Context analysis method, apparatus, device, storage medium and product

Abstract

This application discloses a context analysis method, apparatus, device, storage medium, and product, relating to the field of computer technology. The context analysis method includes: acquiring environmental information collected by a smartwatch; inputting the environmental information into a preset context analysis model to analyze the user's context and obtain context analysis results. The preset context analysis model is obtained through iterative training based on sample environmental information and sample labels. This application automatically acquires environmental information collected by a smartwatch and automatically performs user context analysis using the collected user information to obtain context analysis results. It eliminates the need for manual context setting, thus avoiding the problem in wearable device applications such as smartwatches where different contexts can only be manually set and cannot be automatically analyzed, reducing the efficiency of smartwatch use.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a scenario analysis method, apparatus, device, storage medium, and product. Background Technology

[0002] Contextual analysis refers to the technology of identifying a user's current context by analyzing user behavior, environment, and other relevant information, and then providing personalized services or adjusting device functions accordingly.

[0003] In related technologies, the application of wearable devices such as smartwatches can only be done manually for different scenarios, and the scenarios cannot be automatically analyzed, which reduces the efficiency of using smartwatches. Summary of the Invention

[0004] The main purpose of this application is to provide a scenario analysis method, device, equipment, storage medium and product, which aims to solve the technical problem that smartwatches can only be set manually for different scenarios and cannot automatically analyze the scenarios, thus reducing the efficiency of smartwatch use.

[0005] To achieve the above objectives, this application proposes a context analysis method, which includes:

[0006] Obtain environmental information collected by the smartwatch;

[0007] The environmental information is input into a preset context analysis model to analyze the user's context and obtain context analysis results. The preset context analysis model is obtained through iterative training based on sample environmental information and sample labels.

[0008] In one embodiment, before the step of inputting the environmental information into a preset context analysis model to analyze the user's context and obtain the context analysis result, the following steps are included:

[0009] Obtain sample environment information of users in different scenarios, wherein the sample environment information includes the same number of sample environment information in different scenarios;

[0010] Based on the sample environment information, determine the context weight of the user in different contexts;

[0011] The context corresponding to the sample environment information is used as the sample label;

[0012] Obtain the initial context analysis model;

[0013] Based on the sample environment information, the sample labels, and the context weights, the initial context analysis model is iteratively trained to obtain a preset context analysis model.

[0014] In one embodiment, before the step of using the context corresponding to the sample environment information as the sample label, the following steps are included:

[0015] The sample environment information is labeled with context information at least once to obtain context information;

[0016] The number of times the context information corresponding to the same sample environment information is consistent is calculated to obtain the actual number of consistent instances.

[0017] Based on the actual number of consistent occurrences, a consistency judgment is made on the context information. If the context information is consistent, the context corresponding to the sample environment information is obtained, and the context corresponding to the sample environment information is used as the sample label.

[0018] In one embodiment, the step of iteratively training the initial context analysis model based on the sample environment information and the sample labels to obtain a preset context analysis model includes:

[0019] The sample environment information is input into the initial situation analysis model to perform situation prediction, and the initial situation analysis result is obtained.

[0020] The difference between the initial context analysis results and the sample labels is calculated to obtain the error result;

[0021] Based on the error results, the parameters of the initial scenario analysis model are adjusted until the error results meet the preset threshold, at which point training stops, and a preset scenario analysis model that meets the accuracy requirements is obtained.

[0022] In one embodiment, after the step of inputting the environmental information into a preset context analysis model to analyze the user's context and obtain the context analysis results, the method further includes:

[0023] Based on the results of the context analysis, the user's target mode is determined;

[0024] The target mode is input into a preset strategy model to predict the parameters of the smartwatch under the target mode, and the predicted parameter data is obtained.

[0025] Based on the parameter data, the parameters of the smartwatch are adjusted to obtain a smartwatch that adapts to the target mode after parameter adjustment.

[0026] In one embodiment, the step of inputting the target pattern into a preset strategy model to predict the parameters of the smartwatch under the target pattern and obtaining predicted parameter data includes:

[0027] The target mode is input into a preset strategy model to predict the parameters of the smartwatch under the target mode, thereby obtaining the predicted parameter data.

[0028] Obtain historical parameter data from the user, adjust the predicted parameter data accordingly, and obtain the adjusted predicted parameter data.

[0029] Furthermore, to achieve the above objectives, this application also proposes a context analysis device, which includes:

[0030] The acquisition module is used to acquire environmental information collected by the smartwatch;

[0031] The analysis module is used to input the environmental information into a preset situation analysis model, analyze the user's situation, and obtain the situation analysis results. The preset situation analysis model is obtained by iterative training based on sample environmental information and sample labels.

[0032] In addition, to achieve the above objectives, this application also proposes a context analysis device, the 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 context analysis method as described above.

[0033] 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 which, when executed by a processor, implements the steps of the context analysis method described above.

[0034] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the context analysis method described above.

[0035] One or more technical solutions proposed in this application have at least the following technical effects:

[0036] In contrast to related technologies, where smartwatches and other wearable devices require manual setting of scenarios for different situations and cannot automatically analyze the scenarios, thus reducing the efficiency of smartwatch use, this application automatically acquires environmental information collected by the smartwatch and inputs the collected user information into a preset scenario analysis model to automatically perform user scenario analysis and obtain scenario analysis results. This eliminates the need for manual scenario setting and thus avoids the problem of reduced efficiency in smartwatches and other wearable devices where scenarios can only be set manually and cannot be automatically analyzed. Attached Figure Description

[0037] 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.

[0038] 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.

[0039] Figure 1 This is a flowchart illustrating the scenario analysis method of this application in Implementation Example 1.

[0040] Figure 2 This is a flowchart illustrating Embodiment 2 of the scenario analysis method of this application;

[0041] Figure 3 This is a schematic diagram of the module structure of the scenario analysis device according to an embodiment of this application;

[0042] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the scenario analysis method in the embodiments of this application.

[0043] 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

[0044] 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.

[0045] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0046] The main solution of this application embodiment is: to obtain environmental information collected by a smartwatch; to input the environmental information into a preset context analysis model to analyze the user's context and obtain context analysis results, wherein the preset context analysis model is obtained by iterative training based on sample environmental information and sample labels.

[0047] In related technologies, the application of wearable devices such as smartwatches can only be done manually for different scenarios, and the scenarios cannot be automatically analyzed, which reduces the efficiency of using smartwatches.

[0048] This application automatically acquires environmental information collected by smartwatches and inputs the collected user information into a preset scenario analysis model to automatically perform user scenario analysis and obtain scenario analysis results. No manual scenario setting is required. Therefore, it can avoid the problem in the application of wearable devices such as smartwatches that different scenarios can only be set manually and cannot be automatically analyzed, which reduces the efficiency of smartwatch use.

[0049] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions. The following description uses a context analysis device as an example to illustrate this embodiment and the subsequent embodiments.

[0050] Based on this, embodiments of this application provide a scenario analysis method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the scenario analysis method of this application.

[0051] In this embodiment, the scenario analysis method includes steps S100 to S200:

[0052] Step S100: Obtain environmental information collected by the smartwatch;

[0053] It should be noted that the execution subject of this embodiment is a context analysis device, which is equipped with a smartwatch. The smartwatch is equipped with multiple sensors, including motion sensors, ambient light sensors, and heart rate detectors. These sensors are used to collect various types of information from the user and perform context analysis based on this information to identify the user's current context.

[0054] Understandably, contextual analytics devices acquire user information collected by the sensors of smartwatches. Specifically, after acquiring user information, these devices need to perform database cleaning. The purpose of data cleaning is to remove noise and outliers to ensure data quality. Common data cleaning methods include:

[0055] Noise removal: Use filters (such as low-pass filters, median filters, etc.) to remove high-frequency noise from sensor data.

[0056] Filling missing values: For missing data points, interpolation methods (such as linear interpolation, polynomial interpolation), forward filling (ffill), or backward filling (bfill) can be used to fill them.

[0057] Outlier removal: Use statistical methods (such as Z-score, IQR) or machine learning methods (such as isolated forest, local outlier) to detect and remove outliers.

[0058] Specifically, after data cleaning, context analysis equipment needs to integrate sensor data to form a comprehensive dataset. Common data fusion methods include:

[0059] Time synchronization: Ensure that data from different sensors are synchronized in time, usually by aligning timestamps or using a fixed time window.

[0060] Data merging: Merging data from different sensors into a unified data frame in chronological order for subsequent processing.

[0061] Feature Combination: Combining features from different sensors to form a new feature vector, in order to better reflect the user's activity status.

[0062] Specifically, after data fusion, context analysis devices need to extract useful information from the raw data so that the model can better identify user activities or the environment. Common feature extraction methods include:

[0063] Statistical features: Extract statistical features from sensor data, such as maximum value, minimum value, mean, standard deviation, median, etc.

[0064] Frequency domain features: Perform Fourier transform (FFT) on the sensor data to extract frequency domain features, such as dominant frequency and power spectral density.

[0065] Temporal features: Extract temporal features such as zero-crossing rate, energy, and entropy.

[0066] Custom features: Design specific features based on specific application requirements, such as gait cycle and stride length.

[0067] Specifically, after feature extraction, the context analysis device needs to standardize the data. The purpose of data standardization is to make the data from different sensors comparable, so as to ensure that the model can learn better during the training process.

[0068] Step S200: Input the environmental information into a preset context analysis model to analyze the user's context and obtain context analysis results. The preset context analysis model is obtained through iterative training based on sample environmental information and sample labels.

[0069] It should be noted that the context analysis result reflects the user's current context. The preset context analysis model is a pre-trained model that can predict input data to obtain the context analysis result. The context analysis device inputs pre-processed user information into the preset context analysis model, uses the pre-trained model to perform context prediction, and obtains the predicted context analysis result.

[0070] In one feasible implementation, the steps preceding the step of inputting the environmental information into a preset context analysis model to analyze the user's context and obtain the context analysis results are as follows:

[0071] Obtain sample environment information of users in different scenarios, wherein the sample environment information includes the same number of sample environment information in different scenarios;

[0072] It should be noted that the sample environment information refers to sensor data from the user in different contexts. This data can be obtained from smartwatches or other wearable devices. The sample environment information should be equal across different contexts. When the number of samples differs significantly between different categories, the model may tend to predict the category with the larger sample size. Ensuring equal sample environment information across different contexts can improve the accuracy of model predictions. Sample environment information includes, but is not limited to:

[0073] Location information: Obtain the user's geographical location via GPS or Wi-Fi positioning system.

[0074] Motion sensor data, such as accelerometers and gyroscopes, is used to detect the user's motion state and posture.

[0075] Ambient light sensor: measures the light intensity of the surrounding environment to determine whether the user is outdoors or indoors.

[0076] Temperature and humidity sensors: to understand environmental conditions.

[0077] Heart rate monitor: Monitors the user's heart rate using a photoplethysmography (PPG) sensor.

[0078] Gestational Skin Response Sensor (GSR): Measures skin conductivity to assess emotional state.

[0079] Other biometric data, such as blood oxygen saturation (SpO2).

[0080] Understandably, the context analysis device acquires the above information and uses it as sample environment information for model training.

[0081] Based on the sample environment information, determine the context weight of the user in different contexts;

[0082] It should be noted that contextual weights reflect the degree of influence of different contextual factors on user behavior and needs. First, it is necessary to define the contextual factors that play an important role in the user environment. These factors may include, but are not limited to:

[0083] Time factor: Time periods of the day (morning, noon, evening).

[0084] Location factor: The user's geographical location (home, office, outdoors).

[0085] Activity factors: ongoing activities (such as work, exercise, rest).

[0086] Device status: Device battery level, connection status, etc.

[0087] Health factors: The user's health status (such as heart rate, sleep quality).

[0088] Understandably, contextual analysis devices analyze the impact of different contextual factors on user behavior and needs based on collected sample environmental information. According to the analysis results, the weight of each contextual factor is determined, and the weight reflects the importance of the contextual factor in different user contexts.

[0089] The context corresponding to the sample environment information is used as the sample label;

[0090] Understandably, sample labels record the context represented by the sample's environmental information. Labels may include, but are not limited to:

[0091] Activity status: walking, running, driving, stationary, etc.

[0092] Environmental conditions: indoors, outdoors, office, home, etc.

[0093] Obtain the initial scenario analysis model;

[0094] It should be noted that the initial context analysis model is a pre-trained model. The context analysis device acquires a pre-selected initial context analysis model, which can be used to predict user behavior or preferences in specific situations.

[0095] Based on the sample environment information, the sample labels, and the context weights, the initial context analysis model is iteratively trained to obtain a preset context analysis model.

[0096] Understandably, the context analysis device uses sample environment information as the training set and sample labels as the test set. It trains the model using the training set data, evaluates the model performance on the test set, and makes accurate predictions about the user's situation based on the context weights. It then adjusts the model based on its performance on the test set and repeats the training process until the model performance reaches the expected level, thereby obtaining the preset context analysis model.

[0097] In one feasible implementation, the step of using the context corresponding to the sample environment information as the sample label includes the following steps:

[0098] The sample environment information is labeled with context information at least once to obtain context information;

[0099] It should be noted that sample labels are obtained through annotation. In cases of multiple annotations, it is necessary to check the consistency of the labels to effectively improve the reliability and accuracy of the annotation results. Context analysis equipment uses the same standards and categories to perform multiple context annotations on the sample environment information to obtain contextual information.

[0100] The number of times the context information corresponding to the same sample environment information is consistent is calculated to obtain the actual number of consistent instances.

[0101] Understandably, in the case of two annotations, the actual number of consistent annotations is the same as the number of consistent annotations in the case of multiple annotations. The context analysis device counts the number of consistent annotations in two cases to obtain the actual number of consistent annotations.

[0102] Based on the actual number of consistent occurrences, a consistency judgment is made on the context information. If the context information is consistent, the context corresponding to the sample environment information is obtained, and the context corresponding to the sample environment information is used as the sample label.

[0103] It should be noted that the context analysis device judges the actual number of times the information matches. If the number of times the match exceeds a preset threshold, the context information is judged to be consistent, and the context corresponding to the sample environment information is used as the sample label.

[0104] In one feasible implementation, the step of iteratively training the initial context analysis model based on the sample environment information and the sample labels to obtain a preset context analysis model includes the following steps:

[0105] The sample environment information is input into the initial situation analysis model to perform situation prediction, and the initial situation analysis result is obtained.

[0106] It should be noted that the initial context analysis result is the user's context predicted by the initial context analysis model. The context analysis device inputs sample environmental information into an initially set context analysis model, which generates a prediction result based on the input data, thus yielding the initial context analysis result.

[0107] The difference between the initial context analysis results and the sample labels is calculated to obtain the error result;

[0108] Understandably, the error result reflects the current performance of the model; the smaller the error, the closer the model's prediction is to the true value. Sample labels represent the actual observed values. The context analysis device uses a loss function to measure the difference between the model's prediction and the actual observed values.

[0109] Specifically, different loss functions can be selected depending on the task:

[0110] Regression tasks typically use the mean squared error (MSE), which calculates the average of the sum of squares of the differences between the predicted and actual values.

[0111] Classification tasks: For binary or multi-class classification problems, cross-entropy loss is commonly used, which measures the difference between probability distributions.

[0112] Based on the error results, the parameters of the initial scenario analysis model are adjusted until the error results meet the preset threshold, at which point training stops, and a preset scenario analysis model that meets the accuracy requirements is obtained.

[0113] It should be noted that the error result is the loss. Once the context analysis device calculates the loss, it can calculate the gradient of the loss function L with respect to the model parameters θ using the chain rule. Specifically, for the weights and biases of each layer, their corresponding partial derivatives need to be calculated. The gradient of the loss with respect to the model parameters is calculated through backpropagation. This process involves the chain rule: starting from the output layer, the derivative of the loss function L with respect to the output of that layer is calculated, and the derivative is passed back to the previous layer. The derivatives of the weights and biases of the previous layer with respect to the loss function are calculated, and the derivatives of the loss function with respect to the weights of each layer are passed back in sequence. Finally, the gradient of the parameters of each layer is obtained. With the gradients of the parameters of each layer, the model parameters can be updated according to the optimization algorithm, so that the model can better fit the data in future predictions. This process is repeated until the model converges or reaches the predetermined stopping condition, thus obtaining the preset context analysis model that meets the accuracy requirements.

[0114] In this embodiment, the context analysis device iteratively trains the initial context analysis model to obtain a preset context analysis model that meets the accuracy requirements, automatically analyzes user information, and obtains context analysis results, thereby improving the efficiency of smartwatch usage.

[0115] This application provides a scenario analysis method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the scenario analysis method of this application.

[0116] In one feasible implementation, step S200 is followed by steps A10 to A30:

[0117] Step A10: Based on the context analysis results, determine the target mode in which the user is in;

[0118] Understandably, a target pattern is a user's behavioral pattern in different contexts. Contextual analysis devices can define target patterns based on analysis results, that is, how a user expects the smartwatch to behave or provide certain functions in a specific context. Here are some examples of target patterns for different contexts: Outdoor Mode, Sports Mode, Work Mode, Rest Mode, and Social Mode.

[0119] Step A20: Input the target mode into the preset strategy model to predict the parameters of the smartwatch under the target mode and obtain the predicted parameter data.

[0120] It should be noted that the preset strategy model calculates a series of parameter data based on the input target pattern. The context analysis device inputs the previously determined target pattern into the preset strategy model, which can then predict the most suitable parameter configuration for the smartwatch under that pattern.

[0121] Specifically, to better manage and implement these strategies, contextual analysis devices can pre-set a strategy model. This machine learning-based strategy model can dynamically adjust various parameters of the smartwatch by predicting the user's future behavior, thereby providing a more personalized user experience. The following are the specific steps for implementing this strategy model: Collect user sensor data, such as heart rate, steps, location, and sleep cycles; extract useful features from the raw data, such as average heart rate, step change trends, and location change frequency; select features highly correlated with user behavior to improve the accuracy and efficiency of the prediction model; preprocess the data after feature extraction by removing noise and outliers, filling in missing values, and standardizing or normalizing the data to suit the requirements of machine learning algorithms; input the dataset into the initial strategy model; iteratively train the initial strategy model to obtain a strategy model that meets the accuracy requirements, enabling the model to learn user habits and preferences; deploy the trained model on the smartwatch to predict the user's future behavior in real time, and dynamically adjust various parameters of the smartwatch based on the prediction results to optimize the user experience.

[0122] Step A30: Based on the parameter data, adjust the parameters of the smartwatch to obtain a smartwatch that adapts to the target mode after parameter adjustment.

[0123] Understandably, context analysis devices can adjust the parameters of a smartwatch based on the predicted parameter data corresponding to the target pattern. Specifically, the following are some common patterns and their corresponding smartwatch parameter adjustment schemes:

[0124] 1. Outdoor Mode

[0125] High-light environments: Strong sunlight requires higher screen brightness.

[0126] Exercise needs: Users may exercise outdoors and need to monitor data such as heart rate in real time.

[0127] Parameter adjustment

[0128] Screen brightness: Automatically adjusts screen brightness based on ambient light sensor data to ensure clear display even in bright light.

[0129] Heart rate monitoring: Improve the sampling rate of the heart rate sensor to monitor heart rate changes in real time.

[0130] GPS positioning: Enable GPS positioning to record your movement trajectory.

[0131] Notification frequency: Reduce non-urgent notifications to avoid interfering with the exercise.

[0132] Battery Management: Optimize battery management strategies to ensure sufficient power during extended outdoor activities.

[0133] When the target mode is outdoor mode, the system first acquires real-time data from the ambient light sensor on the smartwatch. This data is used to adjust the screen brightness and dynamically adjusts it based on the prediction results. If the prediction results indicate that the current ambient brightness is high (e.g., in sunlight), the screen brightness is increased to ensure that the user can still clearly see the screen content in strong light. If the ambient brightness is low (e.g., indoors or at night), the screen brightness is decreased to reduce power consumption and protect eyesight. To prevent discomfort caused by sudden changes in screen brightness, a smooth transition effect can be set to gradually adjust the brightness to the target value.

[0134] 2. Sports Mode

[0135] Real-time monitoring: This requires real-time monitoring of data such as heart rate, steps, and distance. Specifically, enable the heart rate sensor and increase its sampling rate to collect data more frequently, ensuring real-time monitoring of heart rate changes. This helps users understand their heart rate zones and adjust exercise intensity accordingly. Accelerometers and gyroscopes are used to monitor the user's steps and distance traveled; increasing the sampling rate of these sensors allows for more accurate recording of the user's movement trajectory and gait information.

[0136] Personalized training recommendations: Provides personalized training plans and suggestions. Specifically, the smartwatch can sync with a fitness app, utilizing the user's exercise history data to create personalized training plans. The app can provide customized exercise suggestions based on factors such as the user's age, gender, weight, and fitness goals, and enables posture recognition algorithms to identify the user's movement posture by analyzing sensor data, promptly alerting the user to adjust when poor posture is detected. This helps prevent sports injuries and improve exercise efficiency.

[0137] Parameter adjustment

[0138] Heart rate sensor sampling rate: Increasing the sampling rate of the heart rate sensor ensures real-time monitoring of heart rate changes. Specifically, increasing the sampling rate of the heart rate sensor captures more subtle heart rate fluctuations, which is especially important for exercises such as high-intensity interval training (HIIT) that require close monitoring of heart rate changes.

[0139] Accelerometer and gyroscope sampling rates: Increase the sampling rate to record motion data more accurately. Specifically, increase the sampling rate of these two sensors to more accurately capture the user's movements and speed. This is especially important for activities such as running and cycling.

[0140] Notification Frequency: Reduce non-urgent notifications to avoid interfering with exercise. Specifically, reduce the number of non-urgent notifications to ensure users are not disturbed while exercising. You can set notification rules in exercise mode to only receive urgent or important notifications.

[0141] Personalized training suggestions: Integrated into the fitness app, providing personalized training suggestions based on the user's historical data.

[0142] Posture correction: Enables posture recognition algorithms to promptly remind users to adjust poor posture.

[0143] 3. Work Mode

[0144] Focus on Needs: Reduce distractions and improve work efficiency. Specifically, enable Focus Mode to block most non-urgent notifications, allowing only notifications from important contacts or key applications to be received. This helps users avoid being disturbed by irrelevant messages while working and concentrate on completing tasks.

[0145] Health Tips: Regularly remind users to take breaks and engage in healthy activities. Specifically, regularly remind users to perform necessary health activities, such as drinking water and doing simple stretching exercises. These tips can help users maintain good lifestyle habits and ensure they don't forget to take care of their health even during busy work schedules.

[0146] Parameter adjustment

[0147] Focus Mode: Blocks non-urgent notifications and only retains reminders for important information.

[0148] Sedentary reminder: Set reasonable reminder intervals, such as once every 30 minutes, to encourage users to get up and move around.

[0149] Health Tip: Remind users to drink water or do some simple stretching exercises regularly.

[0150] Data synchronization: Optimize the data synchronization frequency to ensure timely data updates without affecting battery life.

[0151] Battery Management: Enable power-saving mode to extend battery life.

[0152] 4. Rest Mode

[0153] Sleep monitoring: It is necessary to accurately monitor the user's sleep quality.

[0154] Smart alarm clock: Automatically adjusts alarm time based on the user's sleep cycle.

[0155] Parameter adjustment

[0156] Sleep monitoring: Optimize the sleep monitoring algorithm to improve the accuracy of sleep stage identification.

[0157] Smart alarm clock settings: Automatically adjusts the alarm time according to the user's sleep cycle to ensure that the user wakes up in the best condition.

[0158] Relaxation guidance: Integrates meditation or breathing exercises into the app to help users relax before bed.

[0159] Notification frequency: Reduce notification frequency to minimize nighttime disruptions.

[0160] Screen brightness: Reduce screen brightness to minimize light interference.

[0161] 5. Social Mode

[0162] Frequent interaction: Requires quick responses to messages on social applications.

[0163] Personalized reminders: Set different reminder methods based on user preferences.

[0164] Parameter adjustment

[0165] Notification frequency: Increase the frequency of notifications in social applications to ensure users receive messages promptly.

[0166] Alert methods: Users can choose different alert methods based on their preferences, such as vibration, sound, or screen notification.

[0167] Personalization settings: Allows users to customize the types of notifications they want to receive.

[0168] Battery Management: Optimize battery management strategies to ensure that the battery is not depleted during frequent interactions.

[0169] In one feasible implementation, the step of inputting the target mode into a preset strategy model to predict the parameters of the smartwatch under the target mode and obtaining the predicted parameter data includes the following steps:

[0170] The target mode is input into a preset strategy model to predict the parameters of the smartwatch under the target mode, thereby obtaining the predicted parameter data.

[0171] Understandably, the preset strategy model can predict parameters under the target pattern, thus obtaining predicted parameter data. The scenario analysis device inputs the target pattern into the preset strategy model, predicts the parameters under the target pattern, and obtains predicted parameter data.

[0172] Obtain historical parameter data from the user, adjust the predicted parameter data accordingly, and obtain the adjusted predicted parameter data.

[0173] It should be noted that the user's historical parameter data reflects the user's historical usage habits. The context analysis device can adjust the predicted parameter data based on the user's historical usage habits to avoid the predicted parameter data exceeding the user's usage habits.

[0174] In this embodiment, the context analysis device determines the user's target mode based on the context analysis results obtained from the preset context analysis model, and determines the parameter data corresponding to the target mode. Based on the parameter data corresponding to the target mode, the device adjusts the parameters of the smartwatch to obtain a smartwatch that adapts to the target mode, thereby improving the usage efficiency of the smartwatch.

[0175] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the scenario analysis of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0176] This application also provides a situation analysis device, please refer to... Figure 3 The context analysis device includes:

[0177] Module 10 is used to acquire environmental information collected by the smartwatch;

[0178] The analysis module 20 is used to input the environmental information into a preset situation analysis model, analyze the situation in which the user is located, and obtain the situation analysis results.

[0179] Optionally, the analysis module includes:

[0180] The input module is used to input the environmental information into a preset context analysis model to analyze the user's context and obtain context analysis results. The preset context analysis model is obtained through iterative training based on sample environmental information and sample labels.

[0181] The determination module is used to determine the target mode based on the context analysis results; and to adjust the parameters of the smartwatch based on the target mode to obtain a smartwatch that adapts to the target mode.

[0182] Optionally, the analysis module includes:

[0183] The adjustment module is used to adjust the screen brightness of the smartwatch if the target mode is outdoor mode, so as to obtain a target screen brightness suitable for outdoor use.

[0184] Optionally, the input module includes:

[0185] The training module is used to acquire sample environment information of users in different contexts; use the context corresponding to the sample environment information as sample labels; acquire an initial context analysis model; and iteratively train the initial context analysis model based on the sample environment information and the sample labels to obtain a preset context analysis model.

[0186] Optionally, the training module includes:

[0187] The calculation module is used to input the sample environment information into the initial situation analysis model to perform situation prediction and obtain the initial situation analysis result; calculate the difference between the initial situation analysis result and the sample label to obtain the error result; and adjust the parameters of the initial situation analysis model based on the error result until the error result meets the preset threshold and then stop training to obtain the preset situation analysis model that meets the accuracy requirements.

[0188] The context analysis device provided in this application, employing the context analysis described in the above embodiments, can solve the technical problems of context analysis. Compared with the prior art, the beneficial effects of the context analysis device provided in this application are the same as those of the context analysis provided in the above embodiments, and other technical features in the context analysis device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0189] This application provides a context analysis device, which 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, which are executed by the at least one processor to enable the at least one processor to perform the context analysis in the above embodiment 1.

[0190] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a context analysis device suitable for implementing embodiments of this application. The context analysis device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, tablets, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The scenario analysis device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0191] like Figure 4As shown, the context analysis device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the context analysis device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the scenario analysis device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a scenario analysis device with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0192] 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 ROM 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.

[0193] The context analysis device provided in this application, employing the context analysis described in the above embodiments, can solve the technical problems of context analysis. Compared with the prior art, the beneficial effects of the context analysis device provided in this application are the same as those of the context analysis provided in the above embodiments, and other technical features of the context analysis device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0194] 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.

[0195] 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.

[0196] 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 perform the scenario analysis in the above embodiments.

[0197] 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 (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage 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, RF (Radio Frequency), etc., or any suitable combination thereof.

[0198] The aforementioned computer-readable storage medium may be included in the context analysis device; or it may exist independently and not assembled into the context analysis device.

[0199] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the context analysis device, the context analysis device: acquires environmental information collected by the smartwatch; inputs the environmental information into a preset context analysis model, analyzes the user's context, and obtains context analysis results, wherein the preset context analysis model is obtained through iterative training based on sample environmental information and sample labels.

[0200] 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).

[0201] 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, can 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.

[0202] 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.

[0203] 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 performing the above-described scenario analysis, thereby solving the technical problem of scenario analysis. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the scenario analysis provided in the above embodiments, and will not be repeated here.

[0204] This application also provides a computer program product, including a computer program that, when executed by a processor, performs the scenario analysis steps as described above.

[0205] The computer program product provided in this application can solve the technical problem of context analysis. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the context analysis provided in the above embodiments, and will not be repeated here.

[0206] 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. A context analysis method, characterized in that, The context analysis method includes: Obtain environmental information collected by the smartwatch; Obtain sample environment information of users in different scenarios, wherein the sample environment information includes the same number of sample environment information in different scenarios; Based on the sample environment information, the impact of different contextual factors on user behavior and needs is analyzed. Based on the analysis results, the contextual weight of each contextual factor for the user in different contexts is determined. The context corresponding to the sample environment information is used as the sample label; Obtain the initial context analysis model; Based on the sample environment information, the sample labels, and the context weights, the initial context analysis model is iteratively trained to obtain a preset context analysis model; The environmental information is input into a preset context analysis model to analyze the user's context and obtain context analysis results. The preset context analysis model is obtained through iterative training based on sample environmental information and sample labels. Based on the results of the context analysis, the user's target mode is determined; The target mode is input into a preset strategy model to predict the parameters of the smartwatch under the target mode and obtain the predicted parameter data. When the target mode is a sports mode, the sampling frequency of the heart rate sensor, accelerometer and gyroscope is increased to adjust the sports intensity and accurately record the user's sports trajectory and pace information. Based on the parameter data, the parameters of the smartwatch are adjusted to obtain a smartwatch that adapts to the target mode after parameter adjustment.

2. The context analysis method as described in claim 1, characterized in that, The step of using the context corresponding to the sample environment information as the sample label includes: The sample environment information is labeled with context information at least once to obtain context information; The number of times the context information corresponding to the same sample environment information is consistent is calculated to obtain the actual number of consistent instances. Based on the actual number of consistent occurrences, a consistency judgment is made on the context information. If the context information is consistent, the context corresponding to the sample environment information is obtained, and the context corresponding to the sample environment information is used as the sample label.

3. The context analysis method as described in claim 1, characterized in that, The step of iteratively training the initial context analysis model based on the sample environment information and the sample labels to obtain the preset context analysis model includes: The sample environment information is input into the initial situation analysis model to perform situation prediction, and the initial situation analysis result is obtained. The difference between the initial context analysis results and the sample labels is calculated to obtain the error result; Based on the error results, the parameters of the initial scenario analysis model are adjusted until the error results meet the preset threshold, at which point training stops, and a preset scenario analysis model that meets the accuracy requirements is obtained.

4. The context analysis method as described in claim 1, characterized in that, The step of inputting the target mode into a preset strategy model to predict the parameters of the smartwatch under the target mode and obtaining the predicted parameter data includes: The target mode is input into a preset strategy model to predict the parameters of the smartwatch under the target mode, thereby obtaining the predicted parameter data. Obtain historical parameter data from the user, adjust the predicted parameter data accordingly, and obtain the adjusted predicted parameter data.

5. A situation analysis device, characterized in that, The device includes: The acquisition module is used to acquire environmental information collected by the smartwatch; An analysis module is used to acquire sample environment information of users in different contexts, wherein the sample environment information includes the same number of sample environment information in different contexts; based on the sample environment information, analyze the impact of different context factors on user behavior and needs; based on the analysis results, determine the context weight of each context factor of the user in different contexts; use the context corresponding to the sample environment information as sample labels; acquire an initial context analysis model; and iteratively train the initial context analysis model based on the sample environment information, the sample labels, and the context weights to obtain a preset context analysis model. Optionally, the analysis module is further configured to determine the target mode of the user based on the context analysis results; input the target mode into a preset strategy model to predict the parameters of the smartwatch in the target mode, and obtain predicted parameter data. Specifically, when the target mode is a sports mode, the sampling frequency of the heart rate sensor, accelerometer, and gyroscope is increased to adjust the exercise intensity and accurately record the user's movement trajectory and pace information. Based on the parameter data, the parameters of the smartwatch are adjusted to obtain a smartwatch with adjusted parameters adapted to the target mode.

6. A context analysis device, characterized in that, The 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 context analysis method as described in any one of claims 1 to 4.

7. 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 context analysis method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the context analysis method as described in any one of claims 1 to 4.

Images