Home system based on Internet of Things

Abstract

The invention discloses a home system based on Internet of Things, and relates to the technical field of Internet of Things smart home, and the system comprises the following components: a home equipment control module which is responsible for controlling the operation of home equipment, including an air conditioner, a lighting device and a household appliance, achieves the communication with the equipment through the Internet of Things technology, receives and executes a control instruction, and sends the control instruction to the home equipment control module; the energy consumption monitoring module is used for monitoring energy consumption conditions, including electric quantity and water quantity, of household equipment in real time and sending monitoring data to the energy-saving strategy making module to provide a basis for making an energy-saving strategy; operation of the household equipment is accurately controlled through a PID control algorithm in the household equipment control module and a statistical analysis algorithm of the energy consumption monitoring module, the energy consumption condition of the household equipment is monitored in real time, the system can provide detailed energy consumption data for a user, the user can visually know the energy consumption condition of the user, and the user experience is improved. Therefore, the system can participate in the energy-saving action more actively.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home systems of the Internet of Things, and in particular to a home system based on the Internet of Things. Background Art

[0002] With the rapid development of science and technology, the Internet of Things technology has become an important force in promoting social progress. Through network communication technology, the Internet of Things technology closely connects the physical world with the digital world, and realizes real-time perception, transmission and processing of information. The application field of this technology is extremely wide, especially in the field of smart homes. It has greatly changed people's lifestyles and improved the living experience. Although the smart home system provides people with unprecedented convenience, it faces huge challenges in energy saving and environmental protection.

[0003] Therefore, it is particularly important to use the Internet of Things technology to achieve precise control of home appliances while taking into account the effective use of energy and environmental protection. An ideal Internet of Things home system should have the following characteristics: it is highly intelligent and energy-saving, able to monitor the operating status and energy consumption of home appliances in real time, formulate personalized energy-saving strategies based on user needs and habits, and achieve precise control of home appliances through the Internet of Things technology, improve energy utilization efficiency and user comfort and satisfaction, and achieve harmonious coexistence between man and the environment.

[0004] However, the traditional smart home systems on the market often only focus on the intelligent control of equipment, but ignore the effective use of energy and environmental protection. This leads to a large amount of energy waste during the operation of home appliances, which not only increases the economic burden of users, but also aggravates environmental pressure. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a home system based on the Internet of Things, which can accurately control the operation of home appliances by adopting advanced statistical analysis algorithms, PID control algorithms and particle swarm optimization recognition technologies, achieve efficient use of energy and environmental protection, and improve users' quality of life and living experience.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a home system based on the Internet of Things, characterized in that the system includes the following components:

[0007] Home equipment control module: responsible for controlling the operation of home equipment, including air conditioning, lighting, and household appliances. This module communicates with the equipment through the Internet of Things technology, receives and executes control instructions;

[0008] Energy consumption monitoring module: This module monitors the energy consumption of household appliances in real time, including electricity and water consumption, and sends the monitoring data to the energy-saving strategy formulation module to provide a basis for formulating energy-saving strategies;

[0009] Energy-saving strategy formulation module: Based on the data provided by the energy consumption monitoring module and combined with the user's living habits and preferences, a personalized energy-saving strategy is formulated. This strategy aims to achieve efficient use of energy and reduce waste while meeting the user's comfort needs;

[0010] User interaction module: provides an interactive interface between users and the system. Users can view energy consumption data, adjust energy-saving strategies, and control home appliances through this module. This module also has voice control and remote control functions, allowing users to manage the home system anytime and anywhere.

[0011] Furthermore, the specific steps of the home appliance control module are:

[0012] (1) Device connection and initialization: Scan the surrounding environment through the Internet of Things to discover connectable home devices, establish a stable communication connection with the discovered home devices, ensure the reliability and real-time data transmission, identify the type, model and characteristics of the connected device, and perform initialization settings based on the device information, including the initial status and working mode of the device. Add the successfully connected and initialized devices to the device list to facilitate subsequent management and control;

[0013] (2) Receiving energy-saving strategies: Continuously monitor the instructions sent by the device list to ensure timely acquisition of the latest energy-saving control requirements, parse the received instructions, extract the specific control parameters and requirements for each device, and verify the parsed instructions to ensure the legality and validity of the instructions and prevent the execution of erroneous or illegal instructions;

[0014] (3) Equipment status monitoring: Through the interface provided by the equipment, the operating status and energy consumption status data of the equipment are collected, and the collected data are processed and analyzed to extract the actual operating status and energy consumption status of the equipment, detect whether the equipment is operating abnormally, such as excessive temperature and abnormal energy consumption, and issue early warnings in a timely manner;

[0015] (4) Execute control instructions: Map energy-saving control instructions to specific equipment control parameters, such as adjusting the temperature setting of air conditioners and changing the brightness of lighting equipment. According to the current state and target state of the equipment, calculate the appropriate control parameter value, send control signals to the equipment through the PID control algorithm, and achieve precise control of the equipment.

[0016] (5) Feedback of execution results: Collect the execution results of the equipment, analyze the collected results, evaluate the execution effect of the control instructions, and feed back the analysis results to the energy consumption monitoring module to optimize the subsequent energy-saving strategy.

[0017] Furthermore, the energy consumption monitoring module includes the following specific steps:

[0018] (1) Energy consumption data reception: Receive the analysis results from the home device control module and obtain energy consumption data from the home devices in real time or at a scheduled time according to the collection frequency set by the module. This data may include power consumption and water usage, depending on the monitored devices and system requirements;

[0019] (2) Data processing and analysis: The collected energy consumption data is cleaned, integrated and analyzed using statistical analysis algorithms. The cleaning process includes removing outliers and erroneous data. The integration is the unified processing of different energy consumption data of different devices or the same device. The analysis includes calculating the average value, peak value and change trend of energy consumption.

[0020] (3) Energy consumption status evaluation: Based on the processed data, the module evaluates the energy consumption status of home appliances to determine whether the appliances are operating efficiently or whether there are abnormal energy consumption issues;

[0021] (4) Data storage and transmission: The module stores the processed energy consumption data and evaluation results in a local or cloud database for subsequent analysis and use. At the same time, the module will also send the relevant data to the energy-saving strategy formulation module as a basis for formulating energy-saving strategies.

[0022] Furthermore, the energy-saving strategy formulation module includes the following specific steps:

[0023] (1) Data collection and analysis: First, the energy consumption data of household devices sent by the energy consumption monitoring module are received. These data may include electricity, water, and usage time. Then, the module will use statistical analysis methods to process these data, identify energy consumption peaks and valleys, and analyze the energy consumption characteristics of different devices.

[0024] (2) User behavior pattern recognition: By analyzing historical data and using the K-means algorithm in machine learning, users’ daily behavior patterns can be identified, such as waking time, rest time, and entertainment time. These behavior patterns are crucial for developing personalized energy-saving strategies.

[0025] (3) Energy-saving strategy generation: Based on the above analysis, the energy-saving strategy formulation module will use particle swarm optimization to combine the user's comfort and energy-saving needs to generate a series of energy-saving strategies. These strategies may include adjusting the operating time of the equipment, setting the temperature, and optimizing the equipment combination;

[0026] (4) Strategy evaluation and adjustment: The generated energy-saving strategy will be evaluated through simulation testing or actual operation. Based on the evaluation results, the module will fine-tune the strategy to achieve better energy-saving effects and user satisfaction.

[0027] Furthermore, the user interaction module specifically comprises the following steps:

[0028] (1) Interface display: The current status of home devices, energy consumption data, and the implementation of energy-saving strategies are displayed through a graphical interface;

[0029] (2) User input: Users can input their needs, preferences, or adjust the parameters of energy-saving strategies through the interface;

[0030] (3) Voice control: In addition to interface input, the user interaction module uses a voice recognition algorithm to convert the user's voice commands into instructions that the system can understand, providing a voice control function. Users can control home appliances or adjust energy-saving strategies through voice commands;

[0031] (4) Remote control: Users can remotely control home devices through mobile applications or cloud platforms, no matter where they are.

[0032] Furthermore, the home appliance control module monitors the indoor temperature in real time through the PID control algorithm and compares it with the target value, and automatically adjusts the output of the heating or cooling equipment to keep the indoor temperature within a suitable range. For example, during winter heating, if the indoor temperature is lower than the set value, the PID control algorithm will calculate the appropriate control amount based on the error and the above parameters, increase the output of the heating equipment, and make the indoor temperature gradually rise and approach the set value. At the same time, through the action of integral and differential terms, the system can smoothly reach the target temperature to avoid overshoot or oscillation. The parameters of the PID controller include the proportional coefficient (Kp), integral coefficient (Ki) and differential coefficient (Kd). The specific mathematical formula is: u(t) is the control quantity, that is, the output or adjustment quantity at time (t), and e(t) is the error, that is, the difference between the set value and the actual value. In addition to the temperature control system, the PID control algorithm can also be applied to other home appliances, such as lighting control and curtain control. In these scenarios, the PID control algorithm can also achieve precise control effects by adjusting the control parameters according to the deviation between the set value and the actual value.

[0033] Furthermore, the energy consumption monitoring module describes the distribution characteristics, change trends and correlations of data through statistical analysis algorithms. In energy consumption monitoring, statistical analysis can help us identify peaks and valleys in energy consumption, analyze energy consumption differences between different devices or systems, and find out the relationship between energy consumption and the external environment or operating behavior. By calculating the correlation coefficient in the statistical analysis algorithm, we can quantify the degree of linear correlation between variables, thereby identifying potential energy-saving opportunities and influencing factors. The correlation coefficient is expressed as r, which measures the degree of linear correlation between two variables x and y. Its value range is [-1, 1], where 1 indicates a complete positive correlation, -1 indicates a complete negative correlation, and 0 indicates no correlation. Its calculation formula is: n is the number of data points, x i and i are the x and y values ​​of the ith data point, respectively. and are the means of x and y respectively, and the calculation formula is: The formula calculates the sum of the products of the deviations of x and y and divides it by the product of their respective standard deviations to obtain a standardized measure that represents the degree of linear correlation between x and y. By analyzing the linear correlation of the correlation coefficient in the energy consumption monitoring module, we can analyze energy consumption data more systematically, reveal the relationship between variables, and provide a scientific basis for formulating effective energy-saving strategies, which not only helps to improve energy utilization efficiency and reduce energy consumption costs, but also helps to promote sustainable development and environmental protection.

[0034] Furthermore, the energy-saving strategy formulation module uses the K-means algorithm in machine learning to identify the user's daily behavior patterns, which is crucial for formulating personalized energy-saving strategies. The K-means algorithm divides the data points into K clusters in an iterative manner. The data points in each cluster are as similar as possible, while the data points between different clusters are as different as possible. K initial cluster centers are selected. For each data point xi, its distance to each cluster center cj is calculated and assigned to the nearest cluster center, which is usually measured by the Euclidean distance: Where n is the dimension of the data points, is the data point x i The kth feature of is the cluster center c j The k-th coordinate of , for each cluster, recalculate the cluster center, and the new cluster center is the mean of all data points in the cluster: S j is the set of data points of the jth cluster, |S j |It is S jThe number of data points in the cluster is calculated by repeating the operation of the two cluster centers to obtain the user's daily behavior pattern and formulate a personalized energy-saving strategy.

[0035] Furthermore, the energy-saving strategy formulation module uses particle swarm optimization to identify user behavior patterns to formulate more effective energy-saving strategies, and its operating formula is: i (t+1)=w·v i (t)+c 1 ·r 1 ·(pbest i -x i (t))+c 2 ·r 2 ·(gbest-x i (t)), x i (t+1)=x i (t)+v i (t+1), where vi is the particle velocity, xi is the particle position, w is the inertia weight, c 1 and c 2 is the learning factor, r 1 and r 2 is a random number, pbest i is the individual optimal position, gbest is the global optimal position. In each iteration, the individual optimal and global optimal positions are updated according to the fitness function. Take the optimization of lighting behavior patterns as an example: a group of particles are randomly generated, each particle represents a lighting time series, and the fitness of each particle is calculated, that is, the energy-saving effect of the lighting time series it represents. The speed and position of each particle are updated according to the above formula, and the current position of each particle is compared with its historical optimal position, and the individual optimal is updated. The current positions of all particles are compared, and the global optimal is updated. Repeat the above steps until the optimal lighting time series is found or the maximum number of iterations is reached. Through particle swarm optimization, we can identify behavior patterns based on the user's historical lighting data and optimize the lighting time series to save energy.

[0036] Furthermore, the user interaction module converts the user's voice commands into instructions that the system can understand by adopting a speech recognition algorithm, thereby realizing the control of the home appliances. Taking the hidden Markov model (HMM) in the speech recognition algorithm as an example, the operation mode and operation formula in the user interaction module are as follows: The parameters of the HMM are defined as the state set S = {s 1 ,s 2 ,…,s N}, observation symbol set O = {o 1 ,o 2 ,…,o N}、State transition probability matrix A={a ij}, output probability matrix (or transmission probability matrix) B = {b j (k)}, initialize the probability vector π = {π i}, where N is the number of states, M is the number of observation symbols, a ij =P(s j |s i ) indicates that from s j The state is transferred to s i The probability of the state, b j (k) = P(o k |s j ) means in o k Output observation symbol s in the state j The probability of i =P(s j ) indicates that the initial state is s j The probability of these probabilities is expressed as: state transition probability a ij =P(q t+1 =s j |q t =s i ), q t and q t+1 Represent the states at time t and t+1 respectively, and output probability b j (k) = P(o t =o k |q t =s j ), o t Represents the observation symbol at time t, and initializes the probability π i =P(q 1 =s i ), q 1 It represents the state at the initial moment. In speech recognition, HMM is used to model the temporal characteristics of speech signals and infer the hidden state sequence through some incompletely observable random variables (i.e., acoustic features). Since speech signals are temporal and dynamic, HMM can capture these characteristics well and use probability distribution to bridge the gap between acoustic features and speech phonemes to find the most likely state sequence. This state sequence is then mapped to the corresponding word or phrase, thereby realizing speech recognition.

[0037] Compared with the prior art, this home system based on the Internet of Things has the following beneficial effects:

[0038] 1. The present invention uses the PID control algorithm in the home appliance control module and the statistical analysis algorithm in the energy consumption monitoring module to accurately control the operation of home appliances and monitor the energy consumption of home appliances in real time. The system can provide users with detailed energy consumption data, so that users can intuitively understand their energy consumption and participate in energy-saving actions more actively.

[0039] 2. The present invention uses machine learning and voice recognition algorithms in the energy-saving strategy formulation module and the user interaction module to combine the user's living habits and preferences to formulate energy-saving strategies that meet user needs, and provides a variety of interaction methods, including graphical interface, voice control and remote control, so that users can conveniently manage the home system anytime and anywhere, thereby improving the user experience and the stability and reliability of the system.

[0040] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 This is a process operation diagram of a home system based on the Internet of Things.

[0043] Figure 2 The figure is a flow chart of a home system based on the Internet of Things. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0045] Example 1

[0046] A home system based on the Internet of Things, the system includes the following components:

[0047] Home equipment control module: responsible for controlling the operation of home equipment, including air conditioning, lighting, and household appliances. This module communicates with the equipment through the Internet of Things technology, receives and executes control instructions;

[0048] Energy consumption monitoring module: This module monitors the energy consumption of household appliances in real time, including electricity and water consumption, and sends the monitoring data to the energy-saving strategy formulation module to provide a basis for formulating energy-saving strategies;

[0049] Energy-saving strategy formulation module: Based on the data provided by the energy consumption monitoring module and combined with the user's living habits and preferences, a personalized energy-saving strategy is formulated. This strategy aims to achieve efficient use of energy and reduce waste while meeting the user's comfort needs;

[0050] User interaction module: provides an interactive interface between users and the system. Users can view energy consumption data, adjust energy-saving strategies, and control home appliances through this module. This module also has voice control and remote control functions, allowing users to manage the home system anytime and anywhere.

[0051] The energy consumption monitoring module describes the distribution characteristics, change trends and correlation of data through statistical analysis algorithms. In energy consumption monitoring, statistical analysis can help us identify peaks and valleys of energy consumption, analyze energy consumption differences between different devices or systems, and find out the relationship between energy consumption and external environment or operating behavior. By calculating the correlation coefficient in the statistical analysis algorithm, we can quantify the degree of linear correlation between variables, thereby identifying potential energy-saving opportunities and influencing factors. The correlation coefficient is expressed as r, which measures the degree of linear correlation between two variables x and y. Its value range is [-1, 1], where 1 indicates a complete positive correlation, -1 indicates a complete negative correlation, and 0 indicates no correlation. Its calculation formula is: n is the number of data points, x i and i are the x and y values ​​of the ith data point, respectively. and are the means of x and y respectively, and the calculation formula is: The formula calculates the sum of the products of the deviations of x and y and divides it by the product of their respective standard deviations to obtain a standardized measure that represents the degree of linear correlation between x and y. By analyzing the linear correlation of the correlation coefficient in the energy consumption monitoring module, we can analyze energy consumption data more systematically, reveal the relationship between variables, and provide a scientific basis for formulating effective energy-saving strategies, which not only helps to improve energy utilization efficiency and reduce energy consumption costs, but also helps to promote sustainable development and environmental protection.

[0052] The statistical analysis algorithm used by the energy consumption monitoring module can accurately describe the distribution characteristics, change trends and correlations of the data, helping users quickly identify peaks and troughs in energy consumption, thereby more accurately grasping the energy consumption status. It can also analyze the energy consumption differences between different devices or systems, revealing which devices or systems have energy consumption problems, and thus provide strong support for optimizing energy consumption management.

[0053] Example 2

[0054] The system consists of the following components:

[0055] Home equipment control module: responsible for controlling the operation of home equipment, including air conditioning, lighting, and household appliances. This module communicates with the equipment through the Internet of Things technology, receives and executes control instructions;

[0056] Energy consumption monitoring module: This module monitors the energy consumption of household appliances in real time, including electricity and water consumption, and sends the monitoring data to the energy-saving strategy formulation module to provide a basis for formulating energy-saving strategies;

[0057] Energy-saving strategy formulation module: Based on the data provided by the energy consumption monitoring module and combined with the user's living habits and preferences, a personalized energy-saving strategy is formulated. This strategy aims to achieve efficient use of energy and reduce waste while meeting the user's comfort needs;

[0058] User interaction module: provides an interactive interface between users and the system. Users can view energy consumption data, adjust energy-saving strategies, and control home appliances through this module. This module also has voice control and remote control functions, allowing users to manage the home system anytime and anywhere.

[0059] The energy-saving strategy formulation module uses the K-means algorithm in machine learning to identify users' daily behavior patterns, which is crucial for formulating personalized energy-saving strategies. The K-means algorithm divides data points into K clusters in an iterative manner. The data points in each cluster are as similar as possible, while the data points between different clusters are as different as possible. K initial cluster centers are selected. For each data point x i , calculate its relationship with each cluster center c j , and assigns it to the nearest cluster center, which is usually measured by the Euclidean distance: Where n is the dimension of the data points, is the data point x i The kth feature of is the cluster center c j The k-th coordinate of , for each cluster, recalculate the cluster center, and the new cluster center is the mean of all data points in the cluster: S jis the set of data points of the jth cluster, |S j |It is S j The number of data points in the cluster is calculated by repeating the operation of the two cluster centers to obtain the user's daily behavior pattern and formulate a personalized energy-saving strategy.

[0060] The K-means algorithm in the energy-saving strategy formulation module can automatically divide users' daily behavior patterns into different clusters, adjust the operating status of home appliances in appropriate time periods based on these clusters, understand users' demand for home appliances in different time periods, and automatically adjust the clustering results based on users' actual behavior data to help the system formulate personalized energy-saving strategies, improve energy-saving efficiency, optimize equipment combination and scheduling, have adaptive learning capabilities, and enhance user experience.

[0061] Example 3

[0062] The steps of the system based on Example 1 and Example 2 are as follows:

[0063] (1) Device connection

[0064] The home device control module scans the surrounding environment through the Internet of Things technology and finds connectable home devices;

[0065] Establish a stable communication connection with the discovered home devices to ensure the reliability and real-time performance of data transmission;

[0066] Identify the type, model and characteristics of the connected device and perform initial settings based on the device information;

[0067] Add successfully connected and initialized devices to the device list.

[0068] (2) Energy consumption monitoring and data processing

[0069] The energy consumption monitoring module obtains energy consumption data from home devices in real time or at regular intervals, including power consumption and water usage;

[0070] Use statistical analysis algorithms to clean, integrate and analyze the collected energy consumption data, and calculate the average value, peak value and change trend of energy consumption;

[0071] Evaluate the energy consumption status of home appliances to determine whether the equipment is operating efficiently or has abnormal energy consumption;

[0072] The processed energy consumption data and evaluation results are stored in a local or cloud database and sent for energy-saving strategy formulation and adjustment.

[0073] (3) Energy-saving strategy formulation and adjustment

[0074] Receive energy consumption data of household equipment sent by energy consumption monitoring and data processing;

[0075] Use statistical analysis methods to identify energy consumption peaks and valleys and analyze the energy consumption characteristics of different equipment;

[0076] Use machine learning algorithms to identify users' daily behavior patterns, combine users' comfort and energy-saving needs, and generate a series of energy-saving strategies;

[0077] Conduct simulation tests or actual operation evaluations on the generated energy-saving strategies, and fine-tune the strategies based on the evaluation results.

[0078] (4) Control instruction execution and feedback

[0079] Receive control instructions sent by energy-saving strategy system and adjustment;

[0080] Adjust the operating status of the equipment according to instructions, such as adjusting temperature and brightness;

[0081] Monitor the operating status and energy consumption of the equipment to ensure that the equipment executes according to instructions, and promptly feedback the execution results to the user for interaction and control execution.

[0082] (5) User interaction and control execution

[0083] Display the current status of home devices, energy consumption data, and the implementation of energy-saving strategies through a graphical interface;

[0084] Users can input their needs, preferences, or adjust the parameters of energy-saving strategies through the interface;

[0085] Provide voice control function, users can control home devices or adjust energy-saving strategies through voice commands;

[0086] Users can remotely manage home devices through the remote control function.

[0087] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A home system based on the Internet of Things, characterized in that: The system consists of the following components: Home equipment control module: responsible for controlling the operation of home equipment, including air conditioning, lighting, and household appliances. This module communicates with the equipment through the Internet of Things technology, receives and executes control instructions; Energy consumption monitoring module: This module monitors the energy consumption of household appliances in real time, including electricity and water consumption, and sends the monitoring data to the energy-saving strategy formulation module to provide a basis for formulating energy-saving strategies; Energy-saving strategy formulation module: Based on the data provided by the energy consumption monitoring module and combined with the user's living habits and preferences, a personalized energy-saving strategy is formulated. This strategy aims to achieve efficient use of energy and reduce waste while meeting the user's comfort needs; User interaction module: provides an interactive interface between users and the system. Users can view energy consumption data, adjust energy-saving strategies, and control home appliances through this module. This module also has voice control and remote control functions, allowing users to manage the home system anytime and anywhere.

2. The home system based on the Internet of Things according to claim 1, characterized in that: The specific steps of the home appliance control module are as follows: (1) Device connection and initialization: Scan the surrounding environment through the Internet of Things to discover connectable home devices, establish a stable communication connection with the discovered home devices, ensure the reliability and real-time data transmission, identify the type, model and characteristics of the connected device, and perform initialization settings based on the device information, including the initial status and working mode of the device. Add the successfully connected and initialized devices to the device list to facilitate subsequent management and control; (2) Receiving energy-saving strategies: Continuously monitor the instructions sent by the device list to ensure timely acquisition of the latest energy-saving control requirements, parse the received instructions, extract the specific control parameters and requirements for each device, and verify the parsed instructions to ensure the legality and validity of the instructions and prevent the execution of erroneous or illegal instructions; (3) Equipment status monitoring: Through the interface provided by the equipment, the operating status and energy consumption status data of the equipment are collected, and the collected data are processed and analyzed to extract the actual operating status and energy consumption status of the equipment, detect whether the equipment is operating abnormally, such as excessive temperature and abnormal energy consumption, and issue early warnings in a timely manner; (4) Execute control instructions: Map energy-saving control instructions to specific equipment control parameters, such as adjusting the temperature setting of air conditioners and changing the brightness of lighting equipment. According to the current state and target state of the equipment, calculate the appropriate control parameter value, send control signals to the equipment through the PID control algorithm, and achieve precise control of the equipment. (5) Feedback of execution results: Collect the execution results of the equipment, analyze the collected results, evaluate the execution effect of the control instructions, and feed back the analysis results to the energy consumption monitoring module to optimize the subsequent energy-saving strategy.

3. The home system based on the Internet of Things according to claim 1, characterized in that: The energy consumption monitoring module has the following specific steps: (1) Energy consumption data reception: Receive the analysis results from the home device control module and obtain energy consumption data from the home devices in real time or at a scheduled time according to the collection frequency set by the module. This data may include power consumption and water usage, depending on the monitored devices and system requirements; (2) Data processing and analysis: The collected energy consumption data is cleaned, integrated and analyzed using statistical analysis algorithms. The cleaning process includes removing outliers and erroneous data. The integration is the unified processing of different energy consumption data of different devices or the same device. The analysis includes calculating the average value, peak value and change trend of energy consumption. (3) Energy consumption status evaluation: Based on the processed data, the module evaluates the energy consumption status of home appliances to determine whether the appliances are operating efficiently or whether there are abnormal energy consumption issues; (4) Data storage and transmission: The module stores the processed energy consumption data and evaluation results in a local or cloud database for subsequent analysis and use. At the same time, the module will also send the relevant data to the energy-saving strategy formulation module as a basis for formulating energy-saving strategies.

4. The home system based on the Internet of Things according to claim 1, characterized in that: The energy-saving strategy formulation module has the following specific steps: (1) Data collection and analysis: First, the energy consumption data of household devices sent by the energy consumption monitoring module are received. These data may include electricity, water, and usage time. Then, the module will use statistical analysis methods to process these data, identify energy consumption peaks and valleys, and analyze the energy consumption characteristics of different devices. (2) User behavior pattern recognition: By analyzing historical data and using the K-means algorithm in machine learning, users’ daily behavior patterns can be identified, such as waking time, rest time, and entertainment time. These behavior patterns are crucial for developing personalized energy-saving strategies. (3) Energy-saving strategy generation: Based on the above analysis, the energy-saving strategy formulation module will use particle swarm optimization to combine the user's comfort and energy-saving needs to generate a series of energy-saving strategies. These strategies may include adjusting the operating time of the equipment, setting the temperature, and optimizing the equipment combination; (4) Strategy evaluation and adjustment: The generated energy-saving strategy will be evaluated through simulation testing or actual operation. Based on the evaluation results, the module will fine-tune the strategy to achieve better energy-saving effects and user satisfaction.

5. The home system based on the Internet of Things according to claim 1, characterized in that: The user interaction module has the following specific steps: (1) Interface display: The current status of home devices, energy consumption data, and the implementation of energy-saving strategies are displayed through a graphical interface; (2) User input: Users can input their needs, preferences, or adjust the parameters of energy-saving strategies through the interface; (3) Voice control: In addition to interface input, the user interaction module uses a voice recognition algorithm to convert the user's voice commands into instructions that the system can understand, providing a voice control function. Users can control home appliances or adjust energy-saving strategies through voice commands; (4) Remote control: Users can remotely control home devices through mobile applications or cloud platforms, no matter where they are.

6. The home system based on the Internet of Things according to claim 2, characterized in that: The home appliance control module monitors the indoor temperature in real time through the PID control algorithm and compares it with the target value, and automatically adjusts the output of the heating or cooling equipment to keep the indoor temperature within a suitable range. For example, during winter heating, if the indoor temperature is lower than the set value, the PID control algorithm will calculate the appropriate control amount based on the error and the above parameters, increase the output of the heating equipment, and make the indoor temperature gradually rise and approach the set value. At the same time, through the action of integral and differential terms, the system can smoothly reach the target temperature to avoid overshoot or oscillation. The parameters of the PID controller include the proportional coefficient (Kp), integral coefficient (Ki) and differential coefficient (Kd). The specific mathematical formula is: u(t) is the control quantity, that is, the output or adjustment quantity at time (t), and e(t) is the error, that is, the difference between the set value and the actual value. In addition to the temperature control system, the PID control algorithm can also be applied to other home appliances, such as lighting control and curtain control. In these scenarios, the PID control algorithm can also achieve precise control effects by adjusting the control parameters according to the deviation between the set value and the actual value.

7. The home system based on the Internet of Things according to claim 3, characterized in that: The energy consumption monitoring module describes the distribution characteristics, change trends and correlation of data through statistical analysis algorithms. In energy consumption monitoring, statistical analysis can help us identify peaks and valleys of energy consumption, analyze energy consumption differences between different devices or systems, and find out the relationship between energy consumption and external environment or operating behavior. By calculating the correlation coefficient in the statistical analysis algorithm, we can quantify the degree of linear correlation between variables, thereby identifying potential energy-saving opportunities and influencing factors. The correlation coefficient is expressed as r, which measures the degree of linear correlation between two variables x and y. Its value range is [-1, 1], where 1 indicates a complete positive correlation, -1 indicates a complete negative correlation, and 0 indicates no correlation. Its calculation formula is: n is the number of data points, x i and i are the x and y values ​​of the ith data point, respectively. and are the means of x and y respectively, and the calculation formula is: The formula calculates the sum of the products of the deviations of x and y and divides it by the product of their respective standard deviations to obtain a standardized measure that represents the degree of linear correlation between x and y. By analyzing the linear correlation of the correlation coefficient in the energy consumption monitoring module, we can analyze energy consumption data more systematically, reveal the relationship between variables, and provide a scientific basis for formulating effective energy-saving strategies, which not only helps to improve energy utilization efficiency and reduce energy consumption costs, but also helps to promote sustainable development and environmental protection.

8. The home system based on the Internet of Things according to claim 4, characterized in that: The energy-saving strategy formulation module uses the K-means algorithm in machine learning to identify the user's daily behavior patterns, which is crucial for formulating personalized energy-saving strategies. The K-means algorithm divides the data points into K clusters in an iterative manner. The data points in each cluster are as similar as possible, while the data points between different clusters are as different as possible. K initial cluster centers are selected. For each data point x i , calculate its relationship with each cluster center c j , and assigns it to the nearest cluster center, which is usually measured by the Euclidean distance: Where n is the dimension of the data points, is the data point x i The kth feature of is the cluster center c j The k-th coordinate of , for each cluster, recalculate the cluster center, and the new cluster center is the mean of all data points in the cluster: S j is the set of data points of the jth cluster, |S j |It is S j The number of data points in the cluster is calculated by repeating the operation of the two cluster centers to obtain the user's daily behavior pattern and formulate a personalized energy-saving strategy.

9. The home system based on the Internet of Things according to claim 4, characterized in that: The energy-saving strategy formulation module uses particle swarm optimization to identify user behavior patterns to formulate more effective energy-saving strategies. Its operating formula is: i (t+1)=w·v i (t)+c1·r1·(pbest i -x i (t))+c2·r2·(gbest-x i (t)), x i (t+1)=x i (t)+v i (t+1), where vi is the particle velocity, xi is the particle position, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers, and pbest i is the individual optimal position, gbest is the global optimal position. In each iteration, the individual optimal and global optimal positions are updated according to the fitness function. Take the optimization of lighting behavior patterns as an example: a group of particles are randomly generated, each particle represents a lighting time series, and the fitness of each particle is calculated, that is, the energy-saving effect of the lighting time series it represents. The speed and position of each particle are updated according to the above formula, and the current position of each particle is compared with its historical optimal position, and the individual optimal is updated. The current positions of all particles are compared, and the global optimal is updated. Repeat the above steps until the optimal lighting time series is found or the maximum number of iterations is reached. Through particle swarm optimization, we can identify behavior patterns based on the user's historical lighting data and optimize the lighting time series to save energy.

10. The home system based on the Internet of Things according to claim 5, characterized in that: The user interaction module uses a speech recognition algorithm to convert the user's voice command into instructions that the system can understand, thereby realizing the control of home appliances. Taking the hidden Markov model (HMM) in the speech recognition algorithm as an example, the operation mode and calculation formula in the user interaction module are as follows: The parameters of the HMM are defined as the state set S = {s1, s2, ..., s N }、Observation symbol set O={o1,o2,…,o N }、State transition probability matrix A={a ij }, output probability matrix (or transmission probability matrix) B = {b j (k)}, initialize the probability vector π = {π i }, where N is the number of states, M is the number of observation symbols, a ij =P(s j |s i ) indicates that from s j The state is transferred to s i The probability of the state, b j (k) = P(o k |s j ) means in o k Output observation symbol s in the state j The probability of i =P(s j ) indicates that the initial state is s j The probability of these probabilities is expressed as: state transition probability a ij =P(q t+1 =s j |q t =s i ), q t and q t+1 Represent the states at time t and t+1 respectively, and output probability b j (k) = P(o t =o k |q t =s j ), o t Represents the observation symbol at time t, and initializes the probability π i =P(q1=s i ), q1 represents the state at the initial moment. In speech recognition, HMM is used to model the temporal characteristics of speech signals, and infer the hidden state sequence through some incompletely observable random variables (i.e., acoustic features). Since speech signals are temporal and dynamic, HMM can capture these characteristics well, and use probability distribution to bridge the gap between acoustic features and speech phonemes to find the most likely state sequence. This state sequence is then mapped to the corresponding word or phrase, thereby realizing speech recognition.

Images