Outdoor sports recognition method, wearable device, and storage medium

Abstract

The application discloses an outdoor sports recognition method, a wearable device and a storage medium, relates to the technical field of wearable devices, and discloses an outdoor sports recognition method, which comprises the following steps: acquiring inertial sensing data collected by a wearable device; when it is determined that a wearing user is in a sports state according to the inertial sensing data, calculating an outdoor score of the wearing user based on light interference features and illumination features corresponding to a PPG original waveform collected by the wearable device and the sports state; and when the outdoor score is greater than a preset score, determining that the wearing user is in an outdoor sports state. The application can improve the outdoor sports state recognition accuracy.

Description

Technical Field

[0001] This application relates to the field of wearable device technology, and in particular to outdoor sports recognition methods, wearable devices, and storage media. Background Technology

[0002] Compared to indoor exercise, outdoor activities in natural light environments provide higher intensity and a wider spectrum of light stimulation, especially the high-intensity natural light environment of sunlight, which plays an important role in slowing down the development of myopia, maintaining normal circadian rhythms, and promoting physical and mental health.

[0003] Wearable devices, as consumer electronic terminals worn by users in their daily lives, can continuously collect environmental and human data without interfering with users' normal exercise and life, thereby accurately identifying and quantifying users' outdoor activities and exposure time to sunlight.

[0004] In relevant outdoor sports detection solutions based on smart wearable devices, judgment is usually made based on the activity status or GPS positioning. However, the actual outdoor activities of users in cloudy, shady, or weak GPS environments cannot be accurately identified, making it difficult to effectively distinguish between indoor sports and outdoor activities with natural light exposure.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide an outdoor sports recognition method, wearable device and storage medium, which aims to solve the technical problem of low accuracy in outdoor sports recognition.

[0007] To achieve the above objectives, this application proposes an outdoor sports recognition method, the method comprising: Acquire inertial sensing data collected by wearable devices; When the wearer is determined to be in motion based on the inertial sensing data, the outdoor score of the wearer is calculated based on the light interference characteristics and illumination characteristics corresponding to the PPG raw waveform collected by the wearable device, as well as the motion state. When the outdoor score is greater than the preset score, it is determined that the wearer is in an outdoor sports state.

[0008] In one embodiment, the step of calculating the outdoor score of the wearer based on the light interference characteristics and illumination characteristics corresponding to the original PPG waveform collected by the wearable device, and the motion state, includes: A motion state score is calculated based on the motion state, and a lighting environment score is calculated based on the lighting characteristics. Based on the baseline drift characteristics, random fluctuation characteristics, high-frequency noise characteristics, spectral perturbation characteristics, and local saturation characteristics in the optical interference features, an optical noise score is calculated. The weighted fusion result among the motion state score, the lighting environment score, and the optical noise score is determined as the outdoor score of the wearer.

[0009] In one embodiment, the step of calculating the outdoor score of the wearer based on the light interference characteristics and illumination characteristics corresponding to the original PPG waveform collected by the wearable device, and the motion state, includes: A motion state score is calculated based on the motion state, and a lighting environment score is calculated based on the lighting characteristics. Based on the baseline drift characteristics, random fluctuation characteristics, high-frequency noise characteristics, spectral perturbation characteristics, and local saturation characteristics in the optical interference features, an optical noise score is calculated. The continuity score of the outdoor activity is calculated based on the continuous time coefficient when the outdoor score is greater than the preset score, wherein the continuity score is zero when the continuous time coefficient is the initial value. The weighted fusion result among the motion state score, the lighting environment score, the optical noise score, and the continuity score is determined as the outdoor score of the wearer.

[0010] In one embodiment, before the step of determining that the wearer is in an outdoor exercise state, the outdoor exercise identification method further includes: When the outdoor score is greater than the preset score, update the current continuous time coefficient of the motion state; If the current continuous time coefficient is greater than a preset coefficient threshold, the step of determining that the wearer is in an outdoor sports state is executed. If the current continuous time coefficient is less than or equal to the preset coefficient threshold, the process jumps to the step of calculating the continuity score of the outdoor activity based on the continuous time coefficient of the outdoor score being greater than the preset score.

[0011] In one embodiment, before determining the weighted fusion result among the motion state score, the lighting environment score, the optical noise score, and the continuity score as the outdoor score of the wearer, the outdoor motion recognition method further includes: Obtain the first duration corresponding to the motion state and the second duration for which the illumination feature satisfies a preset illumination threshold; The continuity score of the outdoor activity is calculated based on the first duration and the second duration.

[0012] In one embodiment, the step of calculating the lighting environment score based on the lighting characteristics includes: Obtain the average intensity value of the illumination feature, and the fluctuation feature value within a preset time window; The average intensity value is mapped to a basic score of light intensity, and the fluctuation coefficient is determined based on the fluctuation characteristic value. The lighting environment score is obtained by correcting the basic score of the light intensity using the fluctuation coefficient.

[0013] In one embodiment, before the step of calculating the outdoor score of the wearer based on the light interference features and illumination features corresponding to the original PPG waveform collected by the wearable device and the motion state, the outdoor exercise recognition method further includes: When it is determined from the inertial sensing data that the wearer is in motion, the wearing status information of the wearable device is obtained. When the wearable device is in the wearing state, the steps of calculating the outdoor score of the wearer based on the light interference characteristics and light illumination characteristics corresponding to the PPG raw waveform collected by the wearable device and the motion state are performed.

[0014] In one embodiment, after the step of determining that the user is in an outdoor exercise state when the outdoor score is greater than a preset score, the outdoor exercise recognition method further includes: Trigger the startup process of the outdoor sports mode of the wearable device; The duration of the wearable device in the outdoor sports mode is obtained, and when the duration of the exercise meets the preset duration, the prompt instruction corresponding to the duration of the exercise is executed.

[0015] In addition, to achieve the above objectives, this application also proposes a wearable device, the wearable device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the outdoor sports recognition method as described above.

[0016] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the outdoor sports recognition method described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: By acquiring inertial sensing data collected by wearable devices, and determining the user's activity level based on this data, light interference and illumination features are extracted from the raw PPG waveform collected by the wearable device. These features are then fused with the activity level to calculate the user's outdoor score. Next, the user's outdoor activity level is determined by comparing the outdoor score with a preset score. If the outdoor score is higher than the preset score, the user is considered to be in an outdoor activity state. This allows for effective identification of real outdoor activities in environments with weak positioning signals, such as cloudy days or shady areas, by leveraging the effect of natural light on the PPG signal, thus improving the problem of outdoor activity recognition failure in weak GPS scenarios. Simultaneously, through joint verification of illumination and light interference features, the system distinguishes between real outdoor activities with natural light exposure and easily confused scenarios such as indoor treadmill exercise or activities near windows, reducing misjudgments in non-outdoor scenarios and improving the accuracy of outdoor activity status recognition. This provides reliable scene determination support for wearable devices' automatic outdoor activity recording and light health management functions. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of the outdoor sports identification method of this application. Figure 2 This is a schematic diagram of sensor data acquisition for the outdoor sports recognition method of this application. Figure 3 This is a schematic diagram illustrating the calculation of the time continuity coefficient for the outdoor sports identification method of this application; Figure 4 A simplified flowchart illustrating the outdoor sports recognition method provided in the sixth embodiment of this application; Figure 5 This is a statistical data and reminder diagram for determining when the wearer is in an outdoor activity state, as per this application. Figure 6 This is a schematic diagram of the functional modules of the wearable device of this application; Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the outdoor sports recognition method in this application embodiment.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] Compared to indoor exercise, outdoor activities in natural light environments provide higher intensity and a wider spectrum of light stimulation, especially the high-intensity natural light environment of sunlight, which plays an important role in slowing down the development of myopia, maintaining normal circadian rhythms, and promoting physical and mental health.

[0024] In relevant outdoor sports detection solutions based on smart wearable devices, judgment is usually made based on the activity status or GPS positioning. However, the actual outdoor activities of users in cloudy, shady, or weak GPS environments cannot be accurately identified, making it difficult to effectively distinguish between indoor sports and outdoor activities with natural light exposure.

[0025] Based on this, this application provides a solution that, when a user is in motion, leverages the effect of natural light on the PPG signal to effectively identify real outdoor activities, improving the problem of outdoor activity recognition failure in weak GPS scenarios. Simultaneously, through joint verification of illumination and light interference features, it distinguishes between real outdoor activities with natural light exposure and easily confused scenarios such as indoor treadmill exercise or activities near a window, reducing misjudgments in non-outdoor scenarios and improving the accuracy of outdoor exercise status recognition. This provides reliable scene determination support for wearable devices' automatic outdoor exercise recording, light-based health management, and other related functions.

[0026] It should be noted that the executing entity in this embodiment is a wearable device or a main control device connected to the wearable device, such as a mobile phone or a server. The following description uses a wearable device as an example to illustrate this embodiment and the subsequent embodiments.

[0027] This application provides an outdoor sports recognition method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the outdoor sports recognition method of this application.

[0028] In this embodiment, the outdoor sports recognition method includes steps S10 to S30: Step S10: Acquire inertial sensing data collected by the wearable device.

[0029] Inertial sensing data refers to the time-series sensing data acquired by the inertial measurement unit (IMU) built into wearable devices. It typically includes three-axis acceleration data acquired by an accelerometer and three-axis angular velocity data acquired by a gyroscope. When acquiring inertial sensing data, the wearable device is generally considered to be in a wearing state. At this time, the wearable device can also simultaneously acquire the raw PPG waveform from the wearer. The raw PPG waveform is the raw time-series light intensity signal output by the wearable device's photoplethysmography (PPG) optical sensor. This signal simultaneously includes physiological pulse components caused by changes in blood volume in human tissue, non-physiological interference components caused by ambient light incidence, and circuit background noise.

[0030] In this embodiment, the inertial and optical sensors of the wearable device can collect data based on the same sampling frequency, ensuring that the timestamps of the two types of data are aligned. Specifically, the data acquisition process of the wearable device is as follows: Figure 2 As shown, during data acquisition, the optical sensor utilizes the non-physiological PPG wave characteristics formed by ambient light interference to identify the user's lighting environment and obtain the corresponding raw PPG waveform data. Simultaneously, the accelerometer and gyroscope collect acceleration data and inertial sensing data at the same sampling frequency to identify the current motion state. The sampling frequency can be between 10Hz and 200Hz.

[0031] For example, taking a smart bracelet as an example, an optical sensor is set on the back of the bracelet. The optical sensor collects the raw PPG waveform at a sampling frequency of 10Hz. Specifically, the optical sensor calculates different heart rates by calculating the change in the amount of green light reflected back after passing through the blood. At the same time, an accelerometer collects three-axis acceleration data at a sampling frequency of 10Hz, and a gyroscope collects three-axis angular velocity data at a sampling frequency of 10Hz. Then, by fusing the acceleration and angular velocity data, attitude change information is obtained.

[0032] Optionally, data can be collected from each sensor in a time-sharing manner, and data alignment can be achieved using the clock information of the wearable device. Specifically, after the wearable device is powered on and detected as being worn, the main control unit configures the sampling frequency and range parameters of the inertial measurement unit, as well as the luminous current, sampling frequency, and gain parameters of the PPG optical sensor. Then, a synchronous trigger acquisition action is executed. The main control unit simultaneously starts the acquisition of data from both the inertial sensor and the PPG sensor using the same clock trigger signal. The two types of sensors output data independently according to preset parameters, and each frame of data carries a timestamp generated by the synchronous clock, thereby eliminating the start-up time difference between the different sensors and ensuring strict correspondence between the two types of data in the time dimension. Furthermore, the data can be preprocessed after acquisition, such as performing zero-bias calibration on the inertial data and removing DC bias and filtering out power frequency noise from the raw PPG waveform to obtain preprocessed raw data.

[0033] Step S20: When it is determined that the wearer is in motion based on the inertial sensing data, the outdoor score of the wearer is calculated based on the light interference characteristics and illumination characteristics corresponding to the original PPG waveform collected by the wearable device, as well as the motion state.

[0034] It should be noted that when the algorithm analyzes the inertial sensing data and identifies that the user's current limb movements meet the requirements of a motion state, the user is determined to be in motion. For example, when a user is running outdoors, with each step or arm swing, the inertial measurement unit outputs corresponding acceleration and angular velocity information. When this information matches the information in the preset running feature template, it is confirmed that the wearer is in motion. The motion state determination module of the wearable device directly determines the motion state based on inertial sensing data. This determination process is a standard implementation process for current smart wearable devices and will not be elaborated upon in this application.

[0035] In natural light environments, due to external light leakage and sunlight interference, the original PPG waveform exhibits baseline drift, noise enhancement, and spectral changes. Therefore, light intensity variation data, optical noise characteristics, and baseline drift information can be calculated from these PPG waveform changes. Thus, light interference characteristics are non-physiological signal distortion features extracted from the original PPG waveform caused by ambient light incidence. These include baseline drift characteristics, random fluctuation characteristics, high-frequency noise characteristics, spectral perturbation characteristics, and local saturation characteristics in the PPG signal, used to characterize the degree of interference from ambient light on the PPG signal. Illumination characteristics, on the other hand, are features extracted from the PPG signal or ambient light detection time slots that characterize the intensity and fluctuation patterns of external ambient light. These include light intensity amplitude, light intensity change rate, and light intensity fluctuation frequency, used to directly reflect the strength of external illumination. The outdoor score is a quantitative confidence value obtained by multi-dimensionally fusing motion state, illumination characteristics, and light interference characteristics. A higher score indicates a greater probability that the user is in an outdoor activity scenario.

[0036] In this embodiment, the scores corresponding to the three types of features can be calculated first by weighted summation, and then the outdoor score is obtained by summing the scores and their corresponding weights. Specifically, when the user is in motion based on inertial sensor data, the baseline drift amplitude and high-frequency noise power are extracted from the original PPG waveform as light interference features. At the same time, the average light intensity amplitude is extracted from the DC component of the PPG or the ambient light time slot data as illumination features. The extracted features are normalized to eliminate the influence of dimensions and ensure the effectiveness of the weights of each dimension. Then, the score values ​​corresponding to each parameter are calculated, and finally, these score values ​​are weighted and fused to obtain the outdoor score. Specifically, step S20 includes steps S21 to S23: Step S21: Calculate the motion state score based on the motion state, and calculate the lighting environment score based on the lighting characteristics; Step S22: Calculate the optical noise score based on the baseline drift feature, random fluctuation feature, high-frequency noise feature, spectral perturbation feature, and local saturation feature in the optical interference characteristics. Step S23: Determine the weighted fusion result between the motion state score, the lighting environment score, and the optical noise score as the outdoor score of the wearer.

[0037] The lighting environment score can be calculated by weighting factors such as light intensity and sunlight intensity. Five types of interference sub-features, including baseline drift and high-frequency noise, are extracted from the original PPG waveform. After normalization to eliminate the influence of dimensions, the optical noise score is obtained by weighting. The motion state score is used to quantify the confidence that the user is in effective motion.

[0038] For example, a user wearing a smart bracelet walks briskly outdoors on a cloudy day. The bracelet simultaneously collects inertial sensor data and raw PPG waveforms. The motion state score has a weight of 0.2, the lighting environment score has a weight of 0.35, and the optical noise score has a weight of 0.45. The outdoor determination threshold is preset to 0.7; that is, when the outdoor score > 0.7, the user is determined to be in an outdoor motion state. The variance of the combined acceleration in the collected inertial data is 0.9g. 2 The step frequency is 120 steps per minute. Specifically, when the acceleration variance is less than 0.2g... 2 The time is judged as stationary (corresponding to 0 points), and the weight is higher than 1.0g. 2 A step frequency below 60 steps / minute is considered effective movement (1 point maximum), while a step frequency below 60 steps / minute is considered ineffective movement (0 points maximum). A step frequency between 90 and 160 steps / minute is considered stable walking / running (1 point maximum). Linear interpolation is used within the interval. Therefore, the acceleration variance score = (0.9 - 0.2) / (1.0 - 0.2) = 0.875. The step frequency score = 1. The final movement state score = 0.875 × 0.6 + 1 × 0.4 = 0.925 (the two sub-features are fused with a 6:4 weighting, with acceleration having a higher weight).

[0039] When calculating the lighting environment score, the average light intensity amplitude of 7000 lux (typical outdoor illuminance level on a cloudy day) is extracted from the ambient light time slot data of the PPG sensor. In the calculation benchmark, 1000 lux is the critical level of strong indoor light / window edge, corresponding to 0 points, while 10000 lux is the level of outdoor shade on a sunny day, corresponding to a full score of 1 point. At this time, the lighting environment score = (7000-1000) / (10000-1000)≈0.667.

[0040] When calculating the optical noise score, five types of optical interference sub-features were extracted from the original PPG waveform. The weights of each type of optical interference sub-feature were: baseline drift 0.3, high-frequency noise 0.25, random fluctuation 0.2, spectral perturbation 0.15, and local saturation 0.1. In the detected data, the PPG baseline drift amplitude within 30 seconds was 80mV (10mV (0 points), 100mV (1 point)). The calculated baseline drift score was (80-10) / (100-10)≈0.7782. The current high-frequency noise power of the PPG signal was 35mW (normalized baseline: 5mW (0 points), 50mW (1 point)). Therefore, the high-frequency noise score was (35-5) / (50-5)≈0.6673. The current standard deviation of random fluctuation in the PPG waveform is 15mV (normalized benchmarks are 2mV (0 points) and 20mV (1 point)). Therefore, the random fluctuation score is (15-2) / (20-2)≈0.7224. The current spectral energy proportion of the non-pulse frequency band is 40% (normalized benchmarks are 5% (0 points) and 60% (1 point)). Therefore, the spectral perturbation score is (40-5) / (60-5)≈0.6365. The number of times the PPG signal experiences local saturation within the current 30 seconds is 3 (normalized benchmarks are 0 times (0 points) and 10 times (1 point)). Therefore, the local saturation score is 3 / 10=0.3. Finally, the weighted summation yields the optical noise score: 0.778×0.3+0.667×0.25+0.722×0.2+0.636×0.15+0.3×0.1≈0.67.

[0041] Finally, the scores of the three dimensions are weighted and summed according to preset weights to obtain the comprehensive outdoor scene confidence score: Outdoor Score = Motion Status Score × 0.2 + Lighting Environment Score × 0.35 + Optical Noise Score × 0.45. That is, Outdoor Score = 0.925 × 0.2 + 0.667 × 0.35 + 0.67 × 0.45 ≈ 0.185 + 0.233 + 0.302 = 0.72.

[0042] Step S30: When the outdoor score is greater than the preset score, it is determined that the user is in an outdoor sports state.

[0043] In this embodiment, the calculated current outdoor score is compared with a pre-stored preset score threshold. If the current frame outdoor score is greater than the preset score threshold, the result of determining that the user is in an outdoor sports state is output; otherwise, the result of determining that the user is not in an outdoor sports state is output. For example, if the preset score threshold for the wearable device is 0.7, and the currently calculated outdoor score of 0.72 is greater than the preset threshold of 0.7, then it is determined that the wearer is in an outdoor sports state.

[0044] As an alternative implementation, besides judging by a single calculation, a sliding time window can be used to statistically analyze the pass / fail status of multiple frames' scores, filtering out false judgments caused by momentary interference. Therefore, the outdoor scores of all frames within the window can be cached first, and the percentage of valid frames with scores greater than a preset score can be calculated. When the percentage of valid frames within the window exceeds a preset percentage threshold, the user is determined to be in an outdoor activity state; otherwise, the user remains in a non-activity or non-outdoor state. This avoids false judgments caused by fluctuations in a single score and improves the accuracy of outdoor activity detection. For example, if the wearable device has a sliding window duration of 30 seconds, a preset score threshold of 0.7, and a preset percentage threshold of 80%, and there are 30 frames of score data within the current 30-second window, of which 26 frames have scores greater than 0.7, resulting in an effective percentage of 86.7%, which is greater than the 80% percentage threshold, then the user is determined to be in an outdoor activity state.

[0045] Understandably, in an indoor treadmill workout scenario, the light intensity is typically around 500 lux, resulting in a lighting environment score of only about 0.056. Simultaneously, PPG noise in indoor scenes is primarily motion artifacts, with weaker light-induced interference characteristics, resulting in an optical noise score of approximately 0.3. The calculated total outdoor score is approximately 0.32, far below the 0.7 threshold, preventing misclassification as outdoor exercise and effectively distinguishing between indoor and outdoor natural light exercise. Similarly, even without obstruction, ultraviolet light is absorbed and near-infrared wavelengths are attenuated when light passes through glass. This means the proportion of infrared light in sunlight passing through glass is significantly lower than in real natural light, and the ratio of red to green light also shifts. In the optical noise calculation, motion artifact and lighting coupling corrections are applied to these parameters to accurately identify indoor exercise scenarios under direct sunlight.

[0046] It should be noted that the above parameters are for illustrative purposes only and are not intended to limit this application.

[0047] This embodiment provides an outdoor exercise recognition method. It fuses illumination features and light interference features extracted from the original PPG waveform during exercise to calculate an outdoor score, thus recognizing the outdoor exercise state. This method does not rely on GPS positioning and can still achieve recognition based on the effect of natural light on the PPG signal in environments with weak positioning signals, such as cloudy days or shady areas, improving the problem of recognition failure in weak GPS scenarios. Simultaneously, through dual cross-validation of illumination level and light interference degree, it effectively distinguishes between real outdoor natural lighting scenes and easily confused scenarios such as indoor treadmill exercise or activities near a window, reducing the probability of misjudgment in non-outdoor scenarios and improving the accuracy of outdoor exercise state recognition.

[0048] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, to avoid misjudgment caused by short-term outdoor stays, in addition to analyzing the validity of outdoor scores within continuous time windows, the continuity of the movement state in time can also be determined. Only when the outdoor scores within the continuous time window are all greater than a preset score is the user determined to be in an outdoor movement state. Therefore, in step S30, before determining that the user is in an outdoor movement state, it is necessary to update the current continuous time coefficient of the movement state, and then analyze and judge the updated continuous time coefficient. If the current continuous time coefficient is greater than a preset coefficient threshold, the step of determining that the user is in an outdoor movement state is executed, and the outdoor score is recalculated subsequently.

[0049] Specifically, please refer to Figure 3 The wearable device detects the outdoor exercise status according to a preset time window. It makes a judgment every certain time interval X. When the outdoor score is greater than the preset score, the time continuity coefficient is increased by 1. Then, after waiting for X time, the outdoor score is calculated again. If it is not outdoor exercise, the time continuity coefficient is cleared to zero or reduced by 1 until the time continuity coefficient is greater than the threshold.

[0050] Based on this, as another optional implementation of calculating the outdoor score, after calculating the motion state score, lighting environment score, and optical noise score in step S21, steps S24-S25 are also included: Step S24: Calculate the continuity score of outdoor sports based on the continuous time coefficient of outdoor score being greater than the preset score. Step S25: Determine the weighted fusion result among the motion state score, lighting environment score, optical noise score, and continuity score as the outdoor score for the wearer.

[0051] Understandably, during the first testing period, the continuous time coefficient is usually an initial value such as 0 or 1, corresponding to a continuous score of zero. Therefore, the weight of the continuous time coefficient in the calculated outdoor score is also zero. However, when continuously calculating the outdoor score in subsequent testing windows, it is necessary to combine the continuous score with a weighted calculation. The weighted calculation formula is as follows: , Among them, Motion Score is the motion status score, Light Score is the lighting environment score, Optical Noise Score is the optical noise score, Continuity Score is the continuity score, and W1, W2, W3, and W4 are weighting parameters. Outdoor Score is the outdoor score.

[0052] Specifically, taking a scenario where a user walks from indoors to outdoors and continues walking as an example, a detection interval of 10 seconds is used. The weights of the four components—motion state score, lighting environment score, optical noise score, and continuity score—are 0.2, 0.3, 0.3, and 0.2, respectively, with a preset score of 0.7 for determining outdoor motion state. The continuity score only accumulates and increases when the current outdoor score calculated from the first three components is greater than the preset score. Initially, the continuity score is 0, increasing by 0.3 for each consecutive successful observation, up to a maximum of 1.0. If the score is not met, it is reset to zero.

[0053] In the first testing period, the user had just entered the outdoor area. The measured scores were: motion state score 0.9, lighting environment score 0.82, and optical noise score 0.78. The first three scores were calculated to give an outdoor score of 0.9 × 0.2 + 0.82 × 0.3 + 0.78 × 0.3 = 0.66, which is lower than the preset score of 0.7. Therefore, continuity was not accumulated for this period, and the continuity score remained at its initial value of 0. The final outdoor score was 0.66, failing to meet the judgment standard. In the second testing period, the user was completely outdoors and maintained motion. The measured scores were: motion state score 0.9, lighting environment score 0.9, and optical noise score 0.85. The calculated outdoor score was 0.9 × 0.2 + 0.9 × 0.3 + 0.85 × 0.3 = 0.705, which is greater than the preset score of 0.7. The cumulative number of consecutive successes was 1. Then, in the third testing period (at the 30th second), the user remained in outdoor motion mode, and the outdoor score for this period was increased by 0.3. After 0.2 equals 0.06, it is still higher than the preset score. At this point, the cumulative number of consecutive successful tests is 2, and the continuity score increases to 0.6. This calculation is repeated cyclically. In the eleventh testing cycle, if the current outdoor score is still higher than the preset score and the cumulative number of consecutive successful tests is 10, then the user is directly judged to be in an outdoor activity state. In addition, if the user only stays indoors for a short time, less than two testing cycles, and then returns indoors, the current outdoor score will drop below the preset score as the light intensity decreases. The number of consecutive successful tests will be reset to zero, and the continuity score will remain low. Ultimately, the outdoor score cannot consistently reach the judgment standard, thus avoiding misjudgments caused by short-term outdoor stays.

[0054] Therefore, when the outdoor score is greater than the preset score, after updating the current continuous time coefficient of the exercise state, if the current continuous time coefficient is less than or equal to the preset coefficient threshold, the step of calculating the continuity score is executed. This ensures that the user is determined to be in an outdoor exercise state only when the outdoor activity conditions are met for multiple consecutive time windows.

[0055] It should be noted that the above parameters are for illustrative purposes only and are not intended to limit this application.

[0056] This embodiment provides an outdoor activity recognition method. It weights and fuses three types of scores according to preset weights to obtain a basic outdoor score for the current period. Periodic verification is performed at preset detection intervals. The continuous score is increased only when the basic outdoor score exceeds a preset threshold; otherwise, it is reset to zero. Finally, the basic outdoor score and the continuous score are weighted and fused again to obtain a final outdoor score, which is used to determine whether the user is engaged in outdoor activities. This method eliminates the need for GPS positioning and filters out false positives caused by short-term outdoor stays through a continuous accumulation mechanism, improving the accuracy of outdoor activity recognition.

[0057] Based on the second embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to the second embodiment described above can be referred to the above description and will not be repeated hereafter. Furthermore, the continuity score of outdoor sports can be calculated based on the continuous duration of the movement state and the illumination characteristics. Therefore, before step S25, the following steps are included: Step S26: Obtain the first duration corresponding to the motion state and the second duration in which the illumination features satisfy the preset illumination threshold; Step S27: Calculate the continuity score of outdoor activities based on the first duration and the second duration.

[0058] In this embodiment, the continuity score for outdoor sports can be a continuity score after meeting a single or multiple scoring thresholds, or it can be the continuity of the movement state, the continuity of illumination, etc. Therefore, after calculating the movement state score, the illumination environment score, and the optical noise score, the duration of the movement state and the duration of the illumination feature that meets a preset illumination threshold are obtained. This preset illumination threshold is the critical value of light intensity when natural outdoor light shines on the human body.

[0059] Therefore, after obtaining the first duration of the motion state (i.e., the duration of motion state duration) and the second duration of the illumination characteristics meeting the preset illumination threshold (i.e., the duration of illumination compliance), the duration of motion state duration and the duration of illumination compliance are normalized and calculated according to preset weights to obtain the continuity score of outdoor activities. Finally, the continuity score is weighted and fused together with the motion state score, illumination environment score, and optical noise score to obtain the final outdoor score.

[0060] For example, the maximum score thresholds for both the duration of exercise and the duration of adequate illumination are set at 300 seconds. The weights for exercise duration and adequate illumination duration in the continuity score are 0.3 and 0.7 respectively. The maximum illumination threshold is 5000 lux. A user briefly leaves the room to retrieve an item and returns, a total of only 30 seconds. During this time, the exercise condition is consistently met, but the adequate illumination duration is only 20 seconds (the user is in the shaded area of ​​the corridor for the rest of the time). After normalizing the two durations, the normalized value for exercise duration is 30 / 300 = 0.1, and the normalized value for adequate illumination duration is 20 / 300 ≈ 0.067. The weighted calculation yields a continuity score of 0.1 × 0.3 + 0.067 × 0.7 ≈ 0.077. The motion status score calculated concurrently was 0.9, the lighting environment score was 0.75, and the optical noise score was 0.7. Substituting these scores into the weighted fusion formula for the total outdoor score (with weights of 0.2, 0.35, 0.35, and 0.1 respectively), the final outdoor score was calculated as 0.9 × 0.2 + 0.75 × 0.35 + 0.7 × 0.35 + 0.077 × 0.1 ≈ 0.6952, which is below the threshold of 0.7. Since the duration of lighting meeting the preset threshold was too short, the continuity score was extremely low, directly lowering the total outdoor score. Therefore, it was not initially classified as outdoor activity, thus filtering out false positives from short-term outdoor exposure or brief light exposure.

[0061] It should be noted that the above parameters are for illustrative purposes only and are not intended to limit this application.

[0062] This embodiment provides an outdoor sports recognition method that calculates the continuity score of outdoor sports by combining the duration of illumination and the duration of sports activities. This eliminates the possibility of misidentification in easily confused scenarios such as brief exposure to light near a window or localized strong light, thereby improving the accuracy of outdoor sports status recognition.

[0063] Based on any of the above embodiments, in the fourth embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, when the wearer is in an indoor exercise scenario with direct sunlight, the intensity of direct sunlight near the window is usually less than that of direct sunlight outdoors due to glass attenuation and window frame obstruction. Therefore, when calculating the lighting environment score, data correction calculation can be performed using the light fluctuation information, thereby filtering out invalid environmental interference based on the lighting environment score. Specifically, the step of calculating the lighting environment score in step S21 includes: Step S211: Obtain the average intensity value of the illumination features and the fluctuation feature value within a preset time window.

[0064] Understandably, because architectural glass reflects, absorbs, and blocks wavelengths of sunlight, even when sunlight shines directly onto the surface of the optical sensor of a wearable device through an indoor window, the illuminance will be significantly lower than the natural illuminance of an open outdoor space under the same lighting conditions. Therefore, it is necessary to obtain the average intensity value of the light characteristics and calculate the coefficient of variation (i.e., the ratio of the standard deviation to the mean) of the light intensity data within the window as a fluctuation characteristic value to characterize the degree of fluctuation in light intensity.

[0065] Step S212: Map the average intensity value to the basic score of light intensity, and determine the fluctuation coefficient based on the fluctuation characteristic value.

[0066] The smaller the light intensity variation coefficient, the more uniform and stable the illumination, which is more in line with the characteristics of open outdoor natural light. The closer the fluctuation coefficient is to 1, the smaller the correction force. The larger the variation coefficient, the more intense the light fluctuation, which is more in line with the local light characteristics of window frame shading and alternating light blocking by arm swings. In other words, the smaller the fluctuation coefficient, the greater the correction force.

[0067] In this embodiment, the average intensity value can be normalized and mapped first to obtain the basic score of light intensity, and then the fluctuation coefficient can be determined by the mapping relationship of the preset mapping table of fluctuation characteristic values.

[0068] Step S213: Correct the basic score of light intensity using the fluctuation coefficient to obtain the light environment score.

[0069] In this example, the base light intensity score can be multiplied by the fluctuation coefficient to obtain a corrected lighting environment score. This offsets the problem of inflated scores caused by high average intensity of localized strong light near windows, which is not actually an open outdoor area. For example, the normalized range of the base light intensity score is preset to 1000 lux (corresponding to 0 points) to 10000 lux (corresponding to a full score of 1 point). The coefficient of variation decreases linearly with increasing value in the range of 0.1 to 0.5. When the coefficient of variation is ≥0.5, the fluctuation coefficient is set to 0.5 (maximum correction range). The sliding window duration is set to 30 seconds. When a user exercises on a treadmill near an indoor window, the average light intensity within the 30-second window is 5000 lux, corresponding to a base light intensity score of approximately 0.444. Due to the influence of window frame obstruction and alternating light blocking by arm movements, the light intensity frequently and significantly changes, resulting in a calculated coefficient of variation of 0.45 and a fluctuation coefficient of approximately 0.56. The final corrected lighting environment score is 0.444 × 0.56 ≈ 0.249.

[0070] In an open outdoor walking scene on a cloudy day with the same average light intensity, the natural light is uniform and stable, with a light intensity variation coefficient of only 0.07 and a fluctuation coefficient of 1. The corrected lighting environment score is still 0.444. The average light intensity is the same for both, but the difference in scores after correction is significant. That is, the lighting environment score of the window scene can be greatly reduced, thereby lowering the overall outdoor score and effectively filtering out the risk of misjudgment caused by strong light transmitted through glass.

[0071] This embodiment addresses the issue of inflated scores caused by localized strong light near windows by correcting the base score of illumination intensity through a fluctuation coefficient, based on the difference in fluctuation characteristics between direct indoor light near windows and open outdoor natural light. This reduces the misjudgment rate.

[0072] Based on the first embodiment of this application, in the fifth embodiment of this application, the content that is the same as or similar to the first embodiment described above can be referred to the above description, and will not be repeated hereafter. In addition, before step S20, the following is also included: Step S40: When it is determined from the inertial sensing data that the wearer is in motion, obtain the wearing status information of the wearable device. In this embodiment, when it is initially determined that the wearer is in motion based on inertial sensing data, the wearing status information of the wearable device can be obtained first. This wearing status information is determined by combining the DC component amplitude of the PPG raw waveform with the device's built-in capacitive contact sensor. Only when it is determined that the device is in a normal wearing state will the subsequent feature extraction steps be executed, and the outdoor score will be calculated based on the motion state and the light interference and illumination features corresponding to the PPG raw waveform.

[0073] Understandably, if it is determined that the device is not being worn, the recognition process will be terminated directly, and no further scoring calculations will be performed.

[0074] Based on the first embodiment of this application, in the sixth embodiment of this application, the content that is the same as or similar to the first embodiment described above can be referred to the above description and will not be repeated hereafter. Based on this, after step S30, the following is also included: Step S50: Trigger the startup process of the outdoor sports mode of the wearable device; Step S60: Obtain the duration of the wearable device in outdoor sports mode. When the duration of the exercise meets the preset duration, execute the prompt command corresponding to the duration of the exercise.

[0075] In this embodiment, when the wearable device determines that the user is in an outdoor exercise state, it automatically triggers the outdoor exercise mode startup process without requiring the user to manually start exercise recording. After the outdoor exercise mode is activated, the device simultaneously starts continuous recording of exercise data such as exercise duration, heart rate, and cadence, while adjusting the noise reduction strategy of the optical sensor to adapt to heart rate detection in strong outdoor light environments, ensuring the accuracy of exercise data.

[0076] Furthermore, the wearable device will also track the cumulative effective exercise time in outdoor sports mode in real time. When the cumulative exercise time meets the preset time threshold, a corresponding prompt instruction will be executed. These prompt instructions can be output through device vibration, watch face pop-ups, voice broadcasts, etc., to push reminders to users regarding exercise duration reaching the target, natural light exposure health reminders, or exercise hydration reminders. The preset time can be set by the user or use the system's default health recommendation time. For example, if the system presets the outdoor exercise reminder time to 30 minutes, the prompt instruction will be a vibration combined with a watch face text pop-up, with the message "30 minutes of outdoor walking has been completed, and light exposure has met the target." When a user wears a smart bracelet while walking outdoors, the system determines that the user is in an outdoor exercise state through inertial data and PPG characteristics, and automatically starts the outdoor exercise mode to accumulate effective exercise time. When the accumulated effective exercise time reaches 30 minutes, the bracelet triggers two short vibrations and pops up a reminder on the screen, while simultaneously recording the 30 minutes of natural light exposure time into the device's health data file. If the user enters an indoor place midway, the system recognizes the decrease in light and light interference characteristics and determines that the user has exited the outdoor exercise state, and stops accumulating exercise time. If the accumulated time does not reach the preset threshold, no reminder command will be triggered, thereby realizing the automated management and health guidance of outdoor exercise, improving the user experience and health benefits.

[0077] For example, to help understand the implementation process of the outdoor sports recognition method obtained by combining the above embodiments, please refer to... Figure 4 , Figure 4 A simplified flowchart of an outdoor sports recognition method is provided, specifically: Wearable devices simultaneously collect data from optical sensors, accelerometers, and gyroscopes. Once the data is ready, the recognition process begins. First, a wearing determination is performed, using optical signal characteristics and inertial data characteristics to determine if the device is worn correctly. If it is determined not to be worn, the process skips subsequent steps and returns to the data acquisition phase for continuous monitoring, avoiding misjudgments when the device is removed from the body. If it is determined to be worn, the wearing status is confirmed, and the motion state recognition stage begins. After confirming wearing, the user's motion state is identified based on accelerometer and gyroscope inertial data to determine if they are in a state of continuous limb activity. When valid motion is detected, the current timestamp is obtained, and the cumulative motion duration and continuity coefficient parameters for continuous outdoor judgment are updated synchronously. Combined with the illumination characteristics, light interference characteristics, and motion state extracted from the optical data, the outdoor score (OutdoorScore) is calculated.

[0078] Next, the outdoor score is compared with a preset threshold T. If the outdoor score does not reach the threshold, it means that the current scene does not meet the outdoor characteristics. In this case, the continuous count is reset to zero or decayed, and the accumulated continuous coefficient is reset to filter out single false compliance errors. Then, the process returns to the data collection end to wait for the next detection window. If the outdoor score is greater than the threshold, the continuous coefficient is incremented by 1 to complete the compliance count for this window. Then, it is further determined whether the accumulated continuous duration has reached the preset continuous duration threshold. If it has not reached the threshold, it waits for the next detection window and returns to the parameter update step to continue the loop judgment. If it reaches the threshold, it is judged as a valid outdoor activity, and the outdoor activity duration is officially accumulated. After the statistics are completed, the process returns to the data collection stage to continue the next round of monitoring and judgment.

[0079] Further, please refer to Figure 5 After confirming that the user is engaged in outdoor activities, the wearable device retrieves stored outdoor activity statistics. Based on this data, it calculates the user's cumulative effective outdoor activity time within the current statistical period. The calculated time is then compared to a preset health threshold. If the cumulative time is not lower than the threshold, the user's outdoor activity level meets the requirements, and the reminder process ends directly. If the cumulative time is lower than the threshold, a corresponding health reminder is generated. The reminder type and level are then determined based on the degree of time shortfall and user settings. After classification, the corresponding reminder content is output, and finally, the reminder is pushed to the user through vibration, screen display, and other means to guide the user to make up for the lost outdoor activity time.

[0080] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the outdoor sports identification method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0081] This application provides a wearable device; please refer to [reference needed]. Figure 6The wearable device includes a sensor data acquisition module, a wearing status recognition module, a motion status analysis module, a natural light environment analysis module, an outdoor activity judgment module, an outdoor time statistics module, and a health reminder module. The sensor data acquisition module collects raw sensor data such as inertial and optical sensors, providing basic data input for the entire process. The wearing status recognition module verifies whether the device is in a normal wearing state, filtering out misjudgments in scenarios where the device is not in contact with the user. The motion status analysis module identifies the user's motion state based on inertial sensor data, completing preliminary motion scenario screening. The natural light environment analysis module extracts illumination and light interference features from optical data to determine the natural light attributes of the current environment. The outdoor activity judgment module integrates the analysis results of motion status and natural light environment to determine whether the user is in a valid outdoor activity state. The outdoor time statistics module accumulates the valid outdoor activity time. The health reminder module, based on the accumulated time data, pushes corresponding health reminders to the user when the outdoor activity time is insufficient. Each module transmits processing results level by level according to the data flow, completing a complete functional closed loop from data acquisition to health guidance.

[0082] Furthermore, the wearable device also includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the outdoor sports recognition method in the first embodiment described above.

[0083] The following is for reference. Figure 7 It shows a structural schematic diagram suitable for implementing the wearable device of the embodiments of this application. Figure 7 The wearable device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0084] like Figure 7As shown, the wearable device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the wearable device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, magnetic tape, hard disk, etc.; and a communication device 1009. Communication device 1009 allows the wearable device to communicate wirelessly or wiredly with other devices to exchange data. While the figures show wearable devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0085] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0086] The wearable device provided in this application, employing the outdoor sports recognition method described in the above embodiments, can solve the technical problem of low accuracy in outdoor sports recognition. Compared with the prior art, the beneficial effects of the wearable device provided in this application are the same as those of the outdoor sports recognition method provided in the above embodiments, and other technical features of the wearable device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0087] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0088] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0089] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the outdoor sports recognition method in the above embodiments.

[0090] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM, or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0091] The aforementioned computer-readable storage medium may be included in the wearable device; or it may exist independently and not assembled into the wearable device.

[0092] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a wearable device, cause the wearable device to: Acquire inertial sensing data collected by wearable devices; When the wearer is determined to be in motion based on the inertial sensing data, the outdoor score of the wearer is calculated based on the light interference characteristics and illumination characteristics corresponding to the PPG raw waveform collected by the wearable device, as well as the motion state. When the outdoor score is greater than the preset score, it is determined that the wearer is in an outdoor sports state.

[0093] 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).

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0096] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described outdoor sports recognition method, thereby solving the technical problem of low accuracy in outdoor sports recognition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the outdoor sports recognition method provided in the above embodiments, and will not be repeated here.

[0097] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An outdoor sports recognition method, characterized in that, The outdoor sports identification method includes: Acquire inertial sensing data collected by wearable devices; When the wearer is determined to be in motion based on the inertial sensing data, the outdoor score of the wearer is calculated based on the light interference characteristics and illumination characteristics corresponding to the PPG raw waveform collected by the wearable device, as well as the motion state. When the outdoor score is greater than the preset score, it is determined that the wearer is in an outdoor sports state.

2. The outdoor sports recognition method as described in claim 1, characterized in that, The step of calculating the outdoor score of the wearer based on the light interference characteristics and illumination characteristics corresponding to the original PPG waveform collected by the wearable device, and the motion state, includes: A motion state score is calculated based on the motion state, and a lighting environment score is calculated based on the lighting characteristics. Based on the baseline drift characteristics, random fluctuation characteristics, high-frequency noise characteristics, spectral perturbation characteristics, and local saturation characteristics in the optical interference features, an optical noise score is calculated. The weighted fusion result among the motion state score, the lighting environment score, and the optical noise score is determined as the outdoor score of the wearer.

3. The outdoor sports recognition method as described in claim 1, characterized in that, The step of calculating the outdoor score of the wearer based on the light interference characteristics and illumination characteristics corresponding to the original PPG waveform collected by the wearable device, and the motion state, includes: A motion state score is calculated based on the motion state, and a lighting environment score is calculated based on the lighting characteristics. Based on the baseline drift characteristics, random fluctuation characteristics, high-frequency noise characteristics, spectral perturbation characteristics, and local saturation characteristics in the optical interference features, an optical noise score is calculated. The continuity score of the outdoor activity is calculated based on the continuous time coefficient when the outdoor score is greater than the preset score, wherein the continuity score is zero when the continuous time coefficient is the initial value. The weighted fusion result among the motion state score, the lighting environment score, the optical noise score, and the continuity score is determined as the outdoor score of the wearer.

4. The outdoor sports recognition method as described in claim 3, characterized in that, Before the step of determining that the wearer is in an outdoor sports state, the outdoor sports identification method further includes: When the outdoor score is greater than the preset score, update the current continuous time coefficient of the motion state; If the current continuous time coefficient is greater than a preset coefficient threshold, the step of determining that the wearer is in an outdoor sports state is executed. When the current continuous time coefficient is less than or equal to the preset coefficient threshold, the step of calculating the continuity score of the outdoor activity based on the continuous time coefficient of the outdoor score being greater than the preset score is executed.

5. The outdoor sports recognition method as described in claim 3, characterized in that, Before the step of determining the weighted fusion result among the motion state score, the lighting environment score, the optical noise score, and the continuity score as the outdoor score of the wearer, the outdoor motion recognition method further includes: Obtain the first duration corresponding to the motion state and the second duration for which the illumination feature satisfies a preset illumination threshold; The continuity score of the outdoor activity is calculated based on the first duration and the second duration.

6. The outdoor sports recognition method as described in any one of claims 2 or 3, characterized in that, The step of calculating the lighting environment score based on the lighting characteristics includes: Obtain the average intensity value of the illumination feature, and the fluctuation feature value within a preset time window; The average intensity value is mapped to a basic score of light intensity, and the fluctuation coefficient is determined based on the fluctuation characteristic value. The lighting environment score is obtained by correcting the basic score of the light intensity using the fluctuation coefficient.

7. The outdoor sports recognition method as described in claim 1, characterized in that, Before the steps of calculating the outdoor score of the wearer based on the light interference features and illumination features corresponding to the original PPG waveform collected by the wearable device, and the motion state, the outdoor motion recognition method further includes: When it is determined from the inertial sensing data that the wearer is in motion, the wearing status information of the wearable device is obtained. When the wearable device is in the wearing state, the steps of calculating the outdoor score of the wearer based on the light interference characteristics and light illumination characteristics corresponding to the PPG raw waveform collected by the wearable device and the motion state are performed.

8. The outdoor sports recognition method as described in claim 1, characterized in that, After the step of determining that the user is in an outdoor activity state when the outdoor score is greater than a preset score, the outdoor activity recognition method further includes: Trigger the startup process of the outdoor sports mode of the wearable device; The duration of the wearable device in the outdoor sports mode is obtained, and when the duration of the exercise meets the preset duration, the prompt instruction corresponding to the duration of the exercise is executed.

9. A wearable device, characterized in that, The wearable device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the outdoor sports recognition method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the outdoor sports recognition method as described in any one of claims 1 to 8.

Images