An intelligent home controller and method based on adaptive control technology

Abstract

The present application relates to the technical field of home control, in particular to a smart home controller and method based on adaptive control technology, which comprises a collection and processing unit, an analysis and modeling unit, an adaptive unit, an optimization and prediction unit and an execution control unit; the optimization and prediction unit receives collected data, collected data after preprocessing, preprocessing data after analysis and modeling and data after adaptive adjustment to make optimization decisions, and intelligently predicts according to the collected data and the data after optimization strategy; the present application can intelligently predict future environmental changes and user behaviors, thereby adjusting the control strategy in advance, adjusting the air conditioner temperature in advance according to the user's work and rest rules and outdoor temperature, predicting that the user will not return home for a long time according to the user's positioning information and moving direction and speed, and turning off the air conditioner, lights and the like by using the execution control unit, which not only prepares a comfortable indoor environment for the user in advance, but also reduces energy waste.

Description

Technical Field

[0001] This invention relates to the field of home control technology, and more specifically, to a smart home controller and method based on adaptive control technology. Background Technology

[0002] In real life, we can see some smart home controls, such as manually controlling the air conditioner temperature through electronic devices, controlling the air conditioner temperature by voice, and automatically adjusting the air conditioner temperature. This brings benefits to users' lives. When they get home, they don't need to manually control the air conditioner temperature; they can directly control it by voice. They can also turn on the air conditioner and other devices in advance from a place close to home, preparing a comfortable indoor environment for themselves. From real life, it can be seen that smart air conditioners have brought great help to users' lives.

[0003] While smart air conditioners bring convenience to users, they also have limitations. For example, when the distance is far, voice-activated smart air conditioners cannot receive signals and cannot provide users with a convenient and comfortable environment in a timely manner. Electronic control devices also need to be within range to receive signals, so there is a distance limitation. At the same time, these smart air conditioners still require human operation and cannot adaptively adjust the air conditioning temperature according to the user's preferences. They can only adjust the air conditioning temperature automatically. For example, if the user prefers a lower temperature, a regular smart air conditioner will only automatically adjust the temperature according to its own set temperature range, resulting in the temperature fluctuating between high and low, which greatly reduces the user's experience. It cannot predict when the user will return home, nor can it prepare a comfortable indoor environment for the user in advance. Summary of the Invention

[0004] The purpose of this invention is to provide a smart home controller and method based on adaptive control technology to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, one of the objectives of this invention is to provide a smart home controller based on adaptive control technology, including a data acquisition and processing unit, an analysis and modeling unit, an adaptive unit, an optimization and prediction unit, and an execution and control unit.

[0006] The data acquisition and processing unit is used to acquire data and perform preprocessing operations on the acquired data.

[0007] The analysis and modeling unit is used to receive the collected data after preprocessing and to analyze and model the collected data after preprocessing.

[0008] The adaptive unit is used to receive the acquired data, the acquired data after preprocessing, and the preprocessed data after analysis and modeling, and to perform adaptive adjustments.

[0009] The optimization prediction unit is used to receive the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment, and to make optimization decisions based on the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment, and to make intelligent predictions based on the collected data and the data after optimization decisions.

[0010] The execution control unit is used to receive data after optimized decision-making, receive data after intelligent prediction, and execute commands;

[0011] The optimization prediction unit receives the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment. It makes optimization decisions based on the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment. At the same time, it makes intelligent predictions based on the collected data and the data after optimization decisions.

[0012] As a further improvement to this technical solution, the acquisition and processing unit includes a data acquisition module and a preprocessing module;

[0013] The data acquisition module is used to collect data and transmit the collected data to the preprocessing module, the adaptive unit, and the optimization prediction unit;

[0014] The preprocessing module is used to receive the collected data, perform preprocessing operations on the collected data, and transmit the preprocessed collected data to the analysis and modeling unit, the adaptive unit, and the optimization and prediction unit.

[0015] As a further improvement to this technical solution, the analysis and modeling data includes a data analysis module and a modeling display module;

[0016] The data analysis module is used to receive the collected data after preprocessing in the preprocessing module, and analyze the collected data after preprocessing to analyze the temperature, whether there are people in the room, and the indoor brightness. At the same time, the preprocessed data after analysis is transmitted to the modeling and display module, the adaptive unit, and the optimization and prediction unit.

[0017] The modeling and display module is used to receive the preprocessed operation data after analysis, and to create template data for the preprocessed operation data after analysis, and to display and store the template data;

[0018] The adaptive unit is used to receive data collected in the data acquisition module, data collected after preprocessing in the preprocessing module, and data collected after analysis in the data analysis module. It performs adaptive adjustment based on the collected data, the data collected after preprocessing, and the data collected after analysis, and transmits the adaptively adjusted data to the data analysis module and the optimization prediction unit. At the same time, the data analysis module receives the adaptively adjusted data and performs further analysis.

[0019] As a further improvement to this technical solution, the optimization prediction unit includes an optimization decision module and an intelligent prediction module;

[0020] The optimization decision-making module is used to receive data collected by the data acquisition module, data collected after preprocessing in the preprocessing module, data analyzed after preprocessing in the data analysis module, and data adjusted after adaptive adjustment in the adaptive unit. Based on the collected data, the data collected after preprocessing, the data analyzed, and the data adjusted after adaptive adjustment, the module optimizes the data to obtain an optimized strategy, and then transmits the optimized strategy to the intelligent prediction module and the execution control unit.

[0021] The intelligent prediction module is used to receive the data collected by the data acquisition module, receive the optimized strategy from the optimization decision module, perform intelligent prediction based on the collected data and the optimized strategy, and transmit the intelligently predicted data to the execution control unit.

[0022] As a further improvement to this technical solution, the execution control unit is used to receive the optimized strategy from the optimization decision module, receive the intelligently predicted data from the intelligent prediction module, and execute commands.

[0023] As a further improvement to this technical solution, the intelligent prediction module receives the collected data and optimized strategies, and performs intelligent predictions based on the collected data and optimized strategies to adjust the control equipment in advance, thus preparing a comfortable indoor environment for the user.

[0024] The second objective of this invention is to provide a method for operating a smart home controller based on adaptive control technology, comprising the following steps:

[0025] S1, the data acquisition and processing unit is used to acquire data and perform preprocessing operations on the acquired data;

[0026] S2. The analysis and modeling unit receives the collected data after the preprocessing operation and analyzes it, and then models the preprocessed data after analysis.

[0027] S3. The adaptive unit receives the acquired data, the acquired data after preprocessing, and the preprocessed data after analysis, and performs adaptive adjustment. It then transmits the adaptively adjusted data to the analysis and modeling unit, which re-analyzes the adaptively adjusted data.

[0028] S4. The optimization prediction unit receives the collected data, the collected data after preprocessing, the preprocessed data after analysis, and the data after adaptive adjustment, and performs optimization strategies to obtain the optimized strategies. Then, it performs intelligent prediction on the collected data and the optimized strategies.

[0029] S5. The execution control unit receives the optimized strategy and the intelligently predicted data and executes the commands.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0031] 1. In this smart home controller and method based on adaptive control technology, the intelligent prediction module receives the collected data and optimized strategies, and performs intelligent prediction on the collected data and optimized strategies. It intelligently predicts future environmental changes and user behavior, thereby adjusting the control strategy in advance. Based on the user's work and rest patterns and outdoor temperature, it predicts the user's return time and preferred settings, and adjusts the air conditioning temperature in advance. Based on the user's real-time location information and movement direction and speed, it predicts that the user will not be able to return home for more than two hours, and uses the execution control unit to turn off the air conditioner, lights, etc. that are not turned off. This not only prepares a comfortable indoor environment for the user in advance, but also reduces energy waste. Attached Figure Description

[0032] Figure 1 This is an overall block diagram of the present invention;

[0033] Figure 2 This is a block diagram of the data acquisition and processing unit of the present invention;

[0034] Figure 3 This is a block diagram of the analysis and modeling unit of the present invention;

[0035] Figure 4 This is a block diagram of the optimized prediction unit of the present invention.

[0036] The meanings of the labels in the diagram are as follows:

[0037] 1. Acquisition and processing unit; 11. Data acquisition module; 12. Preprocessing module;

[0038] 2. Analysis and modeling unit; 21. Data analysis module; 22. Modeling display module;

[0039] 3. Adaptive unit;

[0040] 4. Optimize the prediction unit; 41. Optimize the decision-making module; 42. Intelligent prediction module;

[0041] 5. Execution control unit. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Example 1: Please refer to Figures 1-4 As shown, one of the objectives of this embodiment is to provide a smart home controller based on adaptive control technology, including a data acquisition and processing unit 1, an analysis and modeling unit 2, an adaptive unit 3, an optimization and prediction unit 4, and an execution control unit 5;

[0044] Considering the shortcomings of current smart home systems, such as the inability to adaptively adjust settings based on user preferences or to pre-prepare a comfortable indoor environment, we provide a smart home controller based on adaptive control technology. The system comprises: a data acquisition and processing unit 1 for collecting data and preprocessing it; an analysis and modeling unit 2 for receiving the preprocessed data and analyzing and modeling it; an adaptive unit 3 for receiving the collected data, the preprocessed data, and the preprocessed data after analysis and modeling, and performing adaptive adjustments; an optimization and prediction unit 4 for receiving the collected data, the preprocessed data, the preprocessed data after analysis and modeling, and the adaptively adjusted data, and making optimization decisions based on these data, while also performing intelligent predictions based on the collected data and the optimized data; and an execution control unit 5 for receiving the optimized data, the intelligently predicted data, and executing commands.

[0045] The optimization prediction unit 4 receives the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment. Based on the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment, it makes optimization decisions. At the same time, it makes intelligent predictions based on the collected data and the data after optimization decisions, predicting users' needs, behaviors, and habits in advance, thereby better adapting to and meeting users' needs and greatly improving the user experience.

[0046] The following details the above units; please refer to them. Figures 2-4 As shown;

[0047] The data acquisition and processing unit 1 includes a data acquisition module 11 and a preprocessing module 12;

[0048] The data acquisition module 11 is used to collect data, including outdoor seasonal changes, indoor temperature, indoor humidity, indoor lighting, user location information, home appliance operating status, user's daily routine, user preference settings, whether the user is at home, main activity range, user feedback information, etc. Data is collected through appropriate sensors, such as temperature sensors to collect temperature and human body sensors to collect whether the user is at home, so as to accurately sense when the user is at home. Data such as indoor temperature, humidity and changes in user's daily routine can also be collected periodically by setting the collection interval. For example, at regular intervals, the sensors will automatically collect data on the current environment and transmit it. In order to achieve periodic data collection and transmission, smart homes usually use wireless communication technologies such as Wi-Fi, Zigbee, Bluetooth, etc. At the same time, the collected data is transmitted to the preprocessing module 12, the adaptive unit 3, and the optimization prediction unit 4.

[0049] The preprocessing module 12 receives the collected data and performs preprocessing operations on it. These operations include cleaning (removing errors, anomalies, and duplicates from the data), denoising (removing irrelevant or erroneous information that may appear randomly in the data, possibly due to sensor errors, interference during data acquisition, etc.), and handling missing values ​​(methods for handling missing values ​​include deleting samples containing missing values, filling missing values ​​with the global average or median, and using interpolation methods). Preprocessing reduces data errors to ensure data accuracy and completeness, resulting in more reliable data. This provides more accurate data for subsequent adaptive adjustment and intelligent prediction functions. The preprocessed collected data is then transmitted to the analysis and modeling unit 2, the adaptive unit 3, and the optimization and prediction unit 4.

[0050] Analysis and modeling unit 2 includes a data analysis module 21 and a modeling display module 22;

[0051] The data analysis module 21 receives the collected data after preprocessing operations in the preprocessing module 12 and analyzes the collected data after preprocessing operations. It analyzes the temperature, whether there are people in the room, and the indoor brightness. For example, when it is detected that it is summer outside, there are people in the room, the indoor temperature is high, and the indoor temperature is currently low, the preprocessed operation data after analysis is transmitted to the adaptive unit 3. The adaptive unit 3 receives the preprocessed operation data after analysis and performs adaptive adjustment functions according to the preprocessed operation data after analysis. When there are people in the room, it automatically turns on the air conditioner to lower the temperature and turns on the lights to increase the brightness, thereby achieving a more efficient control method. When it is detected that it is summer outside, there are no people in the room, the indoor temperature is high, and the indoor temperature is currently low, no adjustment is required, and the preprocessed operation data after analysis is transmitted to the modeling and display module 22.

[0052] The modeling and display module 22 is used to receive the preprocessed operation data after analysis and to create template data for the preprocessed operation data after analysis. The template data includes temperature, humidity, light, user location information, home appliance operating status, and whether the user is at home. The template data is displayed and stored. Displaying the template data makes it convenient for users to view and receive notifications. Users can view or receive notifications via mobile phone, email, etc. At the same time, the template data is stored in the smart home central controller and encrypted with AES (a symmetric encryption technology, also known as the Rijndael algorithm, which is one of the most widely used encryption technologies and is widely used to protect the confidentiality of sensitive data) to ensure data security.

[0053] The adaptive unit 3 receives data acquired by the data acquisition module 11, data acquired after preprocessing by the preprocessing module 12, and data acquired after analysis by the data analysis module 21. Based on the acquired data, the data acquired after preprocessing, and the data acquired after analysis, it performs adaptive adjustment. According to real-time environmental changes and user needs, it automatically adjusts control parameters and strategies. It performs adaptive adjustment for different indoor temperatures and user behaviors. For example, if the temperature is low and the user is at home, the air conditioner temperature setpoint is increased. The fuzzy controller outputs a suitable air conditioner temperature setpoint based on the current indoor temperature and user behavior. The adaptive adjustment function can be implemented using a fuzzy control algorithm and a fuzzy rule base can be established. The adaptively adjusted data is transmitted to the data analysis module 21 and the optimization prediction unit 4. At the same time, the data analysis module 21 receives the adaptively adjusted data and performs further analysis. Through two analyses, the complexity, uncertainty, or difficult-to-model data in the adaptive adjustment function is reduced, thereby achieving a more intelligent and efficient control method.

[0054] The principle of fuzzy control algorithm:

[0055] 1. Fuzzification: Converting input variables (such as indoor temperature and user behavior) into fuzzy sets, such as "low temperature" and "high temperature";

[0056] 2. Rule base: The rule base is learned from expert knowledge or data. Fuzzy rules usually take the form of "IF...THEN...", such as "IF temperature is low AND user is at home THEN increase air conditioner temperature setting".

[0057] 3. Reasoning: Fuzzy reasoning is a fuzzy logic operation process that simulates the human reasoning process by combining fuzzy input variables and a fuzzy rule base to obtain fuzzy output through fuzzy reasoning.

[0058] 4. Defuzzification: Converting fuzzy outputs into actual output values. The defuzzification process maps fuzzy sets back to specific output values, thereby obtaining the system's control commands.

[0059] Steps to build a fuzzy rule base:

[0060] 1. Define input and output variables: The input variables are the indoor temperature (assuming a range of 20°C to 30°C) and whether the user is at home (assuming the values ​​are "at home" and "not at home"). The output variable is the air conditioner temperature setting (assuming a range of 16°C to 28°C).

[0061] 2. Set fuzzy sets: Set fuzzy sets for input and output variables, such as "low temperature", "moderate temperature", "high temperature", "user at home", "user not at home", etc.

[0062] 3. Establish a rule base: Based on expert knowledge or data learning, formulate fuzzy rules, such as IF the temperature is low AND the user is at home THEN increase the air conditioner temperature setting; IF the temperature is moderate AND the user is at home THEN keep the air conditioner temperature setting unchanged; IF the temperature is high AND the user is at home THEN decrease the air conditioner temperature setting; IF the user is not at home THEN turn off the air conditioner.

[0063] 4. Fuzzy reasoning: Based on the current indoor temperature and user status, fuzzy reasoning is used to obtain a fuzzy air conditioning temperature setpoint.

[0064] 5. Defuzzification: Convert the fuzzy output into a specific air conditioning temperature setpoint, for example, by taking the average or weighted average of the fuzzy output to obtain the actual temperature setpoint.

[0065] The optimization prediction unit 4 includes an optimization decision module 41 and an intelligent prediction module 42;

[0066] The optimization decision module 41 receives data collected by the data acquisition module 11, data collected after preprocessing by the preprocessing module 12, data analyzed by the data analysis module 21, and data adaptively adjusted by the adaptive unit 3. It then optimizes the data based on the collected data, the data collected after preprocessing, the data analyzed, and the data adaptively adjusted to derive an optimized strategy. For example, when multiple people are in a room, the optimized strategy can intelligently select the best operation and decision-making scheme for the user. Simultaneously, it continuously corrects and optimizes based on feedback from different users, their behaviors, and preferences, thereby better addressing the needs of different users and greatly improving the multi-user experience. The optimized strategy is then transmitted to the intelligent prediction module 42.

[0067] The intelligent prediction module 42 receives the data collected by the data acquisition module 11 and the optimized strategy from the optimization decision module 41. Based on the collected data and the optimized strategy, it performs intelligent prediction using a stationary time series model algorithm to predict future environmental changes and user behavior, thereby adjusting the control strategy in advance. For example, based on the user's work and rest patterns and outdoor temperature, it predicts the user's home arrival time and preferred settings, adjusts the air conditioning temperature in advance, and provides the user with a more comfortable indoor environment. The optimized strategy is then transmitted to the execution control unit 5, which receives the optimized strategy from the optimization decision module 41 and the intelligent prediction data from the intelligent prediction module 42, and executes commands to control devices such as air conditioners and lights.

[0068] Stationary time series model algorithm formula:

[0069] ;

[0070] in, It is the predicted value of a time series at time t, representing the performance of the variable of interest at a specific point in time, such as the number of people indoors or user behavior.

[0071] i=1top is an iterative symbol that indicates the range of values ​​for variable i from 1 to p, including integers 1, 2, 3 up to p. Such a symbol is often used in mathematics and statistics to represent multiple iterations of summation, product or other operations on a variable.

[0072] j=1toq is an iterative symbol that indicates the range of values ​​for variable j from 1 to q, including integers 1, 2, 3 up to q. This symbol is similar to i=1top mentioned above, indicating multiple iterations of summation, product or other operations on the variable.

[0073] It is the distance constant, representing the basic level of the time series in a stationary state. A stationary state means that the time series does not have significant trends or seasonal changes in the long term.

[0074] The autoregressive and moving average coefficients represent the relationship between past and current observations. It is a weight, representing the weight of the past... The degree of influence of the observation at each moment on the current moment;

[0075] Indicates the past number The observations at each time point are used to influence the prediction at the current time point;

[0076] It is the moving average coefficient, representing the relationship between the random error term (or residual) at past time points and the observed value at the current time point. It is also a weight, representing the weight of the past [number]th ... The degree of influence of random errors at each moment on the current moment;

[0077] Indicates the past number The random error term at each time step is used to influence the prediction error at the current time step;

[0078] It is the random error term at the current moment, representing the part that the model cannot fully explain and that is difficult to predict.

[0079] Next, we will illustrate this with a specific scenario, such as: in an indoor environmental control system, historical indoor temperature data is used to predict future indoor temperatures so that the air conditioning system can be adjusted in advance to provide a more comfortable environment. Hourly indoor temperature data is collected, and then a stationary time series model is used for prediction.

[0080] Now, let's substitute the formula into this scenario:

[0081] Indoor temperature at any time The observed values ​​represent the variable of the number of people or user behavior indoors;

[0082] This constant term represents the basic temperature level under steady-state conditions, which may be the base temperature of an indoor environment, unaffected by other factors.

[0083] These are autoregressive coefficients, representing the relationship between past temperatures and current temperatures. For example, This indicates the effect of the previous hour's temperature on the current temperature. This indicates the effect of the temperature in the previous two hours on the current temperature;

[0084] This means that in the past... The temperature over an hour is used to influence the temperature forecast for the current moment;

[0085] It is a moving average coefficient, representing the relationship between random errors in the past and the temperature at the current moment. For example, This indicates the impact of random errors from the previous hour on the current temperature. This indicates the impact of random errors from the previous two hours on the current temperature.

[0086] Indicates the past number A random error term for each hour is used to influence the temperature prediction error at the current moment;

[0087] It is the random error term at the current moment, which represents the part that the model cannot fully explain and that is difficult to predict. It may be caused by external factors, sensor noise, etc.

[0088] The intelligent prediction module 42 receives the collected data and optimized strategies, and performs intelligent predictions based on the collected data and optimized strategies to adjust the control equipment in advance. For example, when the system collects the user's location information, movement direction and speed, indoor temperature, humidity, lighting, and user preferences, and predicts based on the user's location, distance from home, and movement speed that the user will arrive home in half an hour, and the indoor lighting is dim and the indoor temperature is high, the system will adjust the equipment in advance according to the user's usual preferences, adjusting the temperature, brightness, etc., to prepare a comfortable indoor environment for the user. At the same time, it can also predict and control the equipment in advance based on the user's behavior. For example, the system collects the user's actions and direction, and predicts based on the user's past actions that the user is about to go to the bathroom, so the system will turn on the lights in advance when the user arrives at the bathroom. When it predicts based on the user's real-time location information, movement direction, and speed that the user will not be able to return home for more than two hours, the execution control unit 5 will turn off the air conditioner, lights, etc., which are not turned off, to reduce energy waste.

[0089] Usage Flow: The adaptive unit 3 receives the collected data, the collected data after preprocessing, and the preprocessed data after analysis, and performs adaptive adjustment. The adaptively adjusted data is then transmitted to the data analysis module 21 and the optimization decision module 41. Simultaneously, the data analysis module 21 receives the adaptively adjusted data and performs further analysis. The optimization decision module 41 receives the collected data, the collected data after preprocessing, the preprocessed data after analysis, and the adaptively adjusted data, and performs optimization to derive an optimized strategy. The optimized strategy is then transmitted to the intelligent prediction module 42 and the execution control unit 5. The intelligent prediction module 42 receives the collected data and the optimized strategy, performs intelligent prediction based on the collected data and the optimized strategy, and transmits the intelligently predicted data to the execution control unit 5 for execution command execution.

[0090] The second objective of this invention is to provide a method for operating a smart home controller based on the above-mentioned adaptive control technology, comprising the following method steps:

[0091] S1, the data acquisition and processing unit 1 is used to acquire data and perform preprocessing operations on the acquired data;

[0092] S2, Analysis and Modeling Unit 2 receives the collected data after preprocessing and analyzes it, and models the preprocessed data after analysis.

[0093] S3, the adaptive unit 3 receives the collected data, the collected data after preprocessing, and the preprocessed data after analysis, and performs adaptive adjustment. It then transmits the adaptively adjusted data to the analysis and modeling unit 2, which re-analyzes the adaptively adjusted data.

[0094] S4. The optimization prediction unit 4 receives the collected data, the collected data after preprocessing, the preprocessed data after analysis, and the data after adaptive adjustment, and performs optimization strategy to obtain the optimized strategy. Then, it performs intelligent prediction on the collected data and the optimized strategy.

[0095] S5, the execution control unit 5 receives the optimized strategy and the intelligently predicted data and executes the command.

[0096] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart home controller based on adaptive control techniques, characterized by: It includes a data acquisition and processing unit (1), an analysis and modeling unit (2), an adaptive unit (3), an optimization and prediction unit (4), and an execution and control unit (5). The data acquisition and processing unit (1) is used to acquire data and perform preprocessing operations on the acquired data; The analysis and modeling unit (2) is used to receive the collected data after preprocessing and to analyze and model the collected data after preprocessing. The adaptive unit (3) is used to receive the collected data, the collected data after preprocessing, and the preprocessed data after analysis and modeling, and to perform adaptive adjustment. The optimization prediction unit (4) is used to receive the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment, and to make optimization decisions based on the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment, and to make intelligent predictions based on the collected data and the data after optimization decisions. The execution control unit (5) is used to receive data after optimized decision-making, receive data after intelligent prediction, and execute commands; The optimization prediction unit (4) receives the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment. It makes optimization decisions based on the collected data, the collected data after preprocessing, the preprocessed data after analysis and modeling, and the data after adaptive adjustment. At the same time, it makes intelligent predictions based on the collected data and the data after optimization decisions. The optimization prediction unit (4) includes an optimization decision module (41) and an intelligent prediction module (42). The intelligent prediction module (42) receives the collected data and the optimized strategy, and performs intelligent prediction on the collected data and the optimized strategy to adjust the control equipment in advance, so as to prepare a comfortable indoor environment for the user in advance. It uses the stationary time series model algorithm formula to perform prediction calculation, predict future environmental changes and user behavior, and thus adjust the control strategy in advance. The algorithm formula for the stationary time series model is expressed as follows: in, It is the predicted value of the time series at time t, representing the performance of the variable of interest at a specific point in time; i=1top is an iterative symbol, indicating that the value of variable i ranges from 1 to p, representing multiple iterations of summation, product or other operations on a variable; j=1toq is an iterative symbol, indicating that the value of variable j ranges from 1 to q, and represents multiple iterations of summation, product or other operations on the variable; It is the distance constant, representing the basic level of the time series in a stationary state. A stationary state means that the time series does not have significant trends or seasonal changes in the long term. The autoregressive and moving average coefficients represent the relationship between past and current observations. It is a weight, representing the weight of the past... The degree of influence of the observation at each moment on the current moment; Indicates the past number The observations at each time point are used to influence the prediction at the current time point; It is the moving average coefficient, representing the relationship between the random error term (or residual) at past time points and the observed value at the current time point. It is also a weight, representing the weight of the past [number]th ... The degree of influence of random errors at each moment on the current moment; Indicates the past number The random error term at each time step is used to influence the prediction error at the current time step; It is the random error term at the current moment, representing the part that the model cannot fully explain and that is difficult to predict.

2. The smart home controller based on adaptive control technology according to claim 1, characterized in that: The acquisition and processing unit (1) includes a data acquisition module (11) and a preprocessing module (12); The data acquisition module (11) is used to acquire data and transmit the acquired data to the preprocessing module (12), the adaptive unit (3), and the optimization prediction unit (4); The preprocessing module (12) is used to receive the collected data and perform preprocessing operations on the collected data, and then transmit the collected data after preprocessing operations to the analysis and modeling unit (2), the adaptive unit (3), and the optimization and prediction unit (4).

3. The smart home controller based on adaptive control technology according to claim 2, characterized in that: The analysis and modeling unit (2) includes a data analysis module (21) and a modeling display module (22); The data analysis module (21) is used to receive the collected data after the preprocessing operation in the preprocessing module (12), and analyze the collected data after the preprocessing operation, including the temperature level, whether there are people in the room, and the indoor brightness level. At the same time, the preprocessed data after analysis is transmitted to the modeling display module (22), the adaptive unit (3), and the optimization prediction unit (4). The modeling and display module (22) is used to receive the preprocessed operation data after analysis, and to create template data for the preprocessed operation data after analysis, and to display and store the template data; The adaptive unit (3) is used to receive the data collected in the data acquisition module (11), the data collected after preprocessing in the preprocessing module (12), and the preprocessing operation data analyzed in the data analysis module (21). It performs adaptive adjustment based on the data collected, the data collected after preprocessing, and the preprocessing operation data analyzed, and transmits the adaptively adjusted data to the data analysis module (21) and the optimization prediction unit (4). At the same time, the data analysis module (21) receives the adaptively adjusted data and performs further analysis.

4. The smart home controller based on adaptive control technology according to claim 3, characterized in that: The optimization prediction unit (4) includes an optimization decision module (41) and an intelligent prediction module (42). The optimization decision module (41) is used to receive the data collected in the data acquisition module (11), the data collected after preprocessing in the preprocessing module (12), the data analyzed in the data analysis module (21), and the data adjusted by the adaptive unit (3). Based on the collected data, the data collected after preprocessing, the data analyzed, and the data adjusted by the adaptive unit, it optimizes the data to obtain the optimized strategy and transmits the optimized strategy to the intelligent prediction module (42) and the execution control unit (5). The intelligent prediction module (42) is used to receive the data collected in the data acquisition module (11), the optimized strategy in the optimization decision module (41), and perform intelligent prediction based on the collected data and the optimized strategy. The intelligently predicted data is transmitted to the execution control unit (5).

5. The smart home controller based on adaptive control technology according to claim 4, characterized in that: The execution control unit (5) is used to receive the optimized strategy from the optimization decision module (41), receive the intelligent prediction data from the intelligent prediction module (42), and execute commands.

6. The smart home controller based on adaptive control technology according to claim 5, characterized in that: The intelligent prediction module (42) receives the collected data and optimized strategies, and performs intelligent prediction on the collected data and optimized strategies to adjust the control equipment in advance and prepare a comfortable indoor environment for the user in advance.

7. A method for operating a smart home controller based on adaptive control technology according to any one of claims 1-6, characterized in that: The methods and steps include the following: S1, the data acquisition and processing unit (1) is used to acquire data and perform preprocessing operations on the acquired data; S2, Analysis and Modeling Unit (2) receives the collected data after preprocessing operation and analyzes it, and models the preprocessed data after analysis. S3, the adaptive unit (3) receives the collected data, the collected data after preprocessing operation, and the preprocessed operation data after analysis and performs adaptive adjustment function, and transmits the adaptively adjusted data to the analysis and modeling unit (2), and the analysis and modeling unit (2) analyzes the adaptively adjusted data again. S4. The optimization prediction unit (4) receives the collected data, the collected data after preprocessing, the preprocessed data after analysis, and the data after adaptive adjustment, and performs optimization strategy to obtain the optimized strategy. Then, it performs intelligent prediction on the collected data and the optimized strategy. S5. The execution control unit (5) receives the optimized strategy and the intelligently predicted data and executes the command.

Images