Electronic cigarette charging control method and device and readable storage medium

Abstract

The invention relates to the technical field of charging control, in particular to an electronic cigarette charging control method and device and a readable storage medium. The method comprises the following steps: acquiring a historical monitoring log of the electronic cigarette; user use behavior recognition and personalized user portrait fitting are carried out on the electronic cigarette historical monitoring log, and a user personalized behavior portrait is constructed; performing smoking trend prediction according to the personalized behavior portrait of the user, and performing electric quantity demand prediction so as to generate an electric quantity demand prediction value at each time point; performing electric quantity deviation compensation demand calculation on the electric quantity demand prediction value at each time point according to an electronic cigarette historical monitoring log, thereby obtaining an electric quantity deviation compensation demand value at each user smoking time point; and performing charging duration prediction based on the electric quantity deviation compensation demand value of each user smoking time point, and performing intelligent charging optimization in an optimal time period to generate a charging time period optimization strategy. According to the invention, efficient, safe and stable electronic cigarette charging control is realized.

Description

Technical Field

[0001] The present invention relates to the field of charging control technology, and in particular to an electronic cigarette charging control method, device and readable storage medium. Background Art

[0002] Electronic cigarettes have developed rapidly around the world in recent years, and have been widely used, especially among young people. The working principle of electronic cigarettes mainly relies on the built-in battery to provide energy to heat the e-liquid and produce smoke for users to inhale. Since the battery is one of the core components of electronic cigarettes, its charging performance directly affects the user experience, safety and life of electronic cigarettes. However, during long-term use and charging, the battery of electronic cigarettes will be affected by many factors, including charging current fluctuations, overcharging, over-discharging, high temperature, etc. These problems will cause battery damage and even safety accidents.

[0003] Traditional electronic cigarette charging control methods mostly rely on simple charging circuit designs, and their charging process lacks real-time monitoring and intelligent regulation. These traditional methods often do not fully consider the health of the battery, which can easily lead to overheating or incomplete charging of the battery during the charging process, thereby affecting the battery life and the performance of the electronic cigarette. As the use of electronic cigarettes gradually increases, traditional charging control methods have been unable to meet the high requirements for charging safety and efficiency. In order to improve the safety, stability and charging efficiency of electronic cigarette charging, an intelligent charging control method is urgently needed. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes an electronic cigarette charging control method, device and readable storage medium to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides an electronic cigarette charging control method, comprising the following steps:

[0006] Step S1: Obtain the electronic cigarette history monitoring log; perform user usage behavior recognition and personalized user portrait fitting on the electronic cigarette history monitoring log to construct a personalized user behavior portrait;

[0007] Step S2: predicting smoking trends and power demand based on the user's personalized behavior profile, thereby generating a power demand forecast value at each time point;

[0008] Step S3: Calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point;

[0009] Step S4: predicting the charging time based on the power deviation compensation requirement value at each user's smoking time point, and performing intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy;

[0010] Step S5: Performing real-time battery life status evaluation based on the electronic cigarette historical monitoring log, and dynamically adjusting the charging rate to construct a dynamic charging rate control strategy;

[0011] Step S6: Perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

[0012] In this specification, an electronic cigarette charging control device is provided, which is used to execute the electronic cigarette charging control method as described above, including:

[0013] The user portrait module is used to obtain the electronic cigarette historical monitoring log; identify the user's usage behavior and fit the personalized user portrait to the electronic cigarette historical monitoring log, and build a personalized user behavior portrait;

[0014] The power demand prediction module is used to predict the smoking trend and power demand based on the user's personalized behavior profile, thereby generating a power demand prediction value at each time point;

[0015] The power deviation compensation module is used to calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point;

[0016] The optimal time period module is used to predict the charging time based on the power deviation compensation demand value of each user's smoking time point, and to perform intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy;

[0017] The charging rate control module is used to evaluate the real-time battery life status based on the electronic cigarette historical monitoring log and to adjust the dynamic charging rate to build a dynamic charging rate control strategy;

[0018] The instant charging control module is used to perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

[0019] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned electronic cigarette charging control methods are implemented.

[0020] The beneficial effects of the present invention are as follows: by collecting and analyzing the historical behavior data of users (such as smoking frequency, smoking duration, smoking intensity, use time period, etc.), a detailed user behavior portrait is constructed. This enables the system to accurately understand the usage needs and preferences of each user, avoiding a "one-size-fits-all" charging strategy, thereby providing personalized data support for subsequent prediction and optimization. According to the user's smoking habits, the system can formulate a specific charging strategy for each user, rather than charging management based on general parameters, to improve the efficiency of the charging process and reduce unnecessary energy waste. By predicting the smoking trend, the smoking behavior and power demand of the user at each moment are accurate. In this way, the system effectively predicts the power consumption of the user at a specific time point to avoid the occurrence of insufficient power. This predictive charging strategy can ensure that the device always maintains sufficient power when the user needs it, greatly improving the user experience. Accurate power demand prediction helps optimize the charging process, avoids overcharging and frequent charging, reduces the frequency of battery use, and effectively extends the service life of the battery. By performing deviation compensation on the power demand prediction value, the system can adjust the charging strategy in real time to compensate for power fluctuations caused by prediction errors, environmental factors or battery performance degradation. Ensure that the battery is in the optimal charging state at all times, avoiding overcharging or insufficient battery power. Compensating for power deviation makes charging control more accurate, avoiding insufficient or overcharging caused by external environment or other uncontrollable factors, and improving charging efficiency and battery health. By predicting the time point and power demand of each user's smoking, the system dynamically selects the optimal charging period for charging. Avoid charging when the user needs to use the device, so as not to affect the user experience. Through intelligent charging period optimization, the system can make full use of the user's idle time for charging, improve charging efficiency, and reduce interference with the user's daily use. Optimizing the charging time period can effectively reduce the damage caused by frequent charging or overcharging of the battery, thereby extending the battery life. By monitoring the health status of the battery in real time (such as battery aging, internal resistance, temperature, etc.), the system dynamically adjusts the charging rate. If the battery is aged or the temperature is too high, the charging rate will automatically slow down to avoid damage caused by overcharging or high temperature. This dynamic charging rate control can effectively manage battery life and extend the battery life cycle. Dynamic adjustment of the charging rate makes the charging process highly adaptable, and can adjust the strategy according to the real-time health status of the battery to avoid charging problems under different battery conditions. By combining the charging rate control strategy and the charging time period optimization strategy, the system can make real-time intelligent adjustments during the charging process to ensure that the charging process meets the battery requirements and the user's usage habits. This iterative optimization process not only improves the efficiency of each charge, but also gradually optimizes the charging strategy over a long period of time to ensure the best charging experience.The system will continuously optimize and adjust based on historical data and real-time feedback, which means that after each charge, the charging strategy will be further improved, continuously improving the battery charging efficiency and health management capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the steps of an electronic cigarette charging control method of the present invention;

[0022] Figure 2 Detailed implementation flow chart of step S1;

[0023] Figure 3 Detailed implementation flow chart of step S2;

[0024] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The present application example provides an electronic cigarette charging control method, device and readable storage medium. The execution subjects of the electronic cigarette charging control method, device and readable storage medium include but are not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] See also Figures 1 to 4 The present invention provides an electronic cigarette charging control method, the electronic cigarette charging control method comprising the following steps:

[0028] Step S1: Obtain the electronic cigarette history monitoring log; perform user usage behavior recognition and personalized user portrait fitting on the electronic cigarette history monitoring log to construct a personalized user behavior portrait;

[0029] Step S2: predicting smoking trends and power demand based on the user's personalized behavior profile, thereby generating a power demand forecast value at each time point;

[0030] Step S3: Calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point;

[0031] Step S4: predicting the charging time based on the power deviation compensation requirement value at each user's smoking time point, and performing intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy;

[0032] Step S5: Performing real-time battery life status evaluation based on the electronic cigarette historical monitoring log, and dynamically adjusting the charging rate to construct a dynamic charging rate control strategy;

[0033] Step S6: Perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

[0034] By collecting and analyzing the user's historical behavior data (such as smoking frequency, smoking duration, smoking intensity, usage time period, etc.), a detailed user behavior profile is constructed. This enables the system to accurately understand the usage needs and preferences of each user, avoiding a "one-size-fits-all" charging strategy, thereby providing personalized data support for subsequent predictions and optimizations. According to the user's smoking habits, the system can formulate a specific charging strategy for each user instead of managing charging based on general parameters, improving the efficiency of the charging process and reducing unnecessary energy waste. By predicting the smoking trend, the user's smoking behavior and power demand at each moment can be accurately determined. In this way, the system effectively predicts the user's power consumption at a specific time point to avoid insufficient power. This predictive charging strategy can ensure that the device always maintains sufficient power when the user needs it, greatly improving the user experience. Accurate power demand prediction helps optimize the charging process, avoids overcharging and frequent charging, reduces the frequency of battery use, and effectively extends the battery life. By compensating for the deviation of the power demand prediction value, the system can adjust the charging strategy in real time to compensate for power fluctuations caused by prediction errors, environmental factors or battery performance degradation. Ensure that the battery is in the optimal charging state at all times to avoid overcharging or insufficient power. Compensating for power deviation makes charging control more accurate, avoids insufficient or overcharging caused by external environment or other uncontrollable factors, and improves charging efficiency and battery health. By predicting the time point and power demand of each user's smoking, the system dynamically selects the optimal charging period for charging. Avoid charging when the user needs to use the device, so as not to affect the user experience. Through intelligent charging period optimization, the system can make full use of the user's idle time for charging, improve charging efficiency, and reduce interference with the user's daily use. Optimizing the charging time period can effectively reduce the damage caused by frequent charging or overcharging of the battery, thereby extending the battery life. By monitoring the health status of the battery in real time (such as battery aging, internal resistance, temperature, etc.), the system dynamically adjusts the charging rate. If the battery is aged or the temperature is too high, the charging rate will automatically slow down to avoid damage caused by overcharging or high temperature. This dynamic charging rate control can effectively manage battery life and extend the battery life cycle. Dynamic adjustment of the charging rate makes the charging process highly adaptable, and can adjust the strategy according to the real-time health status of the battery to avoid charging problems under different battery conditions. Combining the charging rate control strategy and charging time period optimization strategy, the system can make real-time intelligent adjustments during the charging process to ensure that the charging process meets the battery's needs and satisfies the user's usage habits. This iterative optimization process not only improves the efficiency of each charge, but also gradually optimizes the charging strategy over a long period of time to ensure the best charging experience. The system will continue to optimize and adjust based on historical data and real-time feedback, which means that after each charge, the charging strategy will be further improved, continuously improving the battery charging efficiency and health management capabilities.

[0035] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of an electronic cigarette charging control method of the present invention. In this example, the steps of the electronic cigarette charging control method include:

[0036] Step S1: Obtain the electronic cigarette history monitoring log; perform user usage behavior recognition and personalized user portrait fitting on the electronic cigarette history monitoring log to construct a personalized user behavior portrait;

[0037] In this embodiment, the content of the electronic cigarette monitoring log is determined, including the user's smoking frequency, the duration of each smoking, the amount of smoke inhaled, the device temperature, the user's geographic location, etc. The log is usually stored in CSV or JSON format, containing timestamps, event types, and related parameters. Use a data extraction tool (such as Python's Pandas library) to extract historical monitoring logs from a database or cloud storage. Set the time range for data extraction, such as data from the past 6 months, to ensure the comprehensiveness of the analysis. During the extraction process, check the completeness and accuracy of the data to ensure that there are no missing or duplicate records. Use data cleaning techniques such as removing duplicate values ​​and filling missing values ​​to ensure data quality. Convert the extracted monitoring logs into a format that can be used for analysis, unify the time format (such as ISO 8601), and ensure that the timestamps of all records are consistent. Store the data in a Pandas Data Frame for subsequent processing. Select a suitable machine learning algorithm for user behavior identification, such as K-Means clustering or decision tree. K-Means is used to identify users' smoking habits, and decision trees are used to classify users' smoking behavior patterns. Extract features from historical monitoring logs, smoking frequency: the number of times a user smokes per day. Smoking duration: the average duration of each smoking. Inhaled volume: the amount of smoke per puff (can be obtained through device sensors). Usage time period: the time distribution of users' smoking (such as morning, noon, and evening). Standardize the extracted features to ensure that the feature values ​​are on the same scale, and use the Z-score standardization method to make the mean of each feature 0 and the standard deviation 1. Input the extracted features into the selected machine learning model for training. Use 80% of the data as the training set and 20% of the data as the test set to ensure the generalization ability of the model. Set the hyperparameters of the model (such as the K value of K-Means) and optimize through cross-validation. Through the trained model, identify the user's behavior pattern and generate the user's behavior label (such as "frequent smoker", "occasional smoker", "heavy smoker"). Combine the label with the original data to form a user behavior analysis report. Define the dimensions of the user portrait, including basic information (such as age, gender), behavioral characteristics (such as smoking frequency, smoking time period), preference characteristics (such as favorite flavors, brands, etc.), and health status related data (such as self-assessment of health due to smoking). Integrate the identified behavior pattern with the user's basic information and preference characteristics to form a complete user portrait. Use Pandas' merge() function to merge different data sources. Use cluster analysis to segment users and identify the characteristics of different user groups. For example, divide users into groups such as "health conscious" and "social smokers". Use principal component analysis (PCA) to reduce the dimensionality and extract the main factors that affect users' smoking behavior, thereby optimizing the accuracy of personalized user portraits.Use data visualization tools (such as Matplotlib or Seaborn) to visualize user portraits and generate distribution maps and clustering results of user characteristics to facilitate subsequent analysis and decision-making.

[0038] Step S2: predicting smoking trends and power demand based on the user's personalized behavior profile, thereby generating a power demand forecast value at each time point;

[0039] In this embodiment, a suitable time series prediction model is selected, such as ARIMA (autoregressive integrated moving average model) or LSTM (long short-term memory network). ARIMA is suitable for linear data, and LSTM is more suitable for processing nonlinear and complex time series data. For the ARIMA model, set the parameters p (autoregressive term), d (number of differences) and q (moving average term). The best parameter combination is selected by AIC (Akaike Information Criterion). For the LSTM model, set the number of hidden layer units to 50, the batch size to 32, the learning rate to 0.001, and the training cycle to 100 epochs. The data set is divided into a training set and a test set, usually 80% of the data is used as a training set and 20% of the data is used as a test set. Make sure that the training set contains enough historical data to capture trends. Use the training set to train the selected model. For LSTM, the input data needs to be normalized and converted to a three-dimensional array format to meet the input requirements of LSTM. After the model training is completed, use the test set for verification to evaluate the prediction effect of the model. Generate smoking trend prediction values ​​for several time points in the future and record the prediction results. Extract key features of power demand from the user's smoking trend prediction results, including: Power consumption per smoking: The power consumed per smoking is obtained through the device's battery management system (BMS). Smoking frequency: Combined with the smoking trend prediction, calculate the number of cigarettes smoked in a specific time period. Device charging status: Get the current battery power and take into account the charging cycle and the user's charging habits (such as charging at night). Select a regression model for power demand prediction, such as linear regression or random forest regression. The linear regression model is simple and easy to implement, while the random forest regression model can capture complex nonlinear relationships. For linear regression, set the training set and test set to 80% and 20% respectively. For random forest regression, set the number of trees to 100 and the maximum depth to 10. Associate the extracted power demand-related features with the smoking frequency to generate a training data set. Make sure the data set contains timestamps for time series prediction. Use the training set to train the selected regression model and adjust the model parameters to optimize the prediction effect. Use cross-validation to evaluate the model performance to ensure the stability and accuracy of the model. Apply the model to the test set to generate power demand prediction values ​​at each time point. Record each predicted value and compare it with actual consumption to evaluate the accuracy of the model. Integrate the smoking trend prediction results with the power demand prediction results to generate a comprehensive data table containing timestamps, smoking trends, and power demand for subsequent analysis and strategy formulation.

[0040] Step S3: Calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point;

[0041] In this embodiment, the actual power consumption data of the user at each time point is extracted from the historical monitoring log of the electronic cigarette. Ensure that the data format is consistent and contains a timestamp for subsequent comparison and analysis. Align the power demand forecast value with the historical power consumption data by timestamp to ensure that each time point has a corresponding demand forecast value and actual consumption value. Use the merge() function of Pandas to merge the data and generate a data table containing demand and actual consumption. Define the power deviation as the difference between the actual power consumption and the predicted power demand, deviation = actual consumption-predicted demand, positive value indicates that the actual consumption is higher than the predicted demand, and negative value indicates that the actual consumption is lower than the predicted demand. Calculate the data at each time point one by one and record the power deviation value at each time point. Use Python's NumPy library for vectorized calculation to improve calculation efficiency. Store the calculated power deviation value in a new data frame, including timestamp, predicted demand, actual consumption and deviation value. Ensure that the data structure is clear for subsequent analysis. Calculate the compensation demand based on the power deviation. If the deviation value is positive, it is necessary to increase the power to compensate for the deficiency; calculate the compensation demand for the deviation value at each time point, and use the same vectorization method to improve efficiency. The calculated compensation demand value is stored in a data frame, ensuring that the timestamp and compensation demand are included to facilitate subsequent decision-making and policy adjustments. Statistical analysis is performed on the calculated power deviation and compensation demand, such as calculating the mean, median, and standard deviation to evaluate the overall deviation trend and volatility of the compensation demand.

[0042] Step S4: predicting the charging time based on the power deviation compensation requirement value at each user's smoking time point, and performing intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy;

[0043] In this embodiment, the compensation demand at each time point is calculated and processed one by one using Python. The compensation demand value is converted into milliampere-hours (mAh) of current inflow, and the user's smoking behavior is analyzed based on historical monitoring data to identify the user's peak smoking hours and low-peak smoking hours during the day. Common peak hours are 9 to 10 in the morning and 7 to 9 in the evening. Set the intelligent charging optimization goal, that is, try to avoid the peak smoking period during the charging time to ensure that the user's device has sufficient power when needed. Factors to be considered include: flexibility of charging time. Genetic algorithm or dynamic programming algorithm is used to optimize the charging time period. Set the fitness function to minimize the risk of insufficient power during the peak smoking period for users. Use Python to implement the optimization algorithm. According to the user's charging time requirement and behavior analysis results, a charging time period combination is generated, and the fitness value of each combination is calculated. The charging time period with the highest fitness is selected as the final charging strategy through iteration. For example, if the user needs to smoke at 8 pm and the charging time is 1 hour, the optimization result is to choose to start charging at 7 pm. Record the optimized charging time period strategy in a document, including the charging start time, charging end time and reason. Make sure the strategy is simple and easy to understand for users to follow. After users implement the charging strategy, collect user feedback information to understand the effectiveness and rationality of the charging strategy. This can be done through questionnaires or the feedback function in the APP.

[0044] Step S5: Performing real-time battery life status evaluation based on the electronic cigarette historical monitoring log, and dynamically adjusting the charging rate to construct a dynamic charging rate control strategy;

[0045] In this embodiment, historical monitoring logs are obtained from the electronic cigarette device to record the battery's charging and discharging cycles, charging times, charging current and voltage, temperature and other data. These data are usually stored in CSV format, including timestamps and related parameters. Define the battery health state (State of Health, SOH) and remaining useful life (Remaining Useful Life, RUL) as evaluation indicators. Use Python and Pandas libraries to analyze historical data and calculate the current capacity and SOH of the battery. Through time series analysis, identify the changing trend of battery performance for subsequent dynamic adjustment. Implement real-time monitoring of the battery's charging and discharging cycles, and use sensors to regularly collect battery voltage, temperature and other data to ensure the real-time and accuracy of the data. Dynamically adjust the charging rate according to the battery's SOH and current charging state. Generally, a higher charging rate (such as 1C) is used when the battery's SOH is above 80%, and when the SOH is below 80%, the charging rate should be reduced (such as 0.5C) to protect the battery life. Select a suitable algorithm for charging rate calculation, such as fuzzy logic control or rule engine. Fuzzy logic can handle uncertainty and ambiguity and is suitable for dynamic adjustment scenarios. Determine the input variables of fuzzy logic control, including SOH, current temperature, charging current, etc. The output variable is the charging rate, set a reasonable fuzzy set (such as low, medium, and high rates) and the corresponding membership function. Integrate the dynamic charging rate control strategy into the battery management system (BMS) to ensure real-time monitoring of the battery status and automatic adjustment of the charging rate. The BMS should be able to receive sensor data and make decisions based on preset logical rules. Set the monitoring frequency to 1Hz, and read the battery voltage, temperature, SOH and other parameters every second. Dynamically adjust the charging rate based on real-time data and preset control strategies. During the adjustment process, record the changes in charging rate and battery status in real time for subsequent analysis and optimization. Use data visualization tools (such as Matplotlib) to display the battery status and charging rate changes during the charging process. Regularly evaluate the effectiveness of the charging strategy and analyze indicators such as battery charging time, charging efficiency, and service life. Optimize the charging rate control strategy based on the evaluation results.

[0046] Step S6: Perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

[0047] In this embodiment, the previously established dynamic charging rate control strategy is integrated with the real-time battery status monitoring system. This strategy dynamically adjusts the charging rate based on factors such as the battery's state of health (SOH), current temperature, and charging current.

[0048] When SOH>80%, the charging rate is set to 1C;

[0049] When SOH≤80%, the charging rate is reduced to 0.5C;

[0050] When the charging temperature exceeds 45°C, the charging rate is automatically reduced to prevent overheating. Use high-precision sensors (such as current sensors and temperature sensors) to monitor the battery status in real time and collect data. Set the monitoring frequency to 1Hz, and obtain key parameters such as battery voltage, temperature and charging current every second. Use an embedded system (such as a microcontroller or single-board computer) to process real-time data, calculate the current charging rate and compare it with the preset value to ensure that the charging process complies with the dynamic control strategy. Based on the collected real-time data, the system automatically adjusts the charging rate. For example, if the battery temperature reaches 50°C in real time, the system will immediately reduce the charging rate to 0.3C and issue an alarm. Set a feedback mechanism to record key data in the charging process (such as actual charging current, time, temperature changes, etc.) in real time to provide data support for subsequent optimization. Use Python's Pandas and NumPy libraries to analyze real-time monitoring data and evaluate charging efficiency, charging time and battery health status changes. Set evaluation indicators, including: average charging time; charging efficiency (ratio of actual charging capacity to theoretical charging capacity); SOH change rate, etc. Intelligent optimization algorithms such as genetic algorithms (GA) or particle swarm optimization (PSO) are used to iteratively optimize the charging control strategy. These algorithms are suitable for solving multi-objective optimization problems and can find the best solution in complex environments. Based on historical data, the optimization model is trained to identify the best combination of charging rate and time period. For example, multiple charging strategies are generated through GA, charging efficiency and battery life are evaluated under each strategy, and the best strategy is selected for implementation. The optimized charging strategy is applied to real-time charging control, the effect is monitored in real time, and feedback data is collected. The model parameters are adjusted according to the feedback results to further optimize the strategy. The dynamic charging rate control strategy, charging time period optimization strategy and real-time monitoring system are integrated to build an intelligent charging control optimization model. The model should have self-learning capabilities and be able to continuously adjust and optimize the charging strategy based on real-time data. A monitoring mechanism is set up to regularly evaluate the performance of the intelligent charging control optimization model, including charging time, efficiency, and battery health status. Reports are generated regularly to support subsequent decisions.

[0051] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0052] Step S11: obtaining an electronic cigarette history monitoring log; performing user usage behavior recognition on the electronic cigarette history monitoring log, and extracting multiple user usage behavior data;

[0053] Step S12: Calculating the usage frequency based on the usage behavior data of multiple users to obtain the user usage frequency characteristics;

[0054] Step S13: performing a time stamp analysis on the usage behavior data of multiple users, and extracting the time stamp of each usage behavior;

[0055] Step S14: mining the intra-cycle behavior distribution of the timestamp of each usage behavior according to the user's usage frequency characteristics, thereby generating intra-cycle behavior distribution data;

[0056] Step S15: performing temporal usage behavior habit evolution on the usage behavior data of multiple users to generate user temporal behavior habit features;

[0057] Step S16: Fit a personalized user profile based on the behavior distribution data within the period and the user's temporal behavior habit characteristics to construct a personalized user behavior profile.

[0058] In this embodiment, obtaining the historical monitoring log of the electronic cigarette is the basic work. The electronic cigarette device usually records each use of the user, including timestamp, usage time, inhalation amount, device status, etc. These log data are usually stored in the device or in the cloud database, and the integrity and accuracy of the data must be ensured. Design a data collection plan and select a suitable recording frequency. For example, each use record contains at least the following information: Timestamp: record the specific date and time of each use. Usage time: the duration of each smoking of the user, usually in seconds. Inhalation amount: the inhalation amount of each use, in milliliters (ml). Device status: battery status, remaining amount of e-liquid, and other information, which affect user behavior. After obtaining the historical monitoring log, the user's usage behavior is identified and the usage behavior data of multiple users is extracted. The frequency calculation is a key link, which can help understand the user's usage habits and preferences. First, classify each timestamp of the user and record the number of times each user uses it. Set an observation period, such as a week or month for frequency calculation. Usage frequency = number of uses in a certain period / period length. On this basis, record the usage frequency characteristics of each user, perform statistical analysis, and draw a frequency distribution chart to intuitively understand the usage of each user. In the timestamp analysis phase, the goal is to extract the timestamp of each use behavior for further analysis. First, parse the timestamp data in the historical monitoring log to ensure that its format is consistent (for example, in ISO 8601 format). Analyze each user's usage records one by one, extract all usage timestamps for each user, and record their specific order. Set parameters, such as the time period of use (such as the daily usage time period from 8 am to 10 pm), in order to analyze the user's usage habits in a specific time period. On this basis, calculate the interval time between each use (that is, the difference between adjacent timestamps) to identify the user's usage patterns and preferences. For example, if the user uses an e-cigarette at 8:00, 9:00, and 10:00, the interval time is 1 hour. Based on the user's usage frequency characteristics, conduct intra-cycle behavior distribution mining. This step aims to analyze the user's usage behavior distribution in a specific time period, such as daily, weekly, or monthly usage frequency changes. Set the period division, such as dividing a day into multiple time periods (such as morning, lunch time, evening, etc.), and then count the number of uses in each time period. Usage distribution = number of uses in a time period / total time in the time period. If a user uses an e-cigarette 5 times in the morning (8:00-12:00) and the time period is 4 hours in total, the morning usage distribution is 5 times / 4 hours. By analyzing the usage distribution in different cycles, the user's peak usage time and trough usage time are identified to provide a basis for subsequent personalized recommendations. Perform time series analysis on the usage behavior data of multiple users to generate the user's time series behavior habit characteristics.First, use time series analysis methods (such as ARIMA model or LSTM neural network) to model the user's usage data. Set analysis parameters, such as the time window size (such as 7 days, 30 days), and extract the user's usage pattern within this time window. Identify the evolution of usage habits by analyzing the change trend of the user's usage frequency. For example, if the user's usage frequency continues to rise over a period of time, it indicates that his dependence on e-cigarettes has increased. Record the behavioral habit characteristics of each user, including the increase or decrease in the frequency of use, for subsequent analysis and personalized recommendations. Fit personalized user portraits based on the behavioral distribution data within the period and the user's temporal behavioral habit characteristics. User portraits should include multiple dimensions, such as usage frequency, usage scenarios, usage time periods, etc., to fully reflect the user's consumption habits and preferences. Combine the user's usage frequency, behavior distribution, and temporal habits to construct a user feature matrix. Set feature weights, such as setting the weight of usage frequency to 0.5, the weight of behavior distribution to 0.3, and the weight of temporal habits to 0.2, to ensure that the impact of each feature on the user portrait is reasonable. Users are grouped by clustering algorithms (such as K-means or hierarchical clustering) to identify different types of user groups. The generated personalized behavior portraits can be used for subsequent marketing, product recommendations and user management strategies, thereby improving user experience and product satisfaction.

[0059] In this embodiment, the specific steps of step S15 are:

[0060] Extract the start and end time points of each smoking according to multiple user usage behavior data;

[0061] The smoking duration is calculated based on the start and end time points of each smoking, and the smoking duration of each smoking behavior is obtained;

[0062] Quantifying the smoking intensity of multiple users' usage behavior data, thereby generating multiple users' smoking intensity quantification values;

[0063] According to the length of smoking time of each use behavior, the peak smoking period in the cycle is identified to obtain the peak smoking period in the cycle;

[0064] The peak smoking period in the cycle is located according to the timestamp of each use behavior, thereby obtaining the peak smoking period;

[0065] The temporal usage behavior habit evolution is performed according to the quantified values ​​of smoking intensity of multiple users and the smoking peak time periods to generate the user temporal behavior habit characteristics.

[0066] In this embodiment, the start and end time points of each smoking need to be extracted from the user's behavior data. This step usually involves cleaning and preprocessing the data to ensure the accuracy and completeness of the data. Specifically, the user's behavior records (such as timestamps, smoking marks, etc.) must first be screened to identify records marked as "smoking". Then, using the timestamp information, the adjacent smoking records are paired in chronological order to form the start and end time points. A reasonable time threshold needs to be set. For example, if the time difference between two smoking records is less than 5 minutes, it is considered to be the same smoking behavior. Finally, the extracted start and end time points are stored in a data structure for subsequent calculations. After obtaining the start and end time points of each smoking, the next step is to calculate the duration of each smoking. By calculating each pair of start and end time points, the duration of each smoking is obtained. If a user's smoking start time is T_start and the end time is T_end, the smoking duration (duration) is obtained by the formula duration = T_end-T_start. It should be noted that when calculating, it is necessary to ensure that the format of all time points is consistent (such as unified as UTC time or local time) to avoid errors caused by time zone differences. In addition, the average smoking duration and standard deviation of each user are counted for subsequent analysis. Based on the duration of each smoking, the smoking intensity of multiple users is quantified. This process usually uses a weighted average method to combine the smoking duration of each user with their smoking frequency. Specifically, the smoking intensity is defined as: smoking intensity = (number of smoking times per smoking duration) / total duration of the observation period. When quantifying, different weights are used to reflect the smoking habits of different users. In this way, the user's smoking behavior is mapped to a quantitative value for easy comparison and analysis. Finally, the smoking intensity values ​​of all users are counted, and a stratified analysis is performed to identify user groups with high, medium, and low smoking intensity. After obtaining the duration of each smoking, the next step is to identify the peak smoking period within the cycle. This process involves time series analysis of the data. Using the sliding window technique, the time series data is divided into multiple time periods (such as hourly, daily), and the total smoking duration in each time period is calculated. By comparing the duration of smoking in different time periods, the peak smoking period can be identified. A threshold is set (for example, the duration of smoking in a certain time period exceeds 1.5 times the average level) to be considered as the peak smoking period. In addition, the differences in peak periods among different user groups are considered to provide a basis for personalized intervention measures. After determining the peak smoking period, it is necessary to further locate the specific peak time period. This step is achieved by analyzing the timestamp of each smoking. For each peak period, the number of cigarettes and the duration of smoking in that time period are counted to determine the specific time period of the peak. For example, the frequency of smoking behavior is counted by hour to identify which hourly periods have the most concentrated smoking behavior.In this way, specific time recommendations can be provided for intervention measures, such as launching smoking cessation activities or promotional materials for peak hours. Finally, based on the quantified values ​​of smoking intensity of multiple users and the peak smoking time periods, the evolution of temporal usage behavior habits is analyzed. This process involves machine learning and statistical analysis methods, such as cluster analysis and time series prediction. By analyzing the smoking behavior of users in different time periods, the habit characteristics of users are identified, such as seasonality, smoking differences between weekends and weekdays, etc. In addition, regression analysis and other methods are used to explore external factors that affect smoking behavior (such as social activities, psychological state, etc.). Through these analyses, data support can be provided for public health interventions, personalized smoking cessation plans and policy making.

[0067] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0068] Step S21: predicting smoking trends based on the personalized behavior portrait of the user, thereby obtaining a plurality of predicted time points of the user's smoking behavior;

[0069] Step S22: estimating the smoking duration of multiple users' smoking behavior prediction time points one by one, thereby generating the smoking duration of each time point;

[0070] Step S23: Calculate the operating power according to the electronic cigarette historical monitoring log to obtain the operating power parameter of the electronic cigarette;

[0071] Step S24: performing nonlinear power demand calculation on the smoking duration at each time point based on the operating power parameter of the electronic cigarette, thereby obtaining the power demand at each time point;

[0072] Step S25: forecasting the power demand at each time point, thereby generating a predicted value of the power demand at each time point.

[0073] In this embodiment, a personalized behavior portrait is constructed based on the user's historical behavior data. This includes the user's smoking history, the frequency of using electronic cigarettes, the smoking period, and related social and psychological factors. A machine learning model (such as a random forest or a support vector machine) is used to analyze the user data and identify the main features that affect smoking behavior. Next, the user's smoking behavior is modeled using a time series analysis technique (such as an ARIMA model). Future smoking behavior is predicted by analyzing the trend and seasonality of the user's historical smoking data. This process requires setting appropriate parameters, such as the autoregressive order and the number of differences, to ensure the accuracy of the model. Through the output of the model, a prediction of the smoking behavior of multiple users at a specific time point is obtained. These predicted time points are daily, weekly, or monthly frequencies, depending on the user's smoking pattern. The final result will form a data set containing multiple user smoking behavior prediction time points, providing a basis for subsequent analysis. After obtaining the predicted time points of smoking behavior of multiple users, the user characteristics and historical data related to each time point are sorted. These data include the user's past smoking duration, frequency, and usage habits, etc., in order to provide a reference for duration estimation. A smoking duration estimation model is established, and linear regression or multiple regression analysis is used to predict the user's smoking duration at each predicted time point. The input features of the model include the user's behavior profile, historical smoking duration, and external factors (such as stress level and social environment). Using the established model, the smoking duration of each user at the predicted time point is estimated. This process requires the input of each user's characteristics to generate the corresponding smoking duration prediction value. The final result will form a data set containing the smoking duration at each time point to support the subsequent power demand calculation. According to the historical monitoring logs of the e-cigarette, collect relevant operating data. These logs usually contain information such as the working status, smoking duration, and power settings of the e-cigarette. Ensure that the collected data is complete and accurate and can reflect the actual operation of the e-cigarette. Select a suitable power calculation method. The power of an e-cigarette is usually related to voltage and current, P = V × I, where P is power, V is voltage, and I is current. The actual operating power of the e-cigarette is calculated by monitoring the voltage and current data recorded in the log. The calculated operating power parameters are sorted to form structured data for subsequent analysis. The power value in each time period is recorded and associated with the user's smoking behavior to facilitate further processing of the power demand calculation. Based on the operating power parameters of the e-cigarette, a nonlinear power demand calculation is performed for the smoking duration at each time point. Select a suitable nonlinear model, such as polynomial regression or neural network, to better fit the relationship between power and smoking duration. Using the established nonlinear model, the smoking duration at each predicted time point is used as input to calculate the corresponding power demand. This process requires ensuring the accuracy of the model and verifying the calculation results to ensure their rationality.The calculated power demand at each time point is recorded as structured data, including the time point, smoking duration, and power demand value. These data will provide necessary information support for subsequent power demand forecasting. Build a power demand forecasting model based on the power demand at each time point. Use time series forecasting methods (such as LSTM) or regression analysis, considering factors such as power demand, user behavior, and external environment. Based on the constructed model, predict the power demand for each time point. At this time, it is necessary to consider the battery capacity and continuous working time to ensure that the predicted power demand is consistent with actual usage. Record the power demand forecast value at each time point as structured data and generate a detailed power demand forecast report. The report should include power demand, power demand, and related parameters at each time point to facilitate subsequent analysis and decision support.

[0074] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0075] Step S31: extracting battery real-time status monitoring parameters according to the electronic cigarette historical monitoring log;

[0076] Step S32: evaluating the current remaining power of the battery real-time status monitoring parameters to obtain the current remaining power parameters;

[0077] Step S33: performing power deviation analysis on the current remaining power parameter according to the power demand prediction value at each time point, thereby obtaining the current power deviation value;

[0078] Step S34: analyzing the battery capacity attenuation per unit time for the battery real-time status monitoring parameters to generate a battery capacity attenuation law;

[0079] Step S35: Calculate the power deviation compensation requirement according to the battery capacity attenuation law and the current power deviation value, so as to obtain the power deviation compensation requirement value at each smoking time point of the user.

[0080] In this embodiment, the historical monitoring log of the electronic cigarette usually contains battery status information. These logs are stored in CSV, JSON or text files in a specific format. Analyze the file format to determine how to extract the required data. Read the historical monitoring log, assuming that the log records the battery status information for the past 72 hours. Each record includes parameters such as timestamp, battery voltage, current and temperature. Filter out parameters related to the battery status from the read log, such as battery voltage (unit: volt), current (unit: ampere) and temperature (unit: Celsius). For example, assume that the extracted sample data includes battery voltage and current at multiple time points. The extracted battery real-time status monitoring parameters are sorted and stored in a structured data format, such as a table or database, for subsequent analysis. Estimate the current remaining power based on the voltage and current parameters of the battery. Typically, the remaining power of a battery is estimated by the ratio of its voltage to the rated voltage. Based on the extracted battery voltage data, assume that the rated voltage of the battery is 4.2 volts and the current voltage is 3.7 volts. By calculating the ratio of the current voltage to the rated voltage, an estimated value of the remaining power is obtained. For example, assume that the calculated remaining power is 88%. The calculated current remaining power parameters are recorded in the data structure to ensure that the remaining power information corresponding to each time point is complete for subsequent analysis. Use historical usage data or machine learning models to predict the user's power demand at different time points. For example, predictions are made based on the user's smoking habits and historical data. For each time point, calculate the deviation between the predicted power demand value and the current remaining power parameter. If the predicted demand at a certain time point is 75% and the actual remaining power is 88%, the power deviation is +13%. The power deviation value at each time point is recorded in the data structure to ensure that the difference between the power demand and the actual remaining power at each time point can be clearly understood. By analyzing the changes in battery voltage and current in different time periods, the capacity decay of the battery per unit time is determined, usually using a linear regression or exponential decay model. Calculate the battery voltage change per unit time, assuming that the battery voltage drops from 3.8 volts to 3.6 volts in a certain time period. Calculate the capacity decay based on the rated capacity and current voltage changes of the battery. For example, assume that the capacity decay is 5% in this time period. The calculation results are organized into the law of battery capacity decay, including the relationship between the decay rate and the usage time, the effect of temperature on decay, etc. Combining the battery capacity attenuation law and the power deviation value, a compensation model is designed to estimate the power compensation demand at each time point. Set a compensation strategy. For example, when the power deviation is negative, the battery charging efficiency needs to be improved. The required power compensation is estimated based on each user's smoking time and power deviation. For example, if the power deviation at a certain time point is -10%, and the capacity attenuation law shows that the attenuation during this time period is 5%, then the additional power compensation required is 15%.The power deviation compensation requirement value of each user at different smoking time points is recorded in the data structure to provide data support for subsequent power management and optimization.

[0081] In this embodiment, step S4 includes the following steps:

[0082] Step S41: predicting the charging duration based on the power deviation compensation requirement value at each user's smoking time point to generate the charging duration;

[0083] Step S42: performing smoking interval analysis according to the predicted time points of multiple users' smoking behaviors, thereby obtaining user smoking interval data;

[0084] Step S43: matching the user's smoking interval data with the charging time period according to the charging time length, thereby obtaining multiple charging time periods;

[0085] Step S44: avoiding conflicts among multiple charging time periods and generating an optimal charging time period;

[0086] Step S45: Perform intelligent charging optimization according to the optimal charging time period to generate a charging time period optimization strategy.

[0087] In this embodiment, before predicting the charging time, it is necessary to first understand the charging characteristics of the battery. The charging speed of the battery is usually affected by many factors, including the initial power of the battery, the charging power, and the health of the battery. In general, the charging time of the battery is estimated by its power demand and charging power. Collect the user's power deviation compensation demand value. Assume that the power deviation of a user at a specific moment is 15%, which means that at this point in time, the user needs to compensate 15% of the power to meet his smoking needs. Assume that the total capacity of the battery is 3000mAh and the charging power is 1A (i.e. 1000mA). Calculate the required charging time according to the power deviation. The specific calculation steps are: calculate the power to be compensated: the power to be compensated = 15% × 3000mAh = 450mAh, and then use the charging power to calculate the required time: charging time = 450mAh / 1000mA = 0.45 hours ≈ 27 minutes, and record the calculated charging time length in the database to ensure that each user's charging demand is associated with time for subsequent analysis and optimization. Use the time series analysis method to analyze the user's smoking behavior within a day and identify the time pattern of their smoking. Determine the user's smoking interval by analyzing historical data.

[0088] Collect smoking time records of multiple users.

[0089] 2023-10-0110:00

[0090] 2023-10-0110:15

[0091] 2023-10-0110:35

[0092] 2023-10-0111:00

[0093] Calculate the interval between adjacent smoking time points. User A's smoking interval is:

[0094] First interval: 10:15-10:00 = 15 minutes

[0095] Second interval: 10:35-10:15 = 20 minutes

[0096] The third interval: 11:00-10:35 = 25 minutes

[0097] Record these intervals to form the user's smoking behavior pattern. Organize each user's smoking interval data into a structured format, including user ID, smoking time, and corresponding interval time, for subsequent analysis.

[0098] Design a logical matching algorithm to match the charging time period with the user's smoking interval to ensure that the charging time does not conflict with the smoking behavior. Based on the charging time length of step S41, for example, the charging time of user A is 27 minutes. Assume that user A charges in the time period of 10:00-10:27. Check the user's smoking interval data to determine whether there is overlapping smoking time in the charging time period. For example, user A does not have overlapping smoking time during charging, which meets the conditions. Match the user's charging time period with the smoking interval, and record the effective charging time period for subsequent optimization. Design a conflict detection strategy to identify the conflict between the charging time period and the user's smoking time period, and generate the optimal charging time period. Traverse each user's charging time period and smoking time period to check the time overlap. If the charging time period overlaps with the smoking time period, the charging time needs to be adjusted. Assume that the smoking time of user A is 10:00-10:15 and the charging time is 10:00-10:27, and a conflict occurs. In order to avoid the conflict, adjust the charging time to 10:30-10:57 to ensure that the charging time period does not overlap with the smoking time period. Record the optimized charging time period in the database to ensure that each user's charging time period is optimal and does not conflict with their smoking time. Design intelligent charging optimization strategies based on users' smoking habits and charging needs, such as dynamic charging strategies based on user behavior patterns. Develop intelligent charging strategies based on users' charging time periods, smoking behaviors, and battery status. For example, set charging to start 15 minutes after a user smokes to ensure that the battery reaches the best state before the user's next smoke. Regularly evaluate users' smoking behavior and dynamically adjust charging strategies based on feedback data. For example, if a user increases the frequency of smoking within a certain period of time, increase the charging frequency accordingly to ensure that the battery is sufficient during peak user demand periods. Record the generated charging time period optimization strategy in the data structure for subsequent reference and further optimization to ensure charging efficiency and user satisfaction.

[0099] In this embodiment, step S5 includes the following steps:

[0100] Step S51: Calculate current charging voltage and current parameters according to real-time battery status monitoring parameters;

[0101] Step S52: performing real-time charging rate analysis on the current charging voltage and current parameters to obtain a real-time charging rate;

[0102] Step S53: identifying the time series change of internal resistance according to the real-time status monitoring parameters of the battery to generate the battery internal resistance change characteristics;

[0103] Step S54: analyzing the voltage and current fluctuation trend according to the current charging voltage and current parameters, and generating a voltage and current fluctuation trend curve;

[0104] Step S55: evaluating the real-time battery life state according to the battery internal resistance variation characteristics and the voltage and current fluctuation trend curve, thereby obtaining a real-time battery life state curve;

[0105] Step S56: dynamically adjust the real-time charging rate based on the real-time battery life state curve to construct a dynamic charging rate control strategy.

[0106] In this embodiment, a battery management system (BMS) is used to monitor the state of the battery in real time, including parameters such as voltage, temperature, remaining power and internal resistance. Use a high-precision sensor (such as a Hall sensor) to obtain current data. Set the monitoring frequency to 1Hz, and record the voltage and current values ​​of the battery in real time. Ensure the accuracy of data acquisition, the voltage measurement error does not exceed 0.1V, and the current measurement error does not exceed 0.5A. Calculate the current charging voltage and current according to the charging state of the battery (such as constant current, constant voltage, etc.). Use Ohm's law for calculation, record the calculated charging voltage and current in the database, and set the data storage format to CSV for subsequent analysis and processing. Set the analysis time window to 5 minutes, and calculate the charging rate every 5 minutes to ensure that the rate change during the charging process can be captured. In each time window, the charging power is calculated in real time and the charging rate is derived, and the charging rate data is recorded and updated. The pulse test method is used to calculate the internal resistance by applying a short current pulse and measuring the voltage change. Perform internal resistance measurement at a set time interval (such as 10 seconds), and record the voltage change and current pulse measured each time. Use statistical methods to analyze the change trend of internal resistance over time, generate the characteristic curve of internal resistance change, and identify the characteristic points (such as sudden increase or decrease) of internal resistance change with charging state. Use the moving average method to smooth the voltage and current data, and set the window size to 5 seconds. Analyze the fluctuation by calculating the standard deviation and mean. Generate the fluctuation trend curve of voltage and current, use Python's Matplotlib library for visualization, and draw the fluctuation curve to facilitate the observation of trend changes. Establish a life evaluation model based on internal resistance and fluctuation trend, and use the weighted method to combine the internal resistance change and fluctuation to set the weight (such as internal resistance accounts for 70%, fluctuation accounts for 30%). Calculate the real-time life state of the battery according to the evaluation model, generate the life state curve, and indicate the current health state of the battery. Set the charging rate adjustment strategy according to the real-time life state curve. When the battery is in good condition, the charging rate can be increased, otherwise it can be reduced. For example, when the battery life state is higher than 80%, the charging rate can be set to 1C; when it is lower than 50%, it can be adjusted to 0.5C. Monitor the battery status in real time through BMS, and dynamically adjust the charging current and voltage. Use PID control algorithm to optimize the charging process and ensure the stability and safety of the charging process.

[0107] In this embodiment, step S6 includes the following steps:

[0108] Step S61: Performing instant charging control according to a dynamic charging rate control strategy and a charging time period optimization strategy, and collecting real-time charging control monitoring data;

[0109] Step S62: Detect abnormal conditions on the real-time charging control monitoring data and mark abnormal battery status time points;

[0110] Step S63: performing battery failure prediction according to the abnormal battery status time point to obtain battery failure prediction data;

[0111] Step S64: performing adaptive diagnostic decision on the battery fault prediction data, thereby generating an adaptive diagnostic engine;

[0112] Step S65: Iteratively control and optimize the adaptive diagnosis engine, the dynamic charging rate control strategy, and the charging time period optimization strategy to construct an intelligent charging control optimization model.

[0113] In this embodiment, the dynamic charging rate control strategy and the charging time period optimization strategy are integrated to set the parameters of the charging rate and time period. For example, the charging rate is set to 1C, the charging time period is set to 1-3 hours, and it is adjusted in real time according to the battery status. The battery management system (BMS) is used to monitor the battery status in real time, and the charging current and voltage are dynamically adjusted to ensure the safety and efficiency of the charging process. The monitoring frequency is set to 1Hz, and the charging parameters are updated in real time. Parameters such as charging current, voltage, temperature and charging time are collected in real time, and a data collector (such as Arduino or Raspberry Pi) is used to connect the sensor and record the data. The storage format is set to CSV for subsequent analysis. Ensure that the data is recorded once per second, and the collection cycle is set to 1 hour. A threshold-based anomaly detection algorithm is used to set the normal range of current, voltage and temperature. For example, the current range is set to 0-10A, the voltage range is set to 3.0-4.2V, and the temperature range is set to 0-60℃. During the data acquisition process, the battery status is monitored in real time. If any parameter exceeds the set range, the time point is marked as an abnormal state. The timestamp and corresponding parameter value of the abnormal state are recorded, and an abnormal report is generated for subsequent analysis. Use machine learning models (such as random forests or support vector machines) for fault prediction. The features of the training model include the time point of the abnormal state and the corresponding battery state parameters. Collect historical battery failure data and construct training sets and test sets. Set the training set to 70% and the test set to 30%, and use the cross-validation method to evaluate the model performance. According to the real-time monitoring data and the abnormal time point, use the trained model to predict battery failures and output the prediction results, including the fault risk level (such as high, medium, and low). Use fuzzy logic control (Fuzzy Logic Control) or rule engine to generate adaptive diagnostic decisions based on fault prediction data and historical fault cases. Design an adaptive diagnostic engine framework, set the input as fault prediction data, and the output as diagnostic decisions (such as maintenance recommendations, battery replacement, etc.). Establish decision rules based on historical data. For example, if the fault risk level is high and the battery temperature exceeds 55°C, it is recommended to stop charging immediately and perform maintenance. Use genetic algorithms or particle swarm optimization algorithms to iteratively optimize the control strategy, and set the fitness function as a comprehensive evaluation of charging efficiency and battery life. After each charging cycle, the charging rate and time period optimization strategy is adjusted based on the feedback from the adaptive diagnostic engine and the charging efficiency analysis results. The parameters and results of each optimization are recorded for subsequent evaluation and improvement.

[0114] In this embodiment, an electronic cigarette charging control device is also provided, including:

[0115] The user portrait module is used to obtain the electronic cigarette historical monitoring log; identify the user's usage behavior and fit the personalized user portrait to the electronic cigarette historical monitoring log, and build a personalized user behavior portrait;

[0116] The power demand prediction module is used to predict the smoking trend and power demand based on the user's personalized behavior profile, thereby generating a power demand prediction value at each time point;

[0117] The power deviation compensation module is used to calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point;

[0118] The optimal time period module is used to predict the charging time based on the power deviation compensation demand value of each user's smoking time point, and to perform intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy;

[0119] The charging rate control module is used to evaluate the real-time battery life status based on the electronic cigarette historical monitoring log and to adjust the dynamic charging rate to build a dynamic charging rate control strategy;

[0120] The instant charging control module is used to perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

[0121] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned electronic cigarette charging control methods are implemented.

[0122] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0123] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0124] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0125] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An electronic cigarette charging control method, characterized in that: The following steps are involved: Step S1: Obtain the electronic cigarette history monitoring log; perform user usage behavior recognition and personalized user portrait fitting on the electronic cigarette history monitoring log to construct a personalized user behavior portrait; Step S2: predicting smoking trends and power demand based on the user's personalized behavior profile, thereby generating a power demand forecast value at each time point; Step S3: Calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point; Step S4: predicting the charging time based on the power deviation compensation requirement value at each user's smoking time point, and performing intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy; Step S5: Performing real-time battery life status evaluation based on the electronic cigarette historical monitoring log, and dynamically adjusting the charging rate to construct a dynamic charging rate control strategy; Step S6: Perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

2. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: obtaining an electronic cigarette history monitoring log; performing user usage behavior recognition on the electronic cigarette history monitoring log, and extracting multiple user usage behavior data; Step S12: Calculating the usage frequency based on the usage behavior data of multiple users to obtain the user usage frequency characteristics; Step S13: performing a time stamp analysis on the usage behavior data of multiple users, and extracting the time stamp of each usage behavior; Step S14: mining the intra-cycle behavior distribution of the timestamp of each usage behavior according to the user's usage frequency characteristics, thereby generating intra-cycle behavior distribution data; Step S15: performing temporal usage behavior habit evolution on the usage behavior data of multiple users to generate user temporal behavior habit features; Step S16: Fit a personalized user profile based on the behavior distribution data within the period and the user's temporal behavior habit characteristics to construct a personalized user behavior profile.

3. The electronic cigarette charging control method according to claim 2, characterized in that: The specific steps of step S15 are: Extract the start and end time points of each smoking according to multiple user usage behavior data; The smoking duration is calculated based on the start and end time points of each smoking, and the smoking duration of each smoking behavior is obtained; Quantifying the smoking intensity of multiple users' usage behavior data, thereby generating multiple users' smoking intensity quantification values; According to the length of smoking time of each use behavior, the peak smoking period in the cycle is identified to obtain the peak smoking period in the cycle; The peak smoking period in the cycle is located according to the timestamp of each use behavior, thereby obtaining the peak smoking period; The temporal usage behavior habit evolution is performed according to the quantified values ​​of smoking intensity of multiple users and the smoking peak time periods to generate the user temporal behavior habit characteristics.

4. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: predicting smoking trends based on the personalized behavior portrait of the user, thereby obtaining a plurality of predicted time points of the user's smoking behavior; Step S22: estimating the smoking duration of multiple users' smoking behavior prediction time points one by one, thereby generating the smoking duration of each time point; Step S23: Calculate the operating power according to the electronic cigarette historical monitoring log to obtain the operating power parameter of the electronic cigarette; Step S24: performing nonlinear power demand calculation on the smoking duration at each time point based on the operating power parameter of the electronic cigarette, thereby obtaining the power demand at each time point; Step S25: forecasting the power demand at each time point, thereby generating a predicted value of the power demand at each time point.

5. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: extracting battery real-time status monitoring parameters according to the electronic cigarette historical monitoring log; Step S32: evaluating the current remaining power of the battery real-time status monitoring parameters to obtain the current remaining power parameters; Step S33: performing power deviation analysis on the current remaining power parameter according to the power demand prediction value at each time point, thereby obtaining the current power deviation value; Step S34: analyzing the battery capacity attenuation per unit time for the battery real-time status monitoring parameters to generate a battery capacity attenuation law; Step S35: Calculate the power deviation compensation requirement according to the battery capacity attenuation law and the current power deviation value, so as to obtain the power deviation compensation requirement value at each smoking time point of the user.

6. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: predicting the charging duration based on the power deviation compensation requirement value at each user's smoking time point to generate the charging duration; Step S42: performing smoking interval analysis according to the predicted time points of multiple users' smoking behaviors, thereby obtaining user smoking interval data; Step S43: matching the user's smoking interval data with the charging time period according to the charging time length, thereby obtaining multiple charging time periods; Step S44: avoiding conflicts among multiple charging time periods and generating an optimal charging time period; Step S45: Perform intelligent charging optimization according to the optimal charging time period to generate a charging time period optimization strategy.

7. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: Calculate current charging voltage and current parameters according to real-time battery status monitoring parameters; Step S52: performing real-time charging rate analysis on the current charging voltage and current parameters to obtain a real-time charging rate; Step S53: identifying the time series change of internal resistance according to the real-time status monitoring parameters of the battery to generate the battery internal resistance change characteristics; Step S54: analyzing the voltage and current fluctuation trend according to the current charging voltage and current parameters, and generating a voltage and current fluctuation trend curve; Step S55: evaluating the real-time battery life state according to the battery internal resistance variation characteristics and the voltage and current fluctuation trend curve, thereby obtaining a real-time battery life state curve; Step S56: dynamically adjust the real-time charging rate based on the real-time battery life state curve to construct a dynamic charging rate control strategy.

8. The electronic cigarette charging control method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Performing instant charging control according to a dynamic charging rate control strategy and a charging time period optimization strategy, and collecting real-time charging control monitoring data; Step S62: Detect abnormal conditions on the real-time charging control monitoring data and mark abnormal battery status time points; Step S63: performing battery failure prediction according to the abnormal battery status time point to obtain battery failure prediction data; Step S64: performing adaptive diagnostic decision on the battery fault prediction data, thereby generating an adaptive diagnostic engine; Step S65: Iteratively control and optimize the adaptive diagnosis engine, the dynamic charging rate control strategy, and the charging time period optimization strategy to construct an intelligent charging control optimization model.

9. An electronic cigarette charging control device, characterized in that: Used to execute the electronic cigarette charging control method according to claim 1, comprising: The user portrait module is used to obtain the electronic cigarette historical monitoring log; identify the user's usage behavior and fit the personalized user portrait to the electronic cigarette historical monitoring log, and build a personalized user behavior portrait; The power demand prediction module is used to predict the smoking trend and power demand based on the user's personalized behavior profile, thereby generating a power demand prediction value at each time point; The power deviation compensation module is used to calculate the power deviation compensation demand for the power demand forecast value at each time point according to the electronic cigarette historical monitoring log, so as to obtain the power deviation compensation demand value at each user's smoking time point; The optimal time period module is used to predict the charging time based on the power deviation compensation demand value of each user's smoking time point, and to perform intelligent charging optimization in the optimal time period to generate a charging time period optimization strategy; The charging rate control module is used to evaluate the real-time battery life status based on the electronic cigarette historical monitoring log and to adjust the dynamic charging rate to build a dynamic charging rate control strategy; The instant charging control module is used to perform instant charging control according to the dynamic charging rate control strategy and the charging time period optimization strategy, and perform iterative control optimization to build an intelligent charging control optimization model.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electronic cigarette charging control method according to any one of claims 1 to 8 are implemented.

Images