Remote monitoring method and children's smartwatch

Abstract

The present invention provides a remote monitoring method and a children's watch, relating to the technical field of monitoring. The method includes extracting the motion characteristics and sound characteristics of a mobile terminal from various sensor data and generating a current trajectory; based on the motion characteristics and the current trajectory, identifying the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library to obtain the current behavior pattern; inputting the motion characteristics and sound characteristics into a pre-trained prediction model, and using the prediction model to determine whether a moving object is approaching the mobile terminal; when it is determined that the moving object is approaching the mobile terminal, dynamically adjusting a preset distance threshold based on the motion characteristics, sound characteristics, and current trajectory at the current moment; determining whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generating an alarm message and pushing it to an associated terminal pre-paired with the mobile terminal when the distance is less. The present invention provides a more intelligent and personalized remote monitoring method.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technologies, and in particular to a remote monitoring method and a children's smartwatch. Background Art

[0002] With the increasing social concern for children's safety, technologies and products for children's safety guardianship have emerged continuously. Among them, portable terminals such as children's smartwatches, as devices worn by children daily, not only have basic functions such as calling and positioning, but also gradually incorporate remote monitoring technologies to achieve more comprehensive and detailed safety guardianship for children.

[0003] Traditional children's smartwatch monitoring methods mainly rely on GPS positioning technology. By obtaining the location information of children in real time, parents can know the whereabouts of their children at any time. However, in complex environments (such as indoors, high-rise dense areas, etc.), the positioning accuracy is often severely affected, and accurate and reliable children's location information cannot be provided for parents.

[0004] Therefore, it is necessary to provide a remote monitoring method and a children's smartwatch to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a remote monitoring method and a children's smartwatch, providing a more intelligent and personalized remote monitoring method to meet the higher requirements of parents for children's safety guardianship.

[0006] The present invention provides a remote monitoring method, and the monitoring method includes the following steps:

[0007] Extract the motion features and sound features of the mobile terminal from multiple sensor data, and generate a current trajectory based on the motion features, where the multiple sensor data are collected by a sensor component installed on the mobile terminal;

[0008] Based on the motion features and the current trajectory, identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library to obtain the current behavior pattern;

[0009] Input the motion features and the sound features into a pre-trained prediction model, and use the prediction model to determine whether there is a moving object approaching the mobile terminal;

[0010] When it is determined that the moving object is approaching the mobile terminal, dynamically adjust a preset distance threshold based on the motion features, sound features, and current trajectory at the current moment, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object in the current behavior pattern;

[0011] Determine whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to the associated terminal pre-paired with the mobile terminal when it is less.

[0012] Preferably, the multiple sensor data includes accelerometer data, gyroscope data, GPS data, and sound data, where the accelerometer data, the gyroscope data, and the GPS data are used to extract the motion features, and the sound data is used to extract the sound features, and the motion features include accelerometer data features, gyroscope data features, and GPS data features corresponding to the accelerometer data, the gyroscope data, and the GPS data respectively.

[0013] Preferably, the step of generating the current trajectory is as follows:

[0014] Based on the extracted accelerometer data features and gyroscope data features, combined with the position change information and timestamp data in the GPS data features, use a map matching algorithm to generate the current trajectory of the mobile terminal.

[0015] Preferably, based on the motion features and the current trajectory, identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library to obtain the current behavior pattern, including:

[0016] Extract multiple feature vectors related to the behavior pattern from the accelerometer data features, gyroscope data features, and GPS data features, and the feature vectors include acceleration, angular velocity, speed, direction, and rate of change of speed;

[0017] Match the feature vectors with multiple behavior patterns in the preset behavior pattern library, where the behavior pattern library contains multiple known behavior patterns and their corresponding feature vectors;

[0018] Calculate the similarity between the feature vectors and the feature vectors of each known behavior pattern, and select the known behavior pattern with the highest similarity as the current behavior pattern.

[0019] Preferably, inputting the motion features and the sound features into a pre-trained prediction model, and using the prediction model to determine whether there is a moving object approaching the mobile terminal, including:

[0020] Perform fusion processing on the extracted motion features and sound features to form a fusion feature vector;

[0021] Input the fusion feature vector into the pre-trained prediction model, where the prediction model is a neural network model that has been trained to identify and analyze the fusion feature vector to determine whether there is a moving object approaching the mobile terminal.

[0022] Output the judgment result. If the judgment result is that a moving object is approaching, trigger the subsequent step of dynamically adjusting the distance threshold.

[0023] Preferably, the training process of the prediction model includes:

[0024] Collect an annotated data set containing motion features, sound features, and the corresponding situation of the approaching moving object;

[0025] Use the data set to train a neural network model, and adjust the model parameters during the training process to minimize the prediction error rate;

[0026] Evaluate the performance of the neural network model through a cross-validation method, and finally save the trained model as a pre-trained prediction model.

[0027] Preferably, when it is determined that the moving object is approaching the mobile terminal, dynamically adjusting the preset distance threshold based on the motion features, sound features, and current trajectory at the current moment includes:

[0028] Adjust the preset basic distance threshold to obtain a preliminary distance threshold, where the adjustment uses the following formula:

[0029]

[0030] where, T p is the preliminary distance threshold, T0 is the basic distance threshold, F v is the speed adjustment factor, F d is the direction adjustment factor, F n is the noise adjustment factor;

[0031] Calculate the behavior pattern adjustment factor, and adjust the preliminary distance threshold based on the behavior pattern adjustment factor to obtain the final dynamic threshold, and use it as the adjusted distance threshold, where the adjustment of the preliminary distance threshold uses the following formula:

[0032]

[0033] where, T f is the final dynamic threshold, F b is the behavior pattern adjustment factor, v is the speed of the mobile terminal at the current moment, v max is the maximum speed in the current trajectory of the mobile terminal.

[0034] Preferably, in the adjustment of the basic distance threshold, the calculation formula of the speed adjustment factor is:

[0035]

[0036] Among them, F v is the speed adjustment factor, v is the speed of the mobile terminal at the current moment, Δv is the speed change rate in the current trajectory, and α is the influence coefficient of the preset speed change rate;

[0037] The calculation formula of the direction adjustment factor is:

[0038]

[0039] Among them, F d is the direction adjustment factor, d is the direction of the mobile terminal at the current moment, Δd is the direction change rate in the current trajectory, and β is the influence coefficient of the preset direction change rate;

[0040] The calculation formula of the noise adjustment factor is:

[0041]

[0042] Among them, F n is the noise adjustment factor, n is the ambient noise level of the mobile terminal at the current moment, Δn is the noise change rate in the current trajectory, and γ is the influence coefficient of the preset noise change rate.

[0043] Preferably, the calculation formula of the behavior pattern adjustment factor is:

[0044] F b = K b + δ × Δb

[0045] Among them, F b is the behavior pattern adjustment factor, Δb is the behavior pattern change rate, and is expressed as the ratio of the number of times the user's behavior pattern changes to the total time in the current trajectory, δ is the influence coefficient of the preset behavior pattern change rate, and K b is the behavior pattern adjustment coefficient.

[0046] The present invention also provides a children's watch, including a sensor component and a processor,

[0047] The sensor component is used for various sensor data;

[0048] The processor is used to extract the motion characteristics and sound characteristics of the mobile terminal from various sensor data, and generate the current trajectory based on the motion characteristics;

[0049] The processor is used to identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library based on the motion characteristics and the current trajectory, and obtain the current behavior pattern;

[0050] The processor is configured to input the motion feature and the sound feature into a pre-trained prediction model, and use the prediction model to determine whether a moving object is approaching the mobile terminal;

[0051] When the processor determines that the moving object is approaching the mobile terminal, it is configured to dynamically adjust a preset distance threshold based on the motion feature, sound feature, and current trajectory at the current moment, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object in the current behavior mode;

[0052] The processor is configured to determine whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to an associated terminal pre-paired with the mobile terminal when it is less.

[0053] Compared with the related art, the remote monitoring method and the children's watch provided by the present invention have the following beneficial effects:

[0054] The present invention extracts the motion feature and sound feature of the mobile terminal from multiple sensor data, and generates the current trajectory and behavior pattern recognition result based on these features, realizing the accurate perception of the user's behavior pattern. At the same time, the method also uses a pre-trained prediction model to intelligently judge the approach of the moving object, and dynamically adjusts the distance threshold according to the judgment result, thereby realizing the personalized monitoring of the safe distance in different behavior modes. Description of the Drawings

[0055] Figure 1 is a flowchart of the remote monitoring method provided by the present invention;

[0056] Figure 2 is a module structure diagram of the children's watch provided by the present invention. Detailed Embodiments

[0057] The present invention will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only for explaining the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all structures. Furthermore, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0058] It should also be noted that, for ease of description, only the parts related to the present invention rather than all the content are shown in the drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but there can also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0059] Embodiment 1

[0060] The present invention provides a remote monitoring method. Referring to Figure 1 as shown, the monitoring method includes the following steps:

[0061] S1: Extract the motion features and sound features of the mobile terminal from various sensor data, and generate a current trajectory based on the motion features, where the various sensor data are collected by a sensor component installed on the mobile terminal.

[0062] It should be noted that the various sensor data include accelerometer data, gyroscope data, GPS data, and sound data, where the accelerometer data, the gyroscope data, and the GPS data are used to extract the motion features, and the sound data is used to extract the sound features, and the motion features include accelerometer data features, gyroscope data features, and GPS data features corresponding to the accelerometer data, the gyroscope data, and the GPS data respectively.

[0063] In this embodiment, the accelerometer data is sourced from an accelerometer installed on the mobile terminal and can measure the linear acceleration on three axes (X, Y, Z). The accelerometer data is mainly used to extract the linear motion features of the mobile terminal. The acceleration magnitude can be obtained by calculating the square root of the sum of the squares of the acceleration values on the three axes. The acceleration direction is represented by obtaining a unit vector by dividing the acceleration value on each axis by the acceleration magnitude. The acceleration change rate is obtained by calculating the difference between the accelerations at two consecutive time points divided by the time interval.

[0064] Gyroscope data is sourced from the gyroscope installed on the mobile terminal and can measure the angular velocity on three axes (X, Y, Z). Gyroscope data is mainly used to extract the rotational motion characteristics of the mobile terminal. The magnitude of the angular velocity can be obtained by calculating the square root of the sum of the squares of the angular velocity values on the three axes. The direction of the angular velocity is represented by obtaining a unit vector by dividing the angular velocity value on each axis by the magnitude of the angular velocity. The rate of change of the angular velocity is obtained by calculating the difference in angular velocity between two consecutive time points divided by the time interval.

[0065] GPS data is sourced from the GPS receiver installed on the mobile terminal and can provide precise geographical location information. GPS data is mainly used to extract the position and speed characteristics of the mobile terminal. The position information includes the longitude, latitude, and altitude of the mobile terminal. The speed information includes the instantaneous speed of the mobile terminal. The direction information includes the heading angle of the mobile terminal. The rate of change of the position is obtained by calculating the differences in longitude, latitude, and altitude between two consecutive time points divided by the time interval.

[0066] Sound data is sourced from the microphone installed on the mobile terminal and can collect the audio signals of the surrounding environment. Sound data is mainly used to extract the acoustic environment characteristics around the mobile terminal, and the ambient noise level can be obtained by calculating the average sound pressure level of the sound signal.

[0067] From the above detailed description, it can be seen that the accelerometer data provides the linear motion characteristics of the mobile terminal, including the magnitude, direction, and rate of change of the acceleration. The gyroscope data provides the rotational motion characteristics of the mobile terminal, including the magnitude, direction, and rate of change of the angular velocity. The GPS data provides the position and speed characteristics of the mobile terminal, including longitude, latitude, altitude, speed, and direction. The sound data provides the acoustic environment characteristics around the mobile terminal, namely the ambient noise level. These characteristics together constitute the motion characteristics and sound characteristics of the mobile terminal, providing rich data support for subsequent behavior pattern recognition and environmental monitoring.

[0068] Meanwhile, in step S1, the generation step of the current trajectory is as follows:

[0069] Based on the extracted accelerometer data characteristics and gyroscope data characteristics, combined with the position change information and timestamp data in the GPS data characteristics, the current trajectory of the mobile terminal is generated using the map matching algorithm.

[0070] In this embodiment, the collected accelerometer data, gyroscope data, and GPS data are filtered to remove noise and outliers, ensuring the accuracy and consistency of the data.

[0071] Combine the accelerometer data features and gyroscope data features to form a comprehensive motion feature vector. This vector includes information such as acceleration, angular velocity, velocity, and direction.

[0072] Utilize the position and timestamp information in the GPS data to match the comprehensive motion feature vector with the map data. The specific method includes the following steps:

[0073] Dead reckoning: Estimate the path of the mobile terminal between two GPS points based on the acceleration and angular velocity data.

[0074] Map matching: Match the estimated path with the road network on the map to correct the errors caused by GPS signal drift.

[0075] Trajectory optimization: Further optimize the trajectory by combining the velocity and direction information to make it smoother and more accurate.

[0076] S2: Based on the motion features and the current trajectory, identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library to obtain the current behavior pattern.

[0077] Specifically, step S2 includes the following steps:

[0078] S21: Extract multiple feature vectors related to behavior patterns from the accelerometer data features, gyroscope data features, and GPS data features. The feature vectors include acceleration, angular velocity, velocity, direction, and rate of change of velocity.

[0079] In this embodiment, multiple feature vectors related to behavior patterns are extracted from the accelerometer data features, gyroscope data features, and GPS data features.

[0080] Among them, the accelerometer data provides linear motion features, the gyroscope data provides rotational motion features, and the GPS data provides position and velocity features. These feature vectors include acceleration, angular velocity, velocity, direction, rate of change of velocity, etc.

[0081] Exemplarily, the acceleration can be obtained by calculating the square root of the sum of the squares of the acceleration values on the three axes, the angular velocity can be obtained by calculating the square root of the sum of the squares of the angular velocity values on the three axes, the velocity can be directly obtained from the GPS data, the direction can be calculated from the gyroscope data, and the rate of change of velocity is obtained by calculating the difference in velocity between two consecutive time points divided by the time interval.

[0082] S22: Match the feature vectors with multiple behavior patterns in the preset behavior pattern library, where the behavior pattern library contains multiple known behavior patterns and their corresponding feature vectors.

[0083] In this embodiment, the extracted feature vectors are matched with multiple behavior patterns in a preset behavior pattern library. The behavior pattern library contains multiple known behavior patterns and their corresponding feature vectors. These known behavior patterns include, but are not limited to, common behavior patterns such as walking, running, cycling, and standing still. The matching process involves comparing the extracted feature vectors with the feature vectors of each known behavior pattern in the library to find the most similar known behavior pattern. Specifically, the Euclidean distance or cosine similarity between the feature vectors can be calculated for matching.

[0084] S23: Calculate the similarity between the feature vector and the feature vectors of each known behavior pattern, and select the known behavior pattern with the highest similarity as the current behavior pattern.

[0085] In this embodiment, the similarity between the feature vector and the feature vectors of each known behavior pattern is calculated, and the known behavior pattern with the highest similarity is selected as the current behavior pattern.

[0086] Exemplarily, calculate the Euclidean distance between the extracted feature vector and the feature vectors of each known behavior pattern in the library, and select the known behavior pattern with the smallest distance as the current behavior pattern. This can ensure that the recognized behavior pattern is the one that best matches the actual behavior of the current user.

[0087] S3: Input the motion feature and the sound feature into a pre-trained prediction model, and use the prediction model to determine whether there is a moving object approaching the mobile terminal.

[0088] Specifically, step S3 includes the following steps:

[0089] S31: Perform fusion processing on the extracted motion feature and the sound feature to form a fused feature vector.

[0090] In this embodiment, first, the motion feature and the sound feature extracted from multiple sensor data need to be fused to form a comprehensive feature vector. Specifically:

[0091] Motion feature: Includes acceleration, angular velocity, speed, direction, and rate of speed change, etc. These features are extracted from accelerometer data, gyroscope data, and GPS data.

[0092] Sound feature: Includes ambient noise level, etc. These features are extracted from the sound data collected by the microphone.

[0093] The specific steps of the fusion processing include:

[0094] Data preprocessing: Normalize the extracted motion feature and sound feature to ensure that each feature is on the same order of magnitude, which is convenient for subsequent model input.

[0095] Feature concatenation: Concatenate the normalized motion features and sound features into a high-dimensional feature vector. Exemplarily, if the dimension of the motion feature vector is five (acceleration, angular velocity, speed, direction, rate of speed change) and the dimension of the sound feature vector is one (ambient noise level), then the dimension of the final fused feature vector is six.

[0096] S32: Input the fused feature vector into a pre-trained prediction model, where the prediction model is a neural network model that has been trained to recognize and analyze the fused feature vector to determine whether a moving object is approaching the mobile terminal.

[0097] In this embodiment, first ensure that the neural network model used has been fully trained to effectively recognize and analyze the fused feature vector. The model is trained on a large number of labeled data sets, which contain the motion features and sound features of the mobile terminal in various environments, as well as the label information indicating whether there is a moving object approaching.

[0098] Use the fused feature vector formed in step S31 as the input and pass it to the pre-trained neural network model. The fused feature vector contains comprehensive information extracted from various sensors such as accelerometers, gyroscopes, GPS, and microphones, and can comprehensively reflect the current state of the mobile terminal and the surrounding environment.

[0099] After receiving the fused feature vector, the neural network model will perform a series of forward propagation operations to gradually process the input data. This process includes:

[0100] Feature transformation: Perform a non-linear transformation on the input features through multiple layers of neurons to capture the complex relationships in the data.

[0101] Feature extraction: The hidden layers inside the model are responsible for extracting higher-level abstract features from the input features, and these features help to distinguish different situations of moving objects approaching.

[0102] Decision function: Finally, the model generates a value between 0 and 1 through the sigmoid activation function of the output layer, representing the probability of a moving object approaching. Usually, a threshold (e.g., 0.5) is set, and if the threshold is exceeded, it is considered that a moving object is approaching.

[0103] Result output: The result generated by the model will be parsed into a judgment on whether a moving object is approaching. If the judgment result is "a moving object is approaching", then the subsequent step of dynamically adjusting the distance threshold will be triggered.

[0104] Specifically, the training process of the prediction model includes:

[0105] Collect an annotated dataset containing motion features, sound features, and the proximity of corresponding moving objects.

[0106] At the beginning of model training, it is first necessary to collect an annotated dataset with rich information. This dataset should cover motion features, sound features, and the labels of the proximity of corresponding moving objects in various environments.

[0107] Motion features: Collected by accelerometers, gyroscopes, and GPS, including acceleration, angular velocity, speed, direction, and rate of change of speed, etc.

[0108] Sound features: Collect sound features such as ambient noise level through microphones.

[0109] Annotation: Each data point requires a clear label indicating whether a moving object is approaching.

[0110] After the data is collected, preprocessing is required, including data cleaning, missing value handling, outlier detection, etc., to ensure the accuracy and consistency of the data. In addition, for motion features and sound features, normalization processing is also required to bring them to the same order of magnitude for subsequent model input.

[0111] Use the said dataset to train a neural network model, and adjust the model parameters during training to minimize the prediction error rate.

[0112] In this embodiment, a neural network model is constructed to identify and analyze the fused feature vector. This model is a multi-layer perceptron model, including:

[0113] Input layer: Receives the fused feature vector as input.

[0114] Hidden layer: Contains multiple layers of neurons for non-linear transformation and feature extraction of the input features.

[0115] Output layer: Uses the sigmoid activation function to generate a value between 0 and 1, representing the probability of a moving object approaching.

[0116] After the model is constructed, use the collected annotated dataset to train the model. During training, continuously adjust the model parameters to minimize the prediction error rate, which is usually achieved through the backpropagation algorithm.

[0117] Evaluate the performance of the neural network model through cross-validation methods, and finally save the trained model as a pre-trained prediction model.

[0118] In this embodiment, to evaluate the performance of the model, a cross-validation method is adopted. Specifically, the dataset is divided into k equal parts (e.g., k = 5), and each time k - 1 parts are used as the training set, and the remaining part is used as the test set. In this way, k evaluation results can be obtained, and the average value is taken as the final performance evaluation index.

[0119] During the cross-validation process, indicators including but not limited to accuracy, recall rate, F1 score, etc. are used to evaluate the performance of the model. These indicators can help understand the performance of the model in different situations and provide a basis for adjusting the model parameters.

[0120] After sufficient training and evaluation, the trained model is saved as a pre-trained prediction model. This model can be loaded and used in actual applications to determine whether a moving object is approaching the mobile terminal.

[0121] S33: Output the judgment result. If the judgment result is that a moving object is approaching, trigger the subsequent dynamic adjustment step of the distance threshold.

[0122] In this embodiment, the prediction model outputs a binary classification result indicating whether a moving object is approaching the mobile terminal. If the judgment result is that a moving object is approaching, then step S4 will be entered to dynamically adjust the preset distance threshold based on the current motion characteristics, sound characteristics, and current trajectory to ensure the safety of the user.

[0123] S4: When it is judged that the moving object is approaching the mobile terminal, dynamically adjust the preset distance threshold based on the motion characteristics, sound characteristics, and current trajectory at the current moment, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object under the current behavior mode.

[0124] Specifically, step S4 includes the following steps:

[0125] S41: Adjust the preset basic distance threshold to obtain a preliminary distance threshold, where the adjustment uses the following formula:

[0126]

[0127] where, T p is the preliminary distance threshold, T0 is the basic distance threshold, F v is the speed adjustment factor, F d is the direction adjustment factor, F n is the noise adjustment factor.

[0128] In this embodiment, the basic distance threshold is a preset initial value, representing the safe distance that should be maintained between the mobile terminal and the moving object under normal circumstances. This value is usually determined based on experience and experimental data. To adapt to different environments and behavior patterns, a speed adjustment factor, a direction adjustment factor, and a noise adjustment factor are introduced, and these factors are calculated according to the current motion characteristics and sound characteristics.

[0129] The speed adjustment factor reflects the impact of the current speed and speed change on the safe distance. The faster the speed of the child watch wearer, the greater the required safe distance, because when moving at high speed, the reaction time and stopping distance will both increase, and a larger buffer space is needed to avoid collisions. In addition, the speed change rate reflects the trend of speed change. If the speed change rate is large, it means that the speed changes frequently or violently, which increases the uncertainty and requires a larger safe distance to cope with possible emergencies.

[0130] The direction adjustment factor reflects the impact of the current direction and direction change on the safe distance. The direction of the child watch wearer affects their movement trajectory. Exemplarily, the required safe distance is different when going straight and when turning. When going straight, the path is relatively stable and the safe distance can be appropriately reduced; while when turning, the path changes greatly and a larger safe distance is required. In addition, the direction change rate reflects the frequency and amplitude of direction change. If the direction change rate is large, it means that the child changes direction frequently, increasing the uncertainty and complexity of the path, and a larger safe distance is required to ensure safety.

[0131] The noise adjustment factor reflects the impact of the current environmental noise on the safe distance. A high environmental noise level will interfere with the child's attention and perception ability, increasing the risk of accidents. Therefore, a larger safe distance is required in a high-noise environment to compensate for this interference. In addition, the noise change rate reflects the trend of environmental noise change. If the noise change rate is large, it means that the environmental noise is unstable, increasing the uncertainty and potential risks, and a larger safe distance is required to cope with possible emergencies.

[0132] By combining the speed adjustment factor, the direction adjustment factor, and the noise adjustment factor, the initial distance threshold can more comprehensively reflect the current environment and the child's behavior's demand for the safe distance. Specifically, the speed adjustment factor ensures that in the case of high speed or frequent acceleration and deceleration, the safe distance is large enough to prevent collisions caused by insufficient reaction time. The direction adjustment factor ensures that in the case of frequent direction changes or turning, the safe distance is large enough to prevent accidents caused by path changes. The noise adjustment factor ensures that in a high-noise or frequently changing noise environment, the safe distance is large enough to prevent dangers caused by distracted attention.

[0133] S42: Calculate the behavior pattern adjustment factor, and adjust the preliminary distance threshold based on the behavior pattern adjustment factor to obtain the final dynamic threshold, which is used as the adjusted distance threshold. The adjustment of the preliminary distance threshold adopts the following formula:

[0134]

[0135] where, T f is the final dynamic threshold, F b is the behavior pattern adjustment factor, v is the speed of the mobile terminal at the current moment, and v max is the maximum speed in the current trajectory of the mobile terminal.

[0136] In the remote monitoring method provided by the present invention, the behavior pattern influence factor has an important impact on the final dynamic threshold. The reason is that the user's behavior pattern directly affects their safety requirements and risk levels in a specific environment. Different behavior patterns mean that the user may be in different activity states and environmental conditions, and the changes in these states and conditions require the security system to flexibly adjust the safety distance threshold to provide more effective protection. Therefore, it is necessary to further adjust the preliminary distance threshold through the behavior pattern adjustment factor.

[0137] Among them, in the adjustment of the basic distance threshold, the calculation formula of the speed adjustment factor is:

[0138]

[0139] where, F v is the speed adjustment factor, v is the speed of the mobile terminal at the current moment, Δv is the speed change rate in the current trajectory, and α is the influence coefficient of the preset speed change rate.

[0140] In this embodiment, the value 10 is used to standardize the terminal speed so that it affects the threshold within a reasonable range.

[0141] The calculation formula of the direction adjustment factor is:

[0142]

[0143] where, F d is the direction adjustment factor, d is the direction of the mobile terminal at the current moment, Δd is the direction change rate in the current trajectory, and β is the influence coefficient of the preset direction change rate.

[0144] In this embodiment, the value 90 is also used to standardize the terminal direction so that it affects the threshold within a reasonable range.

[0145] The calculation formula of the noise adjustment factor is:

[0146]

[0147] Among them, F n is the noise adjustment factor, n is the ambient noise level of the mobile terminal at the current moment, Δn is the noise change rate in the current trajectory, and γ is the influence coefficient of the preset noise change rate.

[0148] In this embodiment, the value 100 is also used to standardize the ambient noise level so that it affects the threshold within a reasonable range.

[0149] Specifically, the calculation formula of the behavior pattern adjustment factor is:

[0150] F b = K b + δ × Δb

[0151] Among them, F b is the behavior pattern adjustment factor, Δb is the behavior pattern change rate, and is expressed as the ratio of the number of times the user's behavior pattern changes to the total time in the current trajectory, δ is the influence coefficient of the preset behavior pattern change rate, and K b is the behavior pattern adjustment coefficient.

[0152] In this embodiment, the behavior pattern adjustment coefficient is the adjustment coefficient under different behavior patterns. The corresponding adjustment coefficient can be found through a preset mapping table. This mapping table defines the adjustment coefficients corresponding to different behavior patterns for use when calculating the behavior pattern adjustment factor. The construction process of the mapping table includes:

[0153] Define behavior patterns: First, define all possible behavior patterns, such as stationary, walking, jogging, running fast, running, cycling, driving, etc.

[0154] Set adjustment coefficients: Set a reasonable adjustment coefficient for each behavior pattern. These coefficients can be determined based on actual tests and experience to ensure that the safety distance threshold can be reasonably adjusted under different behavior patterns.

[0155] S5: Determine whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to the associated terminal pre-paired with the mobile terminal when it is less.

[0156] In this embodiment, first obtain the relative distance, which specifically includes:

[0157] Obtain the location information of the mobile terminal: Obtain the current location information of the mobile terminal through GPS data, including longitude, latitude, and altitude.

[0158] Estimate the position information of a moving object: Based on the sound data collected by the sound sensor, combined with the accelerometer, gyroscope, and GPS data, estimate the position information of the moving object. The specific method is as follows:

[0159] Sound data processing: Calculate the average sound pressure level of the sound signal and evaluate the environmental noise level.

[0160] Motion data processing: Use the accelerometer and gyroscope data to estimate the motion trajectory and direction of the mobile terminal.

[0161] Position estimation: Combine the sound data and motion data, and use a sound source localization algorithm (specifically, a method based on sound intensity and time difference of arrival) to estimate the position of the moving object.

[0162] Calculate the relative distance: Based on the estimated position information of the mobile terminal and the moving object, calculate the relative distance between the two, where the relative distance is calculated using the Euclidean distance formula.

[0163] Then, compare the relative distance with the dynamic threshold, specifically including:

[0164] Obtain the dynamic threshold: Obtain the finally dynamically adjusted dynamic threshold from step S4.

[0165] Compare the relative distance with the final dynamic threshold: Compare the calculated relative distance with the final dynamic threshold to determine whether it is less than the dynamic threshold.

[0166] Next, generate an alarm message, specifically including:

[0167] If the relative distance is less than the final dynamic threshold, it is considered that the moving object is approaching the mobile terminal, there is a potential safety risk, and an alarm message is generated, including but not limited to the following content: alarm time, position information of the moving object, position information of the mobile terminal, relative distance, dynamic threshold, and the user's current behavior pattern.

[0168] Finally, push the alarm message, specifically including:

[0169] Associated terminal: Determine the associated terminal pre-paired with the mobile terminal. The associated terminal can be devices such as the user's guardian's mobile phone, smart watch, etc.

[0170] Push method: Push the alarm message to the associated terminal through wireless communication technologies (including but not limited to Bluetooth, Wi-Fi, cellular network, etc.).

[0171] Display the alarm message: Display the alarm message on the associated terminal to remind the user to pay attention to safety. The display method can be but not limited to pop-up notifications, vibration prompts, sound alarms, etc.

[0172] Embodiment 2

[0173] The present invention also provides a children's watch. Refer to Figure 2 as shown, which includes a sensor assembly 100 and a processor 200.

[0174] The sensor assembly 100 is used for various sensor data.

[0175] The processor 200 is used to extract the motion characteristics and sound characteristics of the mobile terminal from various sensor data, and generate a current trajectory based on the motion characteristics.

[0176] The processor 200 is used to identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library based on the motion characteristics and the current trajectory, and obtain the current behavior pattern.

[0177] The processor 200 is used to input the motion characteristics and the sound characteristics into a pre-trained prediction model, and use the prediction model to determine whether there is a moving object approaching the mobile terminal.

[0178] When the processor 200 determines that the moving object is approaching the mobile terminal, it dynamically adjusts a preset distance threshold based on the motion characteristics, sound characteristics, and current trajectory at the current moment, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object in the current behavior pattern.

[0179] The processor 200 is used to determine whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to an associated terminal pre-paired with the mobile terminal when it is less.

[0180] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowcharts and / or block diagrams can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0181] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0182] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent in such a process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

Claims

1. A remote monitoring method, characterized in that, The monitoring method includes the following steps: Extract the motion features and sound features of the mobile terminal from various sensor data, and generate a current trajectory based on the motion features, where the various sensor data are collected by a sensor component installed on the mobile terminal; Based on the motion features and the current trajectory, identify the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library to obtain the current behavior pattern; Input the motion features and the sound features into a pre-trained prediction model, and use the prediction model to determine whether a moving object is approaching the mobile terminal; When it is determined that the moving object is approaching the mobile terminal, dynamically adjust a preset distance threshold based on the motion features, sound features, and current trajectory at the current moment, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object in the current behavior pattern; Judge whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to an associated terminal pre-paired with the mobile terminal when it is less; 2. The remote monitoring method according to claim 1, characterized in that, The various sensor data include accelerometer data, gyroscope data, GPS data, and sound data, where the accelerometer data, the gyroscope data, and the GPS data are used to extract the motion features, and the sound data is used to extract the sound features, where the motion features include accelerometer data features, gyroscope data features, and GPS data features corresponding to the accelerometer data, the gyroscope data, and the GPS data respectively.

3. The remote monitoring method according to claim 2, wherein The steps for generating the current trajectory are as follows: Based on the extracted accelerometer data features and gyroscope data features, combined with the position change information and timestamp data in the GPS data features, use a map matching algorithm to generate the current trajectory of the mobile terminal.

4. A remote monitoring method according to claim 3, characterized in that, The identifying the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library based on the motion features and the current trajectory to obtain the current behavior pattern includes: Extract multiple behavior pattern-related feature vectors from the accelerometer data features, gyroscope data features, and GPS data features, where the feature vectors include acceleration, angular velocity, speed, direction, and speed change rate; Match the feature vectors with multiple behavior patterns in the preset behavior pattern library, where the behavior pattern library contains multiple known behavior patterns and their corresponding feature vectors; Calculate the similarity between the feature vectors and the feature vectors of each known behavior pattern, and select the known behavior pattern with the highest similarity as the current behavior pattern.

5. A remote monitoring method according to claim 4, characterized in that, The inputting the motion features and the sound features into a pre-trained prediction model, and using the prediction model to determine whether a moving object is approaching the mobile terminal includes: Perform a fusion process on the extracted motion features and sound features to form a fusion feature vector; Input the fused feature vector into a pre-trained prediction model, where the prediction model is a neural network model trained to recognize and analyze the fused feature vector to determine whether a moving object is approaching the mobile terminal; Output a judgment result. If the judgment result is that a moving object is approaching, trigger subsequent steps for dynamically adjusting the distance threshold.

6. The remote monitoring method according to claim 5, characterized in that, The training process of the prediction model includes: Collect an annotated data set containing motion features, sound features, and the corresponding situation of a moving object approaching; Use the data set to train the neural network model, and adjust the model parameters during the training process to minimize the prediction error rate; Evaluate the performance of the neural network model through a cross-validation method, and finally save the trained model as a pre-trained prediction model.

7. The remote monitoring method according to claim 6, characterized in that, When it is determined that the moving object is approaching the mobile terminal, dynamically adjust the preset distance threshold based on the motion features, sound features, and current trajectory at the current moment, including: Adjust the preset basic distance threshold to obtain a preliminary distance threshold, where the adjustment uses the following formula: Among them, T p is the preliminary distance threshold, T0 is the base distance threshold, F v is the speed adjustment factor, F d is the direction adjustment factor, F n is the noise adjustment factor; Calculate a behavior pattern adjustment factor, and adjust the preliminary distance threshold based on the behavior pattern adjustment factor to obtain a final dynamic threshold, which is used as the adjusted distance threshold. The adjustment of the preliminary distance threshold uses the following formula: Among them, T f is the final dynamic threshold, F b is the behavior pattern adjustment factor, v is the speed of the mobile terminal at the current moment, v max is the maximum speed in the current trajectory of the mobile terminal.

8. A remote monitoring method according to claim 7, characterized in that, In the adjustment of the basic distance threshold, the calculation formula for the speed adjustment factor is: where F v is the speed adjustment factor, v is the speed of the mobile terminal at the current moment, Δv is the speed change rate in the current trajectory, and α is the influence coefficient of the preset speed change rate; The calculation formula for the direction adjustment factor is: Among them, F d is the direction adjustment factor, d is the direction of the mobile terminal at the current moment, Δd is the direction change rate in the current trajectory, and β is the influence coefficient of the preset direction change rate; The calculation formula for the noise adjustment factor is: Among them, F n is the noise adjustment factor, n is the environmental noise level of the mobile terminal at the current moment, Δn is the noise change rate in the current trajectory, and γ is the influence coefficient of the preset noise change rate.

9. The remote monitoring method according to claim 8, wherein The calculation formula for the behavior pattern adjustment factor is: F b = K b + δ × Δb Among them, F b is the behavior pattern adjustment factor, Δb is the behavior pattern change rate, and it is expressed as the ratio of the number of times the user's behavior pattern changes in the current trajectory to the total time. δ is the influence coefficient of the preset behavior pattern change rate, and K b is the behavior pattern adjustment coefficient.

10. A children's watch, characterized in that, It includes a sensor component and a processor. The sensor component is used for various sensor data. The processor is used to extract the motion features and sound features of the mobile terminal from various sensor data, and generate a current trajectory based on the motion features. The processor is used to recognize the behavior pattern of the user corresponding to the mobile terminal through a preset behavior pattern library based on the motion features and the current trajectory, and obtain the current behavior pattern. The processor is used to input the motion features and the sound features into the pre-trained prediction model, and use the prediction model to determine whether a moving object is approaching the mobile terminal. The processor is used to dynamically adjust the preset distance threshold based on the motion features, sound features, and current trajectory at the current moment when it is determined that the moving object is approaching the mobile terminal, where the distance threshold represents the safe distance that should be maintained between the mobile terminal and the moving object in the current behavior pattern. The processor is used to determine whether the relative distance between the moving object and the mobile terminal is less than the dynamically adjusted distance threshold, and generate an alarm message and push it to an associated terminal pre-paired with the mobile terminal when it is less than.

Images