A sensor-based intelligent wearable device physiological function detection method and system

Abstract

The application relates to the technical field of intelligent wearable devices, and provides a physiological function detection method and system of an intelligent wearable device based on a sensor, which comprises the following steps: acquiring detection physiological data of a user detected by an intelligent wearable device and skin state sensor data of a skin state sensor on the intelligent wearable device; the skin state sensor comprises a pressure sensor in contact with the skin of the user and a humidity sensor in contact with the skin of the user; when it is detected that there is abnormal detection physiological data in the detection physiological data, determining a data abnormality reason of the abnormal detection physiological data according to the skin state sensor data; and determining physiological training state information of the user based on the data abnormality reason, the abnormal detection physiological data and the skin state sensor data. According to the scheme, the accuracy of physiological function detection of the intelligent wearable device can be improved.

Description

Technical Field

[0001] This application relates to the field of smart wearable device technology, and in particular to a sensor-based method and system for detecting physiological functions in smart wearable devices. Background Technology

[0002] In the field of modern sports and health management, smart wearable devices have become indispensable health companions in people's daily lives, aiming to continuously acquire and analyze users' physiological data to provide personalized exercise guidance, health warnings, and risk assessments. However, in practical applications, especially in certain specific and complex sports scenarios, existing technologies still face many challenges in terms of the accuracy and continuity of data acquisition, as well as the reliability of multi-parameter comprehensive analysis. These challenges often stem from the specificity of exercise patterns, interference from environmental factors, and differences in individual users' physiological states, leading to distortion and conflicts in sensor data, which in turn affect the system's accurate judgment of the user's true physiological state.

[0003] For example, in complex exercise scenarios involving isometric contractions and high-intensity strength training, when a user performs heavy deadlifts or squats, all the muscles in the body contract strongly, especially the muscles in the arms, back, and legs. This strong muscle contraction directly affects smart wearable devices worn on the wrist, altering the translucency and hemodynamics of local tissues. For optical sensors that rely on photoplethysmography (PPG) technology to measure heart rate, this compression and tissue changes severely interfere with the light emission and reception paths, causing drastic fluctuations in heart rate readings, or even complete signal loss at certain moments, outputting a value far lower than the actual heart rate, or displaying irregular heartbeats. At this point, the heart rate data received by the terminal application has been affected by both the exercise pattern and local physiological changes, significantly reducing its reliability.

[0004] Furthermore, during strength training, users often sweat profusely. The accumulation of sweat, especially in the area where the device is worn, further exacerbates the distortion of sensor data. Sweat forms a conductive and reflective film between the skin and the sensor, which not only affects the optical signal transmission of optical sensors but may also cause changes in the contact resistance of electrode-based sensors (such as those used to measure skin conductivity or ECG signals), introducing additional noise. Simultaneously, the lubricating effect of sweat can cause the device to slip or shift slightly on the wrist, making the contact between the sensor and the skin less stable and further deteriorating signal quality. In this situation, the optical heart rate signal, already weakened by muscle contraction, becomes even more erratic and unreliable, making it almost impossible for the terminal application to extract valid heart rate information.

[0005] Faced with such a complex and contradictory set of data, existing analysis mechanisms are prone to misjudgment. Motion sensors may report low-intensity activity when the user is actually performing high-intensity isometric contractions; optical heart rate sensors may display abnormally low values ​​or drastic fluctuations, severely inconsistent with actual high heart rate states. This situation, caused by the interplay of multiple factors such as specific exercise patterns, local physiological changes, the user's sub-health state, and the device's wearing environment, leads to conflicts and distortions between multi-source information, making it impossible for the system to accurately determine the user's true physiological state and training load. This is a real and pressing problem in the pursuit of refined and personalized sports and health management. Summary of the Invention

[0006] This application provides a sensor-based method and system for detecting physiological functions in smart wearable devices, aiming to solve the problem that the accuracy, continuity, and reliability of multi-parameter comprehensive analysis of physiological data collected by smart wearable devices are insufficient in complex motion scenarios, leading to inaccurate judgment of the user's true physiological state by the system.

[0007] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, a sensor-based method for detecting physiological functions in a smart wearable device is provided, comprising: acquiring physiological data of a user detected by the smart wearable device and skin state sensing data from a skin state sensor on the smart wearable device; the skin state sensor includes a pressure sensor in contact with the user's skin and a humidity sensor in contact with the user's skin; when abnormal physiological data is detected, determining the cause of the abnormal physiological data based on the skin state sensing data; and determining the user's physiological training state information based on the cause of the abnormal data, the abnormal physiological data, and the skin state sensing data.

[0008] Furthermore, in the above method, when the abnormal physiological data to be detected is heart rate data, the cause of the abnormality in the abnormal physiological data to be detected is determined based on the skin state sensor data, including: determining whether any skin state sensor data is greater than or equal to the corresponding preset sensor data threshold; when any skin state sensor data is less than the corresponding preset sensor data threshold, determining that the cause of the abnormality in the abnormal physiological data to be a physical abnormality; when any skin state sensor data is greater than or equal to the corresponding preset sensor data threshold, determining the first moment when the skin state sensor data is equal to the preset sensor data threshold; determining whether the duration between the first moment and the abnormal start moment of the abnormal physiological data is less than a preset duration threshold; if so, determining that the cause of the abnormal physiological data to be an external interference; otherwise, determining that the cause of the abnormal physiological data to be a physical abnormality.

[0009] Based on this, the causes of data anomalies include physical abnormalities or external interference. The user's physiological training status information is determined based on the causes of data anomalies, anomaly detection physiological data, and skin condition sensor data. This includes: determining whether the cause of data anomalies is external interference; when the cause of data anomalies is not external interference, determining the user's physiological training status information to indicate that the user's training is abnormal; when the cause of data anomalies is external interference, obtaining the user's preset normal physiological characteristic information; and determining the user's physiological training status information based on skin condition sensor data, preset normal physiological characteristic information, and anomaly detection physiological data.

[0010] More specifically, in some implementation schemes, the user's physiological training status information is determined based on skin condition sensor data, preset normal physiological characteristic information, and abnormal detection physiological data, including: determining the user's normal detection physiological data range based on pressure sensor data and preset normal physiological characteristic information; and determining the user's physiological training status information based on skin condition sensor data, the user's abnormal detection physiological data, and the normal detection physiological data range.

[0011] Preferably, the preset normal physiological characteristic information includes the range of resting physiological data detected by the user in a resting state. Determining the normal physiological data range of the user based on pressure sensing data and preset normal physiological characteristic information includes: obtaining a first preset correspondence; the first preset correspondence includes a one-to-one correspondence between multiple pressure sensing data ranges and multiple first adjustment coefficients; using the first adjustment coefficient corresponding to the pressure sensing data range in the first preset correspondence as the adjustment coefficient of the resting physiological data range; and multiplying the upper and lower limits of the resting physiological data range by the adjustment coefficient of the resting physiological data range to obtain the normal physiological data range.

[0012] Based on the above, the user's physiological training status information is determined according to skin condition sensor data, abnormal detection physiological data of the user, and the range of normal detection physiological data. This includes: correcting the user's abnormal detection physiological data based on skin condition sensor data to obtain corrected detection physiological data; when the corrected detection physiological data is within the range of normal detection physiological data, the user's physiological training status information is determined to indicate that the user's training is normal; otherwise, the user's physiological training status information is determined to indicate that the user's training is abnormal.

[0013] Furthermore, the abnormal detection physiological data of the user is corrected based on the skin condition sensing data to obtain corrected detection physiological data, including: obtaining a second preset correspondence; the second preset correspondence includes a one-to-one correspondence between multiple humidity sensing data ranges and multiple second adjustment coefficients; using the second adjustment coefficient corresponding to the humidity sensing data range in the second preset correspondence as the adjustment coefficient of the abnormal detection physiological data; multiplying the original data value of the abnormal detection physiological data with the adjustment coefficient of the abnormal detection physiological data to obtain the corrected detection physiological data.

[0014] In one embodiment, correcting abnormal detection physiological data of a user based on skin condition sensing data to obtain corrected detection physiological data includes: obtaining a third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple pressure sensing data ranges and multiple preset data values ​​of abnormal detection physiological data; using the preset data value corresponding to the pressure sensing data range in the third preset correspondence as the target data value; and using the weighted sum of the target data value of the abnormal detection physiological data and the original data value of the abnormal detection physiological data as the corrected detection physiological data.

[0015] As an optional approach, the weighted sum of the target data value and the original data value of the abnormal detection physiological data is used as the corrected detection physiological data. This includes: obtaining a fourth preset correspondence; the fourth preset correspondence includes a one-to-one correspondence between multiple first information and multiple humidity sensing data ranges, the first information includes a first weight value and a second weight value, the sum of the first weight value and the second weight value is 1, and the first weight value is positively correlated with the maximum value of the humidity sensing data range; the first information corresponding to the humidity sensing data range in the fourth preset correspondence is used as the target first information; the product of the first weight value in the target first information and the target data value of the abnormal detection physiological data is used as the first sub-value; the product of the second weight value in the target first information and the original data value of the abnormal detection physiological data is used as the second sub-value; and the sum of the first sub-value and the second sub-value is used as the corrected detection physiological data.

[0016] Secondly, this application also discloses a sensor-based intelligent wearable device physiological function detection system, comprising: an acquisition device and a processing device; the acquisition device is used to acquire the detected physiological data of the user detected by the intelligent wearable device and the skin state sensing data of the skin state sensor on the intelligent wearable device; the skin state sensor includes a pressure sensor in contact with the user's skin and a humidity sensor in contact with the user's skin; the processing device is used to determine the cause of the abnormal detected physiological data based on the skin state sensing data when abnormal detected physiological data is detected; the processing device is used to determine the user's physiological training state information based on the cause of the abnormal data, the abnormal detected physiological data, and the skin state sensing data.

[0017] Beneficial Effects: This application discloses a sensor-based method for detecting physiological functions in smart wearable devices. It acquires physiological data of the user detected by the smart wearable device and skin state sensor data from the device. When abnormal physiological data is detected, the cause of the abnormality is determined based on the skin state sensor data. Finally, the user's physiological training state information is determined based on the cause of the abnormality, the abnormal physiological data, and the skin state sensor data. This method effectively solves the problem in existing technologies where the accuracy, continuity, and reliability of multi-parameter comprehensive analysis of physiological data acquisition by smart wearable devices are insufficient in complex motion scenarios, leading to inaccurate judgments of the user's true physiological state.

[0018] Specifically, this application introduces skin condition sensors (including pressure and humidity sensors) to acquire real-time information about the user's skin contact with the device, such as wearing pressure and skin humidity. When abnormal physiological data (such as heart rate) is detected, the system no longer relies solely on a single physiological data point for judgment, but rather combines this skin condition sensor data to analyze the root cause of the abnormality. For example, if the pressure sensor data shows that the device is worn too tightly or too loosely, or the humidity sensor data shows excessive sweating, this information can help the system determine whether the abnormal physiological data is due to external interference (such as device displacement or the influence of sweat) or a genuine physical abnormality of the user.

[0019] Through this multi-source data fusion and intelligent analysis, this application can more accurately identify data distortion and conflict, avoiding the misjudgments that traditional methods are prone to when faced with complex movement patterns, environmental interference, and differences in individual physiological states of users. This significantly improves the accuracy of judging the user's true physiological state and training load, providing reliable technical support for refined and personalized sports health management. Attached Figure Description

[0020] Figure 1A schematic flowchart illustrating a sensor-based method for detecting physiological functions in a smart wearable device, as provided in this application. Figure 2 A flowchart illustrating another sensor-based method for detecting physiological functions in smart wearable devices provided in this application; Figure 3 A flowchart illustrating another sensor-based method for detecting physiological functions in smart wearable devices provided in this application; Figure 4 This application provides a schematic diagram of the architecture of a sensor-based intelligent wearable device physiological function detection system. Detailed Implementation

[0021] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] Traditional smart wearable devices face numerous challenges in the field of sports and health management, especially in complex sports scenarios, regarding the accuracy and continuity of data collection and the reliability of multi-parameter comprehensive analysis. These challenges often lead to sensor data distortion and conflicts, thereby affecting the system's accurate judgment of the user's true physiological state. For example, during high-intensity strength training or isometric contraction exercises, strong muscle contractions, sweat accumulation, and device wearing stability issues can all cause drastic fluctuations, signal loss, or abnormally low values ​​in optical heart rate sensor data. This makes it difficult for the terminal application to extract effective information, resulting in misjudgments of the user's physiological state and training load.

[0024] In this regard, such as Figure 1 As shown, this application proposes a sensor-based method for detecting physiological functions in smart wearable devices, comprising: S101. Acquire the physiological data of the user detected by the smart wearable device and the skin condition sensing data of the skin condition sensor on the smart wearable device.

[0025] Skin condition sensors include pressure sensors that come into contact with the user's skin and humidity sensors that come into contact with the user's skin.

[0026] S102. When abnormal physiological data is detected in the physiological data, the cause of the abnormality of the abnormal physiological data is determined based on the skin condition sensor data.

[0027] S103. Determine the user's physiological training status information based on the cause of data anomalies, anomaly detection physiological data, and skin condition sensor data.

[0028] This application introduces a skin condition sensor and combines its sensing data to analyze and correct abnormal physiological data. It can effectively distinguish whether the abnormal physiological data is caused by physical abnormalities or by external interference, thereby more accurately assessing the user's physiological training status and overcoming the limitations of existing technologies in data analysis in complex sports scenarios.

[0029] To better understand the technical solutions proposed in this application, it is necessary to explain some key terms and implementation environments involved. In this application, "smart wearable device" refers to an electronic device that can be worn on a user's body and continuously monitor their physiological activities and environmental parameters, such as smartwatches, smart bracelets, and smart clothing. These devices typically integrate multiple sensors to collect the user's physiological and environmental data. "Detecting physiological data" refers to the user's physiological indicator data collected by the smart wearable device through its built-in sensors (such as heart rate sensors, blood oxygen sensors, and body temperature sensors). This data can be real-time and continuous, used to reflect the user's physical state. "Skin condition sensor" is a key component of this application, including a pressure sensor and a humidity sensor that are in contact with the user's skin. The pressure sensor detects the contact pressure between the device and the skin, reflecting the tightness of the fit or the pressure on local tissues; the humidity sensor detects the humidity of the skin surface, reflecting the amount of sweat. This skin condition sensor data is crucial for determining the cause of abnormal physiological data.

[0030] The method proposed in this application first requires acquiring the user's physiological data detected by the smart wearable device and the skin condition sensing data from the skin condition sensors on the smart wearable device. The skin condition sensors include a pressure sensor and a humidity sensor that are in contact with the user's skin.

[0031] Specifically, smart wearable devices can be equipped with various physiological sensors, such as photoplethysmography (PPG) sensors for acquiring heart rate data, electrode sensors for acquiring electrocardiogram (ECG) data, and temperature sensors for acquiring body temperature data. These sensors can collect the user's physiological data in real time or periodically. For example, a PPG sensor measures changes in blood volume by emitting light of a specific wavelength and receiving reflected light, thereby calculating heart rate. Simultaneously, smart wearable devices also integrate skin condition sensors. Pressure sensors, which can be piezoresistive, piezoelectric, or capacitive, can be integrated into the surface of the device that contacts the skin to measure the contact pressure between the device and the skin. For example, when the device is worn too tightly or the user's muscles contract, the pressure sensor will output a higher pressure value. Humidity sensors, which can be capacitive or resistive, can be integrated into the surface of the device that contacts the skin to measure the amount of sweat or humidity on the skin surface. For example, when the user sweats heavily, the humidity sensor will output a higher humidity value. This physiological data and skin condition sensor data can be transmitted by the processor inside the smart wearable device or via a wireless communication module to an external processing device for further analysis.

[0032] When abnormal physiological data is detected, the cause of the abnormality is determined based on skin condition sensor data.

[0033] For example, smart wearable devices can continuously monitor a user's heart rate data. When heart rate data suddenly drops significantly below the normal range, fluctuates drastically, or is lost, it can be identified as abnormal physiological data. To determine whether this abnormality is caused by bodily abnormalities (such as arrhythmia or excessive fatigue) or external interference (such as improper device wearing, excessive sweating, or violent muscle contractions), this application introduces skin condition sensor data for auxiliary judgment. For example, when abnormal heart rate data is detected, the system simultaneously analyzes data from pressure and humidity sensors. If the pressure sensor shows excessive pressure between the device and the skin, or the humidity sensor shows excessive skin surface humidity, these skin condition sensor data may indicate that the abnormal heart rate data is caused by external interference. Conversely, if the skin condition sensor data is within the normal range, the abnormal heart rate data is more likely to indicate a bodily abnormality.

[0034] The user's physiological training status information is determined based on the cause of data anomalies, anomaly detection physiological data, and skin condition sensor data.

[0035] Once the cause of the abnormal physiological data is determined, the system can more accurately assess the user's physiological training status. For example, if abnormal heart rate data is determined to be caused by external interference (such as wearing the device too loosely or excessive sweating), the system can correct the abnormal heart rate data to eliminate the influence of external interference, thereby obtaining a heart rate value closer to reality. The corrected heart rate value can be used to determine whether the user is within the normal training load range. If the corrected heart rate value is within the normal training range, the system can determine that the user's physiological training status indicates that the user's training is normal. Conversely, if the corrected heart rate value still exceeds the normal training range, or if the abnormal heart rate data is determined to be caused by a physical abnormality, the system can determine that the user's physiological training status indicates that the user's training is abnormal, and may issue a warning or provide corresponding suggestions to the user. In this way, this application can provide a more accurate assessment of physiological training status and avoid misjudgments caused by external interference.

[0036] The sensor-based physiological function detection method for smart wearable devices proposed in this application aims to address the problem that existing technologies suffer from sensor data distortion and conflict in complex sports scenarios due to differences in movement patterns, environmental factors, and individual physiological states, which in turn affects the system's accurate judgment of the user's true physiological state. Traditional methods often directly judge the user's state based on physiological data, which is prone to misjudgment when the data is affected by external interference. For example, during high-intensity strength training, muscle contraction may cause abnormal heart rate sensor data, but traditional methods may misjudge this as a user's physical abnormality.

[0037] The core innovation of this application lies in the introduction of a skin condition sensor and the use of its data to differentiate the causes of abnormal physiological data. By acquiring the user's physiological data detected by the smart wearable device and the skin condition sensing data from the skin condition sensor on the smart wearable device, this application can gain a more comprehensive understanding of the environment and local body condition during data collection. When abnormalities are detected in the physiological data, this application no longer simply attributes them to bodily abnormalities, but determines the cause of the abnormal physiological data based on the skin condition sensing data (including pressure sensing data and humidity sensing data). This mechanism can effectively distinguish whether the data abnormalities are caused by external interference such as improper device wearing or excessive sweating, or are indeed caused by internal physiological abnormalities in the user's body.

[0038] Compared to existing technologies, the advantage of this application lies in its ability to provide more accurate assessments of physiological training status. For example, in traditional solutions, if heart rate data shows abnormally low values ​​due to equipment slippage or sweat interference during high-intensity training, the system may misjudge that the user's training intensity is insufficient or that there is a physical problem. However, by analyzing data from pressure and humidity sensors, this application can identify that such anomalies are caused by external interference and correct the abnormal physiological data, thereby obtaining physiological data that is closer to the actual situation. Based on the corrected data, the system can more accurately determine the user's physiological training status, avoiding misjudgments and improving the reliability and effectiveness of exercise health management. This method not only improves the accuracy of data analysis but also provides users with more personalized and reliable health guidance.

[0039] This application further proposes a specific method for determining the cause of abnormality in physiological data when the abnormal detection physiological data is heart rate data, based on skin condition sensor data, in order to improve the accuracy of abnormality cause judgment.

[0040] Specifically, when the abnormal physiological data detected is heart rate data, the cause of the abnormality in the abnormal physiological data is determined based on the aforementioned skin condition sensor data, including the following steps: Determine whether any skin state sensor data is greater than or equal to the corresponding preset sensor data threshold; if any skin state sensor data is less than the corresponding preset sensor data threshold, determine that the cause of the abnormality in the abnormal detection physiological data is a bodily abnormality; if any skin state sensor data is greater than or equal to the corresponding preset sensor data threshold, determine the first moment when the skin state sensor data equals the preset sensor data threshold; determine whether the duration between the first moment and the abnormal start moment of the abnormal detection physiological data is less than a preset duration threshold; if so, determine that the cause of the abnormal detection physiological data is external interference; otherwise, determine that the cause of the abnormal detection physiological data is a bodily abnormality.

[0041] Skin condition sensing data refers to data acquired by skin condition sensors on smart wearable devices. These sensors include pressure sensors and humidity sensors that come into contact with the user's skin. Therefore, skin condition sensing data can include both pressure and humidity sensing data. Preset sensing data thresholds are reference values ​​pre-defined for different types of skin condition sensing data, used to determine whether the skin condition is within the normal range or whether there are abnormalities. For example, a pressure sensor may have a preset pressure threshold, and a humidity sensor may have a preset humidity threshold. The first moment refers to the time when skin condition sensing data first reaches or exceeds its corresponding preset sensing data threshold. The abnormality initiation moment refers to the time when abnormal physiological data (such as heart rate data) begins to show abnormalities. The preset duration threshold is a pre-defined time length used to determine the temporal correlation between changes in skin condition and abnormal physiological data.

[0042] The solution proposed in this application can effectively distinguish whether abnormal physiological data is caused by abnormalities in the user's body or by external interference such as poor contact between the smart wearable device and the skin by introducing threshold judgment and time correlation analysis of skin condition sensing data.

[0043] Specifically, when skin condition sensor data (such as pressure or humidity) is below a preset threshold, it usually indicates good contact between the smart wearable device and the user's skin. In this case, if an abnormal heart rate occurs, it is more likely to be interpreted as a physical abnormality. Conversely, when skin condition sensor data reaches or exceeds a preset threshold (e.g., excessive pressure or humidity may indicate device displacement or excessive sweating), and this change in condition is highly correlated with the onset time of the abnormal heart rate within a preset duration threshold, it can be reasonably inferred that the abnormal heart rate is caused by external interference rather than a true physiological abnormality. This mechanism avoids the one-sidedness of directly judging a physical abnormality based solely on abnormal physiological data, thereby improving the accuracy of determining the cause of the abnormality.

[0044] Through the above technical solution, this application provides a more refined and accurate method for determining the cause of abnormal physiological data, specifically when the detected physiological data is heart rate data. This method effectively distinguishes between physiological data abnormalities caused by user physical abnormalities and those caused by external interference (such as improper device wearing or excessive sweating) by comprehensively analyzing skin condition sensor data and its temporal correlation with abnormal physiological data. This significantly improves the accuracy of abnormality determination, avoids misjudging user physical abnormalities due to external interference, and thus provides a more reliable basis for determining subsequent physiological training status information, making physiological training guidance more targeted and effective.

[0045] This application further proposes the aforementioned method for determining a user's physiological training status information, wherein the causes of data anomalies include physical abnormalities or external interference. The method for determining the user's physiological training status information based on the causes of data anomalies, anomaly detection physiological data, and skin condition sensor data includes: Determine whether the cause of the data anomaly is external interference; if the cause of the data anomaly is not external interference, determine the user's physiological training status information to indicate that the user's training is abnormal; if the cause of the data anomaly is external interference, obtain the user's preset normal physiological characteristic information; determine the user's physiological training status information based on skin condition sensor data, preset normal physiological characteristic information, and abnormal detection physiological data.

[0046] Specifically, the causes of data anomalies can be understood as the root factors leading to abnormal physiological data. "Physical anomalies" refer to deviations from the normal range caused by the user's own physiological state (e.g., fatigue, illness, overtraining); while "external interference" refers to anomalies caused by factors other than the user's physiological state, such as improper use of smart wearable devices, poor sensor contact, or environmental factors (e.g., severe vibration, strong electromagnetic interference). When determining physiological training status information, the identified causes of data anomalies are first assessed to distinguish between external interference and physical anomalies. If the assessment concludes that the cause of the data anomaly is not external interference, i.e., a physical anomaly, then the user's physiological training status information directly indicates an abnormal training state. This means that the abnormal physiological data at this point is considered a true reflection of the user's physical condition, requiring attention and adjustment of the training plan.

[0047] Furthermore, if the data anomaly is determined to be caused by external interference, a more refined strategy is required. In this case, the system acquires the user's preset normal physiological characteristics. These preset normal physiological characteristics may include the user's physiological data range at rest, historical training data, and personal health records. This information provides a reference for assessing the user's physiological baseline under normal conditions. Subsequently, based on skin condition sensor data, preset normal physiological characteristics, and anomaly detection physiological data, the user's physiological training status information is comprehensively determined. This processing method aims to eliminate the influence of external interference on physiological data, thereby more accurately assessing the user's true physiological state after interference has been eliminated.

[0048] This application's solution effectively addresses the problem of inaccurate judgment of physiological training status that may exist in basic solutions by classifying and processing the causes of data anomalies. Specifically, when abnormal physiological data is detected, the system first distinguishes whether the anomaly originates from internal physiological changes in the user's body (physical abnormality) or from external environmental or equipment factors (external interference). This distinction is crucial because anomalies caused by different reasons require different interpretations and response strategies. When an anomaly is determined to be a physical abnormality, the system directly treats it as an indication of training anomaly, prompting the user or relevant personnel to adjust the training intensity or take a break in a timely manner.

[0049] When an anomaly is identified as external interference, the system does not simply categorize it as a training anomaly. Instead, it further incorporates the user's pre-defined normal physiological characteristics and combines this with skin condition sensor data to correct or re-evaluate the anomaly detection physiological data. This layered processing mechanism allows the system to more accurately isolate the impact of external interference on physiological data, thereby avoiding erroneous training guidance caused by misjudging external interference as bodily abnormalities and ensuring the reliability of physiological training status information.

[0050] Through the above technical solution, this application can significantly improve the accuracy and reliability of intelligent wearable devices in judging the user's physiological training status information during physiological function detection. Especially in the presence of external interference, this solution can effectively avoid misjudging abnormal physiological data caused by external factors as abnormalities in the user's body, thereby reducing unnecessary training adjustments or concerns. In addition, by introducing preset normal physiological characteristic information and combining it with skin condition sensor data for comprehensive judgment, the assessment of physiological training status becomes more personalized and refined, more realistically reflecting the user's actual physiological condition and providing users with more accurate training suggestions and health management guidance.

[0051] like Figure 2 As shown, this application further proposes a method for determining a user's physiological training state information based on skin condition sensing data, preset normal physiological characteristic information, and abnormal detection physiological data. The specific steps include: S201. Determine the range of normal physiological data for the user based on pressure sensor data and preset normal physiological characteristic information.

[0052] S202. Determine the user's physiological training status information based on skin condition sensor data, abnormal physiological data of the user, and the range of normal physiological data of the user.

[0053] Specifically, "preset normal physiological characteristic information" can be understood as the physiological data characteristics of a user in a specific state (such as a resting state), such as the resting heart rate range and resting blood pressure range. This information is usually measured and stored in advance. "Pressure sensing data" refers to the pressure value detected by the pressure sensor in the skin condition sensor, reflecting the tightness of contact between the smart wearable device and the skin. By combining pressure sensing data and preset normal physiological characteristic information, a "normal detection physiological data range" that better matches the current wearing state can be dynamically adjusted or determined. For example, when the pressure sensing data indicates that the device is not in close contact with the skin, it may be necessary to appropriately expand or adjust the normal detection physiological data range to avoid misjudgment.

[0054] The "normal range of physiological data" refers to the range of values ​​within which a user's physiological data is considered normal under current wearing and environmental conditions. Once this range is determined, "skin condition sensor data" (including pressure and humidity sensor data) and "abnormal physiological data" can be used to comprehensively assess the user's physiological training status. For example, it can be assessed whether abnormal physiological data falls within the adjusted normal range, or whether the abnormal physiological data can be corrected based on skin condition sensor data before evaluation.

[0055] This application's solution dynamically adjusts the normal physiological data range by introducing pressure-sensing data, thus solving the problem that traditional fixed physiological data ranges may not accurately reflect the user's true physiological state when external interference is present. Specifically, when the contact pressure between the smart wearable device and the skin changes, the quality and accuracy of physiological data acquisition may be affected. For example, wearing the device too loosely may lead to lower heart rate data or artifacts. By utilizing pressure-sensing data, preset normal physiological characteristic information can be corrected to obtain a normal physiological data range that is more adapted to the current wearing conditions.

[0056] Subsequently, the abnormal physiological data is comprehensively evaluated by combining overall skin condition sensor data (including pressure and humidity). For example, abnormal physiological data can be corrected, or it can be directly determined whether it falls within the adjusted range of normal physiological data. This step-by-step and dynamic evaluation mechanism enables a more accurate assessment of the user's physiological training status, even under external interference, avoiding misjudgments caused by improper wearing or environmental factors.

[0057] Through the above technical solution, this application can effectively improve the accuracy and robustness of intelligent wearable devices in judging the user's physiological training status information under the presence of external interference. By dynamically adjusting the range of normal detected physiological data based on pressure sensor data, the benchmark for physiological data evaluation is made more closely aligned with actual wearing conditions, thereby avoiding misjudgments caused by changes in device wearing status. In addition, by combining skin condition sensor data to comprehensively evaluate abnormal detected physiological data, the system's adaptability to complex external interference is further enhanced, enabling users to obtain more reliable physiological training status feedback, thereby better guiding their training activities.

[0058] This application further proposes a more refined and dynamic method for determining the range of normal physiological data. By introducing a preset correspondence and adjustment coefficient, the range of normal physiological data can be adaptively adjusted according to real-time pressure sensing data.

[0059] In the above method, the preset normal physiological characteristic information is set to include the range of resting physiological data detected by the user in a resting state. The range of resting physiological data detected refers to the normal fluctuation range of various physiological indicators (such as heart rate, respiratory rate, etc.) of the user in a completely relaxed and non-exercising state, which is usually obtained by medical experts or through a large amount of data statistics.

[0060] Specifically, the steps for determining the user's normal physiological data range based on pressure sensor data and preset normal physiological characteristic information include: First, a first preset correspondence is obtained. This first preset correspondence is constructed as a one-to-one correspondence between multiple pressure sensing data ranges and multiple first adjustment coefficients. For example, pressure sensing data can be divided into multiple ranges such as low intensity, medium intensity, and high intensity, with each range corresponding to a specific first adjustment coefficient. This first adjustment coefficient is a multiplicative factor used to adjust the range of resting physiological data. Its purpose is to dynamically adjust the "normal" fluctuation range of the user's physiological indicators based on the user's current exercise intensity or external pressure level.

[0061] Secondly, the first adjustment coefficient corresponding to the pressure sensing data range in the first preset correspondence is used as the adjustment coefficient for the resting physiological data range. This means that the system will look up the range of the pressure data in the first preset correspondence based on the real-time acquired pressure sensing data, and extract the first adjustment coefficient corresponding to that range. For example, if the current pressure sensing data indicates that the user is in a moderate-intensity exercise state, the adjustment coefficient corresponding to the moderate-intensity pressure range will be selected.

[0062] Finally, the upper and lower limits of the resting physiological data range are multiplied by an adjustment factor for the resting physiological data range to obtain the normal physiological data range. In this way, the physiological data range at rest is dynamically expanded or reduced to adapt to the user's physiological state under current stress or exercise intensity. For example, if the adjustment factor is greater than 1, the normal physiological data range will be wider than the resting physiological data range to accommodate the normal increase in physiological indicators during exercise; if the adjustment factor is less than 1, the range will be correspondingly narrowed.

[0063] The solution proposed in this application introduces a first preset correspondence and a first adjustment coefficient, making the determination of the normal range of physiological data no longer static, but dynamically adjustable based on real-time pressure sensor data. Because pressure sensor data reflects the user's current exercise intensity or external load, and different exercise intensities cause variations in the fluctuation range of physiological indicators (such as heart rate and respiratory rate) within the normal range, it becomes possible to correct the range of resting physiological data using the adjustment coefficient.

[0064] When pressure sensor data indicates an increase in exercise intensity, the corresponding adjustment coefficient appropriately expands the range of normal physiological data, thus avoiding misjudging normal physiological fluctuations caused by exercise as abnormalities. Conversely, when pressure sensor data indicates a decrease in exercise intensity, the adjustment coefficient may narrow the range to more accurately capture subtle physiological abnormalities. This dynamic adjustment mechanism effectively compensates for the shortcomings of relying solely on statically preset normal physiological characteristic information.

[0065] The above technical solution dynamically adjusts the normal range of detected physiological data based on the user's real-time pressure sensor data, thus making this range more accurately reflect the user's physiological state under different exercise intensities. This significantly improves the accuracy and adaptability of physiological training state information judgment, avoids misjudging abnormalities due to normal fluctuations in physiological data during exercise, and can more sensitively identify physiological abnormalities that truly occur at specific exercise intensities. Furthermore, this solution provides a structured and quantifiable method to determine the normal range of detected physiological data, enhancing the robustness and reliability of the system.

[0066] like Figure 3 As shown, this application further proposes a method for determining a user's physiological training status information based on skin condition sensor data, abnormal detection physiological data, and normal detection physiological data range, specifically including: S301. Correct the abnormal detection physiological data of the user based on the skin condition sensor data to obtain corrected detection physiological data.

[0067] S302. When the corrected physiological data is within the normal range, determine that the user's physiological training status information indicates that the user's training is normal; otherwise, determine that the user's physiological training status information indicates that the user's training is abnormal.

[0068] Specifically, correcting abnormal physiological data of users based on skin condition sensor data refers to adjusting or calibrating the original abnormal physiological data using pressure and humidity sensor data acquired by skin condition sensors. The aim is to eliminate or reduce potential biases caused by external environment, wearing status of smart wearable devices, or skin contact conditions, thereby obtaining corrected physiological data that better reflects the user's true physiological state. Corrected physiological data can be understood as physiological data calibrated after environmental or wearing status adjustments.

[0069] Furthermore, if the corrected physiological data falls within the normal range, the user's physiological training status is considered normal; otherwise, it is considered abnormal. This can be understood as follows: after correcting the abnormal physiological data, the corrected data is compared with a pre-determined range of normal physiological data. If the corrected data falls within the normal range, the user's current physiological state is considered normal, and training can continue; conversely, if the corrected data exceeds the normal range, it indicates that even after correction, the user's physiological state remains abnormal, requiring attention or adjustment of the training plan.

[0070] The solution proposed in this application effectively solves the problem of inaccurate judgments that may result from directly comparing raw abnormal data by first correcting the abnormal detection physiological data based on skin condition sensing data before determining the user's physiological training status information. Specifically, the skin condition sensing data provides real-time information about the contact status between the smart wearable device and the user's skin, as well as the local environment (such as humidity and pressure).

[0071] This information is used to quantify and offset the potential impact of external factors on physiological data. For example, excessive skin humidity may cause a slight deviation in heart rate sensor readings. By correcting the heart rate data using humidity sensing data, we can obtain corrected physiological data that more closely reflects the user's true heart rate. Therefore, comparing the corrected physiological data with the normal range of physiological data can more accurately reflect the user's current physiological training status and avoid misjudgments due to subtle external interference.

[0072] Through the above technical solution, this application can more accurately assess the user's physiological training status. By correcting abnormal physiological data, the subtle influence of external interference on physiological data can be effectively eliminated or reduced, allowing subsequent judgments to be based on more realistic and reliable data. This significantly improves the accuracy and reliability of physiological training status assessment, reduces misjudgments caused by external factors, and thus provides users with more precise training guidance and health management suggestions, enhancing the practical value of smart wearable devices in physiological function detection.

[0073] This application further proposes a step for correcting abnormal physiological data of a user based on skin condition sensor data, and obtaining corrected physiological data includes: Obtain the second preset correspondence; the second preset correspondence includes a one-to-one correspondence between multiple humidity sensing data ranges and multiple second adjustment coefficients; use the second adjustment coefficient corresponding to the humidity sensing data range in the second preset correspondence as the adjustment coefficient of the abnormal detection physiological data; multiply the original data value of the abnormal detection physiological data with the adjustment coefficient of the abnormal detection physiological data to obtain the corrected detection physiological data.

[0074] Specifically, the second preset correspondence refers to a pre-established mapping rule that associates different humidity sensing data ranges with corresponding second adjustment coefficients. For example, when humidity sensing data falls within a specific range, it corresponds to a specific second adjustment coefficient. This correspondence can be established and optimized based on extensive experimental data, physiological models, or expert experience to ensure the accuracy and effectiveness of the correction. Its purpose is to provide a quantitative basis for subsequent correction of abnormal detection physiological data.

[0075] Humidity sensing data can be understood as the humidity information of the user's skin surface collected by the humidity sensor on the smart wearable device. The humidity sensing data range refers to dividing continuous humidity sensing data into several discrete intervals, each interval corresponding to one or a set of second adjustment coefficients. For example, humidity sensing data can be divided into multiple ranges such as "low humidity," "medium humidity," and "high humidity," and different second adjustment coefficients can be set for each range.

[0076] In practical applications, the second adjustment coefficient corresponding to the humidity sensing data range in the second preset correspondence is used as the adjustment coefficient for the abnormal detection physiological data. This means that the system, based on the currently acquired humidity sensing data, finds the range to which the humidity sensing data belongs in the second preset correspondence and extracts the second adjustment coefficient corresponding to that range. This adjustment coefficient will be used to quantitatively correct the abnormal detection physiological data.

[0077] Furthermore, the corrected physiological data is obtained by multiplying the original value of the abnormal physiological data with its adjustment coefficient. This involves using a simple multiplication operation to combine the original abnormal physiological data value with an adjustment coefficient determined based on humidity sensor data, resulting in a corrected physiological data that more closely approximates the actual physiological state. For example, if the original value of the abnormal physiological data is X and the adjustment coefficient is K, then the corrected physiological data is X*K. The purpose is to calibrate the abnormal physiological data by incorporating humidity information, thereby eliminating or reducing the interference of external environmental or skin condition changes on physiological data measurement.

[0078] This application's solution establishes a direct correlation between humidity sensing data and adjustment coefficients for abnormal detection physiological data by introducing a second preset correspondence. When the smart wearable device detects abnormal physiological data, it simultaneously acquires humidity sensing data from the skin condition sensing data. Since humidity sensing data reflects the moisture level of the user's skin surface, and skin moisture often affects the accurate measurement of physiological data (e.g., sweating may cause poor contact or signal distortion in the heart rate sensor), this influence can be quantified by mapping the range of humidity sensing data to a specific second adjustment coefficient.

[0079] Subsequently, the original values ​​of the abnormality detection physiological data are multiplied by the adjustment coefficient to correct the original data. This correction mechanism allows the abnormality detection physiological data to be dynamically adjusted according to real-time skin humidity, effectively reducing measurement errors caused by changes in skin humidity, and making the corrected detection physiological data more accurately reflect the user's true physiological state.

[0080] Through the above technical solution, this application can refine the correction of abnormal physiological data based on humidity sensing data in skin condition sensing data. Compared with correction methods that do not consider the influence of skin humidity, this application establishes a correspondence between the humidity sensing data range and the adjustment coefficient, making the correction process more scientific and quantitative. This effectively reduces the impact of changes in skin humidity (such as sweating) on ​​the accuracy of physiological data measurement, thereby obtaining more accurate corrected physiological data. This precise correction provides a more reliable data foundation for subsequent judgment of the user's physiological training status, significantly improving the accuracy and reliability of physiological training status judgment, avoiding misjudgments caused by external interference, and thus enhancing the practical value of smart wearable devices in physiological function detection.

[0081] This application further proposes that the above-mentioned abnormal detection physiological data of the user based on skin condition sensor data is corrected to obtain corrected detection physiological data, including: Obtain the third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple pressure sensing data ranges and multiple preset data values ​​of abnormal detection physiological data; take the preset data value corresponding to the pressure sensing data range in the third preset correspondence as the target data value; take the weighted sum of the target data value of the abnormal detection physiological data and the original data value of the abnormal detection physiological data as the corrected detection physiological data.

[0082] Specifically, the "third preset correspondence" refers to a pre-established data mapping relationship used to characterize the correction patterns of physiological data under different pressure conditions. This correspondence can be constructed based on a large amount of experimental data, clinical research, or expert experience, and its purpose is to provide a reference "preset data value" for abnormal detection of physiological data under different pressure sensing data ranges. For example, when the pressure of a smart wearable device in contact with the skin is too high or too low, the measurement of physiological data may be interfered with; this preset data value is the benchmark for correcting such interference. The "pressure sensing data range" can be understood as dividing continuous pressure sensing data into several discrete intervals, each interval representing a specific pressure state. For example, "low pressure range," "medium pressure range," and "high pressure range" can be set.

[0083] "Preset data values" refer to the ideal or corrected values ​​that abnormal detection physiological data should approach within a specific pressure sensing data range. These preset data values ​​can be set according to different physiological indicators (such as heart rate, blood oxygen, etc.) and their performance under different pressure conditions. "Target data values" refer to the preset data values ​​that best match the current pressure state, obtained by querying a third preset correspondence based on the current actual pressure sensing data. Their purpose is to provide a pressure-calibrated reference point for subsequent weighted correction. "Weighted sum" refers to combining the target data value and the original data value of the abnormal detection physiological data according to a certain weighting ratio. This weighting method aims to balance the original measurement data and the pressure-calibrated reference data, thereby obtaining a more accurate and reliable corrected detection physiological data.

[0084] The solution proposed in this application introduces a third preset correspondence and uses pressure sensing data to determine the target data value. Then, it corrects the abnormal detection physiological data by weighted summation, which effectively solves the problem that traditional correction methods may be inaccurate due to pressure changes.

[0085] Specifically, when a smart wearable device detects abnormal physiological data, the system first acquires the current pressure sensor data. Since pressure sensor data reflects the tightness and force of contact between the smart wearable device and the skin, and these factors directly affect the measurement accuracy of the physiological data, the system queries a pre-established third-preset correspondence to find a corresponding preset data value based on the range of the current pressure sensor data. This preset data value serves as a reference value for correcting potential deviations in the physiological data within that pressure range—the target data value. Subsequently, this target data value is weighted and summed with the original data value of the abnormal physiological data. This weighted summation mechanism ensures that the corrected physiological data not only considers the original measurement value but also incorporates empirical or model data based on pressure calibration. This effectively reduces errors caused by pressure interference while preserving the original data information, making the corrected physiological data closer to the user's true physiological state.

[0086] Through the above technical solution, this application can more accurately correct abnormal detection physiological data based on skin condition sensing data. Especially when the contact pressure between the smart wearable device and the skin changes, this solution can utilize a preset pressure-physiological data correction relationship to generate a more valuable target data value. By weighted summation, it effectively integrates the original data and calibration data, thereby significantly improving the accuracy and reliability of the corrected physiological data. This allows for a more accurate assessment of the user's physiological training status, avoiding misjudgments caused by external pressure interference, and enhancing the practicality and user experience of smart wearable devices in physiological function detection.

[0087] This application further proposes using a weighted sum of the target data value and the original data value of the anomaly detection physiological data as the corrected detection physiological data, including: Obtain the fourth preset correspondence; the fourth preset correspondence includes a one-to-one correspondence between multiple first information and multiple humidity sensing data ranges, the first information includes a first weight value and a second weight value, the sum of the first weight value and the second weight value is 1, and the first weight value is positively correlated with the maximum value of the humidity sensing data range; take the first information corresponding to the humidity sensing data range in the fourth preset correspondence as the target first information; take the product of the first weight value in the target first information and the target data value of the abnormal detection physiological data as the first sub-value; take the product of the second weight value in the target first information and the original data value of the abnormal detection physiological data as the second sub-value; take the sum of the first sub-value and the second sub-value as the corrected detection physiological data.

[0088] Specifically, the fourth preset correspondence refers to a pre-established association rule used to map different humidity sensing data ranges to corresponding weighted information (i.e., the first information). This correspondence can be stored in the memory of the smart wearable device or dynamically updated via a cloud server. The first information includes two key parameters: a first weight value and a second weight value. The sum of these two weight values ​​is set to 1 to ensure the reasonableness of the weighted sum. It is worth noting that the first weight value is positively correlated with the maximum value of the humidity sensing data range. This means that when skin humidity is higher (i.e., when the humidity sensing data is within a larger humidity sensing data range), the first weight value will increase accordingly, while the second weight value will decrease.

[0089] In practice, firstly, based on the currently acquired humidity sensing data, the humidity sensing data range within the fourth preset correspondence is searched, and the first information corresponding to that range is obtained, which is used as the target first information. Then, the first weight value in the target first information is multiplied by the target data value of the abnormal detection physiological data to obtain the first sub-value. Simultaneously, the second weight value in the target first information is multiplied by the original data value of the abnormal detection physiological data to obtain the second sub-value. Finally, the first and second sub-values ​​are added together to obtain the corrected detection physiological data.

[0090] This application's solution effectively solves the problem of insufficient correction accuracy under different skin humidity conditions by introducing a fourth preset correspondence and dynamically adjusting the weights in the weighted sum based on humidity sensing data. Because the first weight value is positively correlated with the maximum value of the humidity sensing data range, when the user's skin humidity is high, it indicates that the skin may be sweating excessively or in a damp state. At this time, the possibility of abnormal physiological data being affected by external interference (such as poor sensor contact, signal drift, etc.) increases. Therefore, the first weight value is increased, increasing the proportion of the target data value (which is usually determined based on pressure sensing data and preset normal physiological characteristic information, and tends to reflect a normal physiological state) in the corrected physiological data, thus more effectively correcting abnormal data caused by external interference. Conversely, when skin humidity is low, the possibility of external interference decreases, and the second weight value is increased, increasing the proportion of the original abnormal physiological data in the corrected physiological data, retaining more original data information. This adaptive weight adjustment mechanism allows the corrected physiological data to more accurately reflect the user's true physiological state, improving the reliability of physiological training state judgment.

[0091] Through the above technical solution, this application can dynamically adjust the weight allocation in the abnormal detection physiological data correction process according to the actual humidity of the user's skin. Compared with the scheme of correction using fixed weights, the adaptive weight adjustment mechanism of this application can more accurately eliminate or reduce the impact of external interference caused by changes in skin humidity on physiological data detection, thereby making the corrected detection physiological data closer to the user's true physiological state. This can significantly improve the accuracy and reliability of physiological training state information judgment, providing users with more precise training guidance and health monitoring.

[0092] This application also proposes a sensor-based intelligent wearable device physiological function detection system, comprising: an acquisition device and a processing device; the acquisition device is used to acquire the detected physiological data of the user detected by the intelligent wearable device and the skin state sensing data of the skin state sensor on the intelligent wearable device; the skin state sensor includes a pressure sensor in contact with the user's skin and a humidity sensor in contact with the user's skin; the processing device is used to determine the cause of the abnormal detected physiological data based on the skin state sensing data when abnormal detected physiological data is detected; the processing device is used to determine the user's physiological training state information based on the cause of the abnormal data, the abnormal detected physiological data, and the skin state sensing data.

[0093] The system embodiments of this application achieve the above-mentioned physiological function detection through the coordinated operation of the acquisition device and the processing device.

[0094] Specifically, the acquisition device can be understood as the hardware module in a smart wearable device responsible for data acquisition and transmission. For example, the acquisition device may include one or more physiological sensors (such as a photoplethysmography (PPG) sensor for acquiring heart rate data, an electrode sensor for acquiring electrocardiogram (ECG) data, and a temperature sensor for acquiring body temperature data) and skin condition sensors. Pressure sensors, which can be piezoresistive, piezoelectric, or capacitive sensors, can be integrated into the surface of the device that contacts the skin to measure the contact pressure between the device and the skin. Humidity sensors, which can be capacitive or resistive sensors, can be integrated into the surface of the device that contacts the skin to measure the amount of sweat or humidity on the skin surface. These sensors can acquire the user's physiological data and skin condition sensor data in real time or periodically. The acquisition device may also include a data acquisition unit for preliminary digitization and formatting of the raw sensor data, and a communication module for transmitting the acquired data to the processing device via wired or wireless means (such as Bluetooth, Wi-Fi, etc.). In some embodiments, the acquisition device may be a standalone sensor array connected to the main control unit of the smart wearable device via a standard interface. As a specific implementation method, the acquisition device may only contain the sensor itself, while the data acquisition and transmission functions are handled by the main control chip of the smart wearable device.

[0095] The processing device can be understood as a computing unit inside or outside a smart wearable device, configured to perform data analysis and decision-making logic. For example, the processing device can be a microcontroller, microprocessor, digital signal processor, or application-specific integrated circuit (ASIC), and is equipped with memory for storing program instructions and data. The processing device receives physiological data and skin condition sensor data transmitted from the acquisition device by running a pre-set algorithm program.

[0096] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A sensor-based method for detecting physiological functions in smart wearable devices, characterized in that, include: Acquire physiological data of users detected by smart wearable devices and skin condition sensing data from skin condition sensors on smart wearable devices; The skin condition sensor includes a pressure sensor that comes into contact with the user's skin and a humidity sensor that comes into contact with the user's skin; When abnormal physiological data is detected in the physiological data, the cause of the abnormality in the abnormal physiological data is determined based on the skin condition sensing data. The causes of data anomalies include physical abnormalities or external interference; Based on the causes of the data anomalies, the physiological data of the anomaly detection, and the skin condition sensor data, the user's physiological training status information is determined. When the abnormal physiological data detected is heart rate data, the cause of the abnormality in the abnormal physiological data is determined based on the skin condition sensor data, including: Determine whether any skin condition sensor data is greater than or equal to the corresponding preset sensor data threshold; When any skin condition sensor data is less than the corresponding preset sensor data threshold, the abnormality of the abnormal physiological data is determined to be a bodily abnormality. When any skin condition sensor data is greater than or equal to the corresponding preset sensor data threshold, the first moment when the skin condition sensor data is equal to the preset sensor data threshold is determined. Determine whether the time interval between the first moment and the abnormal start time of the abnormal physiological data detection is less than a preset time threshold; If so, determine that the abnormality of the abnormal physiological data is due to external interference; otherwise, determine that the abnormality of the abnormal physiological data is due to a physical abnormality. Corrected physiological data is obtained by correcting abnormal detection data of the user based on skin condition sensor data. If the corrected physiological data falls within the normal range, the user's physiological training status is determined to indicate that the user's training is normal; otherwise, the user's physiological training status is determined to indicate that the user's training is abnormal.

2. The method for detecting physiological functions of a sensor-based smart wearable device according to claim 1, characterized in that, Based on the causes of the data anomalies, the physiological data of anomaly detection, and the skin condition sensor data, the user's physiological training status information is determined, including: Determine whether the data anomaly is caused by external interference; When the cause of data anomalies is not external interference, determine the user's physiological training status information to indicate that the user's training is abnormal; When the cause of data anomalies is external interference, the system acquires the user's preset normal physiological characteristics information. The user's physiological training status information is determined based on skin condition sensor data, preset normal physiological characteristic information, and abnormal detection physiological data.

3. The sensor-based method for detecting physiological functions in a smart wearable device according to claim 2, characterized in that, The user's physiological training status information is determined based on skin condition sensor data, preset normal physiological characteristic information, and abnormal detection physiological data, including: The normal range of physiological data for the user is determined based on pressure sensor data and preset normal physiological characteristic information; The user's physiological training status information is determined based on skin condition sensor data, abnormal physiological data detected by the user, and the range of normal physiological data detected by the user.

4. The sensor-based method for detecting physiological functions in a smart wearable device according to claim 3, characterized in that, The preset normal physiological characteristic information includes the range of resting physiological data detected by the user in a resting state. Based on pressure sensor data and the preset normal physiological characteristic information, the user's normal physiological data range is determined, including: Obtain a first preset correspondence; the first preset correspondence includes a one-to-one correspondence between multiple pressure sensing data ranges and multiple first adjustment coefficients; The first adjustment coefficient corresponding to the pressure sensing data range in the first preset correspondence is used as the adjustment coefficient for the resting detection physiological data range. The normal range of physiological data for resting detection is obtained by multiplying the upper and lower limits of the range of physiological data for resting detection by the adjustment coefficient of the range of physiological data for resting detection.

5. The method for detecting physiological functions of a sensor-based smart wearable device according to claim 1, characterized in that, Based on skin condition sensor data, the abnormal detection physiological data of the user is corrected to obtain corrected detection physiological data, including: Obtain a second preset correspondence; the second preset correspondence includes a one-to-one correspondence between multiple humidity sensing data ranges and multiple second adjustment coefficients; The second adjustment coefficient corresponding to the humidity sensing data range in the second preset correspondence is used as the adjustment coefficient for the abnormal detection physiological data. The corrected physiological data is obtained by multiplying the original data value of the abnormal detection physiological data with the adjustment coefficient of the abnormal detection physiological data.

6. The method for detecting physiological functions of a sensor-based smart wearable device according to claim 1, characterized in that, Based on skin condition sensor data, the abnormal detection physiological data of the user is corrected to obtain corrected detection physiological data, including: Obtain a third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple pressure sensing data ranges and multiple preset data values ​​of abnormal detection physiological data; The preset data value corresponding to the pressure sensing data range in the third preset correspondence is taken as the target data value. The weighted sum of the target data value and the original data value of the anomaly detection physiological data is used as the corrected detection physiological data.

7. The method for detecting physiological functions of a sensor-based smart wearable device according to claim 6, characterized in that, The weighted sum of the target data value and the original data value of the anomaly detection physiological data is used as the corrected detection physiological data, including: Obtain the fourth preset correspondence; the fourth preset correspondence includes a one-to-one correspondence between multiple first information and multiple humidity sensing data ranges, the first information includes a first weight value and a second weight value, the sum of the first weight value and the second weight value is 1, and the first weight value is positively correlated with the maximum value of the humidity sensing data range; The first information corresponding to the humidity sensing data range in the fourth preset correspondence is taken as the target first information. The product of the first weight value in the first information of the target and the target data value of the anomaly detection physiological data is used as the first sub-value; The product of the second weight value in the first information of the target and the original data value of the anomaly detection physiological data is used as the second sub-value; The sum of the first and second sub-values ​​is used as the corrected physiological data for detection.

8. A sensor-based intelligent wearable device physiological function detection system, characterized in that, include: Acquisition device and processing device; Acquisition device, used to acquire the detection physiological data of the user detected by the smart wearable device and the skin state sensing data of the skin state sensor on the smart wearable device; The skin condition sensor includes a pressure sensor that comes into contact with the user's skin and a humidity sensor that comes into contact with the user's skin; The processing device is used to determine the cause of the abnormality in the detected physiological data based on the skin condition sensing data when abnormal physiological data is detected in the physiological data; the cause of the abnormality may include physical abnormalities or external interference. The processing device is also used to determine the user's physiological training status information based on the cause of the data anomaly, the anomaly detection physiological data, and the skin condition sensor data. When the abnormal physiological data detected is heart rate data, the processing device is used to determine the cause of the abnormality in the abnormal physiological data based on the skin condition sensing data, including: Determine whether any skin condition sensor data is greater than or equal to the corresponding preset sensor data threshold; When any skin condition sensor data is less than the corresponding preset sensor data threshold, the abnormality of the abnormal physiological data is determined to be a bodily abnormality. When any skin condition sensor data is greater than or equal to the corresponding preset sensor data threshold, the first moment when the skin condition sensor data is equal to the preset sensor data threshold is determined. Determine whether the time interval between the first moment and the abnormal start time of the abnormal physiological data detection is less than a preset time threshold; If so, determine that the abnormality of the abnormal physiological data is due to external interference; otherwise, determine that the abnormality of the abnormal physiological data is due to a physical abnormality. The processing device is also used to correct the abnormal detection physiological data of the user based on the skin condition sensor data to obtain corrected detection physiological data. The processing device is also used to determine the user's physiological training status information to indicate that the user's training is normal when the corrected physiological data is within the normal range of physiological data; otherwise, it determines the user's physiological training status information to indicate that the user's training is abnormal.

Images