Electricity consumption analysis method and system based on intelligent kettle

Abstract

The invention relates to the technical field of intelligent homes, in particular to an electricity consumption analysis method and system based on an intelligent kettle. The method comprises the following steps of performing historical kettle power utilization log acquisition on the intelligent kettle so as to obtain historical kettle power utilization log data; performing user behavior pattern analysis on the historical kettle power utilization log data to obtain user use behavior pattern data; carrying out electricity consumption waveform analysis on the historical kettle electricity consumption log data so as to obtain electricity consumption mode characteristic data; performing kettle battery executable parameter range calculation on the intelligent kettle according to the user use behavior mode data and the power consumption mode characteristic data so as to obtain battery executable parameter range data; acquiring user behavior instruction data; water level height sensing real-time monitoring is performed on the water body in the intelligent kettle, so that real-time water level data is obtained. According to the invention, a user can be helped to know and manage the power utilization condition of the intelligent kettle, and convenient and intelligent use experience is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and in particular to a method and system for analyzing power consumption based on a smart kettle. Background Art

[0002] With the rapid development of smart home technology, smart devices are increasingly widely used in people's daily lives. Among them, the smart kettle, as an intelligent small household appliance, aims to provide more convenient and intelligent hot water services. However, current smart kettles lack detailed monitoring and analysis of power consumption and lack in-depth understanding of user usage behaviors.

[0003] However, despite the significant progress made by smart kettles in providing convenient and intelligent hot water services, there are still some deficiencies in the power consumption of current smart kettles. Existing smart kettles mainly focus on providing basic heating and temperature control functions, but lack in-depth understanding of user usage behaviors and personalized feedback. This results in relatively vague awareness of users' electricity consumption habits and energy consumption situations, making it impossible to accurately adjust usage patterns to optimize energy utilization.

[0004] Most smart kettles on the current market focus more on technological innovation and appearance design, while relatively neglecting the real-time monitoring and in-depth analysis of power consumption. This makes it difficult for users to obtain detailed information about power utilization when using smart kettles, and also limits users' active participation and decision-making abilities in energy conservation. Summary of the Invention

[0005] Based on this, it is necessary for the present invention to provide a method and system for analyzing power consumption based on a smart kettle to solve at least one of the above technical problems.

[0006] To achieve the above object, a method for analyzing power consumption based on a smart kettle includes the following steps:

[0007] Step S1: Collect historical kettle power consumption logs of the smart kettle to obtain historical kettle power consumption log data; analyze the user behavior patterns of the historical kettle power consumption log data to obtain user usage behavior pattern data;

[0008] Step S2: Analyze the power consumption waveform of the historical kettle power consumption log data to obtain power consumption pattern feature data; calculate the range of executable parameters of the kettle battery for the smart kettle according to the user usage behavior pattern data and the power consumption pattern feature data to obtain battery executable parameter range data;

[0009] Step S3: Obtain user behavior instruction data; perform real-time monitoring on the water level height of the water in the intelligent kettle to obtain real-time water level data; predict the power consumption and heating time of the intelligent kettle based on the user behavior instruction data and the real-time water level data, so as to obtain power consumption prediction data and heating time prediction data;

[0010] Step S4: Perform intelligent heating control operation on the intelligent kettle according to the battery executable parameter range data and the user behavior instruction data, and perform real-time tracking of the current consumption of the heating component of the intelligent kettle during the heating control operation, so as to obtain the complete current consumption data of the kettle;

[0011] Step S6: Construct a two-dimensional structure schematic diagram of the intelligent kettle during the intelligent heating control operation of the intelligent kettle to obtain a kettle structure schematic diagram; obtain the current real-time temperature data of each area of the water body; perform dynamic color rendering on the water body in the kettle structure schematic diagram according to the current real-time temperature data of each area of the water body, so as to obtain a kettle operation heat field mapping diagram;

[0012] Step S6: Analyze the power consumption of the intelligent kettle according to the complete current consumption data of the kettle, the power consumption prediction data, and the heating time prediction data, so as to obtain power consumption analysis data; send the kettle operation heat field mapping diagram and the power consumption analysis data to a preset mobile terminal and perform visualization.

[0013] Through analyzing the historical power consumption log data of the kettle, the usage behavior patterns of users in different scenarios can be deeply understood, including water usage frequency, water consumption, water usage time, etc. This provides a basis for the power consumption analysis of the smart kettle, helps understand users' habits and preferences, and provides personalized hot water services and energy optimization. By understanding the usage behavior patterns of users, the smart kettle can give personalized feedback suggestions according to users' preferences and habits. For example, according to the commonly used heating temperature and time of users, the smart kettle can provide recommended settings to improve the user experience. Through the analysis of the power wave pattern, the power consumption patterns of the smart kettle in different usage scenarios can be understood. This helps discover the laws and characteristics of power consumption behavior, provides a basis for optimizing energy utilization, and is closely related to the power consumption analysis method of the smart kettle. According to the user usage behavior pattern data and the power consumption pattern feature data, the range of battery executable parameters is calculated. This will help optimize the power consumption analysis method of the smart kettle, realize the optimization of the battery usage efficiency and the extension of the battery life on the premise of ensuring normal use. Through the real-time water level data and user behavior instructions, the smart kettle can predict the power consumption and heating time required by users. This provides key prediction capabilities for the power consumption analysis method of the smart kettle, helps users plan and adjust their power consumption strategies in advance, meets users' needs and saves energy. By accurately predicting the power consumption and heating time, the smart kettle can provide more intelligent services. Users can better control the power consumption and heating time, improving the convenience and personalization of the hot water service. According to the battery executable parameter range data and user behavior instructions, the smart kettle can intelligently adjust the heating control to provide hot water services in an optimal way. By real-time tracking the current consumption of the heating component, the smart kettle can dynamically adjust the heating power, realize the power consumption analysis method of the smart kettle, and achieve the effect of saving energy. Real-time tracking of the current consumption of the heating component can help monitor and control the working state of the smart kettle. If abnormal current consumption is found, measures can be taken in time to avoid overheating or other safety problems, improving the safety of user use. By constructing a two-dimensional structure schematic diagram of the kettle and performing dynamic color rendering, the thermal field situation inside the kettle can be visually presented. This helps users understand the working state and energy utilization situation of the smart kettle, and provides a visual display of the power consumption analysis results of the smart kettle. This helps users understand the temperature distribution in different areas of the kettle, as well as the speed and path of heat conduction, so as to better master the hot water heating process. Through the thermal field mapping atlas, users can intuitively understand the temperature changes in each area of the kettle. This enables users to conduct real-time evaluation of the heating effect, judge whether the expected temperature requirements are met, and whether it is necessary to further adjust the heating time or heating power. By analyzing the current consumption data, power consumption prediction data, and heating time prediction data of the kettle, the power consumption situation of the smart kettle can be obtained.This helps users understand their electricity consumption behavior, identify energy waste problems, and take corresponding energy-saving measures. Sending the thermal field mapping atlas and electricity consumption analysis data to the mobile terminal for visual display enables users to intuitively understand the working status and energy utilization of the intelligent kettle. This helps users actively participate and make decisions, optimizing their electricity consumption patterns to achieve the goal of energy conservation and emission reduction. In summary, through data collection, analysis, and prediction, combined with user behavior and real-time monitoring, the present invention provides a method for analyzing the electricity consumption of an intelligent kettle to optimize energy utilization, enhance user experience and safety, and enable users to participate in decision-making through visual display. Users can obtain detailed information about electricity utilization, including electricity consumption, electricity consumption patterns, and energy consumption conditions, etc. This will enhance users' awareness of the energy consumption of the intelligent kettle, enabling them to better understand their electricity consumption habits and energy utilization. The present invention overcomes the deficiencies of current intelligent kettles in terms of electricity consumption, bringing beneficial effects such as enhanced user energy awareness, personalized energy management, cultivation of energy conservation awareness, energy optimization and cost savings, and improved user experience. The present invention will enable users to better understand the energy consumption of the intelligent kettle and, through personalized energy management suggestions and optimization strategies, achieve effective utilization and conservation of energy.

[0014] Preferably, the present invention also provides an electricity consumption analysis system based on an intelligent kettle for executing the above-mentioned method for analyzing the electricity consumption of an intelligent kettle. The electricity consumption analysis system based on an intelligent kettle includes:

[0015] A historical kettle electricity consumption log collection module for collecting historical kettle electricity consumption logs of the intelligent kettle to obtain historical kettle electricity consumption log data; analyzing the user behavior pattern of the historical kettle electricity consumption log data to obtain user usage behavior pattern data;

[0016] An electricity consumption pattern mining and analysis module for performing an electricity waveform analysis on the historical kettle electricity consumption log data to obtain electricity consumption pattern feature data; calculating the range of executable parameters of the kettle battery for the intelligent kettle according to the user usage behavior pattern data and the electricity consumption pattern feature data to obtain battery executable parameter range data;

[0017] A real-time monitoring and prediction module for obtaining user behavior instruction data; performing real-time monitoring of the water level height of the water body in the intelligent kettle to obtain real-time water level data; predicting the electricity consumption and heating time of the intelligent kettle according to the user behavior instruction data and the real-time water level data to obtain electricity consumption prediction data and heating time prediction data;

[0018] A heating control tracking module, which is used to perform intelligent heating control operations on the intelligent kettle according to the battery executable parameter range data and the user behavior instruction data, and to perform real-time tracking of the current consumption of the heating component of the intelligent kettle during the heating control operation, so as to obtain the complete kettle current consumption data;

[0019] A thermal field visualization module, which is used to construct a two-dimensional structure schematic diagram of the intelligent kettle during the intelligent heating control operation of the intelligent kettle, so as to obtain the kettle structure schematic diagram; obtain the current real-time temperature data of each area of the water body; perform dynamic color rendering on the water body in the kettle structure schematic diagram according to the current real-time temperature data of each area of the water body, so as to obtain the kettle operation thermal field mapping atlas;

[0020] An electricity consumption analysis module, which is used to perform electricity consumption analysis on the intelligent kettle according to the complete kettle current consumption data, the electricity consumption prediction data and the heating time prediction data, so as to obtain the electricity consumption analysis data; send the kettle operation thermal field mapping atlas and the electricity consumption analysis data to a preset mobile terminal and perform visualization.

[0021] By collecting the historical electricity consumption log data of the intelligent kettle, the past electricity consumption behaviors and habits of users can be obtained, providing a basis for subsequent user behavior pattern analysis and electricity consumption analysis. By analyzing the historical kettle electricity consumption log data, the user's usage behavior pattern data can be obtained. This helps to understand information such as the user's water usage habits, water usage frequency, and water consumption, and then provide personalized energy management suggestions and optimization strategies. By performing an analysis of the electricity waveform on the historical kettle electricity consumption log data, the characteristic data of the electricity consumption pattern can be obtained. These characteristic data can reveal the user's electricity consumption pattern and behavior rules, providing a basis for calculating the battery executable parameter range and predicting the real-time electricity consumption of the intelligent kettle. By real-time monitoring the water level height in the intelligent kettle and combining with the user behavior instruction data, the electricity consumption and heating time of the intelligent kettle can be predicted. This enables the user to understand the hot water supply situation in advance, improve the user experience, and can make corresponding energy-saving adjustments according to the predicted data. By analyzing the battery executable parameter range data and the user behavior instruction data, intelligent heating control operations can be achieved. At the same time, by real-time tracking the current consumption of the intelligent kettle, the complete current consumption data of the kettle can be obtained, thereby evaluating and optimizing the energy utilization of the intelligent kettle. By constructing a two-dimensional structure schematic diagram of the intelligent kettle and performing dynamic color rendering according to the real-time temperature data, the visualization of the kettle operation thermal field mapping atlas can be realized. This helps the user to intuitively understand the temperature distribution in different areas of the kettle, and then adjust the water usage and heating strategies to improve energy utilization efficiency. By analyzing the complete current consumption data of the kettle, the electricity consumption prediction data, and the heating time prediction data, electricity consumption analysis can be carried out. This enables the user to deeply understand the energy consumption situation of the intelligent kettle, and then make corresponding energy-saving measures and adjustments according to the analysis results to achieve the effective utilization and conservation of energy. Sending the kettle operation thermal field mapping atlas and the electricity consumption analysis data to a preset mobile terminal for visualization, the user can intuitively view the operation situation and electricity consumption situation of the intelligent kettle through the mobile device. This helps to improve the user's awareness of energy utilization and conservation, and encourages the user to participate more actively and make decisions in energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects, and advantages of the present invention will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0023] Figure 1 The step flow schematic diagram of the electricity consumption analysis method based on an intelligent kettle according to an embodiment is shown.

[0024] Figure 2 The detailed step flow schematic diagram of step S5 according to an embodiment is shown.

[0025] Figure 3Shows a detailed step - by - step flowchart of step S6 of an embodiment. Detailed implementation mode

[0026] The following clearly and completely describes the technical method of this invention patent in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus repeated descriptions of them will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that although terms such as "first", "second", etc. may be used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0029] To achieve the above - mentioned purpose, please refer to Figures 1 to 3 , the present invention provides a method for analyzing the electricity consumption of an intelligent kettle. The method includes the following steps:

[0030] Step S1: Collect historical kettle electricity consumption logs of the intelligent kettle to obtain historical kettle electricity consumption log data; analyze the user behavior pattern of the historical kettle electricity consumption log data to obtain user usage behavior pattern data;

[0031] Specifically, for example, a log - recording function can be added to the intelligent kettle to record relevant electricity consumption information during each use, such as time, heating status, heating time, heating amount, etc. Save these records in the storage system of the intelligent kettle. By processing and analyzing the historical electricity consumption log data, extract the user's usage behavior pattern data. Data analysis tools and algorithms, such as clustering analysis, sequence pattern mining, or association rule mining, can be used to identify the user's usage patterns, such as morning water use, lunchtime water use, or nighttime water use.

[0032] Step S2: Conduct an analysis of the historical power consumption log data of the kettle to obtain power consumption pattern feature data; calculate the range of executable parameters for the kettle battery of the intelligent kettle based on the user usage behavior pattern data and the power consumption pattern feature data, so as to obtain the range data of executable parameters for the battery.

[0033] Specifically, for example, the feature data of the power consumption pattern can be extracted through the waveform analysis of the historical power consumption log data of the kettle. Signal processing techniques and algorithms such as Fourier transform or wavelet transform can be used to analyze the characteristics of the power consumption signal, such as frequency, amplitude, and phase. Combine the user usage behavior pattern data with the power consumption pattern feature data, and calculate the range of executable parameters for the battery of the intelligent kettle according to methods such as statistical analysis or rule inference. For example, if the user usage behavior pattern is to frequently perform long-time heating operations, then the range of executable parameters for the battery may need to consider higher power and capacity.

[0034] Step S3: Obtain user behavior instruction data; conduct real-time monitoring of the water level height of the water body in the intelligent kettle to obtain real-time water level data; predict the power consumption and heating time of the intelligent kettle based on the user behavior instruction data and the real-time water level data, so as to obtain the predicted power consumption data and the predicted heating time data.

[0035] Specifically, for example, the user behavior instruction data can be collected through the interface of the intelligent kettle interacting with the user (such as buttons, voice recognition, or mobile applications), such as the temperature selected by the user, the heating time setting, or the heating mode. Add a water level sensor in the intelligent kettle to monitor the height of the water body in the kettle in real time and feedback the water level data to the system. Based on the user behavior instruction data and the real-time water level data, combined with historical data and model algorithms, predict the power consumption and heating time of the intelligent kettle. Machine learning methods such as regression models, time series analysis, or deep learning models can be used to establish the prediction model.

[0036] Step S4: Perform intelligent heating control operations on the intelligent kettle based on the range data of executable parameters for the battery and the user behavior instruction data, and conduct real-time tracking of the current consumption of the heating component of the intelligent kettle during the heating control operation, so as to obtain the complete current consumption data of the kettle.

[0037] Specifically, for example, intelligent heating control can be performed on the intelligent kettle according to the range data of executable parameters for the battery and the user behavior instruction data. According to the temperature and heating time set by the user, adjust the working state and power of the heating component of the intelligent kettle to achieve precise heating control. Add a current sensor in the heating component of the intelligent kettle to monitor the current consumption of the heating component in real time. By connecting the current sensor to the data acquisition system, the current data during the heating process can be obtained.

[0038] Step S5: During the intelligent heating control operation of the intelligent kettle, construct a two-dimensional structural schematic diagram of the intelligent kettle to obtain the kettle structure schematic diagram; obtain the current real-time temperature data of each water area; perform dynamic color rendering on the water body in the kettle structure schematic diagram according to the current real-time temperature data of each water area, so as to obtain the kettle operation heat field mapping atlas.

[0039] Specifically, for example, according to the design and structure of the intelligent kettle, draw a two-dimensional structural schematic diagram of the kettle. The schematic diagram may include key components such as the outer contour of the kettle, the heating component, and the water level sensor. By adding temperature sensors in the kettle, the temperature of each water area is monitored in real time. Connect the temperature sensors to the data acquisition system to obtain the real-time temperature data of each area. According to the current real-time temperature data of each water area, perform dynamic color rendering on the water body in the kettle structure schematic diagram. By mapping different temperature regions to different colors, a kettle operation heat field mapping atlas can be formed to visually display the temperature distribution of the water body.

[0040] Step S6: Analyze the power consumption of the intelligent kettle based on the complete power consumption data of the kettle, the power consumption prediction data, and the heating time prediction data, so as to obtain the power consumption analysis data; send the kettle operation heat field mapping atlas and the power consumption analysis data to a preset mobile terminal and perform visualization.

[0041] Specifically, for example, the power consumption analysis can be performed based on the complete power consumption data of the kettle, the power consumption prediction data, and the heating time prediction data. By integrating the current data, the power consumption situation can be obtained. Send the kettle operation heat field mapping atlas and the power consumption analysis data to a preset mobile terminal. The data can be transmitted to the mobile application through a network connection, and then visualized in the mobile application, for example, displaying the heat field mapping and power consumption situation of the kettle in the form of charts or graphs.

[0042] Through analyzing the historical electricity consumption log data of the kettle, the present invention can deeply understand the user's usage behavior patterns in different scenarios, including water usage frequency, water consumption, water usage time, etc. This provides a basis for the electricity consumption analysis of the intelligent kettle, helps understand the user's habits and preferences, and provides personalized hot water services and energy optimization. By understanding the user's usage behavior patterns, the intelligent kettle can give personalized feedback suggestions according to the user's preferences and habits. For example, according to the commonly used heating temperature and time of the user, the intelligent kettle can provide recommended settings to improve the user's usage experience. Through the analysis of the electrical waveform, the electricity consumption patterns of the intelligent kettle in different usage scenarios can be understood. This helps to discover the laws and characteristics of the electricity consumption behavior and provides a basis for optimizing energy utilization, which is closely related to the electricity consumption analysis method of the intelligent kettle. According to the user usage behavior pattern data and the electricity consumption pattern characteristic data, the battery executable parameter range is calculated. This will help optimize the electricity consumption analysis method of the intelligent kettle, realize the optimization of the battery usage efficiency and the extension of the battery life on the premise of ensuring normal use. Through the real-time water level data and the user behavior instructions, the intelligent kettle can predict the electricity consumption and heating time required by the user. This provides the key prediction ability for the electricity consumption analysis method of the intelligent kettle, helps the user plan and adjust the electricity consumption strategy in advance, meets the user's needs and saves energy. By accurately predicting the electricity consumption and heating time, the intelligent kettle can provide more intelligent services. The user can better control the electricity consumption and heating time, improving the convenience and personalization of the hot water service. According to the battery executable parameter range data and the user behavior instructions, the intelligent kettle can intelligently adjust the heating control to provide the hot water service in an optimal way. By real-time tracking the current consumption of the heating component, the intelligent kettle can dynamically adjust the heating power, realize the electricity consumption analysis method of the intelligent kettle, and achieve the effect of saving energy. Real-time tracking of the current consumption of the heating component can help monitor and control the working state of the intelligent kettle. If abnormal current consumption is found, measures can be taken in time to avoid overheating or other safety problems, improving the safety of user use. By constructing a two-dimensional structure schematic diagram of the kettle and performing dynamic color rendering, the thermal field situation inside the kettle can be visually presented. This helps the user understand the working state and energy utilization situation of the intelligent kettle, and provides a visual display of the electricity consumption analysis results of the intelligent kettle. This helps the user understand the temperature distribution in different areas of the kettle, as well as the speed and path of heat conduction, so as to better master the hot water heating process. Through the thermal field mapping atlas, the user can intuitively understand the temperature change situation in each area of the kettle. This enables the user to conduct a real-time evaluation of the heating effect, judge whether the expected temperature requirement is met, and whether it is necessary to further adjust the heating time or heating power. By analyzing the current consumption data, electricity consumption prediction data and heating time prediction data of the kettle, the electricity consumption situation of the intelligent kettle can be obtained.This helps users understand their electricity consumption behavior, identify energy waste problems, and take corresponding energy-saving measures. Sending the thermal field mapping atlas and electricity consumption analysis data to the mobile terminal for visual display enables users to intuitively understand the working status and energy utilization of the intelligent kettle. This helps users actively participate and make decisions, optimizing their electricity consumption patterns to achieve the goal of energy conservation and emission reduction. In summary, through data collection, analysis, and prediction, combined with user behavior and real-time monitoring, the present invention provides a method for analyzing the electricity consumption of an intelligent kettle to optimize energy utilization, enhance user experience and safety, and enable users to participate in decision-making through visual display. Users can obtain detailed information about electricity utilization, including electricity consumption, electricity consumption patterns, and energy consumption. This will enhance users' awareness of their own energy consumption, enabling them to better understand their electricity consumption habits and energy utilization. The present invention overcomes the deficiencies of current intelligent kettles in electricity consumption, bringing beneficial effects such as enhanced user energy awareness, personalized energy management, cultivation of energy conservation awareness, energy optimization and cost savings, and improved user experience. The present invention will enable users to better understand the energy consumption of the intelligent kettle and achieve effective utilization and conservation of energy through personalized energy management suggestions and optimization strategies.

[0043] Preferably, step S1 includes the following steps:

[0044] Step S11: Collect historical kettle electricity usage logs of the intelligent kettle to obtain historical kettle electricity usage log data;

[0045] Specifically, for example, data collection tools such as intelligent kettle electricity usage log recording software or hardware devices can be prepared. Connect the data collection tool to the intelligent kettle and ensure that it can accurately record electricity usage logs. Start the data collection tool to begin collecting historical kettle electricity usage logs. Use the intelligent kettle within a certain time period to record electricity usage log data. After collection, save the historical kettle electricity usage log data to an appropriate storage medium such as a database or file.

[0046] Step S12: Extract key fields of electricity parameters from the historical kettle electricity usage log data to obtain key electricity parameter data;

[0047] Specifically, for example, for each electricity usage log data, identify and extract key fields related to electricity parameters. Common electricity parameter fields include current, voltage, power, energy consumption, etc. Use appropriate data processing and extraction methods to extract the key fields from each electricity usage log data. Organize and save the extracted key electricity parameter data for subsequent analysis and processing.

[0048] Step S13: Mark the key electricity parameter data with timestamps to obtain electricity parameter-time data;

[0049] Specifically, for example, the acquisition frequency of timestamps can be determined, such as every 1 second, every minute, etc. At each timestamp, the key data of the corresponding electricity consumption parameters are marked and recorded. The timestamp can be in the form of date and time to ensure the timeliness of the data. The marked and recorded electricity consumption parameter-time data are saved into an appropriate data structure, such as a table, a time series database, etc., for subsequent time analysis and visualization.

[0050] Step S14: Detect the daily repeated electricity consumption patterns from the electricity consumption parameter-time data to obtain the daily repeated electricity consumption pattern data;

[0051] Specifically, for example, the electricity consumption parameter-time data can be grouped by date, and the data of the same date are classified together. The electricity consumption parameter data of each date are statistically analyzed to detect the daily repeated electricity consumption patterns therein. Various methods and techniques, such as time series analysis, clustering analysis, etc., can be used to identify and extract the daily repeated electricity consumption patterns. The detected daily repeated electricity consumption pattern data are sorted out and saved for subsequent analysis and application.

[0052] Step S15: Detect the abnormal electricity consumption from the electricity consumption parameter-time data to obtain the abnormal electricity consumption pattern data;

[0053] Specifically, for example, the abnormal electricity consumption can be detected from the electricity consumption parameter data to identify the abnormal electricity consumption patterns therein. Statistical methods, machine learning algorithms, etc. can be used for abnormal detection to find the abnormal data points that do not conform to the normal electricity consumption patterns. According to the results of the abnormal detection, the abnormal data points are marked as the abnormal electricity consumption pattern data. The detected abnormal electricity consumption pattern data are sorted out and saved for subsequent analysis and application.

[0054] Step S16: Conduct user behavior insights on the daily repeated electricity consumption pattern data and the abnormal electricity consumption pattern data to obtain the user usage behavior pattern data.

[0055] Specifically, for example, the daily repeated electricity consumption pattern data and the abnormal electricity consumption pattern data are analyzed and mined to gain insights into the user usage behavior patterns. Methods such as data visualization, association rule mining, clustering analysis, etc. can be used to discover the associations between the patterns and the characteristics of the user usage behavior. According to the analysis results, the user usage behavior pattern data, such as the preferred electricity consumption time periods of the user, the commonly used electricity consumption patterns, etc., are extracted. The user usage behavior pattern data are sorted out and saved for subsequent applications, such as personalized recommendations, energy management, etc.

[0056] By collecting the historical electricity consumption logs of the intelligent kettle, the present invention can obtain the past electricity consumption records of the intelligent kettle. These data include information such as the electricity consumption and electricity consumption time of the kettle, providing basic data for subsequent electricity consumption analysis and user behavior pattern analysis. By analyzing and processing the historical electricity consumption log data of the kettle, key fields of electricity consumption parameters are extracted, such as electricity consumption, electricity consumption time, etc. This can accurately obtain and record the electricity consumption situation of each kettle, providing an accurate data basis for subsequent electricity consumption pattern analysis and anomaly detection. By adding timestamp marks to the key data of electricity consumption parameters, each electricity consumption parameter is associated with its corresponding time to form electricity consumption parameter-time data. This can establish time series data, facilitating subsequent time-related analysis and pattern detection. By analyzing and detecting patterns in the electricity consumption parameter-time data, the daily repeated electricity consumption pattern of the intelligent kettle can be discovered. This includes the daily electricity consumption time period, the variation law of electricity consumption, etc. By understanding the user's daily electricity consumption habits and patterns, it can provide a reference for subsequent electricity consumption prediction and optimization. By detecting anomalies in the electricity consumption parameter-time data, abnormal electricity consumption patterns of the intelligent kettle can be discovered, such as abnormally high electricity consumption, abnormally long heating time, etc. This helps to promptly identify and solve abnormal electricity consumption situations of the kettle, improving electricity consumption safety and efficiency. By analyzing and gaining insights into the daily repeated electricity consumption pattern data and abnormal electricity consumption pattern data, the user's usage behavior pattern can be understood. This includes the user's electricity consumption habits, water usage frequency, changes in water consumption, etc. By deeply understanding the user behavior pattern, it can provide a basis for the optimized design and personalized recommendation of the intelligent kettle.

[0057] Preferably, step S16 includes the following steps:

[0058] Step S161: Import the daily repeated electricity consumption pattern data and abnormal electricity consumption pattern data into a preset metadata relationship modeling platform based on deep learning, and use a variational autoencoder to perform dimensionality reduction and compression on the daily repeated electricity consumption pattern data and abnormal electricity consumption pattern data, so as to obtain potential data of electricity consumption behavior modes and potential data of abnormal electricity consumption patterns;

[0059] Specifically, for example, a metadata structure definition that meets the requirements can be designed according to the field attributes of daily repetition pattern data and abnormal data; a relational database based on the structure can be developed using a deep learning library to support efficient storage and query access; a relationship modeling framework based on a knowledge graph can be designed on the database to support the detailed description of the relationships between tuples; common deep learning model components can be integrated to build an open model development platform; the daily repetition data and abnormal data can be imported into the previously constructed database platform in the designed structure format. The daily repetition power consumption pattern data and power consumption abnormal pattern data are imported into the platform for subsequent model training and analysis. The variational autoencoder (VAE) is used as a dimensionality reduction and compression model to perform dimensionality reduction on the daily repetition power consumption pattern data and power consumption abnormal pattern data. The VAE model is built in the platform, and the daily repetition power consumption pattern data and power consumption abnormal pattern data are used as the training set for model training. After training, the trained VAE model is used to perform dimensionality reduction and compression on the daily repetition power consumption pattern data and power consumption abnormal pattern data to obtain power consumption behavior modal latent data and power consumption abnormal pattern latent data.

[0060] Step S162: Extract the spatio-temporal interaction kernel of the power consumption behavior modal latent data and the power consumption abnormal pattern latent data to obtain the power consumption behavior spatio-temporal interaction kernel data;

[0061] Specifically, for example, based on the method of spatio-temporal interaction kernel, such as the Graph Convolutional Network (GCN), the spatio-temporal interaction kernel between the power consumption behavior modal latent data and the power consumption abnormal pattern latent data can be extracted. The corresponding GCN model is built in the metadata relationship modeling platform based on deep learning, and the power consumption behavior modal latent data and the power consumption abnormal pattern latent data are used as inputs for training. After training, the trained GCN model is used to extract the spatio-temporal interaction kernel of the power consumption behavior modal latent data and the power consumption abnormal pattern latent data to obtain the power consumption behavior spatio-temporal interaction kernel data.

[0062] Step S163: Establish a spatio-temporal adjacency graph of the data correlation based on the power consumption behavior spatio-temporal interaction kernel data to obtain the power consumption behavior spatio-temporal adjacency graph data;

[0063] Specifically, for example, a spatio-temporal adjacency graph of electricity consumption behavior can be constructed based on the correlation between data. During the graph construction process, relevant algorithms in graph theory, such as the nearest neighbor algorithm or the k-nearest neighbor algorithm, can be used to determine the correlation between nodes. The spatio-temporal interaction kernel data of electricity consumption behavior is transformed into the nodes and edges of the graph, where the nodes represent the potential data of electricity consumption behavior modes or the potential data of abnormal electricity consumption patterns, and the edges represent the correlation between them. A complete spatio-temporal adjacency graph of electricity consumption behavior is established and saved as a data structure for subsequent analysis and application.

[0064] Step S164: Identify and locate the hotspots of the user's electricity consumption behavior in the spatio-temporal adjacency graph data of electricity consumption behavior based on the attention mechanism, so as to obtain the emotional nodes of electricity consumption behavior;

[0065] Specifically, for example, an attention mechanism, such as a Graph Attention Network (GAT), can be used to analyze the spatio-temporal adjacency graph data of electricity consumption behavior to identify the hotspots of the user's electricity consumption behavior. A GAT model is built in the metadata relationship modeling platform based on deep learning and trained using the spatio-temporal adjacency graph data of electricity consumption behavior as input. After training, the trained GAT model is used to identify and locate the hotspots of the user's electricity consumption behavior in the spatio-temporal adjacency graph data of electricity consumption behavior to obtain the emotional nodes of electricity consumption behavior. By analyzing the emotional nodes of electricity consumption behavior, the electricity consumption behavior patterns and preferences of users in different regions can be understood, so as to obtain more in-depth data on the user's usage behavior patterns.

[0066] Step S165: Conduct a virtual experiment on the emotional change of electricity consumption behavior near the emotional nodes of electricity consumption behavior, so as to obtain the emotional change data of electricity consumption behavior;

[0067] Specifically, for example, a suitable method can be selected according to the specific situation for the virtual experiment of emotional changes. For example, the method of event-driven simulation can be adopted to simulate the changes in electricity consumption behavior under different emotional states within a specific time period. According to the research objectives and domain knowledge, specific emotional nodes of electricity consumption behavior are selected for the experiment. The emotional nodes can be specific behavioral events of users or the characteristics of electricity consumption behavior within a specific time period. According to the selected emotional nodes, an emotional change experiment is designed to determine the way and degree of emotional changes. Different emotional states can be set, and their impacts on electricity consumption behavior are simulated. For example, the emotional changes can be simulated by adjusting the usage frequency, electricity consumption, or electricity consumption mode of electrical appliances. The data of emotional changes in electricity consumption behavior are recorded in the virtual experiment. Sensors, simulators, or simulation data generation tools can be used to collect the data. The electricity consumption behavior data near the emotional nodes are recorded, including electricity consumption, electricity consumption mode, electrical appliances, etc. The collected data of emotional changes in electricity consumption behavior are processed and analyzed. Statistical methods, time series analysis, or machine learning methods can be used for data analysis to identify and quantify the emotional changes in electricity consumption behavior.

[0068] Step S166: Based on the data of emotional changes in electricity consumption behavior, perform node semantic enhancement on the spatio-temporal adjacency graph data of electricity consumption behavior and extract the keyword tags of the behavior graph, so as to obtain the semantic data of electricity consumption behavior;

[0069] Specifically, for example, according to the requirements and data sources, the spatio-temporal adjacency graph data of electricity consumption behavior is prepared. This data includes electricity consumption behavior nodes and the relationships between them, which can be represented in the form of a graph. The data of emotional changes in electricity consumption behavior is corresponded to the spatio-temporal adjacency graph data of electricity consumption behavior. The electricity consumption behavior nodes related to the emotional changes are found, and the emotional change data is associated with these nodes. Based on the emotional change data, semantic enhancement is performed on the relevant nodes in the spatio-temporal adjacency graph of electricity consumption behavior. Natural language processing techniques, such as word embedding or pre-trained language models (such as BERT), can be used to convert the emotional change data into semantic representations and then apply them to the relevant nodes. Through text processing techniques, keyword tags are marked for the nodes in the spatio-temporal adjacency graph of electricity consumption behavior. Methods such as word frequency statistics, TF-IDF, and text classification models can be used to identify the keyword tags, so as to extract the semantic information of electricity consumption behavior.

[0070] Step S167: Perform clustering on the semantic data of electricity consumption behavior for the electricity consumption behavior patterns, so as to obtain the user usage behavior pattern data.

[0071] Specifically, for example, the electricity consumption behavior semantic data can be prepared to ensure that the data format is suitable for clustering analysis. The semantic data can be represented in vector form, such as word vectors or document vectors. Select a suitable clustering algorithm according to the specific situation. Commonly used clustering algorithms include K-means, hierarchical clustering, DBSCAN, etc. Select an algorithm suitable for processing semantic data, considering its adaptability to high-dimensional data and text data. Select appropriate features for clustering according to the requirements of the clustering algorithm. Feature selection methods, such as correlation analysis, information gain, etc., can be used to select the most representative and discriminative features. Use the selected clustering algorithm to perform clustering analysis on the electricity consumption behavior semantic data. Set the corresponding parameters according to the requirements of the algorithm, such as the number of clusters, distance metric, etc. Analyze the clustering results and interpret the user usage behavior patterns represented by each cluster. Visualization methods, such as the center points of the clusters, similarity matrices between the clusters, etc., can be used to help understand and interpret the clustering results. According to the clustering results, divide the electricity consumption behavior semantic data of each user into the corresponding clusters, so as to obtain the user usage behavior pattern data.

[0072] The present invention performs dimensionality reduction and compression on power consumption data through a deep learning platform, and extracts potential data of power consumption behavior modes and potential data of power consumption abnormal modes. Doing so can reduce the dimension of the data, extract the key features in the data, provide a more efficient data representation for subsequent analysis, and contribute to more accurate modeling and analysis of power consumption behavior. By extracting the spatio-temporal interaction kernels of the potential data of power consumption behavior modes and the potential data of power consumption abnormal modes, the correlation of power consumption behavior data in space and time can be captured. This helps to discover the spatio-temporal interaction patterns between power consumption behaviors, such as similar behavior patterns between different users, and behavior changes between different time periods. These spatio-temporal interaction kernel data provide more detailed information for subsequent analysis. By establishing an adjacency graph of the spatio-temporal interaction kernel data of power consumption behavior, a relationship network between power consumption behaviors can be constructed. This adjacency graph can help analyze the behavior similarity between users, the behavior hot spots, and the propagation and evolution patterns of behaviors. This correlation spatio-temporal adjacency graph data provides a more comprehensive perspective for subsequent analysis and can be used to discover more complex behavior patterns. By applying an attention mechanism to analyze the spatio-temporal adjacency graph data of power consumption behavior, the hot spots of users' power consumption behavior can be identified and located. This helps to discover the important areas and key behavior nodes where users use the kettle, so as to better understand the users' power consumption emotions and preferences. These power consumption behavior emotion nodes provide more emotionally colored data for subsequent analysis, making the understanding of users' behavior more detailed and comprehensive. By conducting virtual experiments on emotional changes near the power consumption behavior emotion nodes, the changes in users' power consumption behavior under different emotional states can be simulated and observed. This helps to understand the impact of users' emotions on power consumption behavior and provides deeper insights for subsequent behavior pattern analysis and personalized recommendations. These power consumption behavior emotion change data provide more information in terms of emotional dimensions for subsequent analysis. By performing node semantic enhancement on the spatio-temporal adjacency graph data of power consumption behavior according to the power consumption behavior emotion change data, more specific semantic information can be assigned to each node. At the same time, by extracting the keyword tags of the behavior graph, the semantic data of power consumption behavior can be obtained. This helps to better understand the users' behavior patterns, identify key behavior features, and provide a more accurate basis for personalized recommendations and behavior pattern analysis. These power consumption behavior semantic data provide more semantic and interpretable data for subsequent analysis. By performing clustering analysis on the power consumption behavior semantic data, similar power consumption behaviors can be classified into the same category, thereby obtaining the user usage behavior pattern data. This helps to discover the differences and similarities in behavior patterns between different users and provides a basis for personalized recommendations, user profiling, and behavior prediction. Through behavior pattern clustering, different user groups and their specific power consumption behavior habits can be identified, thus providing a more targeted solution for the power consumption analysis and personalized recommendations of intelligent kettles.

[0073] Preferably, step S2 includes the following steps:

[0074] Step S21: Perform co-frequency relative time delay analysis on the historical electric kettle power consumption log data to obtain co-frequency relative time delay data;

[0075] Specifically, for example, for the power consumption log data at the same frequency, the relative time delay can be calculated. Methods such as cross-correlation function or cross-correlation function can be used to calculate the relative time delay by comparing the similarity between the power consumption log data at different time points. Denoise and smooth the calculated relative time delay data to eliminate noise and mutations. Signal processing methods such as moving average, median filtering or other methods can be used to smooth the data. Save the processed co-frequency relative time delay data as a data set for use in subsequent steps.

[0076] Step S22: Resample the historical electric kettle power consumption log data according to the co-frequency relative time delay data to obtain a synchronized power consumption log time series signal;

[0077] Specifically, for example, the historical electric kettle power consumption log data can be resampled according to the co-frequency relative time delay data. Adjust the timestamps according to the relative time delay values to align the power consumption log data points in time. Select a suitable resampling method according to the requirements and data characteristics. Methods such as linear interpolation, nearest neighbor interpolation or interpolation methods based on statistical models can be used for resampling. Denoise and handle outliers for the resampled data. Smooth filters, outlier detection or other data processing methods can be used to optimize the data quality. Save the processed synchronized power consumption log time series signal data as a data set for use in subsequent steps.

[0078] Step S23: Perform multi-level wavelet decomposition on the synchronized power consumption log time series signal to obtain the decomposed feature matrix data of the power sub-bands;

[0079] Specifically, for example, according to the data characteristics and analysis purposes, a suitable wavelet basis function can be selected. Commonly used wavelet basis functions include Daubechies wavelet, Symlet wavelet, Haar wavelet, etc. Perform multi-level wavelet decomposition on the synchronized power consumption log time series signal. By iteratively performing low-pass filtering and high-pass filtering on the signal, the signal is decomposed into sub-bands of different frequencies. Extract feature coefficients from each decomposed sub-band. Different feature extraction methods can be selected, such as amplitude, energy, frequency, etc. Organize the extracted sub-band feature coefficients into a feature matrix by level and frequency band. Each row represents a time point, and each column represents the feature coefficients of a sub-band. Save the constructed decomposed feature matrix data of the power sub-bands for use in subsequent steps.

[0080] Step S24: Extract the quantization values of the waveform features within the sub-bands from the feature matrix data decomposed by the electronic band, so as to obtain the waveform feature data of the power consumption pattern;

[0081] Specifically, for example, feature extraction can be performed on the waveforms within each sub-band. Various signal processing and feature extraction methods can be used, such as Fourier transform, time-domain statistical features, frequency-domain features, etc. According to the selected feature extraction method, calculate the quantization values of the waveform features within each sub-band. For example, the mean, variance, peak value, etc. within each sub-band can be calculated. Combine the extracted quantization values of the waveform features within the sub-bands to construct the waveform feature data of the power consumption pattern. Each time point corresponds to a feature vector, which contains the feature quantization values of each sub-band. Save the constructed waveform feature data of the power consumption pattern for subsequent analysis and application.

[0082] Step S25: Conduct time-frequency feature integration analysis on the waveform feature data of the power consumption pattern, so as to obtain the time-frequency feature data of the power consumption pattern;

[0083] Specifically, for example, time-frequency features can be extracted from the waveform feature data of the power consumption pattern. Time-frequency analysis methods can be used, such as short-time Fourier transform (STFT), wavelet transform (WT), etc. These methods can display the energy distribution of the signal at different times and frequencies with time as the horizontal axis and frequency as the vertical axis. Integrate the extracted time-frequency features into the time-frequency feature data of the power consumption pattern. Statistical methods can be adopted, such as calculating indicators such as the average energy and maximum energy within each time period, to describe the characteristics of the power consumption pattern at different times and frequencies. Save the integrated time-frequency feature data of the power consumption pattern as a data set for use in subsequent steps.

[0084] Step S26: Conduct fundamental wave type clustering on the time-frequency feature data of the power consumption pattern, so as to obtain the fundamental wave type data of the power consumption;

[0085] Specifically, for example, a suitable clustering algorithm can be selected to perform clustering analysis on the time-frequency feature data of the power consumption pattern. Commonly used clustering algorithms include K-means clustering, hierarchical clustering, DBSCAN, etc. Standardize the time-frequency feature data of the power consumption pattern to eliminate the dimensional differences between different features. Commonly used standardization methods include Z-score standardization, maximum-minimum standardization, etc. Use the selected clustering algorithm to perform clustering analysis on the standardized time-frequency feature data of the power consumption pattern. Set the number of clusters according to the requirements of the algorithm, and divide the power consumption pattern into different fundamental wave types, where the fundamental wave type data of the power consumption includes multiple types of fundamental waves.

[0086] Step S27: Define the time boundaries for each type of fundamental wave in the power consumption fundamental wave type data to obtain the fundamental wave time boundary data; count the frequencies of each fundamental wave on different time axes according to the fundamental wave time boundary data to obtain the power consumption fundamental wave pattern eigenvalue matrix; integrate the power consumption fundamental wave pattern eigenvalue matrix to obtain the power consumption pattern feature data;

[0087] Specifically, for example, the time boundaries of the power consumption pattern for each fundamental wave type can be defined. Methods such as the threshold method and edge detection can be used to find the start and end time points of the fundamental wave pattern. According to the fundamental wave time boundary data, the frequencies of each fundamental wave on different time axes are counted. The number of occurrences of each fundamental wave type in each time period is counted. The frequency statistics results are integrated into the power consumption fundamental wave pattern eigenvalue matrix. The rows of the matrix represent different fundamental wave types, the columns represent different time periods, and the matrix elements represent the frequencies of the corresponding fundamental wave types in the corresponding time periods. To integrate the power consumption fundamental wave pattern eigenvalue matrix, feature extraction methods such as principal component analysis (PCA) can be used to reduce the feature dimension and retain the main information.

[0088] Step S28: Calculate the range of executable parameters for the kettle battery of the intelligent kettle according to the user usage behavior pattern data and the power consumption pattern feature data to obtain the battery executable parameter range data.

[0089] Specifically, for example, features can be extracted from the user usage behavior pattern data, which can include the average value, maximum value, minimum value, etc. of the boiling time, the average value, standard deviation, etc. of the kettle capacity, and the frequency distribution of the heating temperature. The extracted features are matched with the power consumption pattern feature data to find the power consumption pattern similar to the user usage behavior pattern. According to the matched power consumption pattern, combined with the range of executable parameters of the battery, the range of executable parameters of the battery of the intelligent kettle is calculated. Methods such as rule engines and decision trees can be used for the calculation.

[0090] Through the analysis of the relative time delay at the same frequency, the present invention can obtain the relative time delay data at the same frequency in the historical electricity consumption log data of the kettle. This helps to understand the time differences between different electricity consumption behaviors at the same frequency, and further reveals the time characteristics of the intelligent kettle under different electricity consumption modes. By resampling the time series, a synchronized electricity consumption log time series signal can be obtained. This helps to unify the time intervals of the historical electricity consumption log data of the kettle, making the data more regular and comparable, and thus providing a basis for subsequent analysis. Through multi-level wavelet decomposition, the synchronized electricity consumption log time series signal can be decomposed into characteristic matrix data of different frequency sub-bands. This helps to extract the electricity consumption behavior characteristics in different frequency ranges, including the fundamental wave characteristics and harmonic characteristics of the intelligent kettle, etc., so as to better understand the electricity consumption mode of the intelligent kettle. By extracting the quantization values of the waveform characteristics within the sub-band, the waveform characteristic data of the electricity consumption mode can be obtained. This helps to analyze the waveform shape, amplitude change and other characteristics of the electricity consumption behavior of the intelligent kettle, and further understand the electricity consumption mode of the intelligent kettle. Through the integrated analysis of time-frequency characteristics, the waveform characteristic data of the electricity consumption mode can be transformed into time-frequency characteristic data. This helps to reveal the change laws of the electricity consumption behavior of the intelligent kettle at different times and frequencies, including instantaneous changes, continuous changes and frequency characteristics, etc., so as to more comprehensively understand the electricity consumption mode of the intelligent kettle. Through fundamental wave type clustering, the time-frequency characteristic data of the electricity consumption mode can be classified into different fundamental wave types. This helps to identify and extract the main fundamental wave types in the electricity consumption behavior, so as to better understand the basic characteristics and patterns of the electricity consumption behavior. Through the time boundary delimitation and frequency statistics of the fundamental wave, a characteristic value matrix of the electricity consumption fundamental wave mode and electricity consumption mode characteristic data can be obtained. This helps to conduct a detailed analysis and modeling of the electricity consumption behaviors of different fundamental wave types, and further reveals the pattern characteristics and statistical laws of the electricity consumption behavior. Through the user usage behavior pattern data and the electricity consumption mode characteristic data, the battery executable parameter range of the intelligent kettle can be calculated. This helps to evaluate the battery usage of the intelligent kettle, predict the battery life and optimize the battery management strategy, so as to provide a better user experience and performance management.

[0091] Preferably, step S28 includes the following steps:

[0092] Step S281: Conduct behavior sequence mining on the user usage behavior pattern data to obtain user water usage characteristic data;

[0093] Specifically, for example, sequence mining algorithms such as Sequential Pattern Mining and Sequence Clustering can be used to analyze the user usage behavior pattern data and find the frequent behavior sequences therein. According to the mined frequent behavior sequences, user water usage characteristic data is extracted. It can include common water usage patterns, water usage habits, etc.

[0094] Step S282: Conduct power consumption performance analysis on the power consumption mode feature data to obtain the kettle power consumption feature data;

[0095] Specifically, for example, performance analysis can be conducted on the power consumption mode feature data. Statistical methods can be used, such as calculating indicators like average power consumption, range of power consumption variation, power factor, etc., to describe the power consumption characteristics of the kettle.

[0096] Step S283: Perform energy consumption prediction calculation on the intelligent kettle based on the user water usage feature data and the kettle power consumption feature data to obtain the kettle battery energy consumption range data;

[0097] Specifically, for example, the user water usage feature data and the kettle power consumption feature data can be prepared in a format suitable for calculation, such as converting the feature data into the form of a matrix or vector. Based on the prepared data, an energy consumption prediction model can be established. Machine learning methods can be used, such as linear regression, decision tree, neural network, etc., or a physical model can be used for prediction calculation. Using the established energy consumption prediction model, perform prediction calculation of energy consumption for different user water usage feature data and kettle power consumption feature data. The predicted energy consumption values can be obtained. Save the calculated energy consumption range data as a data set or result file, recording the energy consumption range corresponding to each user water usage feature data and kettle power consumption feature data.

[0098] Step S284: Obtain the charge-discharge characteristic data of the kettle battery and the battery usage duration data;

[0099] Specifically, for example, the charge-discharge characteristic data of the battery can be obtained by conducting experiments or monitoring on the intelligent kettle battery. Professional battery test equipment or sensors can be used for data acquisition, recording information such as voltage, current, capacity, etc. of the battery in different charge-discharge states. Build a timing or recording function in the intelligent kettle to record the duration of each use of the kettle. Or estimate the duration of each use of the kettle through user usage behavior data analysis, and conduct statistics on the collected usage duration data to obtain the used duration of the kettle throughout its life cycle. Organize and save the collected battery charge-discharge characteristic data and battery usage duration data, which can be stored in a database or data file for use in subsequent steps.

[0100] Step S285: Evaluate the life of the intelligent kettle battery based on the charge-discharge characteristic data of the kettle battery and the battery usage duration data to obtain the kettle battery life data;

[0101] Specifically, for example, the charge and discharge characteristic data and battery usage duration data of the kettle battery can be prepared in a format suitable for life assessment, such as converting the data into the form of a matrix or a vector. Based on the prepared data, a life assessment model for the kettle battery is established. Machine learning methods, such as Survival Analysis, Regression Analysis, etc., can be used, or statistical methods can be used for life prediction. The established life assessment model is used to calculate the life of the kettle battery. Based on the charge and discharge characteristic data and usage duration data of the battery, the life of the battery is predicted.

[0102] Step S286: Optimize the intelligent parameters of the intelligent kettle battery according to the kettle battery energy consumption range data and the kettle battery life data, so as to obtain the battery executable parameter range data.

[0103] Specifically, for example, the kettle battery energy consumption range data and battery life data can be prepared in a format suitable for parameter optimization. Select a suitable parameter optimization algorithm, such as Genetic Algorithm, Particle Swarm Optimization, etc. These algorithms can search for the optimal battery parameter combination according to the preset objective function and constraint conditions. Apply the selected optimization algorithm to the kettle battery energy consumption range data and life data, and find the optimal executable parameter range of the battery through iterative optimization.

[0104] The present invention can obtain user water consumption characteristic data by mining user usage behavior pattern data through behavior sequences. This helps to understand the user's usage habits, frequencies, and water consumption patterns, thereby providing a basis for the power consumption analysis of the intelligent kettle. By understanding the user water consumption characteristic data, the power consumption behavior of the intelligent kettle can be better understood, and a basis can be provided for subsequent energy consumption prediction and battery management. By performing power consumption performance analysis on the power consumption pattern characteristic data, kettle power consumption characteristic data can be obtained. This helps to deeply understand the power consumption behavior and its performance of the intelligent kettle, including characteristics such as power consumption, efficiency, and energy consumption of the power consumption pattern. By understanding the kettle power consumption characteristic data, an important basis can be provided for energy consumption prediction, battery life assessment, and intelligent parameter optimization. By performing energy consumption prediction calculations based on the user water consumption characteristic data and the kettle power consumption characteristic data, the battery energy consumption range data of the intelligent kettle can be obtained. This helps to understand the energy consumption situation of the intelligent kettle under different water consumption behaviors, thereby providing guidance for battery management and performance optimization. By obtaining the kettle battery energy consumption range data, the use and charging strategies of the battery can be better planned to extend the battery life and improve the operating efficiency of the intelligent kettle. By obtaining the kettle battery charge and discharge characteristic data and the battery usage duration data, the performance and usage conditions of the intelligent kettle battery can be understood. This helps to evaluate characteristics such as the health status, capacity attenuation, and charge and discharge efficiency of the battery. By understanding the performance and usage duration of the battery, the battery life can be better understood and the battery management strategy can be optimized. By performing a life assessment on the intelligent kettle battery according to the kettle battery charge and discharge characteristic data and the battery usage duration data, the kettle battery life data can be obtained. This helps to understand the life situation of the intelligent kettle battery, including predicting the remaining battery life, assessing the health of the battery, and determining the timing of battery replacement or maintenance. By obtaining the kettle battery life data, the battery management strategy can be optimized, the battery service life can be extended, and the reliability and durability of the intelligent kettle can be improved. By performing intelligent parameter optimization on the intelligent kettle battery according to the kettle battery energy consumption range data and the kettle battery life data, the executable parameter range data of the battery can be obtained. This helps to determine the optimal parameter configuration of the intelligent kettle battery, including the charging rate, discharge rate, etc. By optimizing the parameter configuration of the battery, the performance and efficiency of the intelligent kettle can be improved, while ensuring the safety and life of the battery.

[0105] Preferably, step S3 includes the following steps:

[0106] Step S31: Obtain user behavior instruction data through a preset mobile application interface;

[0107] Specifically, for example, interfaces can be designed and implemented in the mobile application of the smart kettle to obtain user behavior instruction data. The interfaces can use communication protocols such as RESTful API or WebSocket to transmit the user behavior instruction data to the smart kettle through a network connection. In the mobile application, when the user operates the smart kettle, the user behavior instruction data is transmitted to the smart kettle through the interface. For example, when the user clicks the start button or adjusts the slider for water temperature, the corresponding instruction data is sent to the smart kettle. After receiving the user behavior instruction data, the smart kettle performs data parsing to extract the key information in the instruction, such as starting heating, keeping warm, turning off, adjusting water temperature, etc.

[0108] Step S32: Conduct real-time monitoring of the water level height in the smart kettle to obtain real-time water level data; calculate the volume of the water in the smart kettle based on the real-time water level data to obtain water volume data.

[0109] Specifically, for example, a water level sensor can be installed in the smart kettle to monitor the water level height in real time. The sensor can use technologies such as pressure sensors or ultrasonic sensors to convert the water level height into an electrical signal. The smart kettle obtains the real-time water level data by reading the output signal of the water level sensor. An analog input interface or a digital input interface can be used to read the sensor signal. According to the electrical signal output by the sensor, it is converted into the actual water level height data. This can be achieved by calibrating and calibrating the sensor to correspond the output value of the sensor with the known water level height. Based on the real-time water level data and the geometric shape of the smart kettle, the calculation of the water volume is performed. Geometric formulas or numerical integration methods can be used for the calculation to obtain the water volume data.

[0110] Step S33: Extract the target working state data of the kettle from the user behavior instruction data to obtain the target state data of the kettle.

[0111] Specifically, for example, the received user behavior instruction data can be parsed to extract the key information in the instruction that describes the target working state of the kettle. For example, extract the target temperature, target working mode, etc. from the instruction. According to the extracted target working state information, data processing is performed, such as unit conversion, data range verification, etc., to ensure the accuracy and rationality of the data.

[0112] Step S34: Conduct real-time temperature detection of the water in the smart kettle to obtain real-time water temperature data.

[0113] Specifically, for example, a temperature sensor can be installed in the intelligent kettle to monitor the water temperature in real time. The sensor can adopt technologies such as thermistors, thermocouples, or infrared sensors. The intelligent kettle obtains the real-time temperature data of the water body by reading the output signal of the temperature sensor. An analog input interface or a digital input interface can be used to read the sensor signal. According to the electrical signal output by the sensor, it is converted into the actual temperature value. This can be achieved by calibrating and calibrating the sensor, corresponding the output value of the sensor to the known temperature.

[0114] Step S35: When the kettle target state data is the kettle heat preservation state data, calculate the heat preservation efficiency of the intelligent kettle according to the water volume data and the real-time water temperature data, so as to obtain the optimal heat preservation power data; perform intelligent heat preservation operation on the intelligent kettle according to the optimal heat preservation power data;

[0115] Specifically, for example, the heat preservation efficiency can be calculated according to the water volume data and the real-time water temperature data. Calculations can be performed using the heat conduction equation or a model established based on experimental data. The heat preservation efficiency reflects the rate of change of the water temperature and can be used as a basis for selecting the optimal heat preservation power. According to the heat preservation efficiency and the preset heat preservation time requirement, calculate the optimal heat preservation power. Optimization algorithms such as genetic algorithms or particle swarm algorithms can be used to search for the optimal power value. The goal is to enable the water body to maintain a stable temperature within the heat preservation time. According to the calculated optimal heat preservation power, control the heating element of the intelligent kettle to perform heat preservation operation. PWM can be used to adjust the heating power to achieve precise heat preservation control.

[0116] Step S36: When the kettle target state data is the kettle heating state data, perform a heating power consumption prediction calculation on the intelligent kettle according to the preset water heating target temperature data, water volume data, and real-time water temperature data, so as to obtain the power consumption prediction data; perform a heating time prediction on the intelligent kettle according to the power consumption prediction data, so as to obtain the heating time prediction data.

[0117] Specifically, for example, the predicted heating power consumption can be calculated according to the preset water heating target temperature, water volume data, and real-time water temperature data. Calculations can be performed using the relationship between heat capacity, heating power, and heating time. The predicted power consumption can be used as a basis for selecting the heating time. According to the power consumption prediction data and the preset heating power, calculate the predicted heating time. By dividing the predicted power consumption by the heating power, the time required for heating is obtained. This time can be used as a basis for controlling the heating operation. According to the predicted heating time, control the heating element of the intelligent kettle to perform the heating operation. Functions such as a timer or a countdown timer can be used to precisely control the execution of the heating time.

[0118] By obtaining user behavior instruction data, the present invention can understand the operation intention and requirements of users. This helps the intelligent kettle to perform corresponding operations according to user instructions and provide a personalized user experience. Through real-time water level data and volume calculation, the volume data of the water body in the intelligent kettle can be accurately obtained. This helps to understand the water consumption and provides an important basis for subsequent calculation of heat preservation efficiency and prediction of heating power consumption. By extracting the target working state from the user behavior instruction data, the target state of the intelligent kettle can be determined. This helps the intelligent kettle to perform corresponding operations according to user needs, such as heat preservation or heating. Through real-time temperature detection, the real-time temperature data of the water body in the intelligent kettle can be obtained. This helps to understand the temperature change of the water body and provides necessary information for calculation of heat preservation efficiency and prediction of heating power consumption. By calculating the heat preservation efficiency, the optimal heat preservation power of the intelligent kettle in the heat preservation state can be determined. This helps the intelligent kettle to adjust the heat preservation power according to the volume and real-time temperature of the water body to achieve the best heat preservation effect, extend the heat preservation time, and save energy consumption. By calculating the prediction of heating power consumption, the power consumption of the intelligent kettle in the heating state can be estimated. This helps users to understand the energy consumption during the heating process and reasonably arrange electricity consumption according to the predicted power consumption data. By predicting the heating time, the required heating time can be estimated, providing reference for the convenience of users' usage planning.

[0119] Preferably, in step S36, according to the preset target water heating temperature data, water volume data, and real-time water temperature data, the intelligent kettle is calculated for the prediction of heating power consumption through the heating power consumption prediction calculation formula, and the heating power consumption prediction calculation formula is as follows:

[0120]

[0121] In the formula, Q is the predicted power consumption data, T 1 is the target water heating temperature data, T 0 is the real-time water temperature data, m is the water mass data, c p is the specific heat capacity of water, T is the surface temperature of the kettle, η is the heating efficiency of the intelligent kettle, P is the rated power of the intelligent kettle, V is the water volume data, ρ is the density of water, g is the acceleration of gravity, h is the height of the kettle, t is the predicted heating time data, k is the heat conduction coefficient of the kettle, A is the surface area of the kettle, T a is the ambient temperature of the kettle.

[0122] The present invention constructs a heating power consumption prediction calculation formula. In this formula, through Represents the electrical energy required to heat the water body, which is the main part of the power consumption prediction data. It can be calculated based on the mass, specific heat capacity, initial temperature, and target temperature of the water body. This can help users understand the energy consumption of heating the water body, so as to select an appropriate target temperature and save electricity. By Represents the electrical energy required to lift the water body to a certain height, which is the secondary part of the power consumption prediction data. It can be calculated based on the volume, density, acceleration due to gravity, and height of the kettle of the water body. This can help users understand the energy consumption of lifting the water body to a certain height, so as to select an appropriate water volume and avoid wasting electricity. By Represents the electrical energy lost due to heat dissipation of the kettle, which is the auxiliary part of the power consumption prediction data. It can be calculated based on the heat conduction coefficient, surface area, surface temperature, ambient temperature, and heating time of the kettle. This can help users understand the energy loss due to heat dissipation of the kettle, so as to select an appropriate kettle material and shape and reduce electricity consumption. This formula can help users predict the power consumption and heating time of the intelligent kettle, so as to reasonably arrange the water and electricity usage plans, saving energy and time; this formula relates the power consumption and heating time of the kettle to multiple physical parameters, enabling users to adjust the working state of the kettle according to their own needs and preferences, realizing the prediction and control of power consumption.

[0123] Preferably, step S5 includes the following steps:

[0124] Step S51: Obtain the structural parameters of the intelligent kettle;

[0125] Specifically, for example, the structural parameters of the intelligent kettle can be obtained through design documents or product specifications, including but not limited to information such as the height, diameter, and capacity of the kettle.

[0126] Step S52: During the intelligent heating control operation of the intelligent kettle, construct a two-dimensional structural schematic diagram of the intelligent kettle according to the structural parameters of the intelligent kettle to obtain an initial kettle structural schematic diagram; and perform water body annotation on the initial kettle structural schematic diagram according to the real-time water level data to obtain a kettle structural schematic diagram;

[0127] Specifically, for example, according to the structural parameters of the intelligent kettle, drawing software (such as AutoCAD, SketchUp, etc.) or drawing tools can be used to construct a two-dimensional structural schematic diagram of the intelligent kettle. Draw the shape, size, and proportion of the kettle according to the structural parameters, including the bottom, wall surface, lid, etc. of the kettle. According to the real-time water level data, mark the position and height of the water body on the two-dimensional structural schematic diagram. Colors or lines can be used to represent the height of the water level, thus forming a kettle structural schematic diagram.

[0128] Step S53: Use the built-in temperature sensor array of the kettle to obtain the current real-time temperature data of each area of the water body;

[0129] Specifically, for example, a temperature sensor array can be installed inside the intelligent kettle to cover various regions of the water body. The sensor array can include multiple temperature sensors distributed at different positions in the kettle. By reading the output signals of the temperature sensor array, the current real-time temperature data of each region of the water body can be obtained. The signals of the sensor array can be read using an analog input interface or a digital input interface. According to the electrical signals output by the sensor array, they are converted into actual temperature values. This can be achieved by calibrating and calibrating the sensor array to correspond the sensor output values with known temperatures.

[0130] Step S54: Perform temperature zoning on the water body in the intelligent kettle according to the current real-time temperature data of each region of the water body, so as to obtain the water body temperature zoning; perform temperature labeling on the water body in the intelligent kettle according to the water body temperature zoning data, so as to obtain the water body temperature label data;

[0131] Specifically, for example, according to the real-time temperature data obtained by the temperature sensor array built into the kettle, the water body can be divided into multiple temperature regions. Thresholds or algorithm-based methods can be used to determine the temperature zoning. For example, the water body can be divided into a cold zone, a warm zone, and a hot zone. According to the results of the temperature zoning, the temperature of each region is labeled on the schematic diagram of the kettle structure. Different colors, numbers, or other symbols can be used to represent the temperature of each region. For example, different colors are used to represent the cold zone, the warm zone, and the hot zone, or the temperature value is labeled inside each region.

[0132] Step S55: Perform customized rendering on the water body in the schematic diagram of the kettle structure according to the water body temperature label data and the preset temperature-color mapping rule, so as to obtain the static thermal field map of the kettle; call the data obtained by the temperature sensor array built into the kettle in real time, and perform dynamic update rendering on the static thermal field map of the kettle at regular intervals, so as to obtain the running thermal field mapping atlas of the kettle.

[0133] Specifically, for example, a preset temperature-color mapping rule can be defined to map temperature values to corresponding colors. For example, map the low-temperature region to blue, the medium-temperature region to green, and the high-temperature region to red. According to the water body temperature label data and the temperature-color mapping rule, perform customized rendering on the water body in the schematic diagram of the kettle structure. Map each region to the corresponding color according to the temperature value, and rendering can be achieved using drawing software or a graphics processing library. Call the data obtained by the temperature sensor array built into the kettle in real time, and perform dynamic update rendering on the static thermal field map of the kettle at regular intervals. By continuously obtaining the latest temperature data and re-rendering the water body color in the schematic diagram of the kettle structure, a dynamic thermal field mapping atlas is realized.

[0134] By obtaining the structural parameters of the intelligent kettle, the physical characteristics and geometric structure of the kettle can be understood, providing the necessary basic information for subsequent steps, such as constructing a schematic diagram of the kettle structure and temperature zoning. By constructing a schematic diagram of the kettle structure and annotating the water body according to the real-time water level data, the structure and water body distribution of the intelligent kettle can be vividly represented. This helps users intuitively understand the composition and water level of the kettle, providing a visual basis for subsequent temperature zoning and temperature annotation. By using the temperature sensor array built into the kettle, the real-time temperature data of each region of the water body can be obtained. This helps to monitor the temperature change of the water body in real time and provides accurate data support for subsequent temperature zoning and temperature labels. By partitioning and annotating the real-time temperature data of the water body, the water body can be divided into different temperature regions and corresponding temperature labels can be assigned to each region. By partitioning and annotating the temperature of the water body, the power consumption analysis method can more carefully understand the temperature distribution inside the kettle. This helps to evaluate the heating efficiency, heat loss situation and energy consumption contribution of different temperature regions of the kettle, providing more accurate data basis for power consumption analysis. This helps users intuitively understand the temperature distribution of the water body and provides the necessary data basis for subsequent heat field map rendering and heat field mapping. By combining the water body temperature label with the preset temperature-color mapping rule, the water body in the kettle structure schematic diagram can be customized and rendered to form a static heat field map. This helps users intuitively understand the heat distribution of the water body, and then understand the heating effect and heat loss situation of the kettle. At the same time, by real-time calling data and timed dynamic update rendering, the running heat field mapping atlas of the kettle can be displayed in real time, providing more intuitive heat field change information.

[0135] Preferably, step S6 includes the following steps:

[0136] Step S61: Obtain the actual heating duration data of the kettle;

[0137] Specifically, for example, the built-in heating time sensor of the intelligent kettle or related sensor technologies can be used to collect the actual heating duration data of the kettle in real time. The collected actual heating duration data can be recorded and stored, and a database or file system can be used to save the data.

[0138] Step S62: Conduct error analysis on the heating time prediction data and the actual heating duration data of the kettle to obtain the heating time error data;

[0139] Specifically, for example, an appropriate algorithm or model can be used to predict the heating time based on the characteristics of the kettle and the heating parameters. For example, machine learning algorithms such as linear regression, decision tree, or neural network can be used. Compare the predicted heating time with the actual heating duration data and calculate the error between them. Common error metrics such as root mean square error (RMSE) or mean absolute error (MAE) can be used to evaluate the accuracy of the prediction.

[0140] Step S63: Analyze the power utilization efficiency of the intelligent kettle based on the complete power consumption data of the kettle and the power prediction data, so as to obtain the power utilization rate data;

[0141] Specifically, for example, the actual power consumption can be compared with the predicted power consumption to calculate the power utilization efficiency. Generally, the power utilization efficiency can be calculated by the ratio of the actual power consumption to the predicted power consumption.

[0142] Step S64: When the predicted heating time data is greater than the actual heating duration data of the kettle, conduct an analysis of excessive energy consumption on the power utilization rate data, so as to obtain the power consumption analysis data;

[0143] Specifically, for example, the difference between the predicted heating time data and the actual heating duration data can be calculated. If the predicted time is greater than the actual time, it indicates that there is excessive energy consumption. According to the power utilization rate data and the time difference of excessive energy consumption, the corresponding power consumption data can be calculated.

[0144] Step S65: When the predicted heating time data is less than or equal to the actual heating duration data of the kettle, conduct an analysis of power loss on the power utilization rate data, so as to obtain the power consumption analysis data;

[0145] Specifically, for example, the difference between the predicted heating time data and the actual heating duration data can be calculated. If the predicted time is less than or equal to the actual time, it indicates that there is power loss. According to the power utilization rate data and the time difference of power loss, the corresponding power consumption data can be calculated.

[0146] Step S66: Send the thermal field mapping atlas of the kettle operation and the power consumption analysis data to a preset mobile terminal and visualize them.

[0147] Specifically, for example, the heat field mapping spectrum of the kettle operation and the analysis data of power consumption can be transmitted to a preset mobile device through the network. Network communication protocols such as HTTP or MQTT can be used for data transmission. On the mobile device, the received data is parsed, and the heat field mapping spectrum of the kettle operation and the analysis data of power consumption are extracted. Using a mobile application or visualization tool, the heat field mapping spectrum of the kettle operation is visually displayed. Charts, heat maps, or other visualization methods can be used to present the heat field distribution of the kettle. At the same time, the analysis data of power consumption is displayed in the form of charts or other forms so that users can intuitively understand the energy utilization of the kettle.

[0148] By obtaining the actual heating duration data of the kettle, the heating time situation of the kettle in actual use can be understood. This helps to evaluate the heating efficiency of the kettle in the power consumption analysis method, so as to understand the energy consumption situation and the accuracy of the heating time of the kettle. By performing error analysis on the heating time prediction data and the actual heating duration data of the kettle, the accuracy of the prediction model can be evaluated. This helps to evaluate the reliability of the heating time prediction in the power consumption analysis method, so as to provide more accurate power consumption analysis results. By analyzing the complete current consumption data and power prediction data of the kettle, the power utilization rate of the kettle can be calculated, that is, the ratio of the actual consumed electric energy to the predicted consumed electric energy. This data reflects the energy utilization efficiency of the kettle during the heating process. By evaluating the power utilization rate, the energy utilization efficiency level of the kettle can be understood, thus providing basic data for subsequent steps. When the heating time prediction data is greater than the actual heating duration data, it means that the actual consumed electric energy of the kettle is more than the predicted value. By analyzing the power utilization rate data, the degree of excessive energy consumption can be determined, that is, the difference between the actual consumed electric energy and the predicted consumed electric energy. This data can provide information about the insufficient energy utilization efficiency of the kettle, provide data basis for the subsequent power consumption analysis steps, and help formulate optimization strategies. When the heating time prediction data is less than or equal to the actual heating duration data, it means that the actual consumed electric energy of the kettle is less than or equal to the predicted value. By analyzing the power utilization rate data, the degree of power loss can be determined, that is, the difference between the actual consumed electric energy and the predicted consumed electric energy. This data can provide information about the power loss situation of the kettle, provide data basis for the subsequent power consumption analysis steps, and provide suggestions and optimization strategies for improving the kettle efficiency. By sending the heat field mapping spectrum of the kettle operation and the power consumption analysis data to a preset mobile device and visualizing them, a user-friendly interface and intuitive data display can be provided. This helps users better understand the heat distribution situation of the kettle and the power consumption analysis results, so that users can more effectively manage the energy consumption of the kettle and optimize the power consumption strategy.

[0149] Preferably, the present invention further provides a power consumption analysis system based on an intelligent kettle for performing the power consumption analysis method based on an intelligent kettle as described above. The power consumption analysis system based on an intelligent kettle includes:

[0150] A historical kettle power consumption log collection module for collecting historical kettle power consumption logs of the intelligent kettle to obtain historical kettle power consumption log data; performing user behavior pattern analysis on the historical kettle power consumption log data to obtain user usage behavior pattern data;

[0151] A power consumption pattern mining and analysis module for performing power consumption waveform analysis on the historical kettle power consumption log data to obtain power consumption pattern feature data; calculating the range of executable parameters of the kettle battery for the intelligent kettle according to the user usage behavior pattern data and the power consumption pattern feature data to obtain battery executable parameter range data;

[0152] A real-time monitoring and prediction module for obtaining user behavior instruction data; performing real-time monitoring of the water level height sensing in the water body of the intelligent kettle to obtain real-time water level data; predicting the power consumption and heating time of the intelligent kettle according to the user behavior instruction data and the real-time water level data to obtain power consumption prediction data and heating time prediction data;

[0153] A heating control tracking module for performing intelligent heating control operations on the intelligent kettle according to the battery executable parameter range data and the user behavior instruction data, and performing real-time tracking of the current consumption of the heating component of the intelligent kettle during the heating control operation to obtain complete kettle current consumption data;

[0154] A thermal field visualization module for constructing a two-dimensional structure schematic diagram of the intelligent kettle during the intelligent heating control operation of the intelligent kettle to obtain a kettle structure schematic diagram; obtaining current real-time temperature data of each area of the water body; performing dynamic color rendering on the water body in the kettle structure schematic diagram according to the current real-time temperature data of each area of the water body to obtain a kettle operation thermal field mapping diagram;

[0155] A power consumption analysis module for performing power consumption analysis on the intelligent kettle according to the complete kettle current consumption data, the power consumption prediction data, and the heating time prediction data to obtain power consumption analysis data; sending the kettle operation thermal field mapping diagram and the power consumption analysis data to a preset mobile terminal for visualization.

[0156] By collecting the historical power consumption log data of the intelligent kettle, the present invention can obtain the user's past power consumption behaviors and habits, providing a basis for subsequent user behavior pattern analysis and power consumption analysis. By analyzing the historical kettle power consumption log data, the user's usage behavior pattern data can be obtained. This helps to understand information such as the user's water usage habits, water usage frequency, and water consumption, and then provide personalized energy management suggestions and optimization strategies. By performing an analysis of the power waveform of the historical kettle power consumption log data, characteristic data of the power consumption pattern can be obtained. These characteristic data can reveal the user's power consumption pattern and behavior rules, providing a basis for calculating the battery executable parameter range and predicting the real-time power consumption of the intelligent kettle. By continuously monitoring the water level height in the intelligent kettle and combining it with the user behavior instruction data, the power consumption and heating time of the intelligent kettle can be predicted. This enables the user to understand the hot water supply situation in advance, improving the user experience, and corresponding energy-saving adjustments can be made according to the predicted data. By analyzing the battery executable parameter range data and the user behavior instruction data, intelligent heating control operations can be realized. At the same time, by continuously tracking the current consumption of the intelligent kettle, complete current consumption data of the kettle can be obtained, thereby evaluating and optimizing the energy utilization of the intelligent kettle. By constructing a two-dimensional structural schematic diagram of the intelligent kettle and performing dynamic color rendering based on the real-time temperature data, visualization of the kettle operation thermal field mapping atlas can be achieved. This helps the user to intuitively understand the temperature distribution in different areas of the kettle, and then adjust the water usage and heating strategies to improve energy utilization efficiency. By analyzing the complete kettle current consumption data, power consumption prediction data, and heating time prediction data, power consumption analysis can be carried out. This enables the user to deeply understand the energy consumption of the intelligent kettle, and then make corresponding energy-saving measures and adjustments according to the analysis results to achieve effective utilization and conservation of energy. Sending the kettle operation thermal field mapping atlas and the power consumption analysis data to a preset mobile terminal for visualization, the user can intuitively view the operation status and power consumption of the intelligent kettle through a mobile device. This helps to improve the user's awareness of energy utilization and conservation, and encourages the user to participate more actively in and make decisions on energy management.

[0157] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be encompassed within the present invention.

[0158] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can 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 these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A method for analyzing power consumption based on a smart kettle, characterized in that: The following steps are involved: Step S1: collecting historical kettle electricity usage logs for the smart kettle, thereby obtaining historical kettle electricity usage log data; Conduct user behavior pattern analysis on historical kettle electricity usage log data to obtain user usage behavior pattern data; Step S2: Analyze the power consumption waveform of the historical kettle power consumption log data to obtain power consumption pattern characteristic data; Calculate the executable parameter range of the battery of the smart kettle according to the user's usage behavior pattern data and the power usage pattern characteristic data, so as to obtain the executable parameter range data of the battery; Step S3: obtaining user behavior instruction data; performing real-time monitoring of the water level height of the water body in the smart kettle by sensing, thereby obtaining real-time water level data; predicting the power consumption and heating time of the smart kettle according to the user behavior instruction data and the real-time water level data, thereby obtaining power consumption prediction data and heating time prediction data; Step S4: performing intelligent heating control operation on the smart kettle according to the battery executable parameter range data and the user behavior instruction data, and tracking the current consumption of the heating component of the smart kettle in real time during the heating control operation, so as to obtain the complete current consumption data of the kettle; Step S5: constructing a two-dimensional structural diagram of the smart kettle during the smart heating control operation of the smart kettle, thereby obtaining a structural diagram of the kettle; obtaining current real-time temperature data of each zone of the water body; dynamically rendering the water body in the structural diagram of the kettle according to the current real-time temperature data of each zone of the water body, thereby obtaining a thermal field mapping diagram of the kettle operation; Step S6: analyzing the power consumption of the smart kettle according to the complete current consumption data of the kettle, the power consumption prediction data and the heating time prediction data, thereby obtaining power consumption analysis data; The thermal field mapping of the kettle and the power consumption analysis data are sent to the preset mobile terminal and visualized.

2. The method for analyzing power consumption based on a smart kettle according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting historical kettle electricity usage logs for the smart kettle, thereby obtaining historical kettle electricity usage log data; Step S12: extracting the key fields of electricity usage parameters from the historical electricity usage log data of the kettle, thereby obtaining the key data of electricity usage parameters; Step S13: Timestamp the key data of power consumption parameters to obtain power consumption parameter-time data; Step S14: performing daily repetitive power usage pattern detection on the power usage parameter-time data, thereby obtaining daily repetitive power usage pattern data; Step S15: performing power consumption anomaly detection on the power consumption parameter-time data, thereby obtaining power consumption anomaly pattern data; Step S16: Conduct user behavior insights on the daily repeated power usage pattern data and the abnormal power usage pattern data, so as to obtain user usage behavior pattern data.

3. The method for analyzing power consumption based on a smart kettle according to claim 2, characterized in that: Step S16 includes the following steps: Step S161: importing the daily repetitive power consumption pattern data and the power consumption abnormal pattern data into a preset metadata relationship modeling platform based on deep learning, and using a variational autoencoder to reduce the dimension of the daily repetitive power consumption pattern data and the power consumption abnormal pattern data, so as to obtain the power consumption behavior modal potential data and the power consumption abnormal pattern potential data; Step S162: performing spatiotemporal interaction kernel extraction on the power consumption behavior modal potential data and the power consumption abnormal pattern potential data, thereby obtaining the spatiotemporal interaction kernel data of the power consumption behavior; Step S163: establishing a spatiotemporal adjacency graph of data correlation based on the spatiotemporal interaction core data of the electricity consumption behavior, thereby obtaining the spatiotemporal adjacency graph data of the electricity consumption behavior; Step S164: identifying and locating the hotspot areas of user electricity consumption behavior based on the spatiotemporal adjacency graph data of electricity consumption behavior based on the attention mechanism, thereby obtaining the emotion nodes of electricity consumption behavior; Step S165: performing a virtual experiment of power consumption behavior emotion change near the power consumption behavior emotion node, thereby obtaining power consumption behavior emotion change data; Step S166: performing node semantic enhancement on the spatiotemporal adjacency graph data of the electricity consumption behavior according to the emotion change data of the electricity consumption behavior and extracting key word tags of the behavior graph, thereby obtaining semantic data of the electricity consumption behavior; Step S167: clustering the electricity usage behavior patterns on the electricity usage behavior semantic data, thereby obtaining user usage behavior pattern data.

4. The method for analyzing power consumption based on a smart kettle according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing same-frequency relative delay analysis on historical kettle electricity consumption log data, thereby obtaining same-frequency relative delay data; Step S22: resampling the historical kettle electricity consumption log data in time series according to the same frequency relative delay data, thereby obtaining a synchronous electricity consumption log time series signal; Step S23: performing multi-level wavelet decomposition on the synchronous power consumption log time series signal, thereby obtaining power consumption band decomposition feature matrix data; Step S24: extracting the waveform feature quantization value within the sub-band from the power consumption band decomposition feature matrix data, thereby obtaining the power consumption mode waveform feature data; Step S25: performing time-frequency characteristic integration analysis on the power consumption pattern waveform characteristic data, thereby obtaining the power consumption pattern time-frequency characteristic data; Step S26: clustering the power consumption mode time-frequency characteristic data into fundamental wave types, thereby obtaining power consumption fundamental wave type data; Step S27: Delimiting the time boundary of each type of fundamental wave in the power consumption fundamental wave type data, thereby obtaining the fundamental wave time boundary data; counting the frequency of each fundamental wave on different time axes according to the fundamental wave time boundary data, thereby obtaining the power consumption fundamental wave mode eigenvalue matrix; integrating the power consumption fundamental wave mode eigenvalue matrix into a mode characteristic matrix, thereby obtaining the power consumption mode characteristic data; Step S28: Calculate the battery executable parameter range of the smart kettle according to the user's usage behavior pattern data and the power consumption pattern characteristic data, thereby obtaining the battery executable parameter range data.

5. The method for analyzing power consumption based on a smart kettle according to claim 4, characterized in that: Step S28 includes the following steps: Step S281: Performing behavior sequence mining on the user's usage behavior pattern data to obtain the user's water usage characteristic data; Step S282: performing power consumption performance analysis on the power consumption pattern characteristic data, thereby obtaining power consumption characteristic data of the kettle; Step S283: performing energy consumption prediction calculation on the smart kettle according to the user's water consumption characteristic data and the kettle's electricity consumption characteristic data, thereby obtaining kettle battery energy consumption range data; Step S284: Acquire the charging and discharging characteristic data of the kettle battery and the battery usage time data; Step S285: Evaluate the life of the smart kettle battery according to the kettle battery charge and discharge characteristic data and the battery usage time data, thereby obtaining the kettle battery life data; Step S286: Perform intelligent parameter optimization on the smart kettle battery according to the kettle battery energy consumption range data and the kettle battery life data, so as to obtain the battery executable parameter range data.

6. The method for analyzing power consumption based on a smart kettle according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: obtaining user behavior instruction data through a preset mobile terminal application interface; Step S32: performing real-time monitoring of the water level height of the water body in the smart kettle by sensing, thereby obtaining real-time water level data; calculating the volume of the water body in the smart kettle according to the real-time water level data, thereby obtaining water volume data; Step S33: extracting kettle target working state data from the user behavior instruction data, thereby obtaining kettle target state data; Step S34: detecting the real-time temperature of the water body on the smart kettle, thereby obtaining the real-time temperature data of the water body; Step S35: when the kettle target state data is the kettle heat preservation state data, the heat preservation efficiency of the smart kettle is calculated according to the water volume data and the real-time temperature data of the water body, so as to obtain the optimal heat preservation power data; and the smart kettle is subjected to the intelligent heat preservation operation according to the optimal heat preservation power data; Step S36: When the target state data of the kettle is the heating state data of the kettle, the heating power consumption of the smart kettle is predicted and calculated according to the preset water heating target temperature data, water volume data and real-time water temperature data, so as to obtain power consumption prediction data; the heating time of the smart kettle is predicted according to the power consumption prediction data, so as to obtain heating time prediction data.

7. The method for analyzing power consumption based on a smart kettle according to claim 6, characterized in that: In step S36, the heating power consumption of the smart kettle is predicted and calculated according to the preset water body heating target temperature data, water body volume data and water body real-time temperature data through the heating power consumption prediction calculation formula, wherein the heating power consumption prediction calculation formula is as follows: In the formula, Q is the power consumption forecast data, T1 is the water heating target temperature data, T0 is the water real-time temperature data, m is the water quality data, c p is the specific heat capacity of water, T is the surface temperature of the kettle, η is the heating efficiency of the smart kettle, P is the rated power of the smart kettle, V is the water volume data, ρ is the density of water, g is the gravitational acceleration, h is the height of the kettle, t is the predicted heating time data, k is the thermal conductivity coefficient of the kettle, A is the surface area of ​​the kettle, T a is the ambient temperature of the kettle.

8. The method for analyzing power consumption based on a smart kettle according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: obtaining the structural parameters of the smart kettle; Step S52: During the intelligent heating control operation of the intelligent kettle, a two-dimensional structural diagram of the intelligent kettle is constructed according to the structural parameters of the intelligent kettle, thereby obtaining an initial structural diagram of the kettle; and water bodies are marked on the initial structural diagram of the kettle according to the real-time water level data, thereby obtaining a structural diagram of the kettle; Step S53: using the built-in temperature sensor array of the kettle to obtain the current real-time temperature data of each zone of the water body; Step S54: temperature partitioning the water body in the smart kettle according to the current real-time temperature data of each zone of the water body, thereby obtaining the water body temperature partition; temperature labeling the water body in the smart kettle according to the water body temperature partition data, thereby obtaining the water body temperature label data; Step S55: Customize the rendering of the water body in the kettle structure diagram according to the water body temperature label data and the preset temperature-color mapping rules to obtain the static thermal field map of the kettle; call the data obtained by the built-in temperature sensor array of the kettle in real time, and dynamically update and render the static thermal field map of the kettle at regular intervals to obtain the kettle operation thermal field mapping map.

9. The method for analyzing power consumption based on a smart kettle according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: Acquire actual heating time data of the kettle; Step S62: performing error analysis on the heating time prediction data and the actual heating time data of the kettle, thereby obtaining heating time error data; Step S63: analyzing the power utilization efficiency of the smart kettle according to the complete current consumption data of the kettle and the power prediction data, thereby obtaining power utilization rate data; Step S64: when the heating time prediction data is greater than the actual heating time data of the kettle, excess energy consumption analysis is performed on the power utilization rate data, thereby obtaining power consumption analysis data; Step S65: when the heating time prediction data is less than or equal to the actual heating time data of the kettle, performing power loss analysis on the power utilization rate data, thereby obtaining power consumption analysis data; Step S66: Send the kettle operation thermal field mapping graph and power consumption analysis data to a preset mobile terminal and visualize them.

10. A power consumption analysis system based on a smart kettle, characterized in that: Used to perform the power consumption analysis method based on the smart kettle as claimed in claim 1, the power consumption analysis system based on the smart kettle comprises: The historical kettle electricity usage log collection module is used to collect the historical kettle electricity usage log of the smart kettle, so as to obtain the historical kettle electricity usage log data; perform user behavior pattern analysis on the historical kettle electricity usage log data, so as to obtain user usage behavior pattern data; The power consumption pattern mining and analysis module is used to analyze the power consumption waveform of the historical kettle power consumption log data, so as to obtain the power consumption pattern characteristic data; the battery executable parameter range of the smart kettle is calculated based on the user's usage behavior pattern data and the power consumption pattern characteristic data, so as to obtain the battery executable parameter range data; The real-time monitoring and prediction module is used to obtain user behavior instruction data; perform real-time monitoring of the water level height sensor of the water body in the smart kettle, thereby obtaining real-time water level data; predict the power consumption and heating time of the smart kettle according to the user behavior instruction data and the real-time water level data, thereby obtaining power consumption prediction data and heating time prediction data; A heating control tracking module is used to perform intelligent heating control operations on the smart kettle according to the battery executable parameter range data and the user behavior instruction data, and to track the current consumption of the heating component of the smart kettle in real time during the heating control operation, so as to obtain the complete current consumption data of the kettle; The thermal field visualization module is used to construct a two-dimensional structural schematic diagram of the smart kettle during the intelligent heating control operation of the smart kettle, thereby obtaining the kettle structural schematic diagram; obtaining the current real-time temperature data of each area of ​​the water body; dynamically rendering the water body in the kettle structural schematic diagram according to the current real-time temperature data of each area of ​​the water body, thereby obtaining the kettle operation thermal field mapping map; The power consumption analysis module is used to analyze the power consumption of the smart kettle based on the complete current consumption data of the kettle, the power consumption prediction data and the heating time prediction data, so as to obtain the power consumption analysis data; the thermal field mapping map of the kettle operation and the power consumption analysis data are sent to the preset mobile terminal and visualized.

Images