Indoor environment control method and system based on Internet of Things

Through IoT technology and self-learning algorithms, combined with multi-sensor fusion and LSTM model, indoor environment control is optimized, and the existing system cannot respond to various environmental changes in real time, achieving efficient and intelligent indoor environment management, and improving user comfort and energy-saving effects.

CN118915481AInactive Publication Date: 2024-11-08BEIJING WARMLAND ENERGY SERVICE CO LTD

Patent Information

Application Number
CN202410962494.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing indoor environment control system relies on a single sensor or preset mode and cannot respond to changes in multiple environmental variables in real time, resulting in poor user experience and lack of self-learning and optimization capabilities, making it difficult to achieve intelligent control.

Method used

Using an indoor environment control method based on the Internet of Things, collect data through sensor networks, use cloud servers and central control units for preliminary processing and analysis, combine self-learning algorithms and machine learning models (such as LSTM models), optimize environmental control strategies, and realize multiple Sensor fusion and personalized environmental regulation.

Benefits of technology

It improves the accuracy and intelligent control level of environmental parameter detection, provides personalized environmental adjustment solutions, improves user comfort and achieves efficient and energy saving.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915481A_ABST
    Figure CN118915481A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of indoor environment control, and discloses an indoor environment control method and system based on the Internet of Things, and the method comprises the following steps: initializing a system, starting to collect environment data by a sensor network, carrying out the preliminary processing by a central control unit, and transmitting the data to a cloud server; the cloud server establishes a preliminary user behavior model and an environment control strategy by using the data; real-time data processing and data analysis and optimization are carried out, and the cloud server analyzes the collected data regularly, updates a user behavior model and an environment control strategy, carries out anomaly detection and response, and gives an alarm to a user. According to the indoor environment control method and system based on the Internet of Things, efficient and intelligent indoor environment control is achieved through multi-sensor fusion, a self-learning algorithm and user behavior analysis, and the user comfort and the energy-saving effect are improved; and through a machine learning algorithm, the system can self-optimize a control strategy, and the intelligent level of environment control is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of indoor environment control, and in particular to an indoor environment control method and system based on the Internet of Things. Background Art

[0002] The Internet of Things refers to connecting any object to the network through information sensing devices according to the agreed protocol, and the object exchanges and communicates information through information transmission media to realize intelligent identification, positioning, tracking, supervision and other functions. There are three key points in the application of the Internet of Things, namely the perception layer, the network transmission layer and the application layer. Indoor environmental governance is a scientific activity that uses modern scientific and technological methods to quantitatively measure the concentration changes of environmental factors and other indoor environmental pollutants that are harmful to human health in an intermittent or continuous form, and observe and analyze the process and degree of their environmental impact. Indoor environmental monitoring and management research shows that China is a country with a large population. Through local population health surveys, it is found that the general life expectancy of the population with a better indoor environmental detection index is higher than that of those living in places with poorer environments. This is an undeniable result in indoor environmental testing.

[0003] Most existing indoor environmental control systems rely on a single sensor or preset mode for control, and cannot respond to changes in multiple environmental variables in real time, resulting in poor user experience. In addition, existing technologies usually ignore the system's self-learning and optimization capabilities, making it difficult to achieve true intelligent control. Therefore, it is necessary to design corresponding technical solutions to solve this problem. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides an indoor environment control method and system based on the Internet of Things, which solves the technical problems of relying on a single sensor or preset mode for control and being unable to respond to changes in multiple environmental variables in real time, resulting in a poor user experience. The prior art usually ignores the system's self-learning and optimization capabilities, making it difficult to achieve truly intelligent control.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an indoor environment control method based on the Internet of Things, comprising the following method steps:

[0008] S1, system initialization: When the system is first started, the sensor network begins to collect environmental data, the central control unit performs preliminary processing, and transmits the data to the cloud server; the cloud server uses the data to establish a preliminary user behavior model and environmental control strategy;

[0009] S2, real-time data processing: the sensor network monitors environmental parameters in real time and transmits the data to the central control unit through the IoT gateway; the central control unit uses edge computing capabilities to perform preliminary data processing and adjust the operating status of the execution equipment according to the preset control strategy;

[0010] S3, data analysis and optimization: The cloud server regularly analyzes the collected data and updates the user behavior model and environmental control strategy. Through self-learning algorithms, the system can identify user behavior patterns and optimize control strategies based on these patterns.

[0011] The user behavior model and environment control strategy are updated through a self-learning algorithm, and the time series prediction model in supervised learning in machine learning is used. The specific method steps include the following:

[0012] Preprocess the environmental data and user behavior data collected from the sensor network;

[0013] Extract key features and construct feature vectors based on the time sequence.

[0014] Divide the dataset into training and test sets in chronological order to ensure that the model can make predictions based on historical data;

[0015] Use the LSTM model for training. The LSTM model is suitable for processing time series data and can capture long-term dependencies in time series.

[0016] Use the trained LSTM model to predict future environmental parameters and user behaviors;

[0017] Adjust environmental control strategies based on prediction results to optimize user experience;

[0018] LSTM unit formula:

[0019] Input gate: i t =σ(W i ·[h t-1 , x t ]+b i );

[0020] Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f );

[0021] Output gate: o t =σ(W o ·[h t-1 , x t ]+bo );

[0022] Candidate memory cells:

[0023] Memory unit update:

[0024] Hide status update:h t =o t *tanh(C t );

[0025] Loss function: Use mean square error as the loss function:

[0026] Among them, y i is the actual value, is the predicted value;

[0027] Optimization algorithm: Use the back-propagation through time algorithm to train the LSTM model and use the optimization algorithm to update the model parameters;

[0028] S4, anomaly detection and response: The system's built-in anomaly detection module monitors changes in sensor data in real time. When an abnormal situation is detected, the system will automatically turn on response protection and issue an alarm to the user.

[0029] Preferably, the specific method steps for establishing a preliminary user behavior model and an environment control strategy include the following:

[0030] S101, preliminary user behavior model establishment:

[0031] Behavioral pattern recognition: Based on user input preferences and sensor data, use data clustering algorithms to identify preliminary user behavior patterns;

[0032] Time series analysis: Use time series analysis methods to analyze the temporal variation patterns of sensor data and establish a preliminary time series model of user daily behavior;

[0033] S102, Environmental Control Strategy Development:

[0034] Rule setting: Formulate basic environment control rules based on the initial preferences and behavior patterns input by users;

[0035] Preliminary strategy generation: Using optimization algorithms, a preliminary environmental control strategy is generated while ensuring user comfort;

[0036] Multi-objective optimization: In the process of generating preliminary strategies, consider the balance of multiple objectives and perform multi-objective optimization;

[0037] S103, Model Verification and Adjustment:

[0038] Simulation: Conduct simulation on the cloud server to verify the effectiveness of the preliminary user behavior model and environmental control strategy;

[0039] User feedback adjustment: Based on user feedback, adjust the preliminary behavior model and control strategy to ensure that it meets the actual needs of users.

[0040] Preferably, the specific method steps of using the data clustering algorithm include the following:

[0041] S1011, Data Standardization:

[0042] Standardize the collected sensor data to ensure that data of different dimensions can be compared on the same scale;

[0043] Standardization formula:

[0044] Among them, x is the original data, μ is the mean, and σ is the standard deviation;

[0045] S1012, select initial cluster center:

[0046] Randomly select K data points as initial cluster centers;

[0047] S1013, calculate distance and assign data points:

[0048] Calculate the Euclidean distance between each data point and each cluster center, and assign the data point to the cluster center with the closest distance;

[0049] Euclidean distance formula:

[0050] Among them, x i is the data point, μ j is the cluster center, n is the dimension of the feature;

[0051] S1014, update cluster center:

[0052] Calculate the mean of each cluster as the new cluster center;

[0053] New cluster center formula:

[0054] Among them, C j is the jth cluster, |C j | is the number of data points in the jth cluster;

[0055] S1015, repeat steps 3 and 4:

[0056] Until the cluster center no longer changes or the change is less than the set threshold.

[0057] Preferably, the specific steps of using the time series analysis method are:

[0058] S10101, Data Stabilization:

[0059] Perform difference operation on time series data to make it stationary;

[0060] First-order difference formula: y′ t =y t -y t-1 ;

[0061] S10102, determine model parameters:

[0062] The parameters (p, d, q) of the ARIMA model are determined using the autocorrelation function and partial autocorrelation function graphs; p is the number of AR terms, d is the difference order, and q is the number of MA terms;

[0063] S10103, model fitting:

[0064] Using the determined parameters, fit the ARIMA model;

[0065] ARIMA model formula:

[0066]

[0067] Among them, α is a constant term, φ i is the AR term coefficient, θ j is the MA term coefficient, ∈ t is a random error;

[0068] S10104, Model Check:

[0069] Check whether the residual sequence of the model is white noise to ensure that the model fits well;

[0070] S10105, Prediction and Verification:

[0071] The fitted ARIMA model is used for forecasting and compared with the actual data to verify the model effect.

[0072] Preferably, the specific method steps of using the optimization algorithm include the following:

[0073] S1021, define the objective function:

[0074] Define the objective function of linear programming according to the optimization goal of the system, for example, minimizing energy consumption.

[0075] Objective function formula:

[0076] Among them, c i is the cost of item i, x iis the decision variable of the ith item;

[0077] S1022, establish constraints:

[0078] Establish linear constraints based on the actual needs of the system;

[0079] Constraint formula:

[0080] Among them, a ij is the constraint coefficient, b i is the constraint constant;

[0081] S1023, solve the linear programming problem:

[0082] Use the standard linear programming algorithm to find the optimal solution of the objective function.

[0083] Preferably, solving the linear programming problem includes the simplex method steps, specifically:

[0084] S10231, Standard Form Conversion:

[0085] Convert the linear programming problem into standard form, where all constraints are equalities and all variables are non-negative;

[0086] S10232, initial basic feasible solution:

[0087] Select an initial basic feasible solution with all slack variables non-negative;

[0088] S10233, calculate the test number:

[0089] Compute the test number of the objective function:

[0090] c′ j =c j -∑ i∈B c i a ij ;

[0091] Among them, B is the index set of the current base variable, c i is the cost coefficient of the base variable, a ij is the constraint matrix element;

[0092] S10234, inspection optimization direction:

[0093] If all c′ j ≥0, the current solution is the optimal solution; otherwise, select a c′ j A non-basic variable < 0 enters a basic variable, which is called an entry-basic variable.

[0094] S10235, calculate the variables to be swapped in and out:

[0095] Calculate the ratio θ corresponding to all constraints:

[0096] θ i : represents the maximum step length allowed by the current solution under the i-th constraint condition; b i : represents the constant term on the right side of the ith constraint in the current solution; a ij : represents the coefficient of the input variable in the i-th constraint;

[0097] Select the base variable corresponding to the minimum positive proportional value as the swap variable;

[0098] S10236, Update base variables:

[0099] Update the basic variables and recalculate new basic variables and non-basic variables;

[0100] S10237, iterative solution:

[0101] Repeat steps 3-6 until the optimal solution is found.

[0102] Indoor environment control system based on the Internet of Things, including sensor network module, central control unit, cloud server and execution equipment;

[0103] The sensor network module is used to monitor indoor environmental parameters in real time, and uses multi-sensor fusion technology to comprehensively process data from different sensors to generate more accurate environmental parameters;

[0104] The central control unit integrates edge computing capabilities for preliminary processing of sensor data and communicating with the cloud server via an IoT gateway;

[0105] The cloud server is used to store and analyze data and run self-learning algorithms and user behavior analysis models;

[0106] The execution device is used to adjust the indoor environment.

[0107] Preferably, the sensor network module includes a temperature sensor, a humidity sensor, a light sensor, a CO2 sensor, a VOC sensor, a human presence sensor, a door and window status sensor, a water immersion sensor, a smoke sensor, a pressure sensor, a motion sensor, a noise sensor, a spectrum sensor and a meteorological sensor;

[0108] Temperature sensor, used to monitor the temperature of every corner of the room in real time, so as to adjust the precise indoor temperature;

[0109] Humidity sensor, used to monitor the humidity in every corner of the room in real time, so as to adjust the precise indoor humidity;

[0110] Light sensors are used to monitor the indoor area close to sunlight and adjust the indoor lighting system according to the lighting conditions;

[0111] CO2 sensor, used to monitor indoor carbon dioxide concentration and adjust the ventilation system to ensure fresh air;

[0112] VOC sensor, which detects the concentration of volatile organic compounds and helps identify harmful gases in the air;

[0113] Human presence sensor, used to detect whether there is someone in the room, so as to adjust the environmental parameters according to the actual usage;

[0114] Door and window status sensors are used to monitor the open and closed status of doors and windows to help adjust the temperature and ventilation system;

[0115] Water sensors are used to detect possible water flooding in the room, especially in areas such as kitchens and bathrooms;

[0116] Smoke sensor, used to detect smoke concentration and prevent fire;

[0117] Pressure sensors are used to monitor pressure changes in building structures to ensure building safety;

[0118] Motion sensors, which monitor indoor activity and help analyze user behavior patterns;

[0119] Noise sensors to monitor noise levels and further analyze the source and type of noise;

[0120] Spectral sensors, which detect the spectral composition of light to optimize the quality of indoor lighting;

[0121] Meteorological sensors are used to monitor outdoor weather conditions, including wind speed, wind direction, and rainfall, to better regulate the indoor environment.

[0122] Preferably, the execution equipment includes an air conditioning system, a ventilation system, a humidifier, a dryer, an air purifier, a lighting system, a door and window control system, a heating system, an intelligent socket switch, a smoke alarm system, a flood alarm drainage system, an intelligent audio system, and a security alarm system;

[0123] Air conditioning systems, which are used to regulate the temperature and humidity of specific rooms in the house;

[0124] Ventilation system: fresh air system is used to introduce fresh air and exhaust polluted air in the room, especially when CO2 or VOC sensors detect that the air quality has deteriorated; exhaust fans are used to exhaust polluted air in the room to maintain air circulation;

[0125] Humidifiers, used to increase air humidity when the air is dry;

[0126] Dryers, used to reduce humidity when air humidity is too high;

[0127] Air purifier, used to purify harmful substances such as PM2.5 and VOC in the air to ensure indoor air quality;

[0128] Lighting system, using intelligent lighting to automatically adjust brightness and color temperature based on light sensors and user needs; using scene lighting to provide appropriate lighting modes based on user behavior and scene settings;

[0129] Door and window control system, using automatic curtains to automatically open or close curtains according to the detection results of light sensors; using smart doors and windows to automatically open and close doors and windows and adjust ventilation according to environmental needs;

[0130] Heating system, using floor heating to provide comfortable indoor temperature through floor heating; using radiators to provide auxiliary heating indoors;

[0131] Smart socket switch, used to control the switch status of various electrical equipment;

[0132] Smoke alarm system, used to sound an alarm and activate corresponding smoke exhaust equipment when smoke is detected;

[0133] Flood alarm and drainage system, used to sound an alarm and activate drainage equipment when flooding is detected to prevent damage caused by flooding;

[0134] Intelligent audio system, used to adjust the volume and playback content of audio equipment according to noise sensors and user needs;

[0135] The security alarm system uses a burglar alarm to trigger an alarm and notify the user when abnormal activities are detected; a fire alarm is used to automatically alarm and initiate relevant protective measures when smoke or high temperature is detected.

[0136] Preferably, the self-learning algorithm is based on the cooperation between the central control unit and the cloud server, and uses the machine learning algorithm to analyze and learn historical data and continuously optimize the control strategy; by identifying the user's daily behavior pattern, the system pre-adjusts the indoor environment parameters to improve the user's comfort;

[0137] The user behavior analysis model is based on the system obtaining the user's location information and activity status data through smartphones and smart watch devices, and combining the data from the sensor network to analyze the user's behavior habits;

[0138] The system has a built-in anomaly detection module to monitor changes in sensor data in real time, detect and handle abnormal situations in a timely manner, and issue alerts to users.

[0139] (III) Beneficial effects

[0140] Compared with the prior art, the present invention has the following beneficial effects: through multi-sensor fusion, self-learning algorithm and user behavior analysis, efficient and intelligent indoor environment control is achieved, user comfort and energy saving effects are improved;

[0141] Multi-sensor fusion technology improves the detection accuracy of environmental parameters, making environmental control more accurate; through machine learning algorithms, the system can self-optimize control strategies and improve the intelligence level of environmental control; based on user behavior analysis, the system can provide personalized environmental adjustment solutions to enhance user comfort; through intelligent control, the system can achieve efficient energy saving while ensuring comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0142] Figure 1 It is a schematic diagram of the method of the present invention;

[0143] Figure 2 It is a system schematic diagram of the present invention. DETAILED DESCRIPTION

[0144] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0145] See also Figure 1-Figure 2 The embodiment of the present invention provides a technical solution: an indoor environment control method based on the Internet of Things, comprising the following method steps:

[0146] S1, system initialization: When the system is first started, the sensor network begins to collect environmental data, the central control unit performs preliminary processing, and transmits the data to the cloud server; the cloud server uses the data to establish a preliminary user behavior model and environmental control strategy;

[0147] S2, real-time data processing: the sensor network monitors environmental parameters in real time and transmits the data to the central control unit through the IoT gateway; the central control unit uses edge computing capabilities to perform preliminary data processing and adjust the operating status of the execution equipment according to the preset control strategy;

[0148] S3, data analysis and optimization: The cloud server regularly analyzes the collected data and updates the user behavior model and environmental control strategy. Through self-learning algorithms, the system can identify user behavior patterns and optimize control strategies based on these patterns.

[0149] The user behavior model and environment control strategy are updated through a self-learning algorithm, and the time series prediction model in supervised learning in machine learning is used. The specific method steps include the following:

[0150] Preprocess the environmental data and user behavior data collected from the sensor network;

[0151] Extract key features and construct feature vectors based on the time sequence.

[0152] Divide the dataset into training and test sets in chronological order to ensure that the model can make predictions based on historical data;

[0153] Use the LSTM model for training. The LSTM model is suitable for processing time series data and can capture long-term dependencies in time series.

[0154] Use the trained LSTM model to predict future environmental parameters and user behaviors;

[0155] Adjust environmental control strategies based on prediction results to optimize user experience;

[0156] LSTM unit formula:

[0157] Input gate: i t =σ(W i ·[h t-1 , x t ]+b i );

[0158] Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f );

[0159] Output gate: o t =σ(W o ·[h t-1 , x t ]+b o );

[0160] Candidate memory cells:

[0161] Memory unit update:

[0162] Hide status update:h t =o t *tanh(C t );

[0163] Loss function: Use mean square error (MSE) as the loss function:

[0164] Among them, y i is the actual value, is the predicted value;

[0165] Optimization algorithm: Use the back-propagation through time algorithm to train the LSTM model and use the optimization algorithm to update the model parameters;

[0166] S4, anomaly detection and response: The system's built-in anomaly detection module monitors changes in sensor data in real time. When an abnormal situation is detected, the system will automatically turn on response protection and issue an alarm to the user.

[0167] For further improvement, the specific method steps for establishing a preliminary user behavior model and an environmental control strategy include the following:

[0168] S101, preliminary user behavior model establishment:

[0169] Behavioral pattern recognition: Based on user input preferences and sensor data, use data clustering algorithms to identify preliminary user behavior patterns;

[0170] Time series analysis: Use time series analysis methods to analyze the temporal variation patterns of sensor data and establish a preliminary time series model of user daily behavior;

[0171] S102, Environmental Control Strategy Development:

[0172] Rule setting: Formulate basic environment control rules based on the initial preferences and behavior patterns input by users;

[0173] Preliminary strategy generation: Using optimization algorithms, a preliminary environmental control strategy is generated while ensuring user comfort;

[0174] Multi-objective optimization: In the process of generating preliminary strategies, consider the balance of multiple objectives and perform multi-objective optimization;

[0175] S103, Model Verification and Adjustment:

[0176] Simulation: Conduct simulation on the cloud server to verify the effectiveness of the preliminary user behavior model and environmental control strategy;

[0177] User feedback adjustment: Based on user feedback, adjust the preliminary behavior model and control strategy to ensure that it meets the actual needs of users.

[0178] Through the above steps, the system can establish a preliminary user behavior model and environmental control strategy, providing a basis for subsequent real-time data processing, data analysis and optimization. In actual applications, the system will continue to collect more data, and through self-learning and optimization, it will continuously improve and adjust the user behavior model and environmental control strategy.

[0179] In a further improvement, the specific method steps of using the data clustering algorithm include the following:

[0180] S1011, Data Standardization:

[0181] Standardize the collected sensor data to ensure that data of different dimensions can be compared on the same scale;

[0182] Standardization formula:

[0183] Among them, x is the original data, μ is the mean, and σ is the standard deviation;

[0184] S1012, select initial cluster center:

[0185] Randomly select K data points as initial cluster centers;

[0186] S1013, calculate distance and assign data points:

[0187] Calculate the Euclidean distance between each data point and each cluster center, and assign the data point to the cluster center with the closest distance;

[0188] Euclidean distance formula:

[0189] Among them, x i is the data point, μ j is the cluster center, n is the dimension of the feature;

[0190] S1014, update cluster center:

[0191] Calculate the mean of each cluster as the new cluster center;

[0192] New cluster center formula:

[0193] Among them, C j is the jth cluster, |C j | is the number of data points in the jth cluster;

[0194] S1015, repeat steps 3 and 4:

[0195] Until the cluster center no longer changes or the change is less than the set threshold.

[0196] Further improved, the specific steps of using the time series analysis method are:

[0197] S10101, Data Stabilization:

[0198] Perform difference operation on time series data to make it stationary;

[0199] First-order difference formula: y′ t =y t -y t-1 ;

[0200] S10102, determine model parameters:

[0201] The parameters (p, d, q) of the ARIMA model are determined using the autocorrelation function (ACF) and partial autocorrelation function (PACF) plots; p is the number of AR terms, d is the difference order, and q is the number of MA terms;

[0202] S10103, model fitting:

[0203] Using the determined parameters, fit the ARIMA model;

[0204] ARIMA model formula:

[0205]

[0206] Among them, α is a constant term, φ i is the AR term coefficient, θ j is the MA term coefficient, ∈ t is a random error;

[0207] S10104, Model Check:

[0208] Check whether the residual sequence of the model is white noise to ensure that the model fits well;

[0209] S10105, Prediction and Verification:

[0210] The fitted ARIMA model is used for forecasting and compared with the actual data to verify the model effect.

[0211] In a further improvement, the specific method steps of using the optimization algorithm include the following:

[0212] S1021, define the objective function:

[0213] Define the objective function of linear programming according to the optimization goal of the system, for example, minimizing energy consumption.

[0214] Objective function formula:

[0215] Among them, c iis the cost of item i, x i is the decision variable of the ith item;

[0216] S1022, establish constraints:

[0217] Establish linear constraints based on the actual needs of the system;

[0218] Constraint formula:

[0219] Among them, a ij is the constraint coefficient, b i is the constraint constant;

[0220] S1023, solve the linear programming problem:

[0221] Use the standard linear programming algorithm to find the optimal solution of the objective function.

[0222] Further improved, solving the linear programming problem includes simplex method steps, specifically:

[0223] S10231, Standard Form Conversion:

[0224] Convert the linear programming problem into standard form, where all constraints are equalities and all variables are non-negative;

[0225] S10232, initial basic feasible solution:

[0226] Select an initial basic feasible solution with all slack variables non-negative;

[0227] S10233, calculate the test number:

[0228] Compute the test number of the objective function:

[0229] c′ j =c j -∑ i∈B c i a ij ;

[0230] Among them, B is the index set of the current base variable, c i is the cost coefficient of the base variable, a ij is the constraint matrix element;

[0231] S10234, inspection optimization direction:

[0232] If all c′ j ≥0, the current solution is the optimal solution; otherwise, select a c′ j A non-basic variable < 0 enters a basic variable, which is called an entry-basic variable.

[0233] S10235, calculate the variables to be swapped in and out:

[0234] Calculate the ratio θ corresponding to all constraints:

[0235] θ i : represents the maximum step length allowed by the current solution under the i-th constraint condition; b i : represents the constant term on the right side of the ith constraint in the current solution; a ij : represents the coefficient of the input variable in the i-th constraint;

[0236] Select the base variable corresponding to the minimum positive proportional value as the swap variable;

[0237] S10236, Update base variables:

[0238] Update the basic variables and recalculate new basic variables and non-basic variables;

[0239] S10237, iterative solution:

[0240] Repeat steps 3-6 until the optimal solution is found.

[0241] Indoor environment control system based on the Internet of Things, including sensor network module, central control unit, cloud server and execution equipment;

[0242] The sensor network module is used to monitor indoor environmental parameters in real time, and uses multi-sensor fusion technology to comprehensively process data from different sensors to generate more accurate environmental parameters;

[0243] The central control unit integrates edge computing capabilities for preliminary processing of sensor data and communicating with the cloud server via an IoT gateway;

[0244] The cloud server is used to store and analyze data and run self-learning algorithms and user behavior analysis models;

[0245] The execution device is used to adjust the indoor environment.

[0246] In a further improvement, the sensor network module includes a temperature sensor, a humidity sensor, a light sensor, a CO2 sensor, a VOC sensor, a human presence sensor, a door and window status sensor, a water immersion sensor, a smoke sensor, a pressure sensor, a motion sensor, a noise sensor, a spectrum sensor and a meteorological sensor;

[0247] Temperature sensor, used to monitor the temperature of every corner of the room in real time, so as to adjust the precise indoor temperature;

[0248] Humidity sensor, used to monitor the humidity in every corner of the room in real time, so as to adjust the precise indoor humidity;

[0249] Light sensors are used to monitor the indoor area close to sunlight and adjust the indoor lighting system according to the lighting conditions;

[0250] CO2 sensor, used to monitor indoor carbon dioxide concentration and adjust the ventilation system to ensure fresh air;

[0251] VOC sensor, which detects the concentration of volatile organic compounds and helps identify harmful gases in the air;

[0252] Human presence sensor, used to detect whether there is someone in the room, so as to adjust the environmental parameters according to the actual usage;

[0253] Door and window status sensors are used to monitor the open and closed status of doors and windows to help adjust the temperature and ventilation system;

[0254] Water sensors are used to detect possible water flooding in the room, especially in areas such as kitchens and bathrooms;

[0255] Smoke sensor, used to detect smoke concentration and prevent fire;

[0256] Pressure sensors are used to monitor pressure changes in building structures to ensure building safety;

[0257] Motion sensors, which monitor indoor activity and help analyze user behavior patterns;

[0258] Noise sensors to monitor noise levels and further analyze the source and type of noise;

[0259] Spectral sensors, which detect the spectral composition of light to optimize the quality of indoor lighting;

[0260] Meteorological sensors are used to monitor outdoor weather conditions, including wind speed, wind direction, and rainfall, to better regulate the indoor environment.

[0261] Through the comprehensive application of these sensors, indoor and outdoor environmental parameters can be monitored more comprehensively and accurately, thus achieving more intelligent and personalized environmental control.

[0262] In a further improvement, the execution equipment includes an air conditioning system, a ventilation system, a humidifier, a dryer, an air purifier, a lighting system, a door and window control system, a heating system, an intelligent socket switch, a smoke alarm system, a flood alarm drainage system, an intelligent audio system, and a security alarm system;

[0263] Air conditioning systems, which are used to regulate the temperature and humidity of specific rooms in the house;

[0264] Ventilation system: fresh air system is used to introduce fresh air and exhaust polluted air in the room, especially when CO2 or VOC sensors detect that the air quality has deteriorated; exhaust fans are used to exhaust polluted air in the room to maintain air circulation;

[0265] Humidifiers, used to increase air humidity when the air is dry;

[0266] Dryers, used to reduce humidity when air humidity is too high;

[0267] Air purifier, used to purify harmful substances such as PM2.5 and VOC in the air to ensure indoor air quality;

[0268] Lighting system, using intelligent lighting to automatically adjust brightness and color temperature based on light sensors and user needs; using scene lighting to provide appropriate lighting modes based on user behavior and scene settings;

[0269] Door and window control system, using automatic curtains to automatically open or close curtains according to the detection results of light sensors; using smart doors and windows to automatically open and close doors and windows and adjust ventilation according to environmental needs;

[0270] Heating system, using floor heating to provide comfortable indoor temperature through floor heating; using radiators to provide auxiliary heating indoors;

[0271] Smart socket switch, used to control the switch status of various electrical equipment;

[0272] Smoke alarm system, used to sound an alarm and activate corresponding smoke exhaust equipment when smoke is detected;

[0273] Flood alarm and drainage system, used to sound an alarm and activate drainage equipment when flooding is detected to prevent damage caused by flooding;

[0274] Intelligent audio system, used to adjust the volume and playback content of audio equipment according to noise sensors and user needs;

[0275] The security alarm system uses a burglar alarm to trigger an alarm and notify the user when abnormal activities are detected; a fire alarm is used to automatically alarm and initiate relevant protective measures when smoke or high temperature is detected.

[0276] Through these actuators, the system can automatically adjust the indoor environment based on the data provided by sensors to ensure user comfort and safety while improving energy efficiency.

[0277] Specifically, the self-learning algorithm is based on the cooperation between the central control unit and the cloud server, and uses machine learning algorithms to analyze and learn historical data to continuously optimize the control strategy; by identifying the user's daily behavior patterns, the system pre-adjusts indoor environmental parameters to improve user comfort;

[0278] The user behavior analysis model is based on the system obtaining the user's location information and activity status data through smartphones and smart watch devices, and combining the data from the sensor network to analyze the user's behavior habits;

[0279] The system has a built-in anomaly detection module to monitor changes in sensor data in real time, detect and handle abnormal situations in a timely manner, and issue alerts to users.

[0280] In summary, through multi-sensor fusion, self-learning algorithm and user behavior analysis, efficient and intelligent indoor environment control is achieved, user comfort and energy saving effects are improved; multi-sensor fusion technology improves the detection accuracy of environmental parameters and makes environmental control more accurate; through machine learning algorithm, the system can self-optimize control strategy and improve the intelligence level of environmental control; based on user behavior analysis, the system can provide personalized environmental adjustment solutions to improve user comfort; through intelligent control, the system can achieve efficient energy saving while ensuring comfort.

[0281] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0282] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An indoor environment control method based on the Internet of Things, characterized in that: The method comprises the following steps: S1, system initialization: The indoor environment control system includes a sensor network module, a central control unit and a cloud server. When the system is started for the first time, the sensor network module starts to collect environmental data, the central control unit performs preliminary processing, and transmits the data to the cloud server; the cloud server uses the data to establish a preliminary user behavior model and environmental control strategy; S2, real-time data processing: the sensor network monitors environmental parameters in real time and transmits the data to the central control unit through the IoT gateway; the central control unit uses edge computing capabilities to perform preliminary data processing and adjust the operating status of the execution equipment according to the preset control strategy; S3, data analysis and optimization: The cloud server regularly analyzes the collected data and updates the user behavior model and environmental control strategy. Through self-learning algorithms, the system can identify user behavior patterns and optimize control strategies based on these patterns. The user behavior model and environment control strategy are updated through a self-learning algorithm, and the time series prediction model in supervised learning in machine learning is used. The specific method steps include the following: Preprocess the environmental data and user behavior data collected from the sensor network; Extract key features and construct feature vectors based on the time sequence. Divide the dataset into training and test sets in chronological order to ensure that the model can make predictions based on historical data; Use the LSTM model for training. The LSTM model is suitable for processing time series data and can capture long-term dependencies in time series. Use the trained LSTM model to predict future environmental parameters and user behaviors; Adjust environmental control strategies based on prediction results to optimize user experience; LSTM unit formula: Input gate: i t =σ(W i ·[h t-1 ,x t ]+b i ); Forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f ); Output gate: o t =σ(W o ·[h t-1 ,x t ]+b o ); Candidate memory cells: Memory unit update: Hide status update:h t =o t *tanh(C t ); Loss function: Use mean square error as the loss function: Among them, y i is the actual value, is the predicted value; Optimization algorithm: Use the back-propagation through time algorithm to train the LSTM model and use the optimization algorithm to update the model parameters; S4, anomaly detection and response: The system's built-in anomaly detection module monitors changes in sensor data in real time. When an abnormal situation is detected, the system will automatically turn on response protection and issue an alarm to the user.

2. The indoor environment control method based on the Internet of Things according to claim 1 is characterized in that: The specific steps for establishing a preliminary user behavior model and environmental control strategy include the following: S101, preliminary user behavior model establishment: Behavior pattern recognition: Based on user input preferences and sensor data, use data clustering algorithms to identify preliminary user behavior patterns; Time series analysis: Use time series analysis methods to analyze the temporal variation patterns of sensor data and establish a preliminary time series model of user daily behavior; S102, Environmental Control Strategy Development: Rule setting: Formulate basic environment control rules based on the initial preferences and behavior patterns input by users; Preliminary strategy generation: Using optimization algorithms, a preliminary environmental control strategy is generated while ensuring user comfort; Multi-objective optimization: In the process of generating preliminary strategies, consider the balance of multiple objectives and perform multi-objective optimization; S103, Model Verification and Adjustment: Simulation: Conduct simulation on the cloud server to verify the effectiveness of the preliminary user behavior model and environmental control strategy; User feedback adjustment: Based on user feedback, adjust the preliminary behavior model and control strategy to ensure that it meets the actual needs of users.

3. The indoor environment control method based on the Internet of Things according to claim 2 is characterized in that: The specific steps of using data clustering algorithm include the following: S1011, Data Standardization: Standardize the collected sensor data to ensure that data of different dimensions can be compared on the same scale; Standardization formula: Among them, x is the original data, μ is the mean, and σ is the standard deviation; S1012, select initial cluster center: Randomly select K data points as initial cluster centers; S1013, calculate distance and assign data points: Calculate the Euclidean distance between each data point and each cluster center, and assign the data point to the cluster center with the closest distance; Euclidean distance formula: Among them, x i is the data point, μ j is the cluster center, n is the dimension of the feature; S1014, update cluster center: Calculate the mean of each cluster as the new cluster center; New cluster center formula: Among them, C j is the jth cluster, |C j | is the number of data points in the jth cluster; S1015, repeat steps 3 and 4: Until the cluster center no longer changes or the change is less than the set threshold.

4. The indoor environment control method based on the Internet of Things according to claim 2 is characterized in that: The specific steps of using time series analysis method are: S10101, Data Stabilization: Perform difference operation on time series data to make it stationary; First-order difference formula: y′ t =y t -y t-1 ; S10102, determine model parameters: The parameters (p, d, q) of the ARIMA model are determined using the autocorrelation function and partial autocorrelation function graphs; p is the number of AR terms, d is the difference order, and q is the number of MA terms; S10103, model fitting: Using the determined parameters, fit the ARIMA model; ARIMA model formula: Among them, α is a constant term, φ i is the AR term coefficient, θ j is the MA term coefficient, ∈ t is a random error; S10104, Model Check: Check whether the residual sequence of the model is white noise to ensure that the model fits well; S10105, Prediction and Verification: The fitted ARIMA model is used for forecasting and compared with the actual data to verify the model effect.

5. The indoor environment control method based on the Internet of Things according to claim 2 is characterized in that: The specific steps of using the optimization algorithm include the following: S1021, define the objective function: Define the objective function of linear programming according to the optimization goal of the system. For example, minimize energy consumption; Objective function formula: Among them, c i is the cost of item i, x i is the decision variable of the ith item; S1022, establish constraints: Establish linear constraints based on the actual needs of the system; Constraint formula: Among them, a ij is the constraint coefficient, b i is the constraint constant; S1023, solve the linear programming problem: Use the standard linear programming algorithm to find the optimal solution of the objective function.

6. The indoor environment control method based on the Internet of Things according to claim 5 is characterized in that: Solving linear programming problems involves the simplex method steps, specifically: S10231, Standard Form Conversion: Convert the linear programming problem into standard form, where all constraints are equalities and all variables are non-negative; S10232, initial basic feasible solution: Select an initial basic feasible solution with all slack variables non-negative; S10233, calculate the test number: Compute the test number of the objective function: c′ j =c j -S i∈B c i a ij ; Among them, B is the index set of the current base variable, c i is the cost coefficient of the base variable, a ij is the constraint matrix element; S10234, inspection optimization direction: If all c′ j ≥0, the current solution is the optimal solution; otherwise, select a c′ j A non-basic variable < 0 enters a basic variable, which is called an entry-basic variable. S10235, calculate the variables to be swapped in and out: Calculate the ratio θ corresponding to all constraints: θ i : represents the maximum step length allowed by the current solution under the i-th constraint condition; b i : represents the constant term on the right side of the ith constraint in the current solution; a ij : represents the coefficient of the input variable in the i-th constraint; Select the base variable corresponding to the minimum positive proportional value as the swap variable; S10236, Update base variables: Update the basic variables and recalculate new basic variables and non-basic variables; S10237, iterative solution: Repeat steps 3-6 until the optimal solution is found.

7. The indoor environment control system based on the Internet of Things is characterized by: It includes sensor network module, central control unit, cloud server and execution equipment; The sensor network module is used to monitor indoor environmental parameters in real time, and uses multi-sensor fusion technology to comprehensively process data from different sensors to generate more accurate environmental parameters; The central control unit integrates edge computing capabilities for preliminary processing of sensor data and communicating with the cloud server via an IoT gateway; The cloud server is used to store and analyze data and run self-learning algorithms and user behavior analysis models; The execution device is used to adjust the indoor environment.

8. The indoor environment control system based on the Internet of Things according to claim 7 is characterized in that: The sensor network module includes a temperature sensor, a humidity sensor, a light sensor, a CO2 sensor, a VOC sensor, a human presence sensor, a door and window status sensor, a water immersion sensor, a smoke sensor, a pressure sensor, a motion sensor, a noise sensor, a spectrum sensor and a meteorological sensor; Temperature sensor, used to monitor the temperature of every corner of the room in real time, so as to adjust the precise indoor temperature; Humidity sensor, used to monitor the humidity in every corner of the room in real time, so as to adjust the precise indoor humidity; Light sensors are used to monitor the indoor area close to sunlight and adjust the indoor lighting system according to the lighting conditions; CO2 sensor, used to monitor indoor carbon dioxide concentration and adjust the ventilation system to ensure fresh air; VOC sensor, which detects the concentration of volatile organic compounds and helps identify harmful gases in the air; Human presence sensor, used to detect whether there is someone in the room, so as to adjust the environmental parameters according to the actual usage; Door and window status sensors are used to monitor the open and closed status of doors and windows to help adjust the temperature and ventilation system; Water sensors are used to detect possible water flooding in the room, especially in areas such as kitchens and bathrooms; Smoke sensor, used to detect smoke concentration and prevent fire; Pressure sensors are used to monitor pressure changes in building structures to ensure building safety; Motion sensors, which monitor indoor activity and help analyze user behavior patterns; Noise sensors to monitor noise levels and further analyze the source and type of noise; Spectral sensors, which detect the spectral composition of light to optimize the quality of indoor lighting; Meteorological sensors are used to monitor outdoor weather conditions, including wind speed, wind direction, and rainfall, to better regulate the indoor environment.

9. The indoor environment control system based on the Internet of Things according to claim 7, characterized in that: The execution equipment includes air conditioning systems, ventilation systems, humidifiers, dryers, air purifiers, lighting systems, door and window control systems, heating systems, smart socket switches, smoke alarm systems, flood alarm and drainage systems, smart audio systems and security alarm systems; Air conditioning systems, which are used to regulate the temperature and humidity of specific rooms in the house; Ventilation system: fresh air system is used to introduce fresh air and exhaust polluted air in the room, especially when CO2 or VOC sensors detect that the air quality has deteriorated; exhaust fans are used to exhaust polluted air in the room to maintain air circulation; Humidifiers, used to increase air humidity when the air is dry; Dryers, used to reduce humidity when air humidity is too high; Air purifier, used to purify harmful substances such as PM2.5 and VOC in the air to ensure indoor air quality; Lighting system, using smart lights to automatically adjust brightness and color temperature based on light sensors and user needs; Use scene lighting to provide appropriate lighting modes based on user behavior and scene settings; Door and window control system, using automatic curtains to automatically open or close curtains according to the detection results of light sensors; using smart doors and windows to automatically open and close doors and windows and adjust ventilation according to environmental needs; Heating system, using floor heating to provide comfortable indoor temperature through floor heating; using radiators to provide auxiliary heating indoors; Smart socket switch, used to control the switch status of various electrical equipment; Smoke alarm system, used to sound an alarm and activate corresponding smoke exhaust equipment when smoke is detected; Flood alarm and drainage system, used to sound an alarm and activate drainage equipment when flooding is detected to prevent damage caused by flooding; Intelligent audio system, used to adjust the volume and playback content of audio equipment according to noise sensors and user needs; The security alarm system uses a burglar alarm to trigger an alarm and notify the user when abnormal activities are detected; a fire alarm is used to automatically alarm and initiate relevant protective measures when smoke or high temperature is detected.

10. The indoor environment control system based on the Internet of Things according to claim 7, characterized in that: The self-learning algorithm is based on the cooperation between the central control unit and the cloud server. It uses machine learning algorithms to analyze and learn historical data and continuously optimize control strategies. By identifying the user's daily behavior patterns, the system pre-adjusts indoor environmental parameters to improve user comfort. The user behavior analysis model is based on the system obtaining the user's location information and activity status data through smartphones and smart watch devices, and combining the data from the sensor network to analyze the user's behavior habits; The system has a built-in anomaly detection module to monitor changes in sensor data in real time, detect and handle abnormal situations in a timely manner, and issue alerts to users.

Citation Information

Patent Citations

  • Blast furnace batching optimization method based on linear programming

    CN103092087A

  • Method for predicting industrial sewage inflow based on ARIMA model

    CN108564229A

  • Commodity recommendation method based on countermeasure network, electronic device and storage medium

    CN109509056A

  • Thermal power generating unit climbing pressure relieving method under high-proportion photovoltaic grid connection

    CN110854910A

  • Hydraulic structure multi-effect-quantity optimization prediction and visualization method based on LSTM network

    CN112131794A

Cited By

  • Light emitting diode intelligent dimming system based on multispectral control

    CN119697842A

  • Household intelligent environment regulation and control system

    CN119805948A

  • Steam cabinet alarm control system based on mode recognition

    CN119937312A

  • Air conditioner energy-saving control method and system based on smart cloud analysis

    CN119983484A

  • Intelligent household equipment adaptive control method and system based on artificial intelligence

    CN120196003A