A five-eternal household microenvironment control system

Abstract

The present invention discloses a five-constant home microenvironment control system, which relates to the technical field of smart home. The indoor environment is divided into a number of monitoring areas, and the indoor environmental parameters in each monitoring area are obtained in real time. According to the indoor environmental parameters and a preset control strategy, the current environmental conditions are analyzed, and corresponding control instructions are generated. The working state of the equipment is adjusted through the control instructions to achieve the expected environmental effect. The user adjusts the environmental parameters through real-time monitoring and remote control of the home environment according to the expected environmental effect; according to the user's living habits and environmental effects, the user's behavior changes are predicted, it is determined whether the environmental control needs to be adjusted, and an environmental control plan is designed; the indoor environment is intelligently regulated through the environmental control plan, so as to dynamically adjust the environmental control plan, which not only improves the user's quality of life and comfort, but also effectively saves energy and reduces resource waste, thereby realizing the promotion and sustainable development of smart homes.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a five-constant home microenvironment control system. Background Art

[0002] Wuheng home environment control refers to the use of intelligent technology to monitor and adjust the temperature, humidity, air quality and other parameters of the indoor environment to achieve intelligent management of the home environment. It includes sensors, actuators, controllers and other equipment. Through the Internet connection, users can monitor and remotely control the home environment in real time through mobile phones, tablets and other terminals, adjust the working status of air conditioners, humidifiers, purifiers and other equipment, and improve living comfort and energy efficiency. This smart home system not only provides a convenient lifestyle, but also helps save energy, improve indoor air quality, and improve living quality.

[0003] The existing Wuheng Home Furnishing micro-environment control system realizes automated management and intelligent services through data analysis and intelligent algorithms. The system can analyze the user's living habits and environmental needs, and provide personalized environmental control solutions through big data analysis and prediction of user behavior. However, there are some shortcomings in the existing technology: although the system can predict the user's daily activity patterns by analyzing past data, the user's life may change due to various external factors, such as work arrangements, social activities, holidays, etc. If the system fails to capture these changes in time and adjust them, it may cause the system to incorrectly predict the user's activity time, and then provide inappropriate environmental control solutions, affecting the user's comfort and experience. Summary of the invention

[0004] The purpose of the present invention is to provide a five-constant home microenvironment control system to address the deficiencies in the background technology.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a five-constant home microenvironment control system, comprising a data acquisition module, a control module, an execution module, a user terminal, a data analysis module and an intelligent control module;

[0006] Data acquisition module: divides the indoor environment into several monitoring areas, obtains the indoor environmental parameters in each monitoring area in real time, and sends the indoor environmental parameters to the control module;

[0007] Control module: used to analyze the current environmental conditions according to the indoor environmental parameters sent by the data acquisition module and the preset control strategy, and generate corresponding control instructions, and send the control instructions to the execution module;

[0008] Execution module: used to receive the instruction sent by the control module to adjust the working state of the equipment to achieve the expected environmental effect, and send the expected environmental effect to the user terminal;

[0009] User terminal: Users can monitor and remotely control the home environment in real time and adjust environmental parameters according to the expected environmental effects;

[0010] Data analysis module: predicts user behavior changes based on user living habits and environmental effects, determines whether environmental control needs to be adjusted, and designs environmental control plans;

[0011] Intelligent control module: Intelligently control the indoor environment through environmental control solutions, and further analyze and predict the control effects, so as to dynamically adjust the environmental control solutions.

[0012] In a preferred embodiment, in the data acquisition module, the indoor environment is divided into several monitoring areas according to the house structure and usage requirements, and sensors are installed at locations selected in each area to monitor environmental parameters, including ambient temperature, humidity and air quality data.

[0013] In a preferred embodiment, the control of environmental parameters is achieved through fuzzy sets and rule bases, specifically:

[0014] Converting the input environmental parameters into fuzzy data in a fuzzy set, including determining the membership functions of the fuzzy variables and the fuzzy set;

[0015] Select the environmental parameters that need to be controlled, determine the input variables and output variables, divide each variable into several fuzzy sets, define the membership function for each fuzzy set, and convert the exact value of the input variable into a fuzzy value through the membership function;

[0016] Establish a fuzzy rule base, which contains several fuzzy control rules, and each rule describes the relationship between the input fuzzy variables and the output fuzzy variables;

[0017] According to the fuzzy rule base, the fuzzified input data is inferred to generate fuzzy output results, the activation strength of each rule is calculated, and the outputs of all rules are combined to generate a comprehensive fuzzy output;

[0018] The fuzzy output generated by the inference engine is converted into precise control instructions, the fuzzy output is converted into specific control values, and the precise control values ​​obtained by defuzzification are sent to the corresponding actuator modules to adjust the working state of the equipment.

[0019] In a preferred embodiment, in the data analysis module, the user behavior abnormality index is obtained according to the user's activity pattern, and the temperature and humidity data of each time period are extracted according to the environmental parameters to obtain the environmental control effect abnormality index.

[0020] In a preferred embodiment, the method for obtaining the user behavior abnormality index is:

[0021] Collect historical data of users, including activity time period and activity range, preprocess the data, and use the EM algorithm to fit the Gaussian mixture model, where the Gaussian mixture model is: Where K is the number of Gaussian components, φ i is the weight of the i-th Gaussian component, satisfying N(x|μ i ,Σ i ) is the multivariate Gaussian distribution of the i-th Gaussian component, where μ i is the mean vector, Σ i is the covariance matrix;

[0022] For each data point x, calculate its probability density p(x) in the model. Use the probability density function of the model to calculate, that is, substitute the data point x into the expression of the above Gaussian mixture model, and calculate the user behavior anomaly index, that is, the inverse of the probability density of the data point x in the model. The specific calculation expression is: Where KB is the user behavior abnormality index.

[0023] In a preferred embodiment, the method for obtaining the abnormal index of environmental control effect is:

[0024] Acquire temperature and humidity data in real time for each time period, establish corresponding training data sets, design and train a deep generative adversarial network, which includes a generator and a discriminator. The generator is responsible for generating false environmental parameter data, while the discriminator is responsible for distinguishing between real environmental parameter data and false environmental parameter data generated by the generator.

[0025] The calculation expression of the probability of the false environmental parameter data generated by the generator is: LG = -logD(G(z)); where G(z) is the false environmental parameter data generated by the generator, D is the discriminator, and LG is the probability of the generator generating false environmental parameters;

[0026] After training the deep generative adversarial network, the generator is used to generate some false environmental parameter data, which are input into the discriminator. The discriminator will classify them to determine whether they are false environmental parameter data. The calculation expression of the discriminator's discrimination probability for false environmental parameter data is: LD = -logD(x)-log(1-D(G(z))); where LD is the discriminator's discrimination probability, and x is the real environmental parameter data;

[0027] The calculated false environment parameter generation probability of the generator and the discrimination probability of the discriminator are analyzed to calculate the abnormal index of the environmental control effect. The specific calculation expression is: Where GH is the abnormal index of environmental control effect.

[0028] In a preferred embodiment, the user behavior abnormality index and the environmental control effect abnormality index are normalized, and the abnormality evaluation coefficient of the user's behavior and the expected pattern is calculated based on the normalized user behavior abnormality index and the environmental control effect abnormality index.

[0029] In a preferred embodiment, the acquired abnormal assessment coefficient of the user's behavior and expected pattern is compared with the reference threshold of the abnormal assessment coefficient in the historical data. If the abnormal assessment coefficient of the user's behavior and expected pattern is greater than or equal to the reference threshold of the abnormal assessment coefficient, an environmental control abnormal signal is generated to notify the execution module to make corresponding environmental adjustments; if the abnormal assessment coefficient of the user's behavior and expected pattern is less than the reference threshold of the abnormal assessment coefficient, an environmental control normal signal is generated and no adjustment is required.

[0030] In a preferred embodiment, in the intelligent control module, first, at each time point t, according to the current indoor environment abnormality assessment coefficient KM, a corresponding environmental control scheme Ct is generated, Ct = f(KM); f is the output function of the model, and then, the control effect is analyzed and predicted, and the prediction expression is: At = g(Ct, H(t-1)); wherein At represents the control effect at time t, H(t-1) represents the historical data at time t-1, and g is the prediction function; finally, according to the current environmental control scheme Ct and the control effect At, a new environmental control scheme C(t+1( is dynamically adjusted to realize intelligent control of the indoor environment, and the specific control expression is: C(t+1) = h(Ct, At); wherein C(t+1) represents the control scheme at time t+1, and h is the control function.

[0031] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0032] 1. The present invention monitors indoor environmental parameters in real time through the data acquisition module. The control module analyzes the environmental conditions according to these parameters and the preset control strategy, and generates corresponding control instructions. The execution module adjusts the working state of the equipment to achieve the expected environmental effect. The intelligent control module predicts changes in user behavior based on data analysis, dynamically adjusts the environmental control scheme, and realizes intelligent adjustment of the indoor environment. Such intelligent environmental control can improve the user's living comfort and allow users to enjoy a high-quality living environment without too much intervention.

[0033] 2. The present invention predicts user behavior changes and designs personalized environmental control solutions based on the user's living habits and environmental requirements through the data analysis module. The system can dynamically identify user behavior patterns and environmental conditions, provide users with customized services, and meet users' personalized needs for different time periods and different environments. This personalized service can not only improve user experience, but also enhance the user stickiness and market competitiveness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0037] Example 1

[0038] See also Figure 1 As shown, a five-constant home microenvironment control system described in this embodiment includes a data acquisition module, a control module, an execution module, a user terminal, a data analysis module and an intelligent control module;

[0039] Data acquisition module: divides the indoor environment into several monitoring areas, obtains the indoor environmental parameters in each monitoring area in real time, and sends the indoor environmental parameters to the control module;

[0040] Control module: used to analyze the current environmental conditions according to the indoor environmental parameters sent by the data acquisition module and the preset control strategy, and generate corresponding control instructions, and send the control instructions to the execution module;

[0041] Execution module: used to receive the instruction sent by the control module to adjust the working state of the equipment to achieve the expected environmental effect, and send the expected environmental effect to the user terminal;

[0042] User terminal: Users can monitor and remotely control the home environment in real time and adjust environmental parameters according to the expected environmental effects;

[0043] Data analysis module: predicts user behavior changes based on user living habits and environmental effects, determines whether environmental control needs to be adjusted, and designs environmental control plans;

[0044] Intelligent control module: Intelligently control the indoor environment through environmental control solutions, and further analyze and predict the control effects, so as to dynamically adjust the environmental control solutions.

[0045] Among them, in the data acquisition module, the indoor environment is divided into several monitoring areas, and the indoor environmental parameters in each monitoring area are acquired in real time, and the indoor environmental parameters are sent to the control module.

[0046] According to the house structure and usage requirements, the indoor environment is divided into several monitoring areas. For example, the living room, bedroom, kitchen and bathroom, etc. Each area can be further subdivided according to the size of the space. Select a suitable location in each area to install sensors to ensure that the environmental parameters of the area can be fully covered.

[0047] It should be noted here that the division of regions should take into account the uniformity of environmental parameters and the concentration of user activities. The size and number of each monitoring area should be reasonably set according to the size and layout of the room.

[0048] Select the appropriate sensor type based on the environmental parameters that need to be monitored, including ambient temperature, humidity, and air quality data. Install the sensor at the predetermined monitoring point to ensure that the sensor can stably obtain environmental data. At the same time, ensure that the sensor is installed in a location that will not be disturbed by external factors, such as direct sunlight, vents, etc. The sensor should be installed firmly to avoid inaccurate data collection due to vibration or movement.

[0049] The sensor collects environmental parameters in the monitoring area in real time, such as temperature, humidity, carbon dioxide concentration, PM2.5 concentration, etc. The collected data is sent to the control module through a wireless network (such as Wi-Fi, ZigBee, Bluetooth, etc.) or a wired network (such as Ethernet). At the same time, it is necessary to ensure that the communication between the sensor and the control module is stable and has low latency. Data transmission should have certain encryption measures to ensure data security.

[0050] Control module: used to analyze the current environmental conditions according to the indoor environmental parameters sent by the data acquisition module and the preset control strategy, and generate corresponding control instructions, and send the control instructions to the execution module.

[0051] The controller module is used to receive environmental data from the sensor module, including ambient temperature, humidity and air quality data.

[0052] The controller module needs to design multiple interfaces to receive data from different types of sensors, usually using standardized communication protocols (such as Wi-Fi, Zigbee, Bluetooth). The received data may contain information such as timestamp, sensor ID, data value, etc. The data format needs to be standardized for subsequent processing. The received data often contains noise and outliers, and needs to be preprocessed to ensure the accuracy of subsequent analysis and control instructions. Remove missing values, duplicate values, and obvious erroneous data. For example, if the data of a temperature sensor suddenly jumps to an extremely high or low value, it may be faulty data and needs to be cleaned. Convert data of different dimensions to the same dimension range for subsequent processing and analysis.

[0053] Fuzzy logic is used to transform expert experience and rules into control strategies, which are applicable to nonlinear and complex systems. The control of environmental parameters is achieved through fuzzy sets and rule bases, specifically:

[0054] Converting the input environmental parameters into fuzzy data in a fuzzy set, including determining the membership functions of the fuzzy variables and the fuzzy set;

[0055] Select the environmental parameters that need to be controlled (such as temperature, humidity, air quality).

[0056] Determine the input variables (such as the current temperature) and the output variables (such as the cooling power of the air conditioner).

[0057] Divide each variable into several fuzzy sets (such as temperature can be divided into "low", "medium", and "high").

[0058] A membership function is defined for each fuzzy set, usually using triangular, trapezoidal or Gaussian membership functions.

[0059] The exact value of the input variable is converted into a fuzzy value through a membership function. For example, if the current temperature is 25℃, it may belong to both "medium" and "high" fuzzy sets, but with different membership degrees.

[0060] According to expert experience and actual needs, a fuzzy rule base is established. The rule base contains several fuzzy control rules, each of which describes the relationship between input fuzzy variables and output fuzzy variables.

[0061] Use If-Then statements to define rules. For example: If Temperature is High and Humidity is Low, Then Air Conditioning Power is High.

[0062] If temperature is medium and humidity is medium,Then air conditioning power is medium.

[0063] If the temperature is low and the humidity is high, Then the air conditioning power is low.

[0064] Build a rule base that covers all possible situations to ensure that there is a corresponding control strategy for each environmental state.

[0065] According to the fuzzy rule base, the fuzzified input data is inferred to generate fuzzy output results. Commonly used inference methods are Mamdani reasoning and Sugeno reasoning. Among them, Mamdani reasoning: It is suitable for situations where fuzzy values ​​need to be output, and it is intuitive and easy to understand. Sugeno reasoning: It is suitable for situations where precise output is required, and it has high computational efficiency.

[0066] According to the fuzzy rule base, apply If-Then rules to the fuzzified input variables, calculate the activation strength of each rule, and combine the outputs of all rules to generate a comprehensive fuzzy output.

[0067] Convert the fuzzy output generated by the inference engine into precise control instructions. Common defuzzification methods include centroid method and maximum membership method. Centroid Method: Calculate the centroid of the fuzzy output to get an exact value. Max Membership Method: Select the value corresponding to the fuzzy set with the largest membership.

[0068] According to the selected method, the fuzzy output is converted into a specific control value. For example, the air conditioning power is converted from a fuzzy value to an actual power percentage.

[0069] The precise control value obtained by defuzzification is sent to the corresponding actuator module to adjust the working state of the equipment.

[0070] Execution module: used to receive the instructions sent by the control module to adjust the working state of the equipment to achieve the expected environmental effect, and send the expected environmental effect to the user terminal.

[0071] When the system starts, the execution module needs to be initialized and connected to ensure that it can normally receive control instructions and feedback environmental effects.

[0072] Initialize all connected devices (such as air conditioners, humidifiers, purifiers). Check the operating status of the device to ensure that the device is in normal working condition. Perform a self-test of the device to ensure that there are no faults or abnormalities.

[0073] Establish a communication connection with the controller module, usually through a wireless network (such as Wi-Fi, Zigbee, Bluetooth). Establish a communication connection with the user terminal to ensure that feedback data can be sent to the user terminal.

[0074] The execution module needs to continuously listen to the instructions from the controller module, and parse and execute the received instructions. Continuously listen to the control instructions sent by the controller module to ensure real-time response. Receive instructions using the selected communication protocol (such as MQTT, HTTP, CoAP). Parse the received control instructions and extract the device ID, control parameters, and target values ​​in the instructions. Check the integrity and correctness of the instructions to ensure that there are no errors or omissions.

[0075] According to the analyzed control instructions, adjust the working state of each device to achieve the expected environmental effect. Adjust the working mode (such as cooling, heating, ventilation) and power of the air conditioner according to the control instructions. Adjust the temperature setting value and wind speed of the air conditioner to achieve the expected temperature effect. Adjust the working state (such as on, off) and power of the humidifier according to the control instructions. Adjust the humidity setting value of the humidifier to achieve the expected humidity effect. Adjust the working mode (such as automatic, manual) and wind speed of the air purifier according to the control instructions. Adjust the operating intensity of the purifier according to the air quality parameters (such as PM2.5, VOC).

[0076] During the operation of the equipment, the execution module needs to monitor the working status and environmental parameters of the equipment in real time and send feedback data to the user terminal.

[0077] User terminal: Users can monitor and remotely control the home environment and adjust environmental parameters according to the expected environmental effects.

[0078] When the user terminal starts, it needs to be initialized and connected to the controller module and the execution module. Start the user terminal application (APP). Initialize the user interface and load the preset configuration and user preferences. Establish a communication connection with the controller module, usually through the Internet (such as Wi-Fi, mobile data). Establish a communication connection with the execution module to ensure that control instructions can be sent and feedback data can be received.

[0079] The user terminal needs to display the current status of the home environment and the working status of the equipment in real time. Display real-time environmental parameters on the user interface, including temperature, humidity, air quality, etc. Use charts or graphs to intuitively display environmental change trends (such as temperature curves, humidity curves). Display the current working status of each device (such as air conditioners, humidifiers, air purifiers), including working mode, power, set value, etc. Provide real-time feedback information on the operation of the equipment to ensure that users understand the actual working conditions of the equipment.

[0080] Users can adjust environmental parameters through the user terminal to achieve the desired environmental effect. Provide a friendly graphical user interface (GUI) so that users can easily view and adjust environmental parameters. Through controls such as sliders, buttons, and drop-down menus, users can set temperature, humidity, and air quality target values. Set the parameters, temperature setting: users can adjust the target temperature range (such as 20-25℃). Humidity setting: users can adjust the target humidity range (such as 40%-60%). Air quality setting: users can adjust the target air quality indicators (such as PM2.5 concentration, carbon dioxide concentration).

[0081] The new parameters set by the user are sent to the controller module instantly through the APP. The controller module adjusts the control strategy according to the new parameters and generates new control instructions. Users can remotely control the working status of home environment devices through the user terminal. Provides a device control interface to display the status and available operations of each device. Users can select devices and perform operations, such as turning on / off, adjusting modes, and setting power.

[0082] The user's operation generates corresponding control instructions through the APP. The control instructions are sent to the controller module through the Internet, and then sent by the control module to the execution module for execution.

[0083] The user terminal needs to receive and display real-time feedback information from the execution module and the control module. Display the feedback data of the execution module, including the current status of the device and environmental parameters. Provide real-time updated environmental data to ensure that users can keep abreast of changes in the home environment.

[0084] Data analysis module: predict user behavior changes based on user living habits and environmental effects, determine whether environmental control adjustments are needed, and design environmental control plans.

[0085] Collect historical data of users, including wake-up time, bedtime, activity time period, environmental parameters, etc. Preprocess the collected data, including removing outliers, filling missing values, and normalizing data.

[0086] Features are extracted from the collected data. The user's daily activity pattern is extracted based on the activity time period, and the temperature, humidity and other information of each time period are extracted based on the environmental parameters.

[0087] Obtain the user behavior abnormality index based on the user's activity pattern, and extract the temperature and humidity data of each time period based on the environmental parameters to obtain the environmental control effect abnormality index;

[0088] Among them, the method for obtaining the user behavior abnormality index is:

[0089] Collect historical data of users, including activity time period and activity range, pre-process the data, and use the EM algorithm to fit the Gaussian mixture model, where the Gaussian mixture model is: Where K is the number of Gaussian components, φ i is the weight of the i-th Gaussian component, satisfying N(x|μ i ,Σ i ) is the multivariate Gaussian distribution of the i-th Gaussian component, where μ i is the mean vector, Σ i is the covariance matrix;

[0090] For each data point x, calculate its probability density p(x) in the model. Use the probability density function of the model to calculate, that is, substitute the data point x into the expression of the above Gaussian mixture model, and calculate the user behavior anomaly index, that is, the inverse of the probability density of the data point x in the model. The specific calculation expression is: Where KB is the user behavior abnormality index.

[0091] When the user behavior anomaly index is large, it means that the user's behavior is significantly different from the expected pattern, and the environment may need to be controlled and adjusted to adapt to the user's changed behavior.

[0092] In the present invention, the user's historical activity pattern is modeled, and the user's behavior abnormality is quantified using a Gaussian mixture model according to the activity time period and activity range, thereby obtaining the user behavior abnormality index. In this way, the system can identify the deviation of the user's behavior from the normal pattern, and then determine whether the user's behavior requires environmental control adjustment. This intelligent environmental control system can provide users with a personalized comfort experience, adjust the indoor environment according to the user's real-time behavioral changes, and enable users to live and work more comfortably. Through real-time monitoring of environmental parameters and intelligent analysis of user behavior, the system can effectively optimize the indoor environment and improve the user's quality of life, while also improving the system's intelligence level and user experience.

[0093] The method for obtaining the abnormal index of environmental control effect is as follows:

[0094] Acquire temperature and humidity data in real time for each time period, establish corresponding training data sets, design and train a deep generative adversarial network, which includes a generator and a discriminator. The generator is responsible for generating false environmental parameter data, while the discriminator is responsible for distinguishing between real environmental parameter data and false environmental parameter data generated by the generator.

[0095] The calculation expression of the probability of the false environmental parameter data generated by the generator is: LG = -logD(G(z)); where G(z) is the false environmental parameter data generated by the generator, D is the discriminator, and LG is the probability of the generator generating false environmental parameters;

[0096] After training the deep generative adversarial network, the generator is used to generate some false environmental parameter data, which are input into the discriminator. The discriminator will classify them to determine whether they are false environmental parameter data. The calculation expression of the discriminator's discrimination probability for false environmental parameter data is: LD = -logD(x)-log91-D(G(z))); where LD is the discriminator's discrimination probability, and x is the real environmental parameter data;

[0097] The calculated false environment parameter generation probability of the generator and the discrimination probability of the discriminator are analyzed to calculate the abnormal index of the environmental control effect. The specific calculation expression is: Where GH is the abnormal index of environmental control effect.

[0098] When the environmental control effect abnormality index is larger, it means that the generated false environmental parameter data is more likely to be mistaken for real data by the discriminator, that is, the discriminator has a low classification accuracy for false data. This means that the difference between false data and real data is small, or the user's behavior is far from the expected pattern, resulting in the generated false data being unable to accurately simulate the distribution of real environmental parameters. Therefore, when the environmental control effect abnormality index is larger, it means that the deviation between the user's behavior and the expected pattern is greater, and the environmental control system may need more fine-tuning or personalized adaptation to provide an environmental control solution that better meets the actual needs of users.

[0099] The user behavior abnormality index and the environmental control effect abnormality index are normalized, and the abnormality evaluation coefficient of the user's behavior and the expected pattern is calculated based on the normalized user behavior abnormality index and the environmental control effect abnormality index.

[0100] For example, the present invention may use the following formula to calculate the abnormality assessment coefficient of the user's behavior and expected pattern, and the calculation expression is: Where KM is the abnormal evaluation coefficient, KB is the user behavior abnormal index, GH is the environmental control effect abnormal index, a1 and a2 are the proportional coefficients of the user behavior abnormal index and the environmental control effect abnormal index, and a2>a1>0.

[0101] The acquired abnormal assessment coefficient of the user's behavior and expected pattern is compared with the reference threshold of the abnormal assessment coefficient in the historical data. If the abnormal assessment coefficient of the user's behavior and expected pattern is greater than or equal to the reference threshold of the abnormal assessment coefficient, it means that there is a difference between the user's behavior and the expected pattern, and the effect of the indoor environment control may be abnormal. At this time, an environmental control abnormal signal is generated to notify the execution module to make corresponding environmental adjustments; if the abnormal assessment coefficient of the user's behavior and the expected pattern is less than the reference threshold of the abnormal assessment coefficient, it means that the user's behavior is basically consistent with the expected pattern, and the effect of the indoor environment control is normal. At this time, an environmental control normal signal is generated, indicating that the current environmental state is good and no adjustment is required.

[0102] Intelligent control module: Intelligently control the indoor environment through environmental control solutions, and further analyze and predict the control effects, so as to dynamically adjust the environmental control solutions.

[0103] First, at each time point t, according to the current indoor environment abnormality assessment coefficient KM, the corresponding environmental control scheme Ct is generated, Ct = f(KM), f is the output function of the model; then, the control effect is analyzed and predicted, and the prediction expression is: At = g(Ct, H(t-1)); wherein At represents the control effect at time t, H(t-1) represents the historical data at time t-1, and g is the prediction function; finally, according to the current environmental control scheme Ct and the control effect At, a new environmental control scheme C(t+1) is dynamically adjusted to realize intelligent control of the indoor environment. The specific control expression is: C(t+1) = h(Ct, At); wherein C(t+1) represents the control scheme at time t+1, and h is the control function.

[0104] It should be noted here that g(Ct, H(t-1)) represents the control effect at time t, which is calculated based on the current environmental control solution Ct and historical data H(t-1). Specifically, the g function may use machine learning models or statistical methods to predict the environmental control effect at the next time point by analyzing the current environmental parameters and historical data. The purpose of this function is to evaluate the effect of the current control solution and provide a reference for the next adjustment.

[0105] h(Ct, At) represents the new environmental control scheme at time t, which is dynamically adjusted according to the current environmental control scheme Ct and the control effect At. Specifically, the h function may be an optimization algorithm or rule system that adjusts the environmental control scheme to achieve better results based on the current control effect and goal. The purpose of this function is to dynamically adjust the environmental control scheme based on real-time monitoring of the environment and control effects to adapt to environmental changes and user needs.

[0106] In this embodiment, by dividing the indoor environment into several monitoring areas, and obtaining the indoor environmental parameters in each monitoring area in real time, and sending the indoor environmental parameters to the control module, the current environmental conditions are analyzed according to the indoor environmental parameters sent by the data acquisition module and the preset control strategy, and the corresponding control instructions are generated, and the control instructions are sent to the execution module; the instructions sent by the control module are received to adjust the working state of the equipment to achieve the expected environmental effect, and the expected environmental effect is sent to the user terminal; the user monitors and remotely controls the home environment in real time according to the expected environmental effect, and adjusts the environmental parameters; according to the user's living habits and environmental effects, predicts user behavior changes, determines whether the environmental control needs to be adjusted, and designs an environmental control plan; the indoor environment is intelligently regulated through the environmental control plan, and the regulation effect is further analyzed and predicted, so as to dynamically adjust the environmental control plan. All-round monitoring, analysis and regulation of the indoor environment are realized. From real-time acquisition of environmental parameters to adjustment of the environmental control plan according to user behavior prediction, and then to dynamic adjustment of the intelligent regulation module, the system can continuously provide a personalized and comfortable living environment. This intelligent environmental control not only improves the quality of life and comfort of users, but also effectively saves energy, reduces resource waste, and realizes the popularization and sustainable development of smart homes.

[0107] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0108] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0109] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0114] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A five-constant home microenvironment control system, characterized by: It includes data acquisition module, control module, execution module, user terminal, data analysis module and intelligent control module; Data acquisition module: divides the indoor environment into several monitoring areas, obtains the indoor environmental parameters in each monitoring area in real time, and sends the indoor environmental parameters to the control module; Control module: used to analyze the current environmental conditions according to the indoor environmental parameters sent by the data acquisition module and the preset control strategy, and generate corresponding control instructions, and send the control instructions to the execution module; Execution module: used to receive the instruction sent by the control module to adjust the working state of the equipment to achieve the expected environmental effect, and send the expected environmental effect to the user terminal; User terminal: Users can monitor and remotely control the home environment in real time and adjust environmental parameters according to the expected environmental effects; Data analysis module: predicts user behavior changes based on user living habits and environmental effects, determines whether environmental control needs to be adjusted, and designs environmental control plans; Intelligent control module: intelligently control the indoor environment through environmental control schemes, and further analyze and predict the control effects, so as to dynamically adjust the environmental control schemes; In the data analysis module, the user behavior abnormality index is obtained according to the user's activity pattern, and the temperature and humidity data of each time period are extracted according to the environmental parameters to obtain the environmental control effect abnormality index; Among them, the method for obtaining the user behavior abnormality index is: Collect historical data of users, including activity time period and activity range, pre-process the data, and use the EM algorithm to fit the Gaussian mixture model, where the Gaussian mixture model is: Where K is the number of Gaussian components, φ i is the weight of the i-th Gaussian component, satisfying N(x|μ i ,Σ i ) is the multivariate Gaussian distribution of the i-th Gaussian component, where μ i is the mean vector, Σ i is the covariance matrix; For each data point x, calculate its probability density p(x) in the model. Use the probability density function of the model to calculate, that is, substitute the data point x into the expression of the above Gaussian mixture model, and calculate the user behavior anomaly index, that is, the inverse of the probability density of the data point x in the model. The specific calculation expression is: Where KB is the user behavior abnormality index.

2. A five-constant home microenvironment control system according to claim 1, characterized in that: In the data acquisition module, the indoor environment is divided into several monitoring areas according to the house structure and usage requirements. Sensors are installed at locations selected in each area to monitor environmental parameters, including ambient temperature, humidity and air quality data.

3. A five-constant home microenvironment control system according to claim 2, characterized in that: The control of environmental parameters is achieved through fuzzy sets and rule bases, specifically: Converting the input environmental parameters into fuzzy data in a fuzzy set, including determining the membership functions of the fuzzy variables and the fuzzy set; Select the environmental parameters that need to be controlled, determine the input variables and output variables, divide each variable into several fuzzy sets, define the membership function for each fuzzy set, and convert the exact value of the input variable into a fuzzy value through the membership function; Establish a fuzzy rule base, which contains several fuzzy control rules, and each rule describes the relationship between the input fuzzy variables and the output fuzzy variables; According to the fuzzy rule base, the fuzzified input data is inferred to generate fuzzy output results, the activation strength of each rule is calculated, and the outputs of all rules are combined to generate a comprehensive fuzzy output; The fuzzy output generated by the inference engine is converted into precise control instructions, the fuzzy output is converted into specific control values, and the precise control values ​​obtained by defuzzification are sent to the corresponding actuator modules to adjust the working state of the equipment.

4. A five-constant home microenvironment control system according to claim 1, characterized in that: The method for obtaining the abnormal index of environmental control effect is as follows: Acquire temperature and humidity data in real time for each time period, establish corresponding training data sets, design and train a deep generative adversarial network, which includes a generator and a discriminator. The generator is responsible for generating false environmental parameter data, while the discriminator is responsible for distinguishing between real environmental parameter data and false environmental parameter data generated by the generator. The calculation expression of the probability of the false environmental parameter data generated by the generator is: LG = -log D(G(z)); where G(z) is the false environmental parameter data generated by the generator, D is the discriminator, and LG is the probability of the generator generating false environmental parameters; After training the deep generative adversarial network, the generator is used to generate some false environmental parameter data, which are input into the discriminator. The discriminator will classify them to determine whether they are false environmental parameter data. The calculation expression of the discriminator's discrimination probability for false environmental parameter data is: LD = -log D(x)-log(1-D(G(z))); where LD is the discriminator's discrimination probability, and x is the real environmental parameter data; The calculated false environment parameter generation probability of the generator and the discrimination probability of the discriminator are analyzed to calculate the abnormal index of the environmental control effect. The specific calculation expression is: Where GH is the abnormal index of environmental control effect.

5. A five-constant home microenvironment control system according to claim 4, characterized in that: The user behavior abnormality index and the environmental control effect abnormality index are normalized, and the abnormality evaluation coefficient of the user's behavior and the expected pattern is calculated based on the normalized user behavior abnormality index and the environmental control effect abnormality index.

6. A five-constant home microenvironment control system according to claim 5, characterized in that: The acquired abnormal assessment coefficient of the user's behavior and expected pattern is compared with the reference threshold of the abnormal assessment coefficient in the historical data. If the abnormal assessment coefficient of the user's behavior and expected pattern is greater than or equal to the reference threshold of the abnormal assessment coefficient, an environmental control abnormal signal is generated to notify the execution module to make corresponding environmental adjustments; if the abnormal assessment coefficient of the user's behavior and expected pattern is less than the reference threshold of the abnormal assessment coefficient, an environmental control normal signal is generated and no adjustment is required.

7. A five-constant home microenvironment control system according to claim 6, characterized in that: In the intelligent control module, first, at each time point t, according to the current indoor environment abnormality assessment coefficient KM, the corresponding environmental control scheme Ct is generated, Ct = f(KM); f is the output function of the model, and then, the control effect is analyzed and predicted, and the prediction expression is: At = g(Ct, H(t-1)); wherein At represents the control effect at time t, H(t-1) represents the historical data at time t-1, and g is the prediction function; finally, according to the current environmental control scheme Ct and the control effect At, a new environmental control scheme C(t+1) is dynamically adjusted to realize intelligent control of the indoor environment. The specific control expression is: C(t+1) = h(Ct, At); wherein C(t+1) represents the control scheme at time t+1, and h is the control function.

Images