system that can identify, learn, and optimize user health management.

[0034] In this embodiment, in step S4 of determining whether the abnormal value can be data-repaired, it further includes: S41: Based on the time window corresponding to the abnormal value, calculate the data missing rate of the time window; S42: Determine whether the data missing rate exceeds a preset missing value; S43: If so, through the abnormal value, identify the impact content of the missing data on the final sensing data. According to the impact content, guide the user to re-measure the final sensing data additionally. Based on the abnormal data segment of the abnormal value, record the corresponding abnormal reasons in the smartwatch, where the abnormal reasons specifically include sensor detachment, signal loss, and external environmental factors.

[0035] In this embodiment, the system calculates the data loss rate of the time window based on the time window corresponding to the outlier, and then the system determines whether these data loss rates exceed the preset missing values to execute corresponding steps. For example, when the system determines that the data loss rate of the time window does not exceed the preset missing values, the system will consider that the degree of data loss is within an acceptable range and will not have a significant impact on the overall data analysis, prediction, or compensation strategy. The system can still perform effective calculations and processing through the existing data, and the system will calculate according to the original logic without triggering the exception handling mechanism. For example, during sleep monitoring, if the body movement data at individual time points is lost but the overall sleep trend is not affected, the system can still normally calculate the ratio of deep sleep to light sleep and output a reliable sleep report, while continuously tracking the data loss situation of this time window to ensure that the loss rate does not continue to rise in a short period. For example, if the smartwatch occasionally experiences data loss of less than 5% in a day and this situation does not occur frequently, the system can consider that the device sensors and communication modules are still working stably without triggering an additional repair mechanism. And if the loss rate is at a low level but shows an upward trend, the system can dynamically adjust the monitoring threshold to increase the attention to data integrity. For example, if the data loss rate is close to the set threshold (for example, set to 10%, but the current loss rate has reached 8%), the system can give a soft reminder in advance to prompt the user to maintain the device connection stability, such as checking the Bluetooth connection or the wearing position. For example, when the system determines that the data loss rate of the time window exceeds the preset missing values, at this time the system will consider that the data loss will have a significant impact. The system will identify the impact content of the missing data on the final sensing data through the outlier, and according to different impact contents, guide the user to re-measure the final sensing data additionally. Based on the abnormal data segment of the outlier, the corresponding abnormal reasons will be recorded in the smartwatch. The abnormal reasons specifically include sensor detachment, signal loss, and external environmental factors.By identifying outliers and evaluating the impact of missing data on the final sensing data, the system can promptly detect situations that may affect measurement accuracy. When the data loss rate exceeds the preset threshold, the system can take proactive measures to reduce the spread of incorrect data, thereby improving the data integrity recorded by the smartwatch and ensuring that users obtain more reliable health monitoring results. At the same time, by guiding users to re-perform additional measurements, the system can minimize the impact of data loss on the monitoring results. For example, in heart rate monitoring, if the data loss rate is too high, the system can remind the user to adjust the wearing position or re-measure during a specific time period to supplement the missing data and improve the accuracy of health analysis. Moreover, recording the specific reasons for abnormal data segments (such as sensor detachment, signal loss, or external environmental factors) can help the system analyze the root cause of data loss and take targeted measures. For instance, when frequent signal loss is detected, the system can prompt the user to check the Bluetooth connection or adjust the wearing method of the smartwatch to avoid the recurrence of similar problems. By storing and analyzing historical anomaly records, the system can continuously optimize its data acquisition strategy. For example, if a certain user often experiences data loss due to environmental interference, the system can adjust the sampling frequency of the sensor or enhance the signal processing algorithm to adapt to the data acquisition requirements in different environments and improve the stability and adaptability of the smartwatch in complex environments.

[0036] In this embodiment, in step S1 of collecting corresponding trend sensing data by the smartwatch through real-time monitoring of a preset sensor based on the preset usage duration of the smartwatch, it further includes: S11: Detect the time window in which outliers occur based on the preset statistical characteristics of the sensor data, where the statistical characteristics specifically include mean, variance, and standard deviation; S12: Determine whether the number of the time windows reaches the preset threshold; S13: If so, trigger the preset self-calibration mode of the sensor regularly according to the usage duration. Through the self-calibration mode, reduce the error accumulation of the sensor, activate the preset calibration tutorial of the smartwatch, and guide the user to manually calibrate the smartwatch according to the calibration tutorial.

[0037] In this embodiment, the system is based on the statistical characteristics preset according to the sensor data. The statistical characteristics specifically include the mean, variance, and standard deviation. The system detects the time window in which outliers occur, and then determines whether the number of these time windows reaches a preset threshold to execute corresponding steps. For example, when the system determines that the number of time windows does not reach the preset threshold, the system will consider that the current occurrence of outliers is relatively scattered, which may belong to occasional errors rather than systematic or trend anomalies. The system will suspend the execution of compensation or correction measures to avoid unnecessary adjustments to normal data, which helps to reduce unnecessary interventions caused by misjudgment and ensure the stability of data processing. At the same time, the system continues to monitor subsequent data and temporarily stores the current abnormal data. If the occurrence frequency of outliers in the subsequent data increases and gradually reaches the set threshold, the system will re-evaluate the situation and decide whether to take further processing measures, and conduct a local analysis of these scattered outliers. For example, check whether they mainly appear under certain specific conditions (such as in a high-temperature environment or when the wearing is loose). If it is found that the outliers mainly appear under certain specific environments or operating behaviors, the system can prompt the user to make adjustments, such as re-wearing the smart watch or avoiding certain specific interference environments. For example, when the system determines that the number of time windows reaches the preset threshold, the system will consider that the current outliers are relatively concentrated. The system will regularly trigger the self-calibration mode preset in the sensor according to the usage duration of the smart watch. Through this self-calibration mode, the error accumulation of the sensor is reduced, and the calibration tutorial preset in the smart watch is activated. According to these calibration tutorials, the user is guided to manually calibrate the smart watch.By regularly triggering the self - calibration mode of the sensor, the system can effectively reduce the error accumulation of the sensor caused by environmental changes, hardware aging, or continuous use, ensuring that the measurement data of the smart watch always maintains high precision. This is particularly important for functions that rely on sensing data, such as health monitoring and sports tracking, which can improve the user experience and data credibility. At the same time, since the smart watch is used in different scenarios, its sensors may be affected by external factors (such as temperature changes, humidity effects, electromagnetic interference, etc.), resulting in measurement deviations. The system triggers self - calibration based on the usage duration, enabling the device to dynamically adjust according to the actual usage situation, avoiding the gradual distortion of measurement data due to long - term non - calibration, and enhancing the device's adaptive ability. Additionally, by activating the built - in calibration tutorial of the smart watch to guide the user to manually calibrate the device, the user can more intuitively understand the device's status and participate in the device maintenance process. This can not only ensure data accuracy but also improve the user's trust in the device and enhance the user's interaction experience. Because long - term non - calibration of the sensor may lead to large measurement errors, affecting the user's judgment of the smart watch data. For example, if there are long - term deviations in health monitoring data such as heart rate and blood oxygen, it may mislead the user's health management. The system combines self - calibration and manual calibration to reduce the potential risks brought by data errors, ensuring reliable measurement results, thereby enhancing the overall safety and practicality of the device.;

[0038] Reference appendix Figure 2 , which is a sensor error calibration system for a smart watch in an embodiment of the present invention, including: The acquisition module 10 is used to, based on the preset usage duration of the smart watch, monitor a preset sensor in real - time through the smart watch and collect corresponding trend sensing data; The judgment module 20 is used to judge whether the trend sensing data presents a preset deviation trend; The execution module 30 is used to, if so, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points outside the standard deviation range as outliers in the trend sensing data, and classify the outliers, where the outlier classification specifically includes short - term sudden anomalies, long - term drifts, and outliers; The second judgment module 40 is used to judge whether the outliers can be data - repaired; The second execution module 50 is used to, if so, perform drift compensation on the outliers according to the outlier classification, dynamically calibrate the sensing error coefficient of the smart watch, use the pre - collected environmental factors of the smart watch as the compensation input for the sensing error coefficient, and adaptively correct the sensing error coefficient, where the drift compensation specifically includes linear drift compensation, non - linear drift compensation, and periodic drift compensation, and the environmental factors specifically include temperature, humidity, and air pressure.

[0039] In this embodiment, the acquisition module 10 monitors the preset sensors in real time based on the preset used duration of the smart watch, acquires the corresponding trend sensing data, and then the judgment module 20 judges whether these trend sensing data show a preset deviation trend to execute corresponding steps; for example, when the system determines that the trend sensing data collected by the sensor does not show a preset deviation trend, the system will consider that the measurement accuracy and stability of the current sensor still meet the expectations, and there is no obvious drift or abnormal situation. The system will continue to record and store the measurement data according to the existing sensing data processing logic, ensure the continuity and integrity of the data, maintain the existing sensor error compensation strategy, and do not perform additional compensation adjustments to avoid overcorrection affecting the measurement result. At the same time, the current measurement environment (such as temperature, humidity, air pressure) and device status are stored so that when an abnormality is detected in the future, it can be compared with the current state to analyze possible influencing factors, and a regular calibration interval is set. Even if there is no drift, a baseline comparison can be made according to the preset period to detect potential subtle drift trends in advance; for example, when the system determines that the trend sensing data collected by the sensor shows a preset deviation trend, at this time, the execution module 30 will consider that there may be drift or abnormal situation in the measurement accuracy of the current sensor. The system will select preset data points from the trend sensing data, calculate the standard deviation of these data points, mark the data points outside the standard deviation range as outliers in the trend sensing data, and classify these outliers. The outlier classification specifically includes short-term sudden abnormalities, long-term drifts, and outliers; by judging whether the trend sensing data deviates from the set standard, the system can timely identify the sensor measurement error, prevent incorrect data from affecting the final measurement result. The method of calculating the standard deviation and marking outliers helps to exclude accidental interference, improve the stability and accuracy of the data. At the same time, the outliers are divided into short-term sudden abnormalities, long-term drifts, and outliers, enabling the system to adopt corresponding processing strategies for different types of abnormalities. Short-term sudden abnormalities can be processed by smoothing filtering, long-term drifts can trigger an automatic compensation mechanism, and outliers can be used to warn of possible hardware failures of the sensor, improving the fault management ability of the smart watch. And based on the outlier classification, the system can adjust the sensor compensation strategy according to the type of abnormality. For example, a trend compensation algorithm can be used to correct long-term drifts, so that the sensor can still maintain high-precision measurement ability even after long-term use, thereby improving the reliability and user experience of the smart watch in complex environments; then the second judgment module 40 judges whether the outliers in the trend sensing data can be data-repaired to execute corresponding steps;For example, when the system determines that the outliers in the trend sensing data cannot be repaired, the system will consider that it may be caused by sensor hardware failure, severe long-term drift, environmental interference exceeding the compensable range, or excessive data loss, resulting in ineffective compensation. The system will store the unrepaired data separately and mark it in the log or data record to avoid affecting the calculation of normal data. If the number of outliers is small, the system can use historical trend data, neighboring data interpolation, or preset default values for compensation to maintain measurement continuity. At the same time, if abnormal data persists, the system can trigger a self-check mechanism to check the working status of the sensor and send a reminder to the user, such as suggesting recalibration, checking the hardware, or replacing the device. And if the smartwatch has multiple built-in sensors, the system can reduce the data weight of the faulty sensor, give priority to using the data of other sensors for calculation, or switch to an alternative measurement mode (such as using a different algorithm or data source); For example, when the system determines that the outliers in the trend sensing data can be repaired, at this time, the second execution module 50 will consider that the degree of data deviation is small and can be compensated in a timely manner. The system will perform drift compensation on the outliers according to different abnormal classifications. The drift compensation specifically includes linear drift compensation, non-linear drift compensation, and periodic drift compensation, dynamically calibrating the sensing error coefficient of the smartwatch, and using the environmental factors pre-collected by the smartwatch, which specifically include temperature, humidity, and air pressure, as the compensation input for the sensing error coefficient, and adaptively correcting the sensing error coefficient; By performing drift compensation on the outliers, the system can correct them in a timely manner when the degree of data deviation is small, avoiding the influence of incorrect data on the final measurement result. Linear drift compensation is applicable to long-term stable offsets, non-linear drift compensation can correct complex error changes, and periodic drift compensation can adjust for periodically fluctuating errors, thus ensuring the long-term stability and accuracy of the data. At the same time, using the environmental factors (such as temperature, humidity, and air pressure) pre-collected by the smartwatch as the compensation input enables the system to dynamically adjust the error calibration strategy under different environmental conditions. This mechanism can effectively reduce the measurement error caused by external environmental changes, ensuring that the smartwatch can still maintain accurate measurement performance in different scenarios such as high temperature, low temperature, and high humidity. And by adopting an adaptive correction mechanism, the sensing error coefficient can be dynamically adjusted with real-time data, avoiding the influence of long-term error accumulation of the sensor on the measurement result. This not only improves the long-term stability of the data but also reduces the need for frequent calibration or replacement of the device due to the decline in sensor accuracy, thereby extending the service life of the smartwatch and improving the user experience and device reliability.;

[0040] In this embodiment, the execution module further includes: An identification unit, configured to collect the proportion data of the abnormal quantity in the trend sensing data based on the abnormal quantity of the outliers, and identify the distribution information of the outliers according to the proportion data; A judgment unit, configured to judge whether the distribution information matches a preset specific condition, where the specific condition specifically includes that outliers are concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors; An execution unit, configured to, if so, detect the working environment of the sensor, calculate the accuracy error of the sensor according to the working environment, and obtain the corresponding abnormal pattern from the distribution information.

[0041] In this embodiment, the system collects the proportion data of these abnormal quantities in the trend sensing data based on the abnormal quantity of outliers, and identifies the distribution information of these outliers according to different proportion data. Then the system judges whether the distribution information matches a preset specific condition. The specific condition specifically includes that outliers are concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors, so as to execute corresponding steps. For example, when the system determines that the distribution information of outliers cannot match the preset specific condition, the system will consider that the appearance of these outliers is not caused by known patterns or predictable external environmental factors (such as specific time periods, specific environmental factors). The system will appropriately increase the time window or the number of data points to improve the accuracy of system judgment. For example, if the current data analysis is based on 10 minutes, it can be changed to 30 minutes or 1 hour data analysis to capture a wider trend. At the same time, if the distribution of outliers is relatively scattered, it may be necessary to adjust the weight of the standard deviation calculation or the threshold of outlier judgment to prevent over-screening or false negatives of outliers. And if the proportion of outliers continues to increase but the reason is unknown, the system can enter the warning mode, reduce the data credibility, or only for user reference without directly affecting key decisions (such as health warnings). For example, when the system determines that the distribution information of outliers can match the preset specific condition, at this time the system will consider that the appearance of these outliers is caused by known factors. The system will detect the working environment of the sensor, calculate the accuracy error of the sensor according to different working environments, and obtain the corresponding abnormal pattern from the distribution information. By detecting the working environment of the sensor and calculating the accuracy error according to different environmental conditions, the system can dynamically adjust the calibration parameters of the sensor. For example, if the system detects that the environmental temperature increases by 5°C, resulting in a 0.2% increase in the measurement error, this error can be compensated in real time to ensure that the measurement result is not affected by environmental fluctuations. At the same time, by analyzing the distribution pattern of outliers, the system can identify long-term trends and adjust the error compensation strategy. For example, if the system finds that a certain sensor has a high measurement value in a high humidity environment, it can automatically enable a specific humidity calibration algorithm to maintain the accuracy of measurement data in the long term and extend the effective service life of the device. And if the system cannot judge the source of the abnormality, it may mis-trigger the data repair or compensation mechanism, resulting in unnecessary computational consumption and even data distortion. Based on matching outliers with known environmental factors, the system can perform compensation under the correct conditions and avoid interfering with normal data, thereby improving the overall energy efficiency and reliability of the system.

[0042] In this embodiment, it further includes: An extraction module, configured to extract the data anomaly features of the outliers and compare the output data of different sensors in the smart watch, where the data anomaly features specifically include the fluctuation amplitude, the change speed, and the change direction; A third judgment module, configured to judge whether a preset associated anomaly is detected in the output data; A third execution module, configured to, if so, identify the communication protocol interface between the different sensors, and based on the communication protocol interface, obtain the bus communication status of the smart watch, and generate the network communication quality of the smart watch in real time according to the bus communication status, where the bus communication status specifically includes noise interference, data transmission delay, and connection loss, and the network communication quality is specifically the communication quality when data is transmitted between different sensors.

[0043] In this embodiment, the system extracts the data anomaly features of the outliers. The data anomaly features specifically include the fluctuation amplitude, the change speed, and the change direction. The system compares the output data of different sensors in the smart watch, and then determines whether these output data detect a preset associated anomaly to execute corresponding steps. For example, when the system determines that the output data of different sensors in the smart watch do not detect a preset associated anomaly, the system will consider that the current outlier may be a short-term error or accidental fluctuation, rather than being caused by environmental factors, equipment failures, or systematic errors. The system will temporarily store the current outlier and continue to collect data in the subsequent time window to observe whether there is a persistent deviation. For example, if the heart rate sensor reading suddenly soars to 180 bpm in a certain measurement, but there are no anomalies in the acceleration sensor and the skin resistance sensor, it may be a mismeasurement. The system will verify whether the data returns to normal within the next 10 seconds. At the same time, if the anomaly point does not trigger an associated anomaly but appears multiple times in a short period, the system will record these data and mark them as "low-priority anomalies" for review during subsequent data analysis. For example, if the smart watch of a certain user shows short-term heart rate jumps during the morning measurements for three consecutive days, although no associated anomaly is detected, the system will still record it for further analysis. For example, when the system determines that the output data of different sensors in the smart watch detect a preset associated anomaly, the system will consider that the current outlier is caused by environmental factors, equipment failures, or systematic errors. The system will identify the communication protocol interfaces between different sensors. Based on these communication protocol interfaces, the system will obtain the bus communication status of the smart watch. The bus communication status specifically includes noise interference, data transmission delay, and connection loss. According to different bus communication statuses, the system will generate the network communication quality of the smart watch in real time. The network communication quality is specifically the communication quality when data is transmitted between different sensors. By analyzing the communication protocol interfaces and the bus communication status between different sensors, the system can determine whether the anomaly is caused by environmental factors, equipment failures, or systematic errors. This process helps to accurately locate the source of the anomaly, avoid misinterpreting hardware failures or communication anomalies as sensor drift or short-term fluctuations, and at the same time can dynamically evaluate the integrity and accuracy of sensor data during transmission. If the system finds that the data is affected due to poor communication quality, it can take measures such as redundant verification, automatic retransmission, or signal enhancement to ensure data stability. For example, if the data transmission of a certain sensor has a high delay, the system can preferentially use the data of other sensors or perform data compensation to reduce the impact of the anomaly, and can automatically adjust the data processing strategy based on the real-time communication quality assessment. For example, in an environment with high signal noise, the system can reduce the sensor sampling rate to reduce false alarms, or enable redundant sensors for data compensation, thereby improving the measurement accuracy. This adaptive optimization ability enables the smart watch to maintain high-precision operation in a complex environment and improve the user experience.

[0044] In this embodiment, the second execution module further includes: A second recognition unit, configured to recognize the compensation requirement of the sensing error coefficient based on the fluctuation change of the environmental parameters, where the fluctuation change specifically includes the temperature and humidity fluctuation range, air pressure change, and electromagnetic interference; A second judgment unit, configured to judge whether the compensation requirement matches a preset compensation strategy; A second execution unit, configured to, if not, obtain the usage scenario of the smart watch by the user, adaptively optimize the compensation strategy according to the usage scenario, and dynamically adjust the influence coefficient of the error of a single sensor on the compensation strategy based on the preset complementarity between different sensors, where the usage scenario specifically includes a sports scenario, an office and life scenario, and an extreme weather scenario.

[0045] In this embodiment, the system identifies the compensation requirements of the sensing error coefficient based on the fluctuating changes of environmental parameters, which specifically include the temperature and humidity fluctuation range, air pressure change, and electromagnetic interference. Then, the system determines whether the compensation requirements match the pre-set compensation strategy to execute corresponding steps. For example, when the system determines that the compensation requirements of the sensing error coefficient can match the pre-set compensation strategy, the system will consider that the source of the current error is known, and the system already has a corresponding compensation scheme to correct the error. The system will calculate the optimal compensation parameters according to the matched compensation strategy and the current environmental parameter fluctuation situation. For example, if the temperature rises and causes the sensor measurement value to be too high, the system can introduce a temperature compensation factor to dynamically adjust the measurement value. If the electromagnetic interference increases, the system can use a filtering algorithm to reduce the error, or temporarily increase the signal sampling times to improve data accuracy. At the same time, one or more of linear compensation, non-linear compensation, or periodic drift compensation are selected for adjustment. For example, it is applicable to the situation where the error changes linearly with the environmental parameters, such as the error drift caused by temperature change. It is applicable to the situation where the error changes non-linearly with the environment, such as the unstable fluctuation of the sensor output in a high-humidity environment. When the environmental parameters change with periodic characteristics (such as the diurnal temperature difference), the error trend is predicted through historical data and the compensation value is dynamically adjusted. After executing the compensation strategy, the sensing error coefficient will be dynamically updated to ensure that subsequent data collection meets the corrected measurement standard. For example, record the relationship between the current temperature and humidity and the error, optimize the compensation model, and adjust the signal processing algorithm when the electromagnetic interference is strong to ensure stable data collection. For example, when the system determines that the compensation requirements of the sensing error coefficient cannot match the pre-set compensation strategy, the system will consider that the source of the current error is unknown. The system will obtain the usage scenarios of the smart watch by the user, which specifically include sports scenarios, office and life scenarios, and extreme weather scenarios. According to different usage scenarios, the compensation strategy will be adaptively optimized, and based on the complementarity between different sensors, the influence coefficient of the compensation strategy when a single sensor has an error will be dynamically adjusted;By obtaining the user's usage scenarios, such as sports, office life or extreme weather, the system can narrow the possible causes of errors. For example, in sports scenarios, errors may be caused by violent shaking or posture changes, while in extreme weather, errors may be affected by environmental factors such as temperature and humidity. This method can help the system more accurately determine the potential sources of errors, rather than relying on fixed compensation modes. At the same time, according to different usage scenarios, adaptive optimization of compensation strategies can make the compensation scheme more flexible. For example, in sports scenarios, the system can filter the inertial sensor data more strictly to reduce the errors caused by violent sports, and in extreme weather scenarios, the system can increase the data weight of environmental sensors to ensure that changes in the external environment are reasonably considered. This dynamic adjustment method enables the system to maintain high accuracy and reliability under different environmental conditions, and based on the complementarity between different sensors, it can optimize the impact of single sensor errors on the overall compensation strategy. For example, when the data of the acceleration sensor deviates, the system can use the data of the gyroscope for cross-validation to avoid the data error of a single sensor from having too much impact on the final measurement result. Through multi-sensor data fusion, the system can more accurately calculate the source of error, reduce unnecessary compensation corrections, and improve the stability of the overall data. ;

[0046] In this embodiment, the judgment module further includes: A detection unit, configured to detect corresponding instantaneous abnormal events from the trend sensing data based on a preset trend period, wherein the trend period specifically includes a global trend and a local trend; A third judgment unit, used to judge whether the instantaneous abnormal event presents a preset periodic fluctuation; The third execution unit is used to obtain regular change information corresponding to the trend sensor data through the instantaneous abnormal event, and construct a trend change point corresponding to the periodic fluctuation according to the regular change information.

[0047] In this embodiment, the system detects corresponding instantaneous abnormal events from the trend sensing data based on a preset trend period, which specifically includes a global trend and a local trend. Then, the system determines whether these instantaneous abnormal events exhibit a preset periodic fluctuation to execute corresponding steps. For example, when the system determines that the instantaneous abnormal events do not exhibit a preset periodic fluctuation, the system will consider that these abnormal events may be caused by accidental factors, environmental interference, or device errors, rather than systematic or periodic abnormalities. The system will combine the trend sensing data, trace back the environmental parameters (such as temperature and humidity, electromagnetic interference, pressure changes, etc.) when the abnormal events occur, determine whether there is a sudden external interference, and detect the status of the sensors inside the smartwatch, including battery power, transmission signal quality, and hardware operation status, to rule out the possibility of device failures. At the same time, if the abnormality involves multiple sensors and has a greater impact, it may be necessary to further calibrate the sensor parameters of the smartwatch, such as adjusting the sensor sensitivity, optimizing the data sampling frequency, etc., and provide user prompts, record the time, location, and possible environmental factors of the abnormal occurrence, and allow the user to input supplementary information to help the system optimize the abnormal detection strategy. For example, when the system determines that the instantaneous abnormal events exhibit a preset periodic fluctuation, at this time, the system will consider that these abnormal events are not accidental factors and may be systematic or periodic abnormalities. The system will obtain the regular change information corresponding to the trend sensing data through these instantaneous abnormal events, and construct trend change points of periodic fluctuations according to different regular change information. By determining the periodic fluctuation of the instantaneous abnormal events, the system can distinguish accidental abnormalities from systematic abnormalities, avoid misidentifying normal fluctuations as sudden abnormalities, which can improve the accuracy of the smartwatch sensing data, enable the system to perform data analysis and processing more reliably, ensure that users obtain high-quality health monitoring or sports data feedback, and at the same time, by extracting the regular change information in the trend sensing data, the system can construct trend change points of periodic fluctuations, which enables the smartwatch to predict possible future abnormal situations, such as data fluctuations at specific times or under specific conditions, so as to optimize the working mode of the sensors in advance, reduce errors, and improve the intelligence level of the device. And according to different regular change information, the system can optimize the compensation strategy for sensing errors. For example, when a long-term periodic fluctuation is detected, the smartwatch can automatically adjust the sensor sensitivity, data filtering method, or calibration parameters to reduce error accumulation and improve the stability during long-term use, which is particularly important for high-precision scenarios (such as heart rate monitoring, step frequency calculation, etc.).

[0048] In this embodiment, the second judgment module further includes: A calculation unit for calculating the data missing rate of the time window based on the time window corresponding to the abnormal value; A fourth judgment unit for judging whether the data missing rate exceeds a preset missing value; A fourth execution unit, which is used to, if so, identify the impact content of the missing data on the final sensing data through the outlier, guide the user to re-perform additional measurements on the final sensing data according to the impact content, and record the corresponding abnormal cause in the smart watch according to the abnormal data segment of the outlier, where the abnormal cause specifically includes sensor detachment, signal loss, and external environmental factors.

[0049] In this embodiment, the system calculates the data missing rate of the time window based on the time window corresponding to the outlier, and then the system determines whether these data missing rates exceed the preset missing values to execute corresponding steps. For example, when the system determines that the data missing rate of the time window does not exceed the preset missing value, the system will consider that the degree of data loss is within an acceptable range and will not have a significant impact on the overall data analysis, prediction or compensation strategy. The system can still perform effective calculations and processing through the existing data, and the system will calculate according to the original logic without triggering the exception handling mechanism. For example, during sleep monitoring, if the body movement data at individual time points is lost but the overall sleep trend is not affected, the system can still normally calculate the proportion of deep sleep and light sleep and output a reliable sleep report, while continuously tracking the data missing situation of this time window to ensure that the missing rate does not continue to rise in a short period of time. For example, if the smart watch occasionally has a data loss of less than 5% in a day and this situation does not occur frequently, the system can consider that the device sensor and communication module are still working stably without triggering an additional repair mechanism. And if the missing rate is at a low level but shows an upward trend, the system can dynamically adjust the monitoring threshold to increase the attention to data integrity. For example, if the data missing rate is close to the set threshold (for example, set to 10%, but the current missing rate has reached 8%), the system can give a soft reminder in advance to prompt the user to maintain the stability of the device connection, such as checking the Bluetooth connection or the wearing position. For example, when the system determines that the data missing rate of the time window exceeds the preset missing value, at this time the system will consider that the data loss will have a significant impact. The system will identify the impact content of the missing data on the final sensing data through the outlier, and according to different impact contents, guide the user to re-measure the final sensing data additionally. According to the abnormal data segment of the outlier, the corresponding abnormal reasons are recorded in the smart watch, and the abnormal reasons specifically include sensor detachment, signal loss and external environmental factors;By identifying outliers and evaluating the impact of missing data on the final sensing data, the system can promptly detect situations that may affect measurement accuracy. When the data missing rate exceeds the preset threshold, the system can proactively take measures to reduce the spread of incorrect data, thereby improving the data integrity recorded by the smartwatch and ensuring that users obtain more reliable health monitoring results. At the same time, by guiding users to re-perform additional measurements, the system can minimize the impact of data loss on the monitoring results. For example, in heart rate monitoring, if the data missing rate is too high, the system can remind the user to adjust the wearing position or re-measure during a specific time period to supplement the missing data and improve the accuracy of health analysis. Moreover, recording the specific reasons for abnormal data segments (such as sensor detachment, signal loss, or external environmental factors) can help the system analyze the root cause of data loss and take targeted measures. For instance, when frequent signal loss is detected, the system can prompt the user to check the Bluetooth connection or adjust the wearing method of the smartwatch to avoid the recurrence of similar problems. By storing and analyzing historical anomaly records, the system can continuously optimize its data acquisition strategy. For example, if a certain user often experiences data loss due to environmental interference, the system can adjust the sampling frequency of the sensor or enhance the signal processing algorithm to adapt to the data acquisition requirements in different environments and improve the stability and adaptability of the smartwatch in complex environments.

[0050] In this embodiment, the acquisition module further includes: A second detection unit, configured to detect the time window in which outliers occur based on the preset statistical characteristics of the sensor data, where the statistical characteristics specifically include mean, variance, and standard deviation; A fifth judgment unit, configured to judge whether the number of the time windows reaches a preset threshold; A fifth execution unit, configured to, if so, periodically trigger the self-calibration mode preset for the sensor according to the usage duration. Through the self-calibration mode, reduce the error accumulation of the sensor, activate the calibration tutorial preset for the smartwatch, and guide the user to manually calibrate the smartwatch according to the calibration tutorial.

[0051] In this embodiment, the system is based on the statistical characteristics preset according to the sensor data. The statistical characteristics specifically include the mean, variance, and standard deviation. The system detects the time window in which outliers occur, and then determines whether the number of these time windows reaches a preset threshold to execute corresponding steps. For example, when the system determines that the number of time windows does not reach the preset threshold, the system will consider that the current occurrence of outliers is relatively scattered and may belong to occasional errors rather than systematic or trend anomalies. The system will suspend the execution of compensation or correction measures to avoid unnecessary adjustments to normal data, which helps reduce unnecessary interventions caused by misjudgment and ensure the stability of data processing. At the same time, the system continues to monitor subsequent data and temporarily stores the current abnormal data. If the occurrence frequency of outliers in subsequent data increases and gradually reaches the set threshold, the system will re-evaluate the situation and decide whether to take further processing measures, and conduct a local analysis of these scattered outliers. For example, check whether they mainly appear under certain specific conditions (such as high-temperature environments or loose wearing conditions). If it is found that the outliers mainly appear under certain specific environments or operating behaviors, the system can prompt the user to make adjustments, such as re-wearing the smart watch or avoiding certain specific interference environments. For example, when the system determines that the number of time windows reaches the preset threshold, the system will consider that the current outliers are relatively concentrated. The system will regularly trigger the self-calibration mode preset for the sensor according to the usage duration of the smart watch. Through this self-calibration mode, the error accumulation of the sensor is reduced, and the calibration tutorial preset for the smart watch is activated. According to these calibration tutorials, the user is guided to manually calibrate the smart watch.By regularly triggering the self - calibration mode of the sensor, the system can effectively reduce the error accumulation caused by environmental changes, hardware aging, or continuous use of the sensor, ensuring that the measurement data of the smartwatch always maintains high precision. This is particularly important for functions that rely on sensing data, such as health monitoring and sports tracking, which can enhance the user experience and data credibility. At the same time, since the smartwatch is used in different scenarios, its sensors may be affected by external factors (such as temperature changes, humidity effects, electromagnetic interference, etc.), resulting in measurement deviations. The system triggers self - calibration based on the usage duration, enabling the device to dynamically adjust according to the actual usage situation, avoiding the gradual distortion of measurement data due to long - term uncalibrated, enhancing the device's adaptability. And by activating the built - in calibration tutorial of the smartwatch to guide users to manually calibrate the device, users can more intuitively understand the state of the device and participate in the device maintenance process. This not only ensures the accuracy of the data but also improves the user's trust in the device and enhances the user's interaction experience. Because if the sensor is not calibrated for a long time, it may lead to large measurement errors, affecting the user's judgment of the smartwatch data. For example, if there are long - term deviations in health monitoring data such as heart rate and blood oxygen, it may mislead users in health management. The system combines self - calibration and manual calibration to reduce the potential risks brought by data errors, ensuring the reliability of the measurement results, thereby enhancing the overall safety and practicality of the device.

[0052] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A sensor error calibration method for a smart watch, characterized in that: The following steps are involved: Based on the preset usage time of the smart watch, the preset sensor is monitored in real time by the smart watch to collect corresponding trend sensor data; Determining whether the trend sensing data presents a preset deviation trend; If so, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points that exceed the standard deviation range as outliers in the trend sensing data, and classify the outliers into outliers, wherein the outliers are specifically classified into short-term sudden anomalies, long-term drifts, and outliers; Determine whether data repair can be performed on the abnormal value; If possible, the abnormal value is drift compensated according to the abnormal classification, the sensor error coefficient of the smart watch is dynamically calibrated, the environmental factors pre-collected by the smart watch are used as compensation input of the sensor error coefficient, and the sensor error coefficient is adaptively corrected, wherein the drift compensation specifically includes linear drift compensation, nonlinear drift compensation and periodic drift compensation, and the environmental factors specifically include temperature, humidity and air pressure.

2. The sensor error calibration method of a smart watch according to claim 1, characterized in that: The step of marking the data points that are beyond the standard deviation range as abnormal values ​​in the trend sensing data further includes: Based on the abnormal number of the abnormal values, collecting data on the proportion of the abnormal number in the trend sensing data, and identifying distribution information of the abnormal values ​​according to the proportion data; Determining whether the distribution information matches a preset specific condition, wherein the specific condition specifically includes abnormal values ​​concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors; If so, the working environment of the sensor is detected, and according to the working environment, the accuracy error of the sensor is calculated, and the corresponding abnormal pattern is obtained from the distribution information.

3. The sensor error calibration method of a smart watch according to claim 1, characterized in that: Before the step of classifying the abnormal value as abnormal, the method further includes: Extracting data anomaly features of the abnormal value and comparing the output data of different sensors in the smart watch, wherein the data anomaly features specifically include fluctuation amplitude, change speed and change direction; Determining whether a preset associated anomaly is detected in the output data; If so, identify the communication protocol interface between the different sensors, obtain the bus communication status of the smart watch based on the communication protocol interface, and generate the network communication quality of the smart watch in real time according to the bus communication status, wherein the bus communication status specifically includes noise interference, data transmission delay and connection loss, and the network communication quality specifically refers to the communication quality during data transmission between different sensors.

4. The sensor error calibration method of a smart watch according to claim 1, characterized in that: The step of using the environmental factors pre-collected by the smart watch as the compensation input of the sensor error coefficient also includes: Based on the fluctuations of the environmental parameters, identifying the compensation requirements of the sensor error coefficient, wherein the fluctuations specifically include the temperature and humidity fluctuation range, air pressure changes and electromagnetic interference; Determining whether the compensation requirement matches a preset compensation strategy; If not, the user's usage scenario of the smart watch is obtained, and the compensation strategy is adaptively optimized according to the usage scenario. According to the preset complementarity between different sensors, the influence coefficient of the compensation strategy when an error occurs in a single sensor is dynamically adjusted, wherein the usage scenarios specifically include sports scenarios, office life scenarios, and extreme weather scenarios.

5. The sensor error calibration method of a smart watch according to claim 1, characterized in that: The step of determining whether the trend sensing data presents a preset deviation trend also includes: Based on a preset trend period, detecting corresponding instantaneous abnormal events from the trend sensing data, wherein the trend period specifically includes a global trend and a local trend; Determining whether the instantaneous abnormal event exhibits a preset periodic fluctuation; If so, the regular change information corresponding to the trend sensing data is obtained through the instantaneous abnormal event, and the trend change point corresponding to the periodic fluctuation is constructed according to the regular change information.

6. The sensor error calibration method of a smart watch according to claim 1, characterized in that: The step of determining whether the abnormal value can be repaired further includes: Based on the time window corresponding to the outlier, calculate the data missing rate of the time window; Determining whether the data missing rate exceeds a preset missing value; If so, the impact of the missing data on the final sensor data is identified through the abnormal value, and based on the impact, the user is guided to re-measure the final sensor data. Based on the abnormal data segment of the abnormal value, the corresponding abnormal cause is recorded in the smart watch, wherein the abnormal cause specifically includes sensor detachment, signal loss and external environmental factors.

7. The sensor error calibration method of a smart watch according to claim 1, characterized in that: The step of monitoring a preset sensor in real time through the smart watch based on the preset usage time of the smart watch and collecting corresponding trend sensor data also includes: Detecting the time window where abnormal values ​​occur based on preset statistical characteristics of the sensor data, wherein the statistical characteristics specifically include mean, variance and standard deviation; Determine whether the number of the time windows reaches a preset threshold; If so, the preset self-calibration mode of the sensor is triggered periodically according to the usage time. Through the self-calibration mode, the error accumulation of the sensor is reduced, and the preset calibration tutorial of the smart watch is activated. According to the calibration tutorial, the user is guided to manually calibrate the smart watch.

8. A sensor error calibration system for a smart watch, characterized in that: include: A collection module, used to monitor preset sensors in real time through the smart watch based on the preset usage time of the smart watch, and collect corresponding trend sensor data; A judgment module, used to judge whether the trend sensing data presents a preset deviation trend; an execution module, configured to, if yes, select preset data points from the trend sensing data, calculate the standard deviation of the data points, mark the data points that exceed the standard deviation range as abnormal values ​​in the trend sensing data, and classify the abnormal values ​​into abnormalities, wherein the abnormality classification specifically includes short-term sudden abnormalities, long-term drifts and outliers; A second judgment module is used to judge whether the abnormal value can be repaired; The second execution module is used to, if possible, perform drift compensation on the abnormal value according to the abnormal classification, dynamically calibrate the sensor error coefficient of the smart watch, use the environmental factors pre-collected by the smart watch as the compensation input of the sensor error coefficient, and adaptively correct the sensor error coefficient, wherein the drift compensation specifically includes linear drift compensation, nonlinear drift compensation and periodic drift compensation, and the environmental factors specifically include temperature, humidity and air pressure.

9. The sensor error calibration system for a smart watch according to claim 8, characterized in that: The execution module also includes: An identification unit is used to collect data on the proportion of the abnormal number of the abnormal value in the trend sensing data based on the abnormal number of the abnormal value, and identify distribution information of the abnormal value according to the proportion data; A judging unit, used to judge whether the distribution information matches a preset specific condition, wherein the specific condition specifically includes abnormal values ​​concentrated in a specific time period or abnormal fluctuations caused by specific environmental factors; The execution unit is configured to detect the working environment of the sensor, calculate the accuracy error of the sensor according to the working environment, and obtain the corresponding abnormal pattern from the distribution information.

10. The sensor error calibration system for a smart watch according to claim 8, characterized in that: Also includes: An extraction module is used to extract data anomaly features of the abnormal value and compare the output data of different sensors in the smart watch, wherein the data anomaly features specifically include fluctuation amplitude, change speed and change direction; A third judgment module is used to judge whether the output data detects a preset associated anomaly; The third execution module is used to identify the communication protocol interface between the different sensors, obtain the bus communication status of the smart watch based on the communication protocol interface, and generate the network communication quality of the smart watch in real time according to the bus communication status, wherein the bus communication status specifically includes noise interference, data transmission delay and connection loss, and the network communication quality specifically refers to the communication quality when data is transmitted between different sensors.

Images