Intelligent humidifier control system

By generating a global humidity distribution map through multiple sensors and an intelligent control module, combined with smart home linkage and data analysis, the problem of traditional humidifiers being unable to accurately adjust humidity has been solved. This enables precise and uniform humidity control and personalized management, improving user comfort and health.

CN118998915APending Publication Date: 2024-11-22QIDI YADU (BEIJING) TECH CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411179761.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional humidifiers cannot accurately regulate indoor humidity, cannot adapt to environmental changes, lack integration with smart home devices, and cannot meet personalized needs.

Method used

A multi-sensor humidity monitoring module generates a global humidity distribution map, which is then dynamically adjusted in conjunction with an intelligent control module. The humidifier is linked with smart home devices, integrating user interaction and personalized settings, and optimizing the humidification strategy through data analysis.

Benefits of technology

It achieves precise and uniform humidity control, improves user comfort and health, meets personalized needs, and optimizes the overall home environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118998915A_ABST
    Figure CN118998915A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent humidifier control system, and belongs to the technical field of intelligent homes. The humidifier control system comprises a multi-sensor humidity monitoring module which collects humidity data of all areas of a room in real time, generates a global humidity distribution diagram and provides basic information for precise humidification; the intelligent control module is used for analyzing the humidity distribution condition, dynamically adjusting the target humidity and the working mode of the humidifier and ensuring uniform and comfortable air humidity; the user interaction and personalized setting module allows a user to set a humidity range, a priority area and operation time through a mobile terminal App or a voice assistant, and records use habits to optimize operation parameters; the intelligent home linkage module realizes cooperative work of the humidifier and other intelligent home equipment and automatically adjusts a humidification strategy to adapt to the overall environment change; and the data analysis module is used for recording and analyzing the humidity change data, providing air quality optimization suggestions and health reports and continuously optimizing the control strategy of the humidifier.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to an intelligent humidifier control system. Background Art

[0002] As people's living standards improve, the impact of indoor air quality on health and comfort has received more and more attention. Humidity, as one of the important factors of air quality, is directly related to the respiratory system, skin health and overall comfort. However, traditional humidifiers usually only provide a single humidification mode, which is difficult to adapt to the dynamic changes of the indoor environment and cannot be accurately adjusted according to the humidity differences in different areas of the room. This leads to uneven humidity control, and some areas may be over-humidified or under-humidified, thereby reducing the user experience.

[0003] There are already some humidifiers with intelligent control functions on the market, which can achieve automatic humidification through sensor feedback. However, these products generally have the following problems: first, they usually only rely on the data of a single point sensor to adjust the humidity, and cannot fully perceive the humidity distribution of the entire room; second, they lack effective linkage with other smart home devices and cannot dynamically adjust the humidification strategy according to changes in the overall home environment; finally, existing smart humidifiers are still insufficient in meeting the personalized needs of users and cannot be continuously optimized according to user preferences and habits.

[0004] Therefore, developing a more accurate and balanced intelligent humidifier control system to improve users' living comfort and health level and meet their personalized needs for indoor air quality has become a technical challenge that needs to be solved urgently. Summary of the invention

[0005] In order to overcome a series of defects in the prior art, the purpose of this application is to provide an intelligent humidifier control system for the above problems, including the following modules:

[0006] The multi-sensor humidity monitoring module collects humidity data from all areas of the room in real time, generates a global humidity distribution map, and provides basic information for precise humidification;

[0007] Intelligent control module analyzes humidity distribution and dynamically adjusts the target humidity and working mode of the humidifier to ensure uniform and comfortable air humidity;

[0008] User interaction and personalization module, which allows users to set humidity range, priority area and operation time through mobile app or voice assistant, and record usage habits to optimize operation parameters;

[0009] Smart home linkage module enables the humidifier to work in coordination with other smart home devices, automatically adjusting the humidification strategy to adapt to overall environmental changes;

[0010] The data analysis module records and analyzes humidity change data, provides air quality optimization suggestions and health reports, and continuously optimizes the humidifier control strategy.

[0011] Furthermore, the multi-sensor humidity monitoring module includes the following components:

[0012] A distributed humidity sensor network is deployed in various areas of the room to collect humidity data in real time;

[0013] The data acquisition unit is responsible for collecting humidity data from the distributed sensor network;

[0014] a spatial positioning unit for determining the precise location of the distributed humidity sensor network in the room;

[0015] The central processing unit is used to receive and process data from the spatial positioning unit and the distributed humidity sensor network to generate a real-time global humidity distribution map.

[0016] Further, generating a real-time global humidity distribution map includes the following steps:

[0017] Converting the sensor position information provided by the spatial positioning unit into standardized three-dimensional coordinates so as to accurately represent the position of each sensor in the virtual space;

[0018] The processed humidity data are associated with the corresponding three-dimensional coordinate information to form discrete data points, and the Kriging method is used for interpolation to generate a continuous humidity distribution field;

[0019] The room space is divided into uniform three-dimensional grids, and the interpolation algorithm is applied to each grid point to calculate its humidity value;

[0020] Based on the calculated grid point humidity values, a three-dimensional humidity distribution map is generated using isosurface technology;

[0021] An incremental update algorithm and cache mechanism are used to recalculate the changed areas to dynamically update the three-dimensional humidity distribution map.

[0022] Furthermore, the room space is divided into uniform three-dimensional grids, and the interpolation algorithm is applied to each grid point to calculate its humidity value, including the following steps:

[0023] Divide the room space into N x ×N y ×N z A uniform grid, where N x 、N y and Nz Represents the number of grids in the x, y and z directions respectively, and the position of each grid point is expressed as (x i ,y j , z k ), where i∈[1, N x ],j∈[1,N y ],k∈[1,N z ];

[0024] The coordinates and humidity values ​​of the humidity measurement points are known to be (x m ,y m , z m ) and H m , where m∈[1,M], M is the number of known humidity measurement points;

[0025] Calculate the grid points (x i ,y j , z k ) humidity value H i,j,k , the formula is: Among them, d i,j,k,m is the grid point (x i ,y j , z k ) and the measuring point (x m ,y m , z m ), the calculation formula is: p is the weight index of the distance;

[0026] All calculated humidity values ​​H i,j,k Form a three-dimensional humidity distribution map.

[0027] Furthermore, the intelligent control module includes the following components:

[0028] The humidity analysis engine performs real-time analysis of the humidity distribution status and dynamic change trends of each area of ​​the room based on the global humidity distribution map;

[0029] The decision optimization algorithm comprehensively considers the humidity analysis results and the preset target parameters to calculate and determine the optimal operating parameters and working mode of the humidifier;

[0030] Execution instruction generator, converting the optimized operation parameters and working mode into specific equipment control instructions and executing them;

[0031] The pattern learning and optimization module learns the changing patterns of room humidity and user preferences through long-term data accumulation, and continuously optimizes the performance of the decision-making optimization algorithm.

[0032] Further, calculating and determining the optimal operating parameters and working mode of the humidifier includes the following steps:

[0033] A multi-objective optimization model is established based on the user's preset target humidity range, comfort preferences, and priorities for specific areas;

[0034] Based on the analysis of the global humidity distribution map, the areas with uneven humidity and dry hot spots are identified, and the room space is divided into several sub-areas requiring different humidification strategies through the threshold segmentation method;

[0035] Based on the technical specifications and historical operating data of the humidifier, a mathematical model is established to describe the performance characteristics of the humidifier in different operating modes;

[0036] Particle swarm optimization algorithm is used to find the best combination of humidifier operating parameters;

[0037] Perform constraint checks on the optimal humidifier operating parameter combination to ensure that all parameters are within the physical limitations and safe operating range of the humidifier;

[0038] Based on the optimization results, the best operating mode of the humidifier is determined and specific operating parameter settings are generated.

[0039] Further, continuously optimizing the performance of the decision optimization algorithm includes the following steps:

[0040] Continuously collect room humidity, humidifier parameters, user settings and feedback data, structure them into time series and store them in an efficient database;

[0041] Clean, standardize and denoise the data in the database, extract humidity change cycles, peak values ​​and trend characteristics through time series analysis and feature engineering, and analyze user behavior data to extract their preferences and usage habits;

[0042] Using time series clustering, we can identify daily and seasonal changes in room humidity and its response to the external environment from long-term data. At the same time, we can reveal the potential relationship between user behavior and environmental changes through association rule mining technology.

[0043] Build a prediction model based on the mined patterns to predict humidity trends and user needs, and continuously improve prediction accuracy through continuous evaluation and tuning;

[0044] Integrate the prediction model and mined rules into the existing decision optimization algorithm to update parameters and strategies;

[0045] Regular comprehensive assessments are conducted based on new data, and decision optimization algorithms are continuously refined to respond to changes in the environment and evolution of user needs.

[0046] Furthermore, the smart home linkage module includes the following components:

[0047] Device identification and connection manager, automatically identifies and manages smart home devices compatible with the humidifier, and establishes and maintains a stable communication connection;

[0048] Multi-protocol data exchange adapter, supporting and converting multiple smart home communication protocols to ensure seamless data interaction between heterogeneous devices;

[0049] Environmental information integrator, which processes and integrates environmental data from other smart devices to provide comprehensive contextual information for dynamic adjustment of humidification strategies;

[0050] Linkage rule engine, which defines, manages and executes complex linkage rules between devices to achieve collaborative operation of smart devices;

[0051] The scene mode coordinator coordinates the linkage between the humidifier and other smart devices according to the smart scenes preset by the user to optimize the overall home environment.

[0052] Furthermore, the data analysis module includes the following components:

[0053] Data collection and storage engine, real-time collection, processing and persistent storage of humidity change trend and equipment operation status data;

[0054] Time Series Data Analyzer, which performs time series analysis on long-term humidity variation data to identify periodic patterns, trends, and anomalies;

[0055] The air quality assessment module comprehensively analyzes humidity, temperature and air pollutant data to assess the overall air quality and generate targeted improvement suggestions;

[0056] The Health Impact Analyzer evaluates the potential impact of the indoor environment on occupants’ health based on air quality data and user feedback, and generates personalized health reports and warnings.

[0057] Furthermore, the trend is identified by the following formula: Among them, T t represents the humidity trend value identified at time point t; N represents the length of the trend window; H t-n Represents the humidity observation value at the past N time points;

[0058] The periodic pattern is identified by the following formula: Among them, S t represents the periodic component of humidity identified at time point t; P represents the period length;

[0059] Anomalies are identified by the following formula: R t =H t -T t -S t , where Ht represents the humidity observation value at time point t; R t Represents the humidity residual value at time point t. When |R t When |>μσ, it is judged that the humidity is abnormal at time point t, σ represents the standard deviation of the residual; μ represents the threshold coefficient.

[0060] Compared with the prior art, this application has the following beneficial effects:

[0061] This application generates a global humidity distribution map based on multiple sensors and combines it with an intelligent control algorithm to achieve precise and dynamic humidifier adjustment. It also integrates personalized settings and smart home linkage to optimize humidity control strategies, and provides air quality recommendations through data analysis to enhance user experience and health protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a schematic diagram of the structure of an intelligent humidifier control system disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments.

[0064] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0065] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0066] like Figure 1 As shown, an intelligent humidifier control system includes the following modules:

[0067] The multi-sensor humidity monitoring module collects humidity data from all areas of the room in real time, generates a global humidity distribution map, and provides basic information for precise humidification;

[0068] Intelligent control module analyzes humidity distribution and dynamically adjusts the target humidity and working mode of the humidifier to ensure uniform and comfortable air humidity;

[0069] User interaction and personalization module, which allows users to set humidity range, priority area and operation time through mobile app or voice assistant, and record usage habits to optimize operation parameters;

[0070] Smart home linkage module enables the humidifier to work in coordination with other smart home devices, automatically adjusting the humidification strategy to adapt to overall environmental changes;

[0071] The data analysis module records and analyzes humidity change data, provides air quality optimization suggestions and health reports, and continuously optimizes the humidifier control strategy.

[0072] In this embodiment, the multi-sensor humidity monitoring module is the core basic part of the intelligent humidifier control system. The module deploys multiple humidity sensors in different areas of the room to monitor and record the humidity data of each area in real time. These data will be centrally processed to generate a comprehensive humidity distribution map to provide the system with accurate humidity status information. Through real-time monitoring, local differences in humidity can be discovered in time, and the distribution of dry and wet areas can be identified, thereby providing an accurate basis for subsequent humidification operations. This monitoring capability can not only improve the response speed of the humidifier, but also effectively avoid the problem of over-humidification or under-humidification, ensure that the humidity is evenly distributed throughout the room, and thus improve the user's comfort. In addition, this detailed humidity distribution map can help users understand the humidity changes in each area, which is convenient for adjustment and optimization according to actual needs.

[0073] In this embodiment, the intelligent control module uses advanced algorithms to process humidity distribution, thereby realizing intelligent humidification. Specifically, when it is detected that the humidity in a certain area is lower than the set range, the working mode of the humidifier will be automatically adjusted. The intelligent control module can not only adjust the working state of the humidifier, but also conduct a comprehensive analysis based on various factors such as time, weather, and usage habits to achieve optimal humidity control. Through this intelligent control, it can ensure that the humidifier can provide a stable and comfortable humidity level under different environmental conditions, thereby improving the quality of life of users.

[0074] In this embodiment, the user interaction and personalized setting module is designed to enhance the user experience, allowing users to easily set the operating parameters of the humidifier through a mobile App or voice assistant. Users can set the humidity range, priority area, and operating time according to personal needs, and record usage habits so that the operating parameters can be gradually optimized. For example, the humidity requirements for a specific area within a specific time period can be set through the App, and the working mode of the humidifier will be adjusted according to these settings. This personalized setting function enables the humidifier to be accurately adjusted according to the living habits and needs of each user, thereby providing services that are more in line with user needs. At the same time, the usage habit data recorded by the system can help analyze the user's humidification preferences, thereby optimizing future operating strategies and improving overall usage efficiency.

[0075] In this embodiment, the smart home linkage module enables the humidifier to work in coordination with other smart home devices. By integrating various smart home platforms (such as smart lights, curtains, air conditioners, etc.), the module can realize automatic linkage between the humidifier and other devices. For example, when the system detects that the room temperature is too high, it can automatically adjust the working state of the air conditioner and adjust the humidity output of the humidifier to adapt to changes in the overall environment. Smart home linkage can not only improve the working efficiency of the humidifier, but also provide users with a more comfortable living environment. Through this linkage mechanism, the humidifier can form an intelligent ecosystem with other smart devices in the home to optimize the air quality and comfort of the overall home environment.

[0076] In this embodiment, the data analysis module is responsible for recording and analyzing humidity change data, and providing air quality optimization suggestions and health reports. Through long-term tracking of humidity data, the module can identify the pattern of humidity changes and make improvement suggestions accordingly. For example, if it is found that the humidity in certain areas is often too low, suggestions will be made to increase the humidification amount or adjust the position of the humidifier. In addition, the data analysis module can also generate detailed health reports to help users understand the impact of humidity on health. Through continuous optimization and adjustment, the humidifier can continuously improve its control strategy and improve the accuracy of humidity management. This not only helps to maintain the health of the user, but also improves the overall performance of the humidifier and ensures its long-term stable operation.

[0077] Furthermore, the multi-sensor humidity monitoring module includes the following components:

[0078] A distributed humidity sensor network is deployed in various areas of the room to collect humidity data in real time;

[0079] The data acquisition unit is responsible for collecting humidity data from the distributed sensor network;

[0080] a spatial positioning unit for determining the precise location of the distributed humidity sensor network in the room;

[0081] The central processing unit is used to receive and process data from the spatial positioning unit and the distributed humidity sensor network to generate a real-time global humidity distribution map.

[0082] In summary, the multi-sensor humidity monitoring module realizes comprehensive and accurate monitoring of room humidity through the close cooperation of the distributed humidity sensor network, data acquisition unit, spatial positioning unit and central processing unit. These components perform their respective duties and jointly ensure the comprehensive collection, accurate transmission and precise processing of humidity data. The distributed humidity sensor network provides extensive data coverage and detailed humidity information; the data acquisition unit ensures the timely transmission and stability of the data; the spatial positioning unit ensures the accurate location correspondence of the data; and the central processing unit comprehensively processes the data to generate a real-time humidity distribution map. Through these technical means, it is possible to achieve precise control of humidity, optimize the operation strategy of the humidifier, improve the user's comfort experience, and provide a reliable foundation for subsequent data analysis and optimization. Overall, the collaborative work of the above components significantly improves the intelligence level and efficiency of the humidification system, and provides strong support for humidity management in smart home environments.

[0083] Further, generating a real-time global humidity distribution map includes the following steps:

[0084] Converting the sensor position information provided by the spatial positioning unit into standardized three-dimensional coordinates so as to accurately represent the position of each sensor in the virtual space;

[0085] The processed humidity data are associated with the corresponding three-dimensional coordinate information to form discrete data points, and the Kriging method is used for interpolation to generate a continuous humidity distribution field;

[0086] The room space is divided into uniform three-dimensional grids, and the interpolation algorithm is applied to each grid point to calculate its humidity value;

[0087] Based on the calculated grid point humidity values, a three-dimensional humidity distribution map is generated using isosurface technology;

[0088] An incremental update algorithm and cache mechanism are used to recalculate the changed areas to dynamically update the three-dimensional humidity distribution map.

[0089] In summary, the process of generating a real-time global humidity distribution map involves the above-mentioned key steps, from the standardized three-dimensional coordinate conversion of sensor location information to the interpolation of discrete data points, to the application of gridding processing and isosurface technology, and finally to dynamic update through incremental update algorithm and cache mechanism. Each step provides basic support for generating an accurate and real-time humidity distribution map. Standardized three-dimensional coordinates ensure the accuracy of sensor location; Kriging interpolation provides a smooth humidity field; gridding processing and isosurface technology make humidity data visual and easy for users to understand; dynamic update mechanism ensures the real-time and accuracy of graphics. Through the comprehensive application of these technical means, efficient and accurate humidity monitoring and control can be achieved, providing users with a reliable humidity management tool and optimizing the comfort of the indoor environment.

[0090] Furthermore, the room space is divided into uniform three-dimensional grids, and the interpolation algorithm is applied to each grid point to calculate its humidity value, including the following steps:

[0091] Divide the room space into N x ×N y ×N z A uniform grid, where N x 、N y and N z Represents the number of grids in the x, y and z directions respectively, and the position of each grid point is expressed as (x i ,y j , z k ), where i∈[1,N x ],j∈[1,N y ],k∈[1,N z ];

[0092] The coordinates and humidity values ​​of the humidity measurement points are known to be (x m ,y m , z m ) and H m , where m∈[1,M], M is the number of known humidity measurement points;

[0093] Calculate the grid points (x i ,y i , z k ) humidity value H i,j,k , the formula is: Among them, d i,j,k,m is the grid point (x i ,y j , z k ) and the measuring point (x m ,y m , z m ), the calculation formula is: p is the weight index of the distance;

[0094] All calculated humidity values ​​H i,j,k Form a three-dimensional humidity distribution map.

[0095] Furthermore, the intelligent control module includes the following components:

[0096] The humidity analysis engine performs real-time analysis of the humidity distribution status and dynamic change trends of each area of ​​the room based on the global humidity distribution map;

[0097] The decision optimization algorithm comprehensively considers the humidity analysis results and the preset target parameters to calculate and determine the optimal operating parameters and working mode of the humidifier;

[0098] Execution instruction generator, converting the optimized operation parameters and working mode into specific equipment control instructions and executing them;

[0099] The pattern learning and optimization module learns the changing patterns of room humidity and user preferences through long-term data accumulation, and continuously optimizes the performance of the decision-making optimization algorithm.

[0100] In summary, the intelligent control module realizes intelligent management of room humidity through the collaborative work of four key components: humidity analysis engine, decision optimization algorithm, execution instruction generator, and pattern learning and optimization module. The humidity analysis engine provides accurate humidity conditions and change trends by analyzing the global humidity distribution map in real time; the decision optimization algorithm calculates the optimal humidifier operating parameters and working mode based on these analysis results and preset goals; the execution instruction generator converts the optimization results into specific control instructions and directs the humidifier to execute; the pattern learning and optimization module continuously optimizes the decision algorithm through long-term data accumulation and learning, thereby improving the level of intelligence. The close cooperation of these components ensures that the humidifier can accurately adjust according to real-time humidity changes and provide a comfortable humidity environment. Overall, the intelligent control module improves the efficiency and intelligence level of humidity control through comprehensive analysis, optimized decision-making and dynamic adjustment, and significantly improves the user's indoor environment experience.

[0101] Further, calculating and determining the optimal operating parameters and working mode of the humidifier includes the following steps:

[0102] A multi-objective optimization model is established based on the user's preset target humidity range, comfort preferences, and priorities for specific areas;

[0103] Based on the analysis of the global humidity distribution map, the areas with uneven humidity and dry hot spots are identified, and the room space is divided into several sub-areas requiring different humidification strategies through the threshold segmentation method;

[0104] Based on the technical specifications and historical operating data of the humidifier, a mathematical model is established to describe the performance characteristics of the humidifier in different operating modes;

[0105] Particle swarm optimization algorithm is used to find the best combination of humidifier operating parameters;

[0106] Perform constraint checks on the optimal humidifier operating parameter combination to ensure that all parameters are within the physical limitations and safe operating range of the humidifier;

[0107] Based on the optimization results, the best operating mode of the humidifier is determined and specific operating parameter settings are generated.

[0108] In summary, determining the optimal operating parameters and working mode of a humidifier is a multi-step optimization process, which involves establishing a multi-objective optimization model, dividing sub-regions and identifying humidity imbalance areas, establishing a mathematical model of humidifier performance, using a particle swarm optimization algorithm to find the best parameter combination, checking constraints to ensure parameter legitimacy, and finally determining the best working mode and generating operating parameter settings. These steps ensure that the humidifier can achieve the best humidity control effect under various operating conditions by comprehensively considering user needs, environmental conditions, and equipment performance. Establishing a multi-objective optimization model provides clear goals and constraints for the optimization process, and dividing sub-regions and identifying humidity imbalance areas help the system accurately adjust the humidification strategy for different areas. The performance mathematical model and particle swarm optimization algorithm provide a scientific basis for parameter configuration in actual operation, and the constraint check ensures the practical feasibility of the optimization results. Finally, the specific operating parameter settings generated will effectively guide the operation of the humidifier and ensure that it can provide long-lasting and stable humidity management in a dynamic environment. Through these comprehensive measures, the smart humidifier system can achieve precise humidity control and improve the user's comfort and quality of life.

[0109] Further, continuously optimizing the performance of the decision optimization algorithm includes the following steps:

[0110] Continuously collect room humidity, humidifier parameters, user settings and feedback data, structure them into time series and store them in an efficient database;

[0111] Clean, standardize and denoise the data in the database, extract humidity change cycles, peak values ​​and trend characteristics through time series analysis and feature engineering, and analyze user behavior data to extract their preferences and usage habits;

[0112] Using time series clustering, we can identify daily and seasonal changes in room humidity and its response to the external environment from long-term data. At the same time, we can reveal the potential relationship between user behavior and environmental changes through association rule mining technology.

[0113] Build a prediction model based on the mined patterns to predict humidity trends and user needs, and continuously improve prediction accuracy through continuous evaluation and tuning;

[0114] Integrate the prediction model and mined rules into the existing decision optimization algorithm to update parameters and strategies;

[0115] Regular comprehensive assessments are conducted based on new data, and decision optimization algorithms are continuously refined to respond to changes in the environment and evolution of user needs.

[0116] In summary, continuously optimizing the performance of the decision optimization algorithm is a systematic process, involving continuous data collection and structuring, data cleaning and feature extraction, time series clustering and association rule mining, prediction model construction and improvement, model integration into the decision optimization algorithm, and regular evaluation and optimization. Through the above steps, the accuracy and intelligence level of humidity control can be continuously improved. Data collection and preprocessing provide a reliable foundation for the algorithm, time series analysis and feature extraction reveal the laws of humidity changes and user behavior, and the prediction model provides a basis for future humidity changes. Integrating the prediction results into the decision optimization algorithm ensures that the humidifier can be intelligently adjusted according to actual needs. Regular evaluation and optimization ensure that it can cope with changes in the environment and needs and maintain efficient humidity management. Overall, by continuously optimizing the decision optimization algorithm, the intelligent humidifier system can provide a more accurate humidity control solution and improve user comfort and satisfaction.

[0117] Furthermore, the smart home linkage module includes the following components:

[0118] Device identification and connection manager, automatically identifies and manages smart home devices compatible with the humidifier, and establishes and maintains a stable communication connection;

[0119] Multi-protocol data exchange adapter, supporting and converting multiple smart home communication protocols to ensure seamless data interaction between heterogeneous devices;

[0120] Environmental information integrator, which processes and integrates environmental data from other smart devices to provide comprehensive contextual information for dynamic adjustment of humidification strategies;

[0121] Linkage rule engine, which defines, manages and executes complex linkage rules between devices to achieve collaborative operation of smart devices;

[0122] The scene mode coordinator coordinates the linkage between the humidifier and other smart devices according to the smart scenes preset by the user to optimize the overall home environment.

[0123] In summary, the smart home linkage module realizes efficient collaborative operation of humidifiers and other smart home devices through five key components: device identification and connection manager, multi-protocol data exchange adapter, environmental information integrator, linkage rule engine and scene mode coordinator. The device identification and connection manager ensures that all compatible devices can be stably connected and effectively managed; the multi-protocol data exchange adapter solves the compatibility issues between different communication protocols and realizes seamless data transmission between devices; the environmental information integrator provides comprehensive context information through comprehensive environmental data to support accurate humidification strategy formulation; the linkage rule engine realizes the collaborative work of smart devices by setting complex linkage rules; the scene mode coordinator optimizes the overall home environment settings according to the user's preset scenes. The collaborative work of these components not only improves the intelligence level of the system, but also enhances the user experience, and realizes a more comfortable and efficient home environment through comprehensive device linkage and scene management.

[0124] Furthermore, the data analysis module includes the following components:

[0125] Data collection and storage engine, real-time collection, processing and persistent storage of humidity change trend and equipment operation status data;

[0126] Time Series Data Analyzer, which performs time series analysis on long-term humidity variation data to identify periodic patterns, trends, and anomalies;

[0127] The air quality assessment module comprehensively analyzes humidity, temperature and air pollutant data to assess the overall air quality and generate targeted improvement suggestions;

[0128] The Health Impact Analyzer evaluates the potential impact of the indoor environment on occupants’ health based on air quality data and user feedback, and generates personalized health reports and warnings.

[0129] In summary, the data analysis module achieves a comprehensive analysis of humidity changes and equipment operation status through four core components: data acquisition and storage engine, time series data analyzer, air quality assessment module, and health impact analyzer. These components work together to provide in-depth data insights and health management support for the smart home system. The data acquisition and storage engine ensures the real-time acquisition and persistent storage of high-quality data, providing a reliable basis for analysis. The time series data analyzer identifies the regularity and anomalies of humidity changes through time series analysis, and supports the optimization of humidification strategies. The air quality assessment module evaluates air quality and makes improvement suggestions through comprehensive analysis of environmental data, thereby improving the comfort of the indoor environment. The health impact analyzer generates personalized health reports and warnings by evaluating the potential impact of air quality on the health of residents, helping users to manage their health effectively. Overall, the integration and collaboration of these components realizes the intelligent monitoring and optimization of the home environment, and improves the quality of life and health level of users.

[0130] Furthermore, the trend is identified by the following formula: Among them, T t represents the humidity trend value identified at time point t; N represents the length of the trend window; H t-n Represents the humidity observation value at the past N time points;

[0131] The periodic pattern is identified by the following formula: Among them, S t represents the periodic component of humidity identified at time point t; P represents the period length;

[0132] Anomalies are identified by the following formula: R t =H t -T t -S t , where H t represents the humidity observation value at time point t; R t Represents the humidity residual value at time point t. When |R t When |>μσ, it is judged that the humidity is abnormal at time point t, σ represents the standard deviation of the residual; μ represents the threshold coefficient.

[0133] In summary, the trend recognition formula extracts the long-term pattern of humidity changes by calculating the average value within the sliding window, the periodic pattern recognition formula uses the sine function to capture the periodic fluctuations of humidity data, and the abnormal situation recognition formula finds abnormal points in the data by calculating the humidity residual value and standard deviation. The combination of these analysis methods can comprehensively analyze the changing characteristics of humidity data, thereby providing more accurate humidity control and environmental optimization solutions for smart home systems. By reasonably applying these formulas, we can achieve a deep understanding of humidity data and improve the intelligence level and responsiveness of humidity management.

[0134] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent humidifier control system, characterized in that: Includes the following modules: The multi-sensor humidity monitoring module collects humidity data from all areas of the room in real time, generates a global humidity distribution map, and provides basic information for precise humidification; Intelligent control module analyzes humidity distribution and dynamically adjusts the target humidity and working mode of the humidifier to ensure uniform and comfortable air humidity; User interaction and personalization module, which allows users to set humidity range, priority area and operation time through mobile app or voice assistant, and record usage habits to optimize operation parameters; Smart home linkage module enables the humidifier to work in coordination with other smart home devices, automatically adjusting the humidification strategy to adapt to overall environmental changes; The data analysis module records and analyzes humidity change data, provides air quality optimization suggestions and health reports, and continuously optimizes the humidifier control strategy.

2. The intelligent humidifier control system according to claim 1, characterized in that: The multi-sensor humidity monitoring module includes the following components: A distributed humidity sensor network is deployed in various areas of the room to collect humidity data in real time; The data acquisition unit is responsible for collecting humidity data from the distributed sensor network; a spatial positioning unit for determining the precise location of the distributed humidity sensor network in the room; The central processing unit is used to receive and process data from the spatial positioning unit and the distributed humidity sensor network to generate a real-time global humidity distribution map.

3. The intelligent humidifier control system according to claim 2, characterized in that: Generating a real-time global humidity distribution map involves the following steps: Converting the sensor position information provided by the spatial positioning unit into standardized three-dimensional coordinates so as to accurately represent the position of each sensor in the virtual space; The processed humidity data are associated with the corresponding three-dimensional coordinate information to form discrete data points, and the Kriging method is used for interpolation to generate a continuous humidity distribution field; The room space is divided into uniform three-dimensional grids, and the interpolation algorithm is applied to each grid point to calculate its humidity value; Based on the calculated grid point humidity values, a three-dimensional humidity distribution map is generated using isosurface technology; An incremental update algorithm and cache mechanism are used to recalculate the changed areas to dynamically update the three-dimensional humidity distribution map.

4. The intelligent humidifier control system according to claim 3, characterized in that: The room space is divided into a uniform three-dimensional grid, and the interpolation algorithm is applied to each grid point to calculate its humidity value, including the following steps: Divide the room space into N x ×N y ×N z A uniform grid, where N x 、N y and N z Represents the number of grids in the x, y and z directions respectively, and the position of each grid point is expressed as (x i ,y j , z k ), where i∈[1, N x ],j∈[1,N y ],k∈[1,N z ]; The coordinates and humidity values ​​of the humidity measurement points are known to be (x m ,y m , z m ) and H m , where m∈[1,M], M is the number of known humidity measurement points; Calculate the grid points (x i ,y j , z k ) humidity value H i,j,k , the formula is: Among them, d i,j,k,m is the grid point (x i ,y j , z k ) and the measuring point (x m ,y m , z m ), the calculation formula is: p is the weight index of the distance; All calculated humidity values ​​H i,j,k Form a three-dimensional humidity distribution map.

5. The intelligent humidifier control system according to claim 1, characterized in that: The intelligent control module includes the following components: The humidity analysis engine performs real-time analysis of the humidity distribution status and dynamic change trend of each area of ​​the room based on the global humidity distribution map; The decision optimization algorithm comprehensively considers the humidity analysis results and the preset target parameters to calculate and determine the optimal operating parameters and working mode of the humidifier; Execution instruction generator, converting the optimized operation parameters and working mode into specific equipment control instructions and executing them; The pattern learning and optimization module learns the changing patterns of room humidity and user preferences through long-term data accumulation, and continuously optimizes the performance of the decision-making optimization algorithm.

6. The intelligent humidifier control system according to claim 5, characterized in that: Calculating and determining the optimal operating parameters and operating mode of the humidifier includes the following steps: A multi-objective optimization model is established based on the user's preset target humidity range, comfort preferences, and priorities for specific areas; Based on the analysis of the global humidity distribution map, the areas with uneven humidity and dry hot spots are identified, and the room space is divided into several sub-areas requiring different humidification strategies through the threshold segmentation method; Based on the technical specifications and historical operating data of the humidifier, a mathematical model is established to describe the performance characteristics of the humidifier in different operating modes; Particle swarm optimization algorithm is used to find the best combination of humidifier operating parameters; Perform constraint checks on the optimal humidifier operating parameter combination to ensure that all parameters are within the physical limitations and safe operating range of the humidifier; Based on the optimization results, the best operating mode of the humidifier is determined and specific operating parameter settings are generated.

7. The intelligent humidifier control system according to claim 5, characterized in that: Continuously improving the performance of the decision optimization algorithm includes the following steps: Continuously collect room humidity, humidifier parameters, user settings and feedback data, structure them into time series and store them in an efficient database; Clean, standardize and denoise the data in the database, extract humidity change cycles, peak values ​​and trend characteristics through time series analysis and feature engineering, and analyze user behavior data to extract their preferences and usage habits; Using time series clustering, we can identify daily and seasonal changes in room humidity and its response to the external environment from long-term data. At the same time, we can reveal the potential relationship between user behavior and environmental changes through association rule mining technology. Build a prediction model based on the mined patterns to predict humidity trends and user needs, and continuously improve prediction accuracy through continuous evaluation and tuning; Integrate the prediction model and mined rules into the existing decision optimization algorithm to update parameters and strategies; Regular comprehensive assessments are conducted based on new data, and decision optimization algorithms are continuously refined to respond to changes in the environment and evolution of user needs.

8. The intelligent humidifier control system according to claim 1, characterized in that: The smart home linkage module includes the following components: Device identification and connection manager, automatically identifies and manages smart home devices compatible with the humidifier, and establishes and maintains a stable communication connection; Multi-protocol data exchange adapter, supporting and converting multiple smart home communication protocols to ensure seamless data interaction between heterogeneous devices; Environmental information integrator, which processes and integrates environmental data from other smart devices to provide comprehensive contextual information for dynamic adjustment of humidification strategies; Linkage rule engine, which defines, manages and executes complex linkage rules between devices to achieve collaborative operation of smart devices; The scene mode coordinator coordinates the linkage between the humidifier and other smart devices according to the smart scenes preset by the user to optimize the overall home environment.

9. The intelligent humidifier control system according to claim 1, characterized in that: The data analysis module includes the following components: Data collection and storage engine, real-time collection, processing and persistent storage of humidity change trend and equipment operation status data; Time Series Data Analyzer, which performs time series analysis on long-term humidity variation data to identify periodic patterns, trends, and anomalies; The air quality assessment module comprehensively analyzes humidity, temperature and air pollutant data to assess the overall air quality and generate targeted improvement suggestions; The Health Impact Analyzer evaluates the potential impact of the indoor environment on occupants’ health based on air quality data and user feedback, and generates personalized health reports and warnings.

10. The intelligent humidifier control system according to claim 9, characterized in that: Identify trends using the following formula: Among them, T t represents the humidity trend value identified at time point t; N represents the length of the trend window; H t-n Represents the humidity observation value at the past N time points; The periodic pattern is identified by the following formula: Among them, S t represents the periodic component of humidity identified at time point t; P represents the period length; Anomalies are identified by the following formula: R t =H t -T t -S t , where H t represents the humidity observation value at time point t; R t Represents the humidity residual value at time point t. When |R t When |>μσ, it is judged that the humidity is abnormal at time point t, σ represents the standard deviation of the residual; μ represents the threshold coefficient.

Citation Information

Cited By

  • Temperature and humidity control method and system for smart home

    CN119333942A

  • Efficient machine room equipment control decision-making method and system based on machine learning

    CN120891734A

  • Multi-area dehumidification distributed control method and system of high-low voltage power distribution cabinet

    CN121123773A