A UV protection evaluation method and device and an intelligent wearable device

Abstract

This application relates to the field of smart wearable technology, and discloses a UV protection assessment method, device, and smart wearable device. The UV protection assessment method includes: acquiring multi-source data, including any combination of ambient light data, ambient temperature and humidity data, raw UV data, positioning data, motion data, and heart rate data; acquiring raw UV data from a UV sensor or a weather API; determining a baseline UV intensity based on the raw UV data; identifying the user's current UV exposure status based on the multi-source data, and compensating for the baseline UV intensity accordingly to obtain the actual UV intensity. This application's embodiment combines multi-source data to identify the user's current UV exposure status, and corrects the baseline UV intensity through status compensation to obtain an actual UV intensity value that fits the current environment and the user's status. This effectively solves the problem of significant deviation between raw UV data and actual UV exposure levels, achieving dynamic, personalized, and highly accurate UV intensity assessment.

Description

Technical Field

[0001] This application relates to the field of smart wearable technology, and in particular to a UV (Ultraviolet) protection assessment method, apparatus, and smart wearable device. Background Technology

[0002] The inventors' research revealed that existing UV protection technologies, which rely on data collected by UV sensors, mobile weather apps, or regional UV index services for evaluation, have at least the following significant drawbacks: Most wearable devices (such as watches and wristbands) have UV sensors worn on the wrist. The UV data they collect is affected by wrist occlusion (clothing, the arm itself), angle (not facing the sky), and height differences, resulting in a significant deviation from the actual UV exposure intensity of key exposed parts of the human body (such as the head and face), leading to inaccurate assessments.

[0003] Mobile weather apps or regional UV index services provide macro-regional average values, which cannot reflect the real-time differences in UV exposure of users in their micro-environment.

[0004] Therefore, improvements to existing technologies are necessary.

[0005] The above information is provided as background information only to aid in understanding this application and does not constitute an assertion or admission that any of the above content can be used as prior art relative to this application. Summary of the Invention

[0006] This application provides a UV protection assessment method, apparatus, and smart wearable device to solve the problem of inaccurate assessment caused by a large deviation between the detected UV intensity and the actual situation in the prior art.

[0007] To achieve the above objectives, this application provides the following technical solution: In a first aspect, embodiments of this application provide a UV protection assessment method, including: Acquire multi-source data, which includes any combination of ambient light data, ambient temperature and humidity data, raw UV data, positioning data, motion data, and heart rate data; The ambient light data includes ambient light intensity and / or rate of change of illumination; the motion data includes acceleration, angular velocity and / or attitude angle; the raw UV data is obtained from a UV sensor or a weather API. The baseline UV intensity is determined based on the original UV data; Based on the multi-source data, the user's current UV exposure status is identified, and the base UV intensity is compensated according to the current UV exposure status to obtain the actual UV intensity.

[0008] Optionally, determining the baseline UV intensity based on the original UV data includes: Determine whether the UV sensor is currently blocked; If not, the data collected by the UV sensor will be determined as the baseline UV intensity. If so, first determine the ambient light correction factor based on the current ambient light intensity, and then determine the base UV intensity based on the weather API data and the ambient light correction factor.

[0009] Optionally, identifying the user's current UV exposure status includes: The current scene and activity status are identified based on the location data and the motion data; Based on the current scenario and activity status, estimate the head exposure coefficient, user posture correction coefficient, and / or UV sensor position deviation compensation coefficient. The actual UV intensity is determined based on the base UV intensity, the head exposure coefficient, the user posture correction coefficient, and / or the UV sensor position deviation compensation coefficient.

[0010] Optionally, the method for estimating the head exposure coefficient includes: When the current scene is outdoors, detect whether the person is currently under an umbrella, wearing a hat, or being shaded by trees. If so, the head exposure coefficient is set to a first head exposure coefficient corresponding to the umbrella state, a second head exposure coefficient corresponding to the hat state, or a third head exposure coefficient corresponding to the tree shade state, based on the detection results. If not, then set the head exposure coefficient as the fourth head exposure coefficient; Among them, the first head exposure coefficient, the second head exposure coefficient, and the third head exposure coefficient are all less than the fourth head exposure coefficient.

[0011] Optionally, the method for detecting whether the current state is under an umbrella includes: Based on the motion data, the current posture characteristics are analyzed and obtained, including arm raising angle, grip stability and swing amplitude; Based on the ambient light data, the current illumination characteristics are analyzed and obtained, including the continuous illumination intensity and the amplitude of illumination fluctuation. The posture features and / or illumination features are input into an SVM classifier to obtain a determination result of whether the current state is under an umbrella.

[0012] Optionally, it also includes: obtaining the current umbrella ultraviolet protection factor (UPF); the first head exposure factor is a set value when the umbrella UPF is higher than a preset umbrella protection factor threshold, and a set value when the first head exposure factor is lower than a preset umbrella protection factor threshold.

[0013] Optionally, the method for estimating the user pose correction coefficient includes: When the current scene is outdoors, based on the motion data, it is detected whether the current state is upright walking, lying down or looking down; If so, the user posture correction coefficient is set to the first posture correction coefficient corresponding to the upright walking state, the second posture correction coefficient corresponding to the lying state, or the third posture correction coefficient corresponding to the head-down state, based on the detection results. The first attitude correction coefficient, the second attitude correction coefficient, and the third attitude correction coefficient decrease sequentially.

[0014] Optionally, when the raw UV data is acquired from the UV sensor, the method for estimating the UV sensor position deviation compensation coefficient includes: Determine whether the UV sensor is worn on the head. If so, set the UV sensor position deviation compensation coefficient as the first position deviation compensation coefficient; otherwise, set the UV sensor position deviation compensation coefficient as the second position deviation compensation coefficient. The second position deviation compensation coefficient is higher than the first position deviation compensation coefficient.

[0015] Optionally, the UV protection assessment method further includes: The multi-source data also includes umbrella information, sunscreen information and / or exercise intensity. The umbrella information includes umbrella type and umbrella UPF. The sunscreen information includes sun protection factor SPF, UVA sun protection factor PA, application time and / or water and sweat resistance index. By combining the actual UV intensity, the umbrella information, the sunscreen information, the exercise intensity, and / or the ambient temperature and humidity data, the umbrella protection factor and the remaining protection time of the sunscreen are dynamically evaluated. The overall UV protection level is assessed based on the umbrella's protection factor and the remaining protection time of the sunscreen.

[0016] Optionally, the UV protection assessment method further includes: Based on the actual UV intensity, the comprehensive UV protection level, the current scene, makeup status, and / or personal preference information, generate and output corresponding UV protection suggestions and / or health care tips.

[0017] Secondly, embodiments of this application provide a UV protection assessment device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the UV protection assessment method described above.

[0018] Thirdly, embodiments of this application provide a smart wearable device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the UV protection assessment method described above.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions thereon, which are executed by a computer processor to implement the UV protection assessment method described in any of the above claims.

[0020] The UV protection assessment scheme provided in this application first obtains multi-source heterogeneous data such as ambient light, ambient temperature and humidity, raw UV, positioning, movement, and heart rate. Second, it determines a baseline UV intensity based on the raw UV data (from a UV sensor / weather API). Finally, it combines the multi-source data to identify the user's current UV exposure status and corrects the baseline UV intensity through status compensation to obtain an actual UV intensity value that fits the current environment and the user's status. This solves the problem of significant deviation between raw UV data and actual UV exposure levels, and has the following beneficial effects: 1) Effectively reduces the inherent bias of raw UV data: It breaks through the limitations of single raw UV data, and corrects the assessment bias caused by various exposure influencing factors through exposure status compensation, so that the assessment value is highly matched with the actual UV exposure level of the human body.

[0021] 2) It achieves dynamic perception of UV exposure status: By integrating multi-source data such as motion, positioning, and ambient light, it can identify key exposure characteristics such as environmental occlusion, body posture, and activity status of users in real time, so that the UV intensity assessment results can be dynamically adjusted according to the user's status, rather than a static fixed value.

[0022] 3) It lays a data foundation for subsequent accurate protection assessment: The actual UV intensity output provides accurate core data support for subsequent dynamic protection effect assessment and personalized protection suggestion generation, making the entire UV protection assessment system adaptable to different scenarios and of practical reference value.

[0023] This application has other features and advantages that will be apparent from or will be set forth in detail in the accompanying drawings and following detailed description, which together serve to explain the particular principles of this application. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of the UV protection assessment method provided in the embodiments of this application; Figure 2 This is a hardware principle block diagram of the smartwatch provided in the embodiments of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] To address the issue of significant discrepancies between existing UV detection data and actual conditions, please refer to... Figure 1 This application provides a UV protection assessment method, including: S1. Acquire multi-source data, which includes any combination of ambient light data, ambient temperature and humidity data, raw UV data, positioning data, motion data, and heart rate data.

[0028] Ambient light data, used to perceive the lighting characteristics of the user's environment, is the core data for identifying environmental occlusion and whether the sensor is blocked. It includes two core indicators: ambient light intensity and / or rate of change of light. Ambient light data refers to the intensity of visible light in the user's environment. It quantifies the brightness of ambient light and can help determine whether the user is in a low-light shadow area such as a tree shade area or a bright, open area on a sunny day. Light intensity variation rate: refers to the amplitude / rate of change in ambient light intensity per unit time, which can help determine whether the lighting is stable.

[0029] Ambient temperature and humidity data refers to the temperature and relative humidity of the user's environment. It can be used to help determine the decline in the protective effect of sunscreen, the degree of sweating of the user, etc. The higher the temperature and the greater the humidity, the more the user usually sweats, and the faster the sunscreen will decline due to the loss of sweat.

[0030] Raw UV data refers to uncorrected baseline UV data obtained directly from the data acquisition point. It serves as the primary basis for determining baseline UV intensity. The data sources can be of two types: Built-in / external UV sensor: Directly collects ultraviolet radiation data of the user's surrounding environment, providing localized microscopic UV data; Weather API: Macro UV Index (UVI) data for the user's location obtained from the meteorological service interface, which is the regional average UV data.

[0031] Location data refers to user geographic location data obtained through positioning technologies such as GPS / BeiDou. It is mainly used to identify the user's basic indoor / outdoor scenarios and is the basic data for delineating the boundaries of UV protection assessment scenarios.

[0032] Motion data, used to perceive a user's physical activity state and limb posture, is the core data for identifying various behaviors such as user movement / rest state, head posture, and umbrella use. It includes three core indicators: acceleration, angular velocity, and / or posture angle. Acceleration: refers to the acceleration of the user's body / wearable device. It can be used to quantify the speed and force of movement, and can help determine the state of activities such as walking and running, as well as the stability of holding objects (such as umbrellas). Angular velocity: refers to the rotational angular velocity of the user's body / wearable device. It can be used to quantify the amplitude and speed of limb swing and head rotation, and can help determine the amplitude of arm swing and changes in head posture. Posture angle: refers to the spatial posture angle of the human body / wearable device calculated by sensors. It can include pitch angle (angle of head turning up and down) and roll angle (angle of head turning left and right). It is the key data for determining the head posture such as upright, head down, and lying down.

[0033] Heart rate data refers to a user's real-time heart rate value, which can be used to quantify the intensity of a user's physical activity and the degree of sweating. Generally, the higher the heart rate, the greater the intensity of the user's exercise and the more sweat they produce, which can help correct the sweat attenuation coefficient of sunscreen.

[0034] S2. Determine the base UV intensity based on the original UV data.

[0035] Baseline UV intensity, a benchmark UV intensity value determined based on raw UV data, serves as the fundamental reference value for subsequent exposure compensation.

[0036] S3. Identify the user's current UV exposure status based on multi-source data, and compensate the base UV intensity according to the current UV exposure status to obtain the actual UV intensity.

[0037] In summary, this application provides a UV protection assessment method based on multi-source data fusion. First, it obtains heterogeneous data from multiple sources, including ambient light, ambient temperature and humidity, raw UV intensity, location data, motion data, and heart rate data. A baseline UV intensity is determined based on the raw UV data (from a UV sensor / weather API). Then, it combines the multi-source data to identify the user's current UV exposure status. Status compensation is used to correct the baseline UV intensity, resulting in an actual UV intensity value that closely matches the current environment and the user's status. This solves the problem of significant discrepancies between raw UV data and actual UV exposure levels, and has the following effects: 1) Effectively reduces the inherent bias of raw UV data: Breaking through the limitations of single raw UV data, the evaluation bias caused by various exposure factors such as sensor position, environmental occlusion, and human posture is corrected through exposure state compensation, so that the evaluation value is highly matched with the actual UV exposure level of the human body.

[0038] 2) It achieves dynamic perception of UV exposure status: By integrating multi-source data such as motion, positioning, and ambient light, it can identify key exposure characteristics such as environmental occlusion, body posture, and activity status of users in real time, so that the UV intensity assessment results can be dynamically adjusted according to the user's status, rather than a static fixed value.

[0039] 3) It lays a data foundation for subsequent accurate protection assessment: The actual UV intensity output provides accurate core data support for subsequent dynamic protection effect assessment and personalized protection suggestion generation, making the entire UV protection assessment system adaptable to different scenarios and of practical reference value.

[0040] In one alternative implementation, step S2, determining the base UV intensity based on the raw UV data, may include: Determine if the UV sensor is currently blocked; If not, the data collected by the UV sensor will be used to determine the base UV intensity. If so, first determine the ambient light correction factor based on the current ambient light intensity, and then determine the base UV intensity based on the weather API data and the ambient light correction factor.

[0041] In this embodiment, valid raw UV data is selected based on whether the UV sensor is blocked. When unblocked, the UV sensor value that is more closely related to the user's micro-environment is directly used. When blocked, the macro-weather API data is calibrated by the ambient light correction coefficient, so that the basic UV intensity is adapted to the user's real-time actual environment. This effectively avoids the problems of UV sensor failure due to blockage and deviation from a single data source, improves the accuracy and adaptability of the basic UV intensity, and lays a reliable benchmark for subsequent actual UV intensity compensation.

[0042] The inventors also discovered that existing technologies have the following drawbacks: The scene and behavior recognition is crude: the existing technology has insufficient accuracy in recognizing user scenes (indoor / outdoor, stationary / moving), especially lacking the ability to recognize key UV protection behaviors such as "using an umbrella" and "wearing a hat", and cannot dynamically adjust the evaluation based on the user's active protection behavior. Lack of assessment of UV exposure risk to the head: The head and face are the main sensitive areas for UV damage (such as sunburn, aging, and skin cancer risk). Current technology cannot accurately assess the actual UV exposure risk to this area, resulting in unclear core targets for protection recommendations.

[0043] However, it is important to emphasize that head exposure, user posture, and UV sensor location are the three main sources of UV data bias in outdoor scenarios. This is because when the head is blocked (by an umbrella, hat, or in the shade, etc.), the blockage directly reduces the actual UV radiation received by the head; head posture (looking down, lying down, etc.) changes the effective UV receiving area, and the smaller the area, the less UV radiation is actually received; UV sensors are mostly worn on the wrist (not the head), and the UV exposure environment and received amount on the wrist and head are inherently different, so the UV sensor data collected directly cannot reflect the actual situation on the head.

[0044] Therefore, to further improve the accuracy of assessing the true UV exposure intensity of the head, in one optional implementation, the method for identifying the user's current UV exposure status in step S3 may include: Identify the current scene and activity status based on location data and motion data; Based on the current scenario and activity status, estimate the head exposure coefficient, user posture correction coefficient, and / or UV sensor position deviation compensation coefficient. The actual UV intensity is determined based on the base UV intensity, head exposure coefficient, user posture correction coefficient, and / or UV sensor position deviation compensation coefficient.

[0045] Location data, obtained through GPS / BeiDou and other positioning technologies, is related to the user's geographical location. In this embodiment, it is used to determine the user's basic indoor / outdoor scene and is the foundational dimension for scene recognition. Motion data, including human activity perception data such as acceleration, angular velocity, and posture angle, is used to determine the user's stationary / walking / running activity state and the posture characteristics of the head and limbs. It is the core dimension for activity state recognition. The current scene and activity state are the user's real-time comprehensive state identified by the fusion of location data and motion data. It can be a combination of the basic scene (indoor / outdoor) and the activity (stationary / walking / running), such as indoor stationary / active, outdoor stationary / running / walking / running, etc.

[0046] The head exposure factor is a correction factor that quantifies the impact of a user's head occlusion status (umbrella, hat, natural shadow, etc.) on UV reception intensity. For example, the head exposure factor can be selected from 0 to 1, with a smaller value for stronger occlusion.

[0047] The user posture correction coefficient is a correction coefficient that quantifies the impact of the user's head posture (upright, head down, lying down, etc.) on the effective UV receiving area. For example, the value of the user posture correction coefficient can be selected from 0 to 1, with a smaller value for a smaller effective receiving area.

[0048] The UV sensor position deviation compensation coefficient is a compensation coefficient that corrects the data acquisition deviation caused by the UV sensor not being worn on the head (such as on the wrist), and its value can be ≥1.

[0049] The formula for calculating actual UV intensity is: Actual UV intensity (Head_UVI) = Base UV intensity (Base UVI) × Head exposure coefficient × User posture correction coefficient × UV sensor position deviation compensation coefficient.

[0050] This implementation method identifies the current scene and activity status by fusing positioning data and motion data from two dimensions, and uses the current scene and activity status as the basis for estimating various compensation coefficients. Finally, the actual UV intensity is obtained through multi-coefficient collaborative correction, which realizes the accurate binding between scene and activity status and compensation coefficients, avoids one-size-fits-all estimation of coefficients, and makes the values ​​of coefficients such as head exposure and posture correction adapt to the user's real-time scene and activity status. This reduces multi-dimensional deviations such as sensor position, head occlusion, and body posture, and greatly improves the accuracy of actual UV intensity assessment.

[0051] Furthermore, methods for estimating the head exposure factor may include: When the current scene is outdoors, detect whether the person is currently under an umbrella, wearing a hat, or being shaded by trees. If so, the head exposure coefficient is set to the first head exposure coefficient corresponding to the umbrella state, the second head exposure coefficient corresponding to the hat state, and the third head exposure coefficient corresponding to the tree shade state. If not, then set the head exposure coefficient to the fourth head exposure coefficient; Among them, the first head exposure coefficient, the second head exposure coefficient, and the third head exposure coefficient are all smaller than the fourth head exposure coefficient.

[0052] This embodiment overcomes the limitations of existing technologies that lack head occlusion recognition. It accurately identifies three types of head occlusion in outdoor scenarios: umbrella, hat, and tree shade. Differentiated coefficients are set for different occlusion states to quantify the different attenuation degrees of UV reception intensity caused by umbrellas, hats, and tree shade. This avoids the coarseness of a "one-size-fits-all" correction for various occlusion states, making the value of the head exposure coefficient more consistent with the actual UV exposure under different occlusion methods. This significantly improves the correction accuracy of the head exposure coefficient and provides a reliable basis for the accurate calculation of actual UV intensity.

[0053] Furthermore, methods for detecting whether the umbrella is currently in use can include: Based on motion data, the current posture characteristics are analyzed, including arm elevation angle, grip stability, and swing amplitude. Based on ambient light data, the current illumination characteristics are analyzed, including continuous light intensity and light fluctuation amplitude. The pose features and / or illumination features are input into the SVM (support vector machine) classifier to obtain a judgment result on whether the current state is under an umbrella.

[0054] Among these, arm elevation angle refers to the spatial elevation of the arm relative to the torso when holding an object, and is a fundamental characteristic of umbrella-holding. Grip stability refers to the stability of the hand when holding an object. Swing amplitude refers to the range of arm swing with body movement. Typically, when opening an umbrella, users need to raise their arms and hold the handle steadily to prevent the umbrella from shaking and falling, which is significantly different from the characteristics of simply raising or swinging the arm. Therefore, arm elevation angle, grip stability, and swing amplitude can be used to identify the state of umbrella-holding.

[0055] Continuous light intensity refers to the average ambient light intensity in the area surrounding a user's head over a period of time; light fluctuation amplitude refers to the maximum difference in ambient light intensity in the area surrounding a user's head over a period of time. Typically, when a user uses an umbrella, the umbrella blocks direct sunlight from above their head, creating a localized, continuous low-light area around the head. Furthermore, because the umbrella provides stable coverage, the light intensity only fluctuates slightly with the user's movement, resulting in a slight fluctuation in light intensity that is relatively consistent with the user's walking frequency. Therefore, continuous light intensity and light fluctuation amplitude can also be used to identify the state of umbrella use.

[0056] Based on this, this embodiment uses motion data and ambient light data to capture the user's actual posture features (arm raised, stable grip, and slight swinging) and / or illumination features (continuous low light, slight light fluctuations) while holding an umbrella. The feature dimensions are highly consistent with the actual umbrella-holding behavior and environmental influences. Furthermore, an SVM classifier is introduced to determine the state of the fused dual-dimensional features, which can adapt to the slight fluctuations in features in the umbrella-holding scenario, improve the robustness and accuracy of umbrella-holding state detection, reduce false / false judgments with low confidence, effectively reduce the deviation in head UV exposure caused by the inability to recognize or misjudge the umbrella-holding state, and further improve the accuracy of subsequent actual UV intensity calculation.

[0057] Considering the diverse types of umbrellas, and the fact that different types of umbrellas may have different UV protection capabilities due to material differences, in an optional embodiment, the above method further includes: obtaining the current umbrella UPF (Ultraviolet Protection Factor); a first head exposure factor set when the umbrella UPF is higher than a preset umbrella protection factor threshold, and a first head exposure factor set when the umbrella UPF is lower than the preset umbrella protection factor threshold. In practical applications, the umbrella UPF can be obtained either by direct input from the user or automatically identified based on the umbrella information selected by the user (such as category, material, function, etc.).

[0058] In one optional implementation, the method for estimating the user pose correction coefficient includes: When the current scene is outdoors, based on motion data, it can detect whether the person is currently in an upright walking state, a lying down state, or a head-down state. If so, the user posture correction coefficient is set to the first posture correction coefficient corresponding to the upright walking state, the second posture correction coefficient corresponding to the lying down state, and the third posture correction coefficient corresponding to the head-down state. Among them, the first attitude correction coefficient, the second attitude correction coefficient, and the third attitude correction coefficient decrease in sequence.

[0059] In this embodiment, the upright walking state refers to a head posture with a head pitch angle within a corresponding allowable range (e.g., -10° to 10°), where the head and face are basically horizontal during outdoor activities, with most of the head facing the sky and a relatively large UV radiation receiving area. The lying-down state refers to a posture with a head roll angle within a corresponding set range (e.g., >80°), where one side of the head is blocked, and only a portion is exposed to UV radiation. The head-down state refers to a lowered posture with a head pitch angle within a corresponding set range (e.g., >30°), where the front of the head is blocked by itself, and only a small area on the top / back is exposed to UV radiation. Based on this, this embodiment sets coefficient gradients for various postures, corresponding to the size of the effective UV receiving area of ​​the head in each posture, further improving the accuracy of subsequent calculations of actual UV intensity.

[0060] When raw UV data is acquired from a UV sensor, the estimation method for the UV sensor position deviation compensation coefficient may include: Determine whether the UV sensor is worn on the head. If so, set the UV sensor position deviation compensation coefficient as the first position deviation compensation coefficient; otherwise, set the UV sensor position deviation compensation coefficient as the second position deviation compensation coefficient. The second position deviation compensation coefficient is higher than the first position deviation compensation coefficient.

[0061] At this point, because the wearing position of the UV sensor affects the matching degree between the collected data and the actual UV exposure level of the head, sensors worn off-head (wrist / arm, etc.) are easily affected by body obstruction and exposure angle, resulting in collected UV data that is lower than the actual value on the head; while the data collected when worn on the head has a relatively smaller deviation. Therefore, this embodiment, based on the raw UV data collected by the UV sensor, determines whether the UV sensor is worn on the head and matches two different types of position deviation compensation coefficients (the coefficient is higher when not worn on the head) to compensate for the deviation between the sensor data collected when not worn on the head and the actual UV exposure of the head, further improving the calculation accuracy of the actual UV intensity, while also being compatible with multiple UV sensor wearing scenarios.

[0062] The inventors also found that existing technologies have the drawbacks of being static and simplistic in their assessment of protective effects: they only provide static recommendations based on the UV index or the SPF value of sunscreen, without considering the decrease in the protective effect of sunscreen due to sweating or the passage of time, or the actual blocking effect of physical protection such as umbrellas; and they do not incorporate personalized information of users (such as makeup status, menstrual cycle, and personal preferences), resulting in recommendations that lack specificity.

[0063] Therefore, in one optional implementation, the above-mentioned UV protection assessment method further includes: Multi-source data also includes umbrella information, sunscreen information and / or exercise intensity. Umbrella information includes umbrella type and umbrella UPF (Ultraviolet Protection Factor). Sunscreen information includes SPF (Sun Protection Factor), PA (Protection Factor of UVA), application time and / or water and sweat resistance index. By combining actual UV intensity, umbrella information, sunscreen information, exercise intensity and / or ambient temperature and humidity data, dynamically assess the umbrella protection factor and the remaining protection time of the sunscreen; The overall UV protection level (e.g., high / medium / low / no protection) is assessed based on the umbrella's protection factor and the remaining protection time of the sunscreen.

[0064] The higher the SPF value, the stronger the sunscreen's ability to protect the skin from sunburn. PA is an indicator of a sunscreen's ability to prevent skin tanning. It primarily represents the sunscreen's protection against UVA (long-wave ultraviolet radiation that causes sunburn). Water and sweat resistance are indicators of sunscreen's durability, measuring its ability to maintain its original sun protection effect when exposed to water, continuous sweating, or slight friction. It is an important parameter for adapting sunscreen to different usage scenarios, directly affecting whether the sunscreen is suitable for outdoor high temperatures, sports, wading, and other situations prone to sweating / water contact.

[0065] Generally, the higher the UV protection factor of the umbrella, the longer the remaining protection time of the sunscreen, the higher the overall UV protection level, and the better the user's current overall UV protection effect.

[0066] It's important to note that umbrella information can be used to analyze the actual area of ​​head protection and UPF (Ultraviolet Filter Factor). For example, the UPF of a professional sun umbrella is greater than that of a rain umbrella, and the shading area of ​​a large-canopy umbrella is greater than that of a small-canopy umbrella, directly affecting the umbrella's actual UV protection capability. Sunscreen information is a crucial means for female users to achieve UV protection; its SPF, PA, application time, and water / sweat resistance are all important factors influencing its UV protection capability.

[0067] This application embodiment integrates multi-source data such as environment, sports, umbrellas, and sunscreen, which can not only reduce the deviation of actual assessment results and make the assessment results more in line with real scenarios and improve the accuracy of assessment, but also realize dynamic and personalized protection level assessment, effectively improving the user experience.

[0068] In one optional implementation, the UV protection assessment method further includes: Based on the actual UV intensity, comprehensive UV protection level, current scenario (indoor stillness / activity, outdoor stillness / walking / running, etc.), makeup status (no makeup / light makeup / heavy makeup) and / or personal preference information (user's sun protection behavior preferences, such as disliking applying sunscreen, preferring physical protection, refusing sunscreen spray, etc.), generate and output corresponding UV protection suggestions and / or health care tips.

[0069] This application's embodiments incorporate personalized information such as makeup status and personal preferences, combined with real-time UV intensity, UV protection level, and current scene, to generate highly user-adaptive protection suggestions and tips. This makes the suggestions more targeted and operable, significantly improving the value of UV protection suggestions and / or health care tips, and enhancing the user experience.

[0070] To facilitate understanding, an application example is provided below: 1. System Hardware Components Please see Figure 2 Taking a smartwatch as an example, it includes: a three-axis accelerometer, a three-axis gyroscope, a three-axis magnetometer, an ambient light sensor (including UV sensing function), a heart rate sensor, a GPS module, a temperature and humidity sensor, a processor, memory, a display screen, and a communication module. An optional external UV sensor can be attached (such as clipped to the brim of a hat to communicate with the watch via Bluetooth).

[0071] 2. Data Acquisition and Preprocessing

[0072] 2.1 Motion sensor: Acquires acceleration (100Hz), angular velocity (100Hz), and attitude angle (Euler angles / quaternions, 50Hz), performs low-pass filtering to remove noise, and extracts time-domain features (mean, variance, peak value) and frequency-domain features.

[0073] 2.2 Ambient light sensor: Collects light intensity (Lux, 1Hz) and UV index (UVI, 0.5Hz), and performs smoothing filtering.

[0074] 2.3 Location Information: Obtain a rough location type (indoor / outdoor / urban / suburban) through GPS positioning.

[0075] 2.4 Other: Heart rate (1Hz), temperature and humidity (0.1Hz).

[0076] 3. Refined scene and behavior recognition

[0077] 3.1 Basic Scene Classification: Using a random forest model, input motion features and location type, and output labels such as "indoor stationary" and "outdoor walking".

[0078] 3.2 Umbrella Status Judgment: ① Posture characteristics: Calculate the arm raising angle (based on the posture angle, if the average raising angle is between 60° and 120°), grip stability (acceleration variance < 0.1g²), and swing amplitude (peak difference in angular velocity < 50° / s).

[0079] ② Illumination characteristics: Detected continuous low illumination (<10000 Lux) or slight illumination fluctuations (amplitude <1000 Lux) synchronized with walking rhythm (step frequency 1-2 Hz).

[0080] ③ The SVM classifier outputs "umbrella in place" (confidence > 0.8) or "umbrella not in place".

[0081] 4. Head UV Exposure Difference Compensation

[0082] 4.1 Baseline UVI Acquisition: If the UV sensor is not blocked (judged by light intensity > 50000 Lux and low rate of change), then the baseline UVI (i.e., baseline UV intensity) = UV sensor reading; otherwise, the baseline UVI = regional UVI obtained from the weather API × ambient light correction factor (if the ambient light intensity is much lower than that of a sunny day at the same time, then the correction factor < 1).

[0083] 4.2 Head Exposure Factor: ① When the umbrella is open, the head exposure factor is 0.2 (UPF50+ umbrella) or 0.3-0.5 (ordinary umbrella). ②If the user inputs "wearing a hat" status as "yes", the head exposure coefficient is 0.3; ③ Tree shade was detected (light fluctuation frequency 1-2Hz, average intensity <20000Lux), head exposure coefficient = 0.4; ④ Otherwise, the head exposure coefficient = 1.0.

[0084] 4.3 User attitude correction coefficient: ① When walking upright (with pitch angle between -10° and 10°), the user posture correction factor is 1.0; ② When the head is tilted down (pitch angle > 30°), the user posture correction factor is 0.6; ③ When lying down (roll angle > 80°), the user posture correction coefficient is 0.8.

[0085] 4.4 UV sensor position deviation compensation coefficient: If a wrist UV sensor is used and the head is exposed (without an umbrella / hat, no obstruction), the position deviation compensation coefficient of the UV sensor is 1.2 obtained through training with experimental data (the wrist usually receives about 20% less UV than the head due to angle issues).

[0086] 4.5 Calculation Example: Base UVI = 8 (sunny outdoor), umbrella = no, hat = no, no obstruction, upright walking, using wrist sensor. Then Head_UVI (i.e., actual UV intensity) = 8 × 1.0 × 1.0 × 1.2 = 9.6.

[0087] 5. Dynamic protection effectiveness evaluation

[0088] 5.1 Umbrella Protection Factor: Umbrella = Yes (UPF50+), Umbrella Protection Factor = 0.98.

[0089] 5.2 Remaining sunscreen time: ①SPF30, base duration = 3 hours; ② Exercise intensity = moderate (MET=5), heart rate = 120 bpm, temperature = 30°C, humidity = 60%, non-waterproof, then the sweat attenuation coefficient F_sweat = 0.6; ③ Application time = current time - 1.5 hours, then the application time Elapsed_Time = 1.5 hours; ④ Remaining duration = max(0, 3h × 0.6 - 1.5h) = 0.3h.

[0090] 5.3 Overall Protection Level: Head_UVI=9.6 (High), Umbrella Protection Factor=0.98, Sunscreen Remaining Time: 0.3h, then the overall protection level is medium (because the sunscreen is about to expire).

[0091] 6. Personalized suggestion generation

[0092] Based on the overall protection level of "medium", the scenario of "outdoor walking", the user's makeup status of "wearing makeup", and the personal preference of "preferring physical protection", the following suggestion is generated: "The current risk of UV exposure to the head is high. Your parasol provides good protection, but the remaining protection time of the sunscreen is less than 30 minutes. It is recommended to find a shady place to rest as soon as possible, or reapply sunscreen spray that will not damage your makeup."

[0093] Secondly, embodiments of this application provide a UV protection assessment device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the UV protection assessment method described in any of the above embodiments.

[0094] Thirdly, embodiments of this application provide a smart wearable device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the UV protection assessment method as described in any of the above embodiments. This smart wearable device can specifically be various devices such as smartwatches / smart bracelets and smart glasses, and is not specifically limited thereto.

[0095] The above-described apparatus / device can perform the methods provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for performing the methods, which will not be elaborated here.

[0096] Fourthly, Embodiment 4 of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the UV protection assessment method as provided in all embodiments of this application.

[0097] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0098] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0099] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0100] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. A UV protection assessment method, characterized in that, include: Acquire multi-source data, which includes any combination of ambient light data, ambient temperature and humidity data, raw UV data, positioning data, motion data, and heart rate data; The ambient light data includes ambient light intensity and / or rate of change of illumination; the motion data includes acceleration, angular velocity and / or attitude angle; the raw UV data is obtained from a UV sensor or a weather API. The baseline UV intensity is determined based on the original UV data; Based on the multi-source data, the user's current UV exposure status is identified, and the base UV intensity is compensated according to the current UV exposure status to obtain the actual UV intensity.

2. The UV protection assessment method according to claim 1, characterized in that, The determination of the base UV intensity based on the original UV data includes: Determine whether the UV sensor is currently blocked; If not, the data collected by the UV sensor will be determined as the baseline UV intensity. If so, first determine the ambient light correction factor based on the current ambient light intensity, and then determine the base UV intensity based on the weather API data and the ambient light correction factor.

3. The UV protection assessment method according to claim 1, characterized in that, The identification of the user's current UV exposure status includes: The current scene and activity status are identified based on the location data and the motion data; Based on the current scenario and activity status, estimate the head exposure coefficient, user posture correction coefficient, and / or UV sensor position deviation compensation coefficient. The actual UV intensity is determined based on the base UV intensity, the head exposure coefficient, the user posture correction coefficient, and / or the UV sensor position deviation compensation coefficient.

4. The UV protection assessment method according to claim 3, characterized in that, The method for estimating the head exposure coefficient includes: When the current scene is outdoors, detect whether the person is currently under an umbrella, wearing a hat, or being shaded by trees. If so, the head exposure coefficient is set to a first head exposure coefficient corresponding to the umbrella state, a second head exposure coefficient corresponding to the hat state, or a third head exposure coefficient corresponding to the tree shade state, based on the detection results. If not, then set the head exposure coefficient as the fourth head exposure coefficient; Among them, the first head exposure coefficient, the second head exposure coefficient, and the third head exposure coefficient are all less than the fourth head exposure coefficient.

5. The UV protection assessment method according to claim 4, characterized in that, The method for detecting whether the current state is under umbrella includes: Based on the motion data, the current posture characteristics are analyzed and obtained, including arm raising angle, grip stability and swing amplitude; Based on the ambient light data, the current illumination characteristics are analyzed and obtained, including the continuous illumination intensity and the amplitude of illumination fluctuation. The posture features and / or illumination features are input into an SVM classifier to obtain a determination result of whether the current state is under an umbrella.

6. The UV protection assessment method according to claim 4, characterized in that, Also includes: Obtain the current UPF of the umbrella; the first head exposure coefficient is the set value when the umbrella UPF is higher than the preset umbrella protection coefficient threshold, and the first head exposure coefficient is the set value when the umbrella UPF is lower than the preset umbrella protection coefficient threshold.

7. The UV protection assessment method according to claim 3, characterized in that, The method for estimating the user posture correction coefficient includes: When the current scene is outdoors, based on the motion data, it is detected whether the current state is upright walking, lying down or looking down; If so, the user posture correction coefficient is set to the first posture correction coefficient corresponding to the upright walking state, the second posture correction coefficient corresponding to the lying state, or the third posture correction coefficient corresponding to the head-down state, based on the detection results. The first attitude correction coefficient, the second attitude correction coefficient, and the third attitude correction coefficient decrease sequentially.

8. The UV protection assessment method according to claim 3, characterized in that, When the raw UV data is acquired from the UV sensor, the estimation method for the UV sensor position deviation compensation coefficient includes: Determine whether the UV sensor is worn on the head. If so, set the UV sensor position deviation compensation coefficient as the first position deviation compensation coefficient; otherwise, set the UV sensor position deviation compensation coefficient as the second position deviation compensation coefficient. The second position deviation compensation coefficient is higher than the first position deviation compensation coefficient.

9. The UV protection assessment method according to claim 1, characterized in that, The UV protection assessment method also includes: The multi-source data also includes umbrella information, sunscreen information and / or exercise intensity. The umbrella information includes umbrella type and umbrella UPF. The sunscreen information includes sun protection factor SPF, UVA sun protection factor PA, application time and / or water and sweat resistance index. By combining the actual UV intensity, the umbrella information, the sunscreen information, the exercise intensity, and / or the ambient temperature and humidity data, the umbrella protection factor and the remaining protection time of the sunscreen are dynamically evaluated. The overall UV protection level is assessed based on the umbrella's protection factor and the remaining protection time of the sunscreen.

10. The UV protection assessment method according to claim 9, characterized in that, The UV protection assessment method also includes: Based on the actual UV intensity, the comprehensive UV protection level, the current scene, makeup status, and / or personal preference information, generate and output corresponding UV protection suggestions and / or health care tips.

11. A UV protection assessment device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the UV protection assessment method as described in any one of claims 1-10.

12. A smart wearable device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the UV protection assessment method as described in any one of claims 1-10.

13. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that, The computer-executable instructions are executed by a computer processor to implement the UV protection assessment method as described in any one of claims 1-10.

Images